/* * 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); }
/* * 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, unsigned long stack_size, int __user *child_tidptr, struct pid *pid, int trace) { int retval; struct task_struct *p; 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 or signal handlers or * parent with the forking task. */ if (clone_flags & CLONE_SIGHAND) { if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) || (task_active_pid_ns(current) != current->nsproxy->pid_ns_for_children)) 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) >= task_rlimit(p, RLIMIT_NPROC)) { if (p->real_cred->user != INIT_USER && !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) goto bad_fork_free; } current->flags &= ~PF_NPROC_EXCEEDED; retval = copy_creds(p, clone_flags); if (retval < 0) goto bad_fork_free; /* * 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; delayacct_tsk_init(p); /* Must remain after dup_task_struct() */ p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER); 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; p->utimescaled = p->stimescaled = 0; #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE p->prev_cputime.utime = p->prev_cputime.stime = 0; #endif #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN seqlock_init(&p->vtime_seqlock); p->vtime_snap = 0; p->vtime_snap_whence = VTIME_SLEEPING; #endif #if defined(SPLIT_RSS_COUNTING) memset(&p->rss_stat, 0, sizeof(p->rss_stat)); #endif 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->start_time = ktime_get_ns(); p->real_start_time = ktime_get_boot_ns(); p->io_context = NULL; p->audit_context = NULL; if (clone_flags & CLONE_THREAD) threadgroup_change_begin(current); 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_threadgroup_lock; } #endif #ifdef CONFIG_CPUSETS p->cpuset_mem_spread_rotor = NUMA_NO_NODE; p->cpuset_slab_spread_rotor = NUMA_NO_NODE; seqcount_init(&p->mems_allowed_seq); #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 #ifdef CONFIG_DEBUG_MUTEXES p->blocked_on = NULL; /* not blocked yet */ #endif #ifdef CONFIG_BCACHE p->sequential_io = 0; p->sequential_io_avg = 0; #endif /* 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); if (retval) goto bad_fork_cleanup_policy; retval = audit_alloc(p); if (retval) goto bad_fork_cleanup_perf; /* copy all the process information */ shm_init_task(p); retval = copy_semundo(clone_flags, p); if (retval) goto bad_fork_cleanup_audit; retval = copy_files(clone_flags, p); 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(clone_flags, stack_start, stack_size, p); if (retval) goto bad_fork_cleanup_io; if (pid != &init_struct_pid) { pid = alloc_pid(p->nsproxy->pid_ns_for_children); if (IS_ERR(pid)) { retval = PTR_ERR(pid); goto bad_fork_cleanup_io; } } 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_BLOCK p->plug = NULL; #endif #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 and stepping should be turned off in the * child regardless of CLONE_PTRACE. */ user_disable_single_step(p); 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->pid = pid_nr(pid); if (clone_flags & CLONE_THREAD) { p->exit_signal = -1; p->group_leader = current->group_leader; p->tgid = current->tgid; } else { if (clone_flags & CLONE_PARENT) p->exit_signal = current->group_leader->exit_signal; else p->exit_signal = (clone_flags & CSIGNAL); 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; INIT_LIST_HEAD(&p->thread_group); p->task_works = NULL; /* * 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; } else { p->real_parent = current; p->parent_exec_id = current->self_exec_id; } spin_lock(¤t->sighand->siglock); /* * Copy seccomp details explicitly here, in case they were changed * before holding sighand lock. */ copy_seccomp(p); /* * 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 (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_PGID, task_pgrp(current)); init_task_pid(p, PIDTYPE_SID, task_session(current)); if (is_child_reaper(pid)) { ns_of_pid(pid)->child_reaper = p; p->signal->flags |= SIGNAL_UNKILLABLE; } p->signal->leader_pid = pid; p->signal->tty = tty_kref_get(current->signal->tty); list_add_tail(&p->sibling, &p->real_parent->children); list_add_tail_rcu(&p->tasks, &init_task.tasks); attach_pid(p, PIDTYPE_PGID); attach_pid(p, PIDTYPE_SID); __this_cpu_inc(process_counts); } else { current->signal->nr_threads++; atomic_inc(¤t->signal->live); atomic_inc(¤t->signal->sigcnt); list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group); list_add_tail_rcu(&p->thread_node, &p->signal->thread_head); } attach_pid(p, PIDTYPE_PID); nr_threads++; } total_forks++; spin_unlock(¤t->sighand->siglock); syscall_tracepoint_update(p); write_unlock_irq(&tasklist_lock); proc_fork_connector(p); cgroup_post_fork(p); if (clone_flags & CLONE_THREAD) threadgroup_change_end(current); perf_event_fork(p); trace_task_newtask(p, clone_flags); uprobe_copy_process(p, clone_flags); return p; bad_fork_free_pid: if (pid != &init_struct_pid) free_pid(pid); bad_fork_cleanup_io: if (p->io_context) exit_io_context(p); 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)) free_signal_struct(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_perf: perf_event_free_task(p); bad_fork_cleanup_policy: #ifdef CONFIG_NUMA mpol_put(p->mempolicy); bad_fork_cleanup_threadgroup_lock: #endif if (clone_flags & CLONE_THREAD) threadgroup_change_end(current); delayacct_tsk_free(p); bad_fork_cleanup_count: atomic_dec(&p->cred->user->processes); exit_creds(p); bad_fork_free: free_task(p); fork_out: return ERR_PTR(retval); }
/* * 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); }
static void do_fork(struct thread *td, struct fork_req *fr, struct proc *p2, struct thread *td2, struct vmspace *vm2, struct file *fp_procdesc) { struct proc *p1, *pptr; int trypid; struct filedesc *fd; struct filedesc_to_leader *fdtol; struct sigacts *newsigacts; sx_assert(&proctree_lock, SX_SLOCKED); sx_assert(&allproc_lock, SX_XLOCKED); p1 = td->td_proc; trypid = fork_findpid(fr->fr_flags); sx_sunlock(&proctree_lock); p2->p_state = PRS_NEW; /* protect against others */ p2->p_pid = trypid; AUDIT_ARG_PID(p2->p_pid); LIST_INSERT_HEAD(&allproc, p2, p_list); allproc_gen++; LIST_INSERT_HEAD(PIDHASH(p2->p_pid), p2, p_hash); tidhash_add(td2); PROC_LOCK(p2); PROC_LOCK(p1); sx_xunlock(&allproc_lock); bcopy(&p1->p_startcopy, &p2->p_startcopy, __rangeof(struct proc, p_startcopy, p_endcopy)); pargs_hold(p2->p_args); PROC_UNLOCK(p1); bzero(&p2->p_startzero, __rangeof(struct proc, p_startzero, p_endzero)); /* Tell the prison that we exist. */ prison_proc_hold(p2->p_ucred->cr_prison); PROC_UNLOCK(p2); /* * Malloc things while we don't hold any locks. */ if (fr->fr_flags & RFSIGSHARE) newsigacts = NULL; else newsigacts = sigacts_alloc(); /* * Copy filedesc. */ if (fr->fr_flags & RFCFDG) { fd = fdinit(p1->p_fd, false); fdtol = NULL; } else if (fr->fr_flags & RFFDG) { fd = fdcopy(p1->p_fd); fdtol = NULL; } else { fd = fdshare(p1->p_fd); if (p1->p_fdtol == NULL) p1->p_fdtol = filedesc_to_leader_alloc(NULL, NULL, p1->p_leader); if ((fr->fr_flags & RFTHREAD) != 0) { /* * Shared file descriptor table, and shared * process leaders. */ fdtol = p1->p_fdtol; FILEDESC_XLOCK(p1->p_fd); fdtol->fdl_refcount++; FILEDESC_XUNLOCK(p1->p_fd); } else { /* * Shared file descriptor table, and different * process leaders. */ fdtol = filedesc_to_leader_alloc(p1->p_fdtol, p1->p_fd, p2); } } /* * Make a proc table entry for the new process. * Start by zeroing the section of proc that is zero-initialized, * then copy the section that is copied directly from the parent. */ PROC_LOCK(p2); PROC_LOCK(p1); bzero(&td2->td_startzero, __rangeof(struct thread, td_startzero, td_endzero)); bcopy(&td->td_startcopy, &td2->td_startcopy, __rangeof(struct thread, td_startcopy, td_endcopy)); bcopy(&p2->p_comm, &td2->td_name, sizeof(td2->td_name)); td2->td_sigstk = td->td_sigstk; td2->td_flags = TDF_INMEM; td2->td_lend_user_pri = PRI_MAX; #ifdef VIMAGE td2->td_vnet = NULL; td2->td_vnet_lpush = NULL; #endif /* * Allow the scheduler to initialize the child. */ thread_lock(td); sched_fork(td, td2); thread_unlock(td); /* * Duplicate sub-structures as needed. * Increase reference counts on shared objects. */ p2->p_flag = P_INMEM; p2->p_flag2 = p1->p_flag2 & (P2_NOTRACE | P2_NOTRACE_EXEC | P2_TRAPCAP); p2->p_swtick = ticks; if (p1->p_flag & P_PROFIL) startprofclock(p2); /* * Whilst the proc lock is held, copy the VM domain data out * using the VM domain method. */ vm_domain_policy_init(&p2->p_vm_dom_policy); vm_domain_policy_localcopy(&p2->p_vm_dom_policy, &p1->p_vm_dom_policy); if (fr->fr_flags & RFSIGSHARE) { p2->p_sigacts = sigacts_hold(p1->p_sigacts); } else { sigacts_copy(newsigacts, p1->p_sigacts); p2->p_sigacts = newsigacts; } if (fr->fr_flags & RFTSIGZMB) p2->p_sigparent = RFTSIGNUM(fr->fr_flags); else if (fr->fr_flags & RFLINUXTHPN) p2->p_sigparent = SIGUSR1; else p2->p_sigparent = SIGCHLD; p2->p_textvp = p1->p_textvp; p2->p_fd = fd; p2->p_fdtol = fdtol; if (p1->p_flag2 & P2_INHERIT_PROTECTED) { p2->p_flag |= P_PROTECTED; p2->p_flag2 |= P2_INHERIT_PROTECTED; } /* * p_limit is copy-on-write. Bump its refcount. */ lim_fork(p1, p2); thread_cow_get_proc(td2, p2); pstats_fork(p1->p_stats, p2->p_stats); PROC_UNLOCK(p1); PROC_UNLOCK(p2); /* Bump references to the text vnode (for procfs). */ if (p2->p_textvp) vrefact(p2->p_textvp); /* * Set up linkage for kernel based threading. */ if ((fr->fr_flags & RFTHREAD) != 0) { mtx_lock(&ppeers_lock); p2->p_peers = p1->p_peers; p1->p_peers = p2; p2->p_leader = p1->p_leader; mtx_unlock(&ppeers_lock); PROC_LOCK(p1->p_leader); if ((p1->p_leader->p_flag & P_WEXIT) != 0) { PROC_UNLOCK(p1->p_leader); /* * The task leader is exiting, so process p1 is * going to be killed shortly. Since p1 obviously * isn't dead yet, we know that the leader is either * sending SIGKILL's to all the processes in this * task or is sleeping waiting for all the peers to * exit. We let p1 complete the fork, but we need * to go ahead and kill the new process p2 since * the task leader may not get a chance to send * SIGKILL to it. We leave it on the list so that * the task leader will wait for this new process * to commit suicide. */ PROC_LOCK(p2); kern_psignal(p2, SIGKILL); PROC_UNLOCK(p2); } else PROC_UNLOCK(p1->p_leader); } else { p2->p_peers = NULL; p2->p_leader = p2; } sx_xlock(&proctree_lock); PGRP_LOCK(p1->p_pgrp); PROC_LOCK(p2); PROC_LOCK(p1); /* * Preserve some more flags in subprocess. P_PROFIL has already * been preserved. */ p2->p_flag |= p1->p_flag & P_SUGID; td2->td_pflags |= (td->td_pflags & TDP_ALTSTACK) | TDP_FORKING; SESS_LOCK(p1->p_session); if (p1->p_session->s_ttyvp != NULL && p1->p_flag & P_CONTROLT) p2->p_flag |= P_CONTROLT; SESS_UNLOCK(p1->p_session); if (fr->fr_flags & RFPPWAIT) p2->p_flag |= P_PPWAIT; p2->p_pgrp = p1->p_pgrp; LIST_INSERT_AFTER(p1, p2, p_pglist); PGRP_UNLOCK(p1->p_pgrp); LIST_INIT(&p2->p_children); LIST_INIT(&p2->p_orphans); callout_init_mtx(&p2->p_itcallout, &p2->p_mtx, 0); /* * If PF_FORK is set, the child process inherits the * procfs ioctl flags from its parent. */ if (p1->p_pfsflags & PF_FORK) { p2->p_stops = p1->p_stops; p2->p_pfsflags = p1->p_pfsflags; } /* * This begins the section where we must prevent the parent * from being swapped. */ _PHOLD(p1); PROC_UNLOCK(p1); /* * Attach the new process to its parent. * * If RFNOWAIT is set, the newly created process becomes a child * of init. This effectively disassociates the child from the * parent. */ if ((fr->fr_flags & RFNOWAIT) != 0) { pptr = p1->p_reaper; p2->p_reaper = pptr; } else { p2->p_reaper = (p1->p_treeflag & P_TREE_REAPER) != 0 ? p1 : p1->p_reaper; pptr = p1; } p2->p_pptr = pptr; LIST_INSERT_HEAD(&pptr->p_children, p2, p_sibling); LIST_INIT(&p2->p_reaplist); LIST_INSERT_HEAD(&p2->p_reaper->p_reaplist, p2, p_reapsibling); if (p2->p_reaper == p1) p2->p_reapsubtree = p2->p_pid; sx_xunlock(&proctree_lock); /* Inform accounting that we have forked. */ p2->p_acflag = AFORK; PROC_UNLOCK(p2); #ifdef KTRACE ktrprocfork(p1, p2); #endif /* * Finish creating the child process. It will return via a different * execution path later. (ie: directly into user mode) */ vm_forkproc(td, p2, td2, vm2, fr->fr_flags); if (fr->fr_flags == (RFFDG | RFPROC)) { VM_CNT_INC(v_forks); VM_CNT_ADD(v_forkpages, p2->p_vmspace->vm_dsize + p2->p_vmspace->vm_ssize); } else if (fr->fr_flags == (RFFDG | RFPROC | RFPPWAIT | RFMEM)) { VM_CNT_INC(v_vforks); VM_CNT_ADD(v_vforkpages, p2->p_vmspace->vm_dsize + p2->p_vmspace->vm_ssize); } else if (p1 == &proc0) { VM_CNT_INC(v_kthreads); VM_CNT_ADD(v_kthreadpages, p2->p_vmspace->vm_dsize + p2->p_vmspace->vm_ssize); } else { VM_CNT_INC(v_rforks); VM_CNT_ADD(v_rforkpages, p2->p_vmspace->vm_dsize + p2->p_vmspace->vm_ssize); } /* * Associate the process descriptor with the process before anything * can happen that might cause that process to need the descriptor. * However, don't do this until after fork(2) can no longer fail. */ if (fr->fr_flags & RFPROCDESC) procdesc_new(p2, fr->fr_pd_flags); /* * Both processes are set up, now check if any loadable modules want * to adjust anything. */ EVENTHANDLER_INVOKE(process_fork, p1, p2, fr->fr_flags); /* * Set the child start time and mark the process as being complete. */ PROC_LOCK(p2); PROC_LOCK(p1); microuptime(&p2->p_stats->p_start); PROC_SLOCK(p2); p2->p_state = PRS_NORMAL; PROC_SUNLOCK(p2); #ifdef KDTRACE_HOOKS /* * Tell the DTrace fasttrap provider about the new process so that any * tracepoints inherited from the parent can be removed. We have to do * this only after p_state is PRS_NORMAL since the fasttrap module will * use pfind() later on. */ if ((fr->fr_flags & RFMEM) == 0 && dtrace_fasttrap_fork) dtrace_fasttrap_fork(p1, p2); #endif /* * Hold the process so that it cannot exit after we make it runnable, * but before we wait for the debugger. */ _PHOLD(p2); if (p1->p_ptevents & PTRACE_FORK) { /* * Arrange for debugger to receive the fork event. * * We can report PL_FLAG_FORKED regardless of * P_FOLLOWFORK settings, but it does not make a sense * for runaway child. */ td->td_dbgflags |= TDB_FORK; td->td_dbg_forked = p2->p_pid; td2->td_dbgflags |= TDB_STOPATFORK; } if (fr->fr_flags & RFPPWAIT) { td->td_pflags |= TDP_RFPPWAIT; td->td_rfppwait_p = p2; td->td_dbgflags |= TDB_VFORK; } PROC_UNLOCK(p2); /* * Now can be swapped. */ _PRELE(p1); PROC_UNLOCK(p1); /* * Tell any interested parties about the new process. */ knote_fork(p1->p_klist, p2->p_pid); SDT_PROBE3(proc, , , create, p2, p1, fr->fr_flags); if (fr->fr_flags & RFPROCDESC) { procdesc_finit(p2->p_procdesc, fp_procdesc); fdrop(fp_procdesc, td); } if ((fr->fr_flags & RFSTOPPED) == 0) { /* * If RFSTOPPED not requested, make child runnable and * add to run queue. */ thread_lock(td2); TD_SET_CAN_RUN(td2); sched_add(td2, SRQ_BORING); thread_unlock(td2); if (fr->fr_pidp != NULL) *fr->fr_pidp = p2->p_pid; } else { *fr->fr_procp = p2; } PROC_LOCK(p2); /* * Wait until debugger is attached to child. */ while (td2->td_proc == p2 && (td2->td_dbgflags & TDB_STOPATFORK) != 0) cv_wait(&p2->p_dbgwait, &p2->p_mtx); _PRELE(p2); racct_proc_fork_done(p2); PROC_UNLOCK(p2); }
static uint32_t sys_fork(va_list ap) { (void)ap; return (uint32_t)sched_fork(); }
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); if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND)) return ERR_PTR(-EINVAL); if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM)) return ERR_PTR(-EINVAL); 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) >= task_rlimit(p, RLIMIT_NPROC)) { if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) && p->real_cred->user != INIT_USER) goto bad_fork_free; } current->flags &= ~PF_NPROC_EXCEEDED; retval = copy_creds(p, clone_flags); if (retval < 0) goto bad_fork_free; 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); 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 = p->stime = p->gtime = 0; p->utimescaled = p->stimescaled = 0; #ifndef CONFIG_VIRT_CPU_ACCOUNTING p->prev_utime = p->prev_stime = 0; #endif #if defined(SPLIT_RSS_COUNTING) memset(&p->rss_stat, 0, sizeof(p->rss_stat)); #endif p->default_timer_slack_ns = current->timer_slack_ns; task_io_accounting_init(&p->ioac); acct_clear_integrals(p); posix_cpu_timers_init(p); 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; if (clone_flags & CLONE_THREAD) threadgroup_change_begin(current); 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_CPUSETS p->cpuset_mem_spread_rotor = NUMA_NO_NODE; p->cpuset_slab_spread_rotor = NUMA_NO_NODE; seqcount_init(&p->mems_allowed_seq); #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; p->curr_chain_key = 0; p->lockdep_recursion = 0; #endif #ifdef CONFIG_DEBUG_MUTEXES p->blocked_on = NULL; p->blocked_by = NULL; p->blocked_since = 0; #endif #ifdef CONFIG_CGROUP_MEM_RES_CTLR p->memcg_batch.do_batch = 0; p->memcg_batch.memcg = NULL; #endif sched_fork(p); retval = perf_event_init_task(p); if (retval) goto bad_fork_cleanup_policy; retval = audit_alloc(p); if (retval) goto bad_fork_cleanup_policy; retval = copy_semundo(clone_flags, p); if (retval) goto bad_fork_cleanup_audit; retval = copy_files(clone_flags, p); 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(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; } p->pid = pid_nr(pid); p->tgid = p->pid; if (clone_flags & CLONE_THREAD) p->tgid = current->tgid; p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL; p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL; #ifdef CONFIG_BLOCK p->plug = NULL; #endif #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 if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM) p->sas_ss_sp = p->sas_ss_size = 0; user_disable_single_step(p); 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); if (clone_flags & CLONE_THREAD) p->exit_signal = -1; else if (clone_flags & CLONE_PARENT) p->exit_signal = current->group_leader->exit_signal; else p->exit_signal = (clone_flags & CSIGNAL); p->pdeath_signal = 0; p->exit_state = 0; p->nr_dirtied = 0; p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10); p->dirty_paused_when = 0; p->group_leader = p; INIT_LIST_HEAD(&p->thread_group); cgroup_fork_callbacks(p); cgroup_callbacks_done = 1; write_lock_irq(&tasklist_lock); 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); 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) { current->signal->nr_threads++; atomic_inc(¤t->signal->live); atomic_inc(¤t->signal->sigcnt); p->group_leader = current->group_leader; list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group); } if (likely(p->pid)) { ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); if (thread_group_leader(p)) { if (is_child_reaper(pid)) p->nsproxy->pid_ns->child_reaper = p; p->signal->leader_pid = pid; 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(&p->sibling, &p->real_parent->children); list_add_tail_rcu(&p->tasks, &init_task.tasks); __this_cpu_inc(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); if (clone_flags & CLONE_THREAD) threadgroup_change_end(current); perf_event_fork(p); trace_task_newtask(p, clone_flags); return p; bad_fork_free_pid: if (pid != &init_struct_pid) free_pid(pid); bad_fork_cleanup_io: if (p->io_context) exit_io_context(p); bad_fork_cleanup_namespaces: if (unlikely(clone_flags & CLONE_NEWPID)) pid_ns_release_proc(p->nsproxy->pid_ns); exit_task_namespaces(p); bad_fork_cleanup_mm: if (p->mm) mmput(p->mm); bad_fork_cleanup_signal: if (!(clone_flags & CLONE_THREAD)) free_signal_struct(p->signal); bad_fork_cleanup_sighand: __cleanup_sighand(p->sighand); bad_fork_cleanup_fs: exit_fs(p); bad_fork_cleanup_files: exit_files(p); 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 if (clone_flags & CLONE_THREAD) threadgroup_change_end(current); 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); exit_creds(p); bad_fork_free: free_task(p); fork_out: return ERR_PTR(retval); }