内核进程的复制
在通过fork系统调用创建进程时，最终会进入内核的do_fork函数，这个函数的大部分工作都是进程的复制，就是把大部分工作都委托给函数copy_process函数来完成。本博文主要讨论进程的复制工作。
下面分成几个段，所在代码包含了整个copy_process函数
一，标志检查
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 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);
retval = security_task_create(clone_flags);
if (retval)
goto fork_out;
这是函数的开始部分，先进行传入的参数检查，主要是：
- 如果创建进程的时候，要求创建一个新的命名空间（CLONE_NEWNS），并且同时要求与父进程共享所有的文件系统信息（CLONE_FS)，这是不允许的。此时是要求共享其文件系统。
- 在用CLONE_THREAD标志时，必须使用CLONE_SIGHAND标志，后者表示共享相同的信号处理表。
- 在使用CLONE_SIGHAND标志时，必须使用CLONE_VM标志，后者表示子进程和你进程共享虚拟地址空间，也只有这个时候，才能提供共享的信号处理程序。
retval = -ENOMEM; p = dup_task_struct(current); if (!p) goto fork_out;dup_task_struct用来建立父进程的副本，函数如下：
static struct task_struct *dup_task_struct(struct task_struct *orig)
{
struct task_struct *tsk;
struct thread_info *ti;
int err;
prepare_to_copy(orig);
tsk = alloc_task_struct();
if (!tsk)
return NULL;
ti = alloc_thread_info(tsk);
if (!ti) {
free_task_struct(tsk);
return NULL;
}
*tsk = *orig;//将父进程的内容填充新的进程
tsk->stack = ti;
err = prop_local_init_single(&tsk->dirties);
if (err) {
free_thread_info(ti);
free_task_struct(tsk);
return NULL;
}
setup_thread_stack(tsk, orig);
#ifdef CONFIG_CC_STACKPROTECTOR
tsk->stack_canary = get_random_int();
#endif
/* One for us, one for whoever does the "release_task()" (usually parent) */
atomic_set(&tsk->usage,2);//使用计数器置为2，表示当前进程描述符处于活动状态。
atomic_set(&tsk->fs_excl, 0);
#ifdef CONFIG_BLK_DEV_IO_TRACE
tsk->btrace_seq = 0;
#endif
tsk->splice_pipe = NULL;
return tsk;
}
- 调用alloc_task_struct为新进程分配进程结构，返回tsk指针。
- 为新的进程分配一个核心态栈，也就是tsk->stack。栈和thread_info一同保存在一个联合结构中。thread_info用于保存进程所需的特定于处理器的底层信息，定义如下：
struct thread_info { struct task_struct *task; /* 不前的主进程 */ unsigned long flags; struct exec_domain *exec_domain; /* 执行区间 */ int preempt_count; /* 内核抢占所需的一个计数器*/ __u32 cpu; /* 进程正在其上执行的CPU数目 */ struct restart_block restart_block;//用于实现信号机制 };
而进程的栈和thread_info的联合体定义如下：union thread_union { struct thread_info thread_info; unsigned long stack[THREAD_SIZE/sizeof(long)]; };在分配了栈后，调用setup_thread_stack确定栈内的布局。这个函数完成的操作是：把父进程的thread_info（进程描述结构）值复制给tsk的进程描述结构。然后将tsk的进程描述符中的task域改为tsk。#define task_thread_info(task) ((struct thread_info *)(task)->stack) static inline void setup_thread_stack(struct task_struct *p, struct task_struct *org) { *task_thread_info(p) = *task_thread_info(org); task_thread_info(p)->task = p; }在执行完setup_thread_stack之后，父子进程除了stack的指针之外是完全一样的。
三，检查进程数创建限制
rt_mutex_init_task(p);//互斥锁初始化
#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 != current->nsproxy->user_ns->root_user)
goto bad_fork_free;
}
atomic_inc(&p->user->__count);
atomic_inc(&p->user->processes);
get_group_info(p->group_info);增加组的使用计数
进程结构task_struct中有一个域，名为：user_struct，这个域保存了当前用户的使用资源计数。
struct task_struct{
......
struct user_struct *user;
......
};
在user_struct结构中包含processes表示当前的用户能够创建最多的进程数。如果超过限制，就放弃创建进程。root用户除外。如果没有超过限制，就将user_struct结构的引用计数加1，并将已经创建的进程数加1。
四，线程检查
检查线程创建是否超过最大限制，这个比较简单
/* * 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;
五，写入数据
在这里，进程描述符task_struct已经建立好了，其和父进程是一样的，除了栈地址不一样之外，现在开始修改一些值。
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;当前还有加载任何执行的系统调用，所以为0以标识
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);
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->gtime = cputime_zero;
p->utimescaled = cputime_zero;
p->stimescaled = cputime_zero;
p->prev_utime = cputime_zero;
p->prev_stime = cputime_zero;
#ifdef CONFIG_TASK_XACCT
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 */
#endif
task_io_accounting_init(p);
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->real_start_time = p->start_time;
monotonic_to_bootbased(&p->real_start_time);
#ifdef CONFIG_SECURITY
p->security = NULL;
#endif
p->io_context = NULL;
p->audit_context = NULL;
cgroup_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_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
这里是对一些值进行初始化，和各种策略相关的值，如调度等等，有些值是很重要的。
六，加入调度
/* Perform scheduler related setup. Assign this task to a CPU. */ sched_fork(p, clone_flags);这可以使用是进程可以参加调度，但此时进程的状态改为正在TASK_RUNNING，这以防止内核的其他部分将其改为可运行状态，因为我们对进程的设置还没有完成，这样调度进程会有问题。
七，开始复制
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)))System V信号量 goto bad_fork_cleanup_audit; if ((retval = copy_files(clone_flags, p)))文件描述符 goto bad_fork_cleanup_semundo; if ((retval = copy_fs(clone_flags, p)))文件系统上下文 goto bad_fork_cleanup_files; if ((retval = copy_sighand(clone_flags, p)))进程信息处理程序 goto bad_fork_cleanup_fs; if ((retval = copy_signal(clone_flags, p))) goto bad_fork_cleanup_sighand; if ((retval = copy_mm(clone_flags, p)))地址空间 goto bad_fork_cleanup_signal; if ((retval = copy_keys(clone_flags, p))) goto bad_fork_cleanup_mm; if ((retval = copy_namespaces(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_namespaces;这里有各种Copy。
八，分配PID等操作
if (pid != &init_struct_pid) {
retval = -ENOMEM;
pid = alloc_pid(task_active_pid_ns(p));
if (!pid)
goto bad_fork_cleanup_namespaces;
if (clone_flags & CLONE_NEWPID) {
retval = pid_ns_prepare_proc(task_active_pid_ns(p));
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;
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
/* 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);
/* 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);
/* for sys_ioprio_set(IOPRIO_WHO_PGRP) */
p->ioprio = current->ioprio;
/*
* 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());
九，初始化父子关系
/* 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_free_pid;
}
如果创建的是线程或者是PARENT选项，则其父进程为current的父进程。
十，线程创建部分
如果本次创建的是线程，一些另于进程创建的操作。
if (clone_flags & CLONE_THREAD) {
p->group_leader = current->group_leader;//线程组长就是当前线程的组长
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);
}
}
十一，新进程插入进程链表
if (likely(p->pid)) {
add_parent(p);
if (unlikely(p->ptrace & PT_PTRACED))
__ptrace_link(p, current->parent);
if (thread_group_leader(p)) {
if (clone_flags & CLONE_NEWPID)
p->nsproxy->pid_ns->child_reaper = p;如果创建新的命名空间，则将命名空间的child_reaper设为当前创建的进程，这个进程就是这个创建的命名空间的init进程。
p->signal->tty = current->signal->tty;
set_task_pgrp(p, task_pgrp_nr(current));
set_task_session(p, task_session_nr(current));
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++;
}add_parent宏将进程的children链表与父进程连接，实现如下
#define add_parent(p) list_add_tail(&(p)->sibling,&(p)->parent->children)十二，最后
total_forks++; spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); proc_fork_connector(p); cgroup_post_fork(p); return p; bad_fork_free_pid: if (pid != &init_struct_pid) free_pid(pid); bad_fork_cleanup_namespaces: exit_task_namespaces(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_cgroup: #endif cgroup_exit(p, cgroup_callbacks_done); 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); }