fork.c

	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;
 	}
#endif

#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;

	/*
	 * 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->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());

	/*
	 * Check for pending SIGKILL! The new thread should not be allowed
	 * to slip out of an OOM kill. (or normal SIGKILL.)
	 */
	if (sigismember(&current->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;

	spin_lock(&current->sighand->siglock);
	if (clone_flags & CLONE_THREAD) {
		/*
		 * 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(&current->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);
		}

		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(&current->signal->cpu_timers[0]) ||
		    !list_empty(&current->signal->cpu_timers[1]) ||
		    !list_empty(&current->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;

	SET_LINKS(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);
		if (p->pid)
			__get_cpu_var(process_counts)++;
	}
	attach_pid(p, PIDTYPE_TGID, p->tgid);
	attach_pid(p, PIDTYPE_PID, p->pid);

	nr_threads++;
	total_forks++;
	spin_unlock(&current->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:
	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);
bad_fork_cleanup_cpuset:
#endif
	cpuset_exit(p);
bad_fork_cleanup:
	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);
}

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

task_t * __devinit fork_idle(int cpu)
{
	task_t *task;
	struct pt_regs regs;

	task = copy_process(CLONE_VM, 0, idle_regs(&regs), 0, NULL, NULL, 0);
	if (!task)
		return ERR_PTR(-ENOMEM);
	init_idle(task, cpu);
	unhash_process(task);
	return task;
}

static inline int fork_traceflag (unsigned clone_flags)
{
	if (clone_flags & CLONE_UNTRACED)
		return 0;
	else if (clone_flags & CLONE_VFORK) {
		if (current->ptrace & PT_TRACE_VFORK)
			return PTRACE_EVENT_VFORK;
	} else if ((clone_flags & CSIGNAL) != SIGCHLD) {
		if (current->ptrace & PT_TRACE_CLONE)
			return PTRACE_EVENT_CLONE;
	} else if (current->ptrace & PT_TRACE_FORK)
		return PTRACE_EVENT_FORK;

	return 0;
}

/*
 *  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 pid = alloc_pidmap();

	if (pid < 0)
		return -EAGAIN;
	if (unlikely(current->ptrace)) {
		trace = fork_traceflag (clone_flags);
		if (trace)
			clone_flags |= CLONE_PTRACE;
	}

	p = copy_process(clone_flags, stack_start, regs, stack_size, parent_tidptr, child_tidptr, pid);
	/*
	 * 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;

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

		if ((p->ptrace & PT_PTRACED) || (clone_flags & CLONE_STOPPED)) {
			/*
			 * We'll start up with an immediate SIGSTOP.
			 */
			sigaddset(&p->pending.signal, SIGSTOP);
			set_tsk_thread_flag(p, TIF_SIGPENDING);
		}

		if (!(clone_flags & CLONE_STOPPED))
			wake_up_new_task(p, clone_flags);
		else
			p->state = TASK_STOPPED;

		if (unlikely (trace)) {
			current->ptrace_message = pid;
			ptrace_notify ((trace << 8) | SIGTRAP);
		}

		if (clone_flags & CLONE_VFORK) {
			wait_for_completion(&vfork);
			if (unlikely (current->ptrace & PT_TRACE_VFORK_DONE))
				ptrace_notify ((PTRACE_EVENT_VFORK_DONE << 8) | SIGTRAP);
		}
	} else {
		free_pidmap(pid);
		pid = PTR_ERR(p);
	}
	return pid;
}

#ifndef ARCH_MIN_MMSTRUCT_ALIGN
#define ARCH_MIN_MMSTRUCT_ALIGN 0
#endif

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


/*
 * Check constraints on flags passed to the unshare system call and
 * force unsharing of additional process context as appropriate.
 */
static inline 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 && atomic_read(&fs->count) > 1)) {
		*new_fsp = __copy_fs_struct(current->fs);
		if (!*new_fsp)
			return -ENOMEM;
	}

	return 0;
}

/*
 * Unshare the namespace structure if it is being shared
 */
static int unshare_namespace(unsigned long unshare_flags, struct namespace **new_nsp, struct fs_struct *new_fs)
{
	struct namespace *ns = current->namespace;

	if ((unshare_flags & CLONE_NEWNS) &&
	    (ns && atomic_read(&ns->count) > 1)) {
		if (!capable(CAP_SYS_ADMIN))
			return -EPERM;

		*new_nsp = dup_namespace(current, new_fs ? new_fs : current->fs);
		if (!*new_nsp)
			return -ENOMEM;
	}

	return 0;
}

/*
 * Unsharing of sighand for tasks created with CLONE_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) &&
	    (sigh && 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;
}

/*
 * Unsharing of semundo for tasks created with CLONE_SYSVSEM is not
 * supported yet
 */
static int unshare_semundo(unsigned long unshare_flags, struct sem_undo_list **new_ulistp)
{
	if (unshare_flags & CLONE_SYSVSEM)
		return -EINVAL;

	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.
 */
asmlinkage long sys_unshare(unsigned long unshare_flags)
{
	int err = 0;
	struct fs_struct *fs, *new_fs = NULL;
	struct namespace *ns, *new_ns = NULL;
	struct sighand_struct *sigh, *new_sigh = NULL;
	struct mm_struct *mm, *new_mm = NULL, *active_mm = NULL;
	struct files_struct *fd, *new_fd = NULL;
	struct sem_undo_list *new_ulist = NULL;

	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))
		goto bad_unshare_out;

	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_namespace(unshare_flags, &new_ns, new_fs)))
		goto bad_unshare_cleanup_fs;
	if ((err = unshare_sighand(unshare_flags, &new_sigh)))
		goto bad_unshare_cleanup_ns;
	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_semundo(unshare_flags, &new_ulist)))
		goto bad_unshare_cleanup_fd;

	if (new_fs || new_ns || new_sigh || new_mm || new_fd || new_ulist) {

		task_lock(current);

		if (new_fs) {
			fs = current->fs;
			current->fs = new_fs;
			new_fs = fs;
		}

		if (new_ns) {
			ns = current->namespace;
			current->namespace = new_ns;
			new_ns = ns;
		}

		if (new_sigh) {
			sigh = current->sighand;
			rcu_assign_pointer(current->sighand, new_sigh);
			new_sigh = sigh;
		}

		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);
	}

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_ns:
	if (new_ns)
		put_namespace(new_ns);

bad_unshare_cleanup_fs:
	if (new_fs)
		put_fs_struct(new_fs);

bad_unshare_cleanup_thread:
bad_unshare_out:
	return err;
}