fork.c

	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;

	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);
	INIT_LIST_HEAD(&p->children);
	INIT_LIST_HEAD(&p->sibling);
#ifdef CONFIG_PREEMPT_RCU
	p->rcu_read_lock_nesting = 0;
	p->rcu_flipctr_idx = 0;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
	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;

	/* Perform scheduler related setup. Assign this task to a CPU. */
	sched_fork(p, clone_flags);

	retval = perf_counter_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(&current->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(&current->sighand->siglock);
		write_unlock_irq(&tasklist_lock);
		retval = -ERESTARTNOINTR;
		goto bad_fork_free_pid;
	}

	if (clone_flags & CLONE_THREAD) {
		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(&current->sighand->siglock);
	write_unlock_irq(&tasklist_lock);
	proc_fork_connector(p);
	cgroup_post_fork(p);
	perf_counter_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:
	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_policy:
	perf_counter_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);
	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:
	atomic_dec(&p->cred->user->processes);
	put_cred(p->real_cred);
	put_cred(p->cred);
bad_fork_free:
	free_task(p);
fork_out:
	return ERR_PTR(retval);
}

noinline struct pt_regs * __cpuinit __attribute__((weak)) idle_regs(struct pt_regs *regs)
{
	memset(regs, 0, sizeof(struct pt_regs));
	return regs;
}

struct task_struct * __cpuinit fork_idle(int cpu)
{
	struct task_struct *task;
	struct pt_regs regs;

	task = copy_process(CLONE_VM, 0, idle_regs(&regs), 0, NULL,
			    &init_struct_pid, 0);
	if (!IS_ERR(task))
		init_idle(task, cpu);

	return task;
}

/*
 *  Ok, this is the main fork-routine.
 *
 * It copies the process, and if successful kick-starts
 * it and waits for it to finish using the VM if required.
 */
long do_fork(unsigned long clone_flags,
	      unsigned long stack_start,
	      struct pt_regs *regs,
	      unsigned long stack_size,
	      int __user *parent_tidptr,
	      int __user *child_tidptr)
{
	struct task_struct *p;
	int trace = 0;
	long nr;

	/*
	 * Do some preliminary argument and permissions checking before we
	 * actually start allocating stuff
	 */
	if (clone_flags & CLONE_NEWUSER) {
		if (clone_flags & CLONE_THREAD)
			return -EINVAL;
		/* hopefully this check will go away when userns support is
		 * complete
		 */
		if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SETUID) ||
				!capable(CAP_SETGID))
			return -EPERM;
	}

	/*
	 * We hope to recycle these flags after 2.6.26
	 */
	if (unlikely(clone_flags & CLONE_STOPPED)) {
		static int __read_mostly count = 100;

		if (count > 0 && printk_ratelimit()) {
			char comm[TASK_COMM_LEN];

			count--;
			printk(KERN_INFO "fork(): process `%s' used deprecated "
					"clone flags 0x%lx\n",
				get_task_comm(comm, current),
				clone_flags & CLONE_STOPPED);
		}
	}

	/*
	 * When called from kernel_thread, don't do user tracing stuff.
	 */
	if (likely(user_mode(regs)))
		trace = tracehook_prepare_clone(clone_flags);

	p = copy_process(clone_flags, stack_start, regs, stack_size,
			 child_tidptr, NULL, trace);
	/*
	 * Do this prior waking up the new thread - the thread pointer
	 * might get invalid after that point, if the thread exits quickly.
	 */
	if (!IS_ERR(p)) {
		struct completion vfork;

		trace_sched_process_fork(current, p);

		nr = task_pid_vnr(p);

		if (clone_flags & CLONE_PARENT_SETTID)
			put_user(nr, parent_tidptr);

		if (clone_flags & CLONE_VFORK) {
			p->vfork_done = &vfork;
			init_completion(&vfork);
		}

		audit_finish_fork(p);
		tracehook_report_clone(regs, clone_flags, nr, p);

		/*
		 * We set PF_STARTING at creation in case tracing wants to
		 * use this to distinguish a fully live task from one that
		 * hasn't gotten to tracehook_report_clone() yet.  Now we
		 * clear it and set the child going.
		 */
		p->flags &= ~PF_STARTING;

		if (unlikely(clone_flags & CLONE_STOPPED)) {
			/*
			 * We'll start up with an immediate SIGSTOP.
			 */
			sigaddset(&p->pending.signal, SIGSTOP);
			set_tsk_thread_flag(p, TIF_SIGPENDING);
			__set_task_state(p, TASK_STOPPED);
		} else {
			wake_up_new_task(p, clone_flags);
		}

		tracehook_report_clone_complete(trace, regs,
						clone_flags, nr, p);

		if (clone_flags & CLONE_VFORK) {
			freezer_do_not_count();
			wait_for_completion(&vfork);
			freezer_count();
			tracehook_report_vfork_done(p, nr);
		}
	} else {
		nr = PTR_ERR(p);
	}
	return nr;
}

#ifndef ARCH_MIN_MMSTRUCT_ALIGN
#define ARCH_MIN_MMSTRUCT_ALIGN 0
#endif

static void sighand_ctor(void *data)
{
	struct sighand_struct *sighand = data;

	spin_lock_init(&sighand->siglock);
	init_waitqueue_head(&sighand->signalfd_wqh);
}

void __init proc_caches_init(void)
{
	sighand_cachep = kmem_cache_create("sighand_cache",
			sizeof(struct sighand_struct), 0,
			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_DESTROY_BY_RCU|
			SLAB_NOTRACK, sighand_ctor);
	signal_cachep = kmem_cache_create("signal_cache",
			sizeof(struct signal_struct), 0,
			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
	files_cachep = kmem_cache_create("files_cache",
			sizeof(struct files_struct), 0,
			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
	fs_cachep = kmem_cache_create("fs_cache",
			sizeof(struct fs_struct), 0,
			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
	mm_cachep = kmem_cache_create("mm_struct",
			sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
	vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC);
	mmap_init();
}

/*
 * Check constraints on flags passed to the unshare system call and
 * force unsharing of additional process context as appropriate.
 */
static void check_unshare_flags(unsigned long *flags_ptr)
{
	/*
	 * If unsharing a thread from a thread group, must also
	 * unshare vm.
	 */
	if (*flags_ptr & CLONE_THREAD)
		*flags_ptr |= CLONE_VM;

	/*
	 * If unsharing vm, must also unshare signal handlers.
	 */
	if (*flags_ptr & CLONE_VM)
		*flags_ptr |= CLONE_SIGHAND;

	/*
	 * If unsharing signal handlers and the task was created
	 * using CLONE_THREAD, then must unshare the thread
	 */
	if ((*flags_ptr & CLONE_SIGHAND) &&
	    (atomic_read(&current->signal->count) > 1))
		*flags_ptr |= CLONE_THREAD;

	/*
	 * If unsharing namespace, must also unshare filesystem information.
	 */
	if (*flags_ptr & CLONE_NEWNS)
		*flags_ptr |= CLONE_FS;
}

/*
 * Unsharing of tasks created with CLONE_THREAD is not supported yet
 */
static int unshare_thread(unsigned long unshare_flags)
{
	if (unshare_flags & CLONE_THREAD)
		return -EINVAL;

	return 0;
}

/*
 * Unshare the filesystem structure if it is being shared
 */
static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp)
{
	struct fs_struct *fs = current->fs;

	if (!(unshare_flags & CLONE_FS) || !fs)
		return 0;

	/* don't need lock here; in the worst case we'll do useless copy */
	if (fs->users == 1)
		return 0;

	*new_fsp = copy_fs_struct(fs);
	if (!*new_fsp)
		return -ENOMEM;

	return 0;
}

/*
 * Unsharing of sighand is not supported yet
 */
static int unshare_sighand(unsigned long unshare_flags, struct sighand_struct **new_sighp)
{
	struct sighand_struct *sigh = current->sighand;

	if ((unshare_flags & CLONE_SIGHAND) && atomic_read(&sigh->count) > 1)
		return -EINVAL;
	else
		return 0;
}

/*
 * Unshare vm if it is being shared
 */
static int unshare_vm(unsigned long unshare_flags, struct mm_struct **new_mmp)
{
	struct mm_struct *mm = current->mm;

	if ((unshare_flags & CLONE_VM) &&
	    (mm && atomic_read(&mm->mm_users) > 1)) {
		return -EINVAL;
	}

	return 0;
}

/*
 * Unshare file descriptor table if it is being shared
 */
static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp)
{
	struct files_struct *fd = current->files;
	int error = 0;

	if ((unshare_flags & CLONE_FILES) &&
	    (fd && atomic_read(&fd->count) > 1)) {
		*new_fdp = dup_fd(fd, &error);
		if (!*new_fdp)
			return error;
	}

	return 0;
}

/*
 * unshare allows a process to 'unshare' part of the process
 * context which was originally shared using clone.  copy_*
 * functions used by do_fork() cannot be used here directly
 * because they modify an inactive task_struct that is being
 * constructed. Here we are modifying the current, active,
 * task_struct.
 */
SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
{
	int err = 0;
	struct fs_struct *fs, *new_fs = NULL;
	struct sighand_struct *new_sigh = NULL;
	struct mm_struct *mm, *new_mm = NULL, *active_mm = NULL;
	struct files_struct *fd, *new_fd = NULL;
	struct nsproxy *new_nsproxy = NULL;
	int do_sysvsem = 0;

	check_unshare_flags(&unshare_flags);

	/* Return -EINVAL for all unsupported flags */
	err = -EINVAL;
	if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND|
				CLONE_VM|CLONE_FILES|CLONE_SYSVSEM|
				CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET))
		goto bad_unshare_out;

	/*
	 * CLONE_NEWIPC must also detach from the undolist: after switching
	 * to a new ipc namespace, the semaphore arrays from the old
	 * namespace are unreachable.
	 */
	if (unshare_flags & (CLONE_NEWIPC|CLONE_SYSVSEM))
		do_sysvsem = 1;
	if ((err = unshare_thread(unshare_flags)))
		goto bad_unshare_out;
	if ((err = unshare_fs(unshare_flags, &new_fs)))
		goto bad_unshare_cleanup_thread;
	if ((err = unshare_sighand(unshare_flags, &new_sigh)))
		goto bad_unshare_cleanup_fs;
	if ((err = unshare_vm(unshare_flags, &new_mm)))
		goto bad_unshare_cleanup_sigh;
	if ((err = unshare_fd(unshare_flags, &new_fd)))
		goto bad_unshare_cleanup_vm;
	if ((err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy,
			new_fs)))
		goto bad_unshare_cleanup_fd;

	if (new_fs ||  new_mm || new_fd || do_sysvsem || new_nsproxy) {
		if (do_sysvsem) {
			/*
			 * CLONE_SYSVSEM is equivalent to sys_exit().
			 */
			exit_sem(current);
		}

		if (new_nsproxy) {
			switch_task_namespaces(current, new_nsproxy);
			new_nsproxy = NULL;
		}

		task_lock(current);

		if (new_fs) {
			fs = current->fs;
			write_lock(&fs->lock);
			current->fs = new_fs;
			if (--fs->users)
				new_fs = NULL;
			else
				new_fs = fs;
			write_unlock(&fs->lock);
		}

		if (new_mm) {
			mm = current->mm;
			active_mm = current->active_mm;
			current->mm = new_mm;
			current->active_mm = new_mm;
			activate_mm(active_mm, new_mm);
			new_mm = mm;
		}

		if (new_fd) {
			fd = current->files;
			current->files = new_fd;
			new_fd = fd;
		}

		task_unlock(current);
	}

	if (new_nsproxy)
		put_nsproxy(new_nsproxy);

bad_unshare_cleanup_fd:
	if (new_fd)
		put_files_struct(new_fd);

bad_unshare_cleanup_vm:
	if (new_mm)
		mmput(new_mm);

bad_unshare_cleanup_sigh:
	if (new_sigh)
		if (atomic_dec_and_test(&new_sigh->count))
			kmem_cache_free(sighand_cachep, new_sigh);

bad_unshare_cleanup_fs:
	if (new_fs)
		free_fs_struct(new_fs);

bad_unshare_cleanup_thread:
bad_unshare_out:
	return err;
}

/*
 *	Helper to unshare the files of the current task.
 *	We don't want to expose copy_files internals to
 *	the exec layer of the kernel.
 */

int unshare_files(struct files_struct **displaced)
{
	struct task_struct *task = current;
	struct files_struct *copy = NULL;
	int error;

	error = unshare_fd(CLONE_FILES, &copy);
	if (error || !copy) {
		*displaced = NULL;
		return error;
	}
	*displaced = task->files;
	task_lock(task);
	task->files = copy;
	task_unlock(task);
	return 0;
}