sys.c

ok_pgid:
	err = security_task_setpgid(p, pgid);
	if (err)
		goto out;

	if (process_group(p) != pgid) {
		detach_pid(p, PIDTYPE_PGID);
		p->signal->pgrp = pgid;
		attach_pid(p, PIDTYPE_PGID, pgid);
	}

	err = 0;
out:
	/* All paths lead to here, thus we are safe. -DaveM */
	write_unlock_irq(&tasklist_lock);
	return err;
}

asmlinkage long sys_getpgid(pid_t pid)
{
	if (!pid) {
		return process_group(current);
	} else {
		int retval;
		struct task_struct *p;

		read_lock(&tasklist_lock);
		p = find_task_by_pid(pid);

		retval = -ESRCH;
		if (p) {
			retval = security_task_getpgid(p);
			if (!retval)
				retval = process_group(p);
		}
		read_unlock(&tasklist_lock);
		return retval;
	}
}

#ifdef __ARCH_WANT_SYS_GETPGRP

asmlinkage long sys_getpgrp(void)
{
	/* SMP - assuming writes are word atomic this is fine */
	return process_group(current);
}

#endif

asmlinkage long sys_getsid(pid_t pid)
{
	if (!pid) {
		return current->signal->session;
	} else {
		int retval;
		struct task_struct *p;

		read_lock(&tasklist_lock);
		p = find_task_by_pid(pid);

		retval = -ESRCH;
		if(p) {
			retval = security_task_getsid(p);
			if (!retval)
				retval = p->signal->session;
		}
		read_unlock(&tasklist_lock);
		return retval;
	}
}

asmlinkage long sys_setsid(void)
{
	struct pid *pid;
	int err = -EPERM;

	if (!thread_group_leader(current))
		return -EINVAL;

	down(&tty_sem);
	write_lock_irq(&tasklist_lock);

	pid = find_pid(PIDTYPE_PGID, current->pid);
	if (pid)
		goto out;

	current->signal->leader = 1;
	__set_special_pids(current->pid, current->pid);
	current->signal->tty = NULL;
	current->signal->tty_old_pgrp = 0;
	err = process_group(current);
out:
	write_unlock_irq(&tasklist_lock);
	up(&tty_sem);
	return err;
}

/*
 * Supplementary group IDs
 */

/* init to 2 - one for init_task, one to ensure it is never freed */
struct group_info init_groups = { .usage = ATOMIC_INIT(2) };

struct group_info *groups_alloc(int gidsetsize)
{
	struct group_info *group_info;
	int nblocks;
	int i;

	nblocks = (gidsetsize + NGROUPS_PER_BLOCK - 1) / NGROUPS_PER_BLOCK;
	/* Make sure we always allocate at least one indirect block pointer */
	nblocks = nblocks ? : 1;
	group_info = kmalloc(sizeof(*group_info) + nblocks*sizeof(gid_t *), GFP_USER);
	if (!group_info)
		return NULL;
	group_info->ngroups = gidsetsize;
	group_info->nblocks = nblocks;
	atomic_set(&group_info->usage, 1);

	if (gidsetsize <= NGROUPS_SMALL) {
		group_info->blocks[0] = group_info->small_block;
	} else {
		for (i = 0; i < nblocks; i++) {
			gid_t *b;
			b = (void *)__get_free_page(GFP_USER);
			if (!b)
				goto out_undo_partial_alloc;
			group_info->blocks[i] = b;
		}
	}
	return group_info;

out_undo_partial_alloc:
	while (--i >= 0) {
		free_page((unsigned long)group_info->blocks[i]);
	}
	kfree(group_info);
	return NULL;
}

EXPORT_SYMBOL(groups_alloc);

void groups_free(struct group_info *group_info)
{
	if (group_info->blocks[0] != group_info->small_block) {
		int i;
		for (i = 0; i < group_info->nblocks; i++)
			free_page((unsigned long)group_info->blocks[i]);
	}
	kfree(group_info);
}

EXPORT_SYMBOL(groups_free);

/* export the group_info to a user-space array */
static int groups_to_user(gid_t __user *grouplist,
    struct group_info *group_info)
{
	int i;
	int count = group_info->ngroups;

	for (i = 0; i < group_info->nblocks; i++) {
		int cp_count = min(NGROUPS_PER_BLOCK, count);
		int off = i * NGROUPS_PER_BLOCK;
		int len = cp_count * sizeof(*grouplist);

		if (copy_to_user(grouplist+off, group_info->blocks[i], len))
			return -EFAULT;

		count -= cp_count;
	}
	return 0;
}

/* fill a group_info from a user-space array - it must be allocated already */
static int groups_from_user(struct group_info *group_info,
    gid_t __user *grouplist)
 {
	int i;
	int count = group_info->ngroups;

	for (i = 0; i < group_info->nblocks; i++) {
		int cp_count = min(NGROUPS_PER_BLOCK, count);
		int off = i * NGROUPS_PER_BLOCK;
		int len = cp_count * sizeof(*grouplist);

		if (copy_from_user(group_info->blocks[i], grouplist+off, len))
			return -EFAULT;

		count -= cp_count;
	}
	return 0;
}

/* a simple Shell sort */
static void groups_sort(struct group_info *group_info)
{
	int base, max, stride;
	int gidsetsize = group_info->ngroups;

	for (stride = 1; stride < gidsetsize; stride = 3 * stride + 1)
		; /* nothing */
	stride /= 3;

	while (stride) {
		max = gidsetsize - stride;
		for (base = 0; base < max; base++) {
			int left = base;
			int right = left + stride;
			gid_t tmp = GROUP_AT(group_info, right);

			while (left >= 0 && GROUP_AT(group_info, left) > tmp) {
				GROUP_AT(group_info, right) =
				    GROUP_AT(group_info, left);
				right = left;
				left -= stride;
			}
			GROUP_AT(group_info, right) = tmp;
		}
		stride /= 3;
	}
}

/* a simple bsearch */
static int groups_search(struct group_info *group_info, gid_t grp)
{
	int left, right;

	if (!group_info)
		return 0;

	left = 0;
	right = group_info->ngroups;
	while (left < right) {
		int mid = (left+right)/2;
		int cmp = grp - GROUP_AT(group_info, mid);
		if (cmp > 0)
			left = mid + 1;
		else if (cmp < 0)
			right = mid;
		else
			return 1;
	}
	return 0;
}

/* validate and set current->group_info */
int set_current_groups(struct group_info *group_info)
{
	int retval;
	struct group_info *old_info;

	retval = security_task_setgroups(group_info);
	if (retval)
		return retval;

	groups_sort(group_info);
	get_group_info(group_info);

	task_lock(current);
	old_info = current->group_info;
	current->group_info = group_info;
	task_unlock(current);

	put_group_info(old_info);

	return 0;
}

EXPORT_SYMBOL(set_current_groups);

asmlinkage long sys_getgroups(int gidsetsize, gid_t __user *grouplist)
{
	int i = 0;

	/*
	 *	SMP: Nobody else can change our grouplist. Thus we are
	 *	safe.
	 */

	if (gidsetsize < 0)
		return -EINVAL;

	/* no need to grab task_lock here; it cannot change */
	get_group_info(current->group_info);
	i = current->group_info->ngroups;
	if (gidsetsize) {
		if (i > gidsetsize) {
			i = -EINVAL;
			goto out;
		}
		if (groups_to_user(grouplist, current->group_info)) {
			i = -EFAULT;
			goto out;
		}
	}
out:
	put_group_info(current->group_info);
	return i;
}

/*
 *	SMP: Our groups are copy-on-write. We can set them safely
 *	without another task interfering.
 */
 
asmlinkage long sys_setgroups(int gidsetsize, gid_t __user *grouplist)
{
	struct group_info *group_info;
	int retval;

	if (!capable(CAP_SETGID))
		return -EPERM;
	if ((unsigned)gidsetsize > NGROUPS_MAX)
		return -EINVAL;

	group_info = groups_alloc(gidsetsize);
	if (!group_info)
		return -ENOMEM;
	retval = groups_from_user(group_info, grouplist);
	if (retval) {
		put_group_info(group_info);
		return retval;
	}

	retval = set_current_groups(group_info);
	put_group_info(group_info);

	return retval;
}

/*
 * Check whether we're fsgid/egid or in the supplemental group..
 */
int in_group_p(gid_t grp)
{
	int retval = 1;
	if (grp != current->fsgid) {
		get_group_info(current->group_info);
		retval = groups_search(current->group_info, grp);
		put_group_info(current->group_info);
	}
	return retval;
}

EXPORT_SYMBOL(in_group_p);

int in_egroup_p(gid_t grp)
{
	int retval = 1;
	if (grp != current->egid) {
		get_group_info(current->group_info);
		retval = groups_search(current->group_info, grp);
		put_group_info(current->group_info);
	}
	return retval;
}

EXPORT_SYMBOL(in_egroup_p);

DECLARE_RWSEM(uts_sem);

EXPORT_SYMBOL(uts_sem);

asmlinkage long sys_newuname(struct new_utsname __user * name)
{
	int errno = 0;

	down_read(&uts_sem);
	if (copy_to_user(name,&system_utsname,sizeof *name))
		errno = -EFAULT;
	up_read(&uts_sem);
	return errno;
}

asmlinkage long sys_sethostname(char __user *name, int len)
{
	int errno;
	char tmp[__NEW_UTS_LEN];

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (len < 0 || len > __NEW_UTS_LEN)
		return -EINVAL;
	down_write(&uts_sem);
	errno = -EFAULT;
	if (!copy_from_user(tmp, name, len)) {
		memcpy(system_utsname.nodename, tmp, len);
		system_utsname.nodename[len] = 0;
		errno = 0;
	}
	up_write(&uts_sem);
	return errno;
}

#ifdef __ARCH_WANT_SYS_GETHOSTNAME

asmlinkage long sys_gethostname(char __user *name, int len)
{
	int i, errno;

	if (len < 0)
		return -EINVAL;
	down_read(&uts_sem);
	i = 1 + strlen(system_utsname.nodename);
	if (i > len)
		i = len;
	errno = 0;
	if (copy_to_user(name, system_utsname.nodename, i))
		errno = -EFAULT;
	up_read(&uts_sem);
	return errno;
}

#endif

/*
 * Only setdomainname; getdomainname can be implemented by calling
 * uname()
 */
asmlinkage long sys_setdomainname(char __user *name, int len)
{
	int errno;
	char tmp[__NEW_UTS_LEN];

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (len < 0 || len > __NEW_UTS_LEN)
		return -EINVAL;

	down_write(&uts_sem);
	errno = -EFAULT;
	if (!copy_from_user(tmp, name, len)) {
		memcpy(system_utsname.domainname, tmp, len);
		system_utsname.domainname[len] = 0;
		errno = 0;
	}
	up_write(&uts_sem);
	return errno;
}

asmlinkage long sys_getrlimit(unsigned int resource, struct rlimit __user *rlim)
{
	if (resource >= RLIM_NLIMITS)
		return -EINVAL;
	else {
		struct rlimit value;
		task_lock(current->group_leader);
		value = current->signal->rlim[resource];
		task_unlock(current->group_leader);
		return copy_to_user(rlim, &value, sizeof(*rlim)) ? -EFAULT : 0;
	}
}

#ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT

/*
 *	Back compatibility for getrlimit. Needed for some apps.
 */
 
asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *rlim)
{
	struct rlimit x;
	if (resource >= RLIM_NLIMITS)
		return -EINVAL;

	task_lock(current->group_leader);
	x = current->signal->rlim[resource];
	task_unlock(current->group_leader);
	if(x.rlim_cur > 0x7FFFFFFF)
		x.rlim_cur = 0x7FFFFFFF;
	if(x.rlim_max > 0x7FFFFFFF)
		x.rlim_max = 0x7FFFFFFF;
	return copy_to_user(rlim, &x, sizeof(x))?-EFAULT:0;
}

#endif

asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim)
{
	struct rlimit new_rlim, *old_rlim;
	int retval;

	if (resource >= RLIM_NLIMITS)
		return -EINVAL;
	if(copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
		return -EFAULT;
       if (new_rlim.rlim_cur > new_rlim.rlim_max)
               return -EINVAL;
	old_rlim = current->signal->rlim + resource;
	if ((new_rlim.rlim_max > old_rlim->rlim_max) &&
	    !capable(CAP_SYS_RESOURCE))
		return -EPERM;
	if (resource == RLIMIT_NOFILE && new_rlim.rlim_max > NR_OPEN)
			return -EPERM;

	retval = security_task_setrlimit(resource, &new_rlim);
	if (retval)
		return retval;

	task_lock(current->group_leader);
	*old_rlim = new_rlim;
	task_unlock(current->group_leader);

	if (resource == RLIMIT_CPU && new_rlim.rlim_cur != RLIM_INFINITY &&
	    (cputime_eq(current->signal->it_prof_expires, cputime_zero) ||
	     new_rlim.rlim_cur <= cputime_to_secs(
		     current->signal->it_prof_expires))) {
		cputime_t cputime = secs_to_cputime(new_rlim.rlim_cur);
		read_lock(&tasklist_lock);
		spin_lock_irq(&current->sighand->siglock);
		set_process_cpu_timer(current, CPUCLOCK_PROF,
				      &cputime, NULL);
		spin_unlock_irq(&current->sighand->siglock);
		read_unlock(&tasklist_lock);
	}

	return 0;
}

/*
 * It would make sense to put struct rusage in the task_struct,
 * except that would make the task_struct be *really big*.  After
 * task_struct gets moved into malloc'ed memory, it would
 * make sense to do this.  It will make moving the rest of the information
 * a lot simpler!  (Which we're not doing right now because we're not
 * measuring them yet).
 *
 * This expects to be called with tasklist_lock read-locked or better,
 * and the siglock not locked.  It may momentarily take the siglock.
 *
 * When sampling multiple threads for RUSAGE_SELF, under SMP we might have
 * races with threads incrementing their own counters.  But since word
 * reads are atomic, we either get new values or old values and we don't
 * care which for the sums.  We always take the siglock to protect reading
 * the c* fields from p->signal from races with exit.c updating those
 * fields when reaping, so a sample either gets all the additions of a
 * given child after it's reaped, or none so this sample is before reaping.
 */

static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
{
	struct task_struct *t;
	unsigned long flags;
	cputime_t utime, stime;

	memset((char *) r, 0, sizeof *r);

	if (unlikely(!p->signal))
		return;

	switch (who) {
		case RUSAGE_CHILDREN:
			spin_lock_irqsave(&p->sighand->siglock, flags);
			utime = p->signal->cutime;
			stime = p->signal->cstime;
			r->ru_nvcsw = p->signal->cnvcsw;
			r->ru_nivcsw = p->signal->cnivcsw;
			r->ru_minflt = p->signal->cmin_flt;
			r->ru_majflt = p->signal->cmaj_flt;
			spin_unlock_irqrestore(&p->sighand->siglock, flags);
			cputime_to_timeval(utime, &r->ru_utime);
			cputime_to_timeval(stime, &r->ru_stime);
			break;
		case RUSAGE_SELF:
			spin_lock_irqsave(&p->sighand->siglock, flags);
			utime = stime = cputime_zero;
			goto sum_group;
		case RUSAGE_BOTH:
			spin_lock_irqsave(&p->sighand->siglock, flags);
			utime = p->signal->cutime;
			stime = p->signal->cstime;
			r->ru_nvcsw = p->signal->cnvcsw;
			r->ru_nivcsw = p->signal->cnivcsw;
			r->ru_minflt = p->signal->cmin_flt;
			r->ru_majflt = p->signal->cmaj_flt;
		sum_group:
			utime = cputime_add(utime, p->signal->utime);
			stime = cputime_add(stime, p->signal->stime);
			r->ru_nvcsw += p->signal->nvcsw;
			r->ru_nivcsw += p->signal->nivcsw;
			r->ru_minflt += p->signal->min_flt;
			r->ru_majflt += p->signal->maj_flt;
			t = p;
			do {
				utime = cputime_add(utime, t->utime);
				stime = cputime_add(stime, t->stime);
				r->ru_nvcsw += t->nvcsw;
				r->ru_nivcsw += t->nivcsw;
				r->ru_minflt += t->min_flt;
				r->ru_majflt += t->maj_flt;
				t = next_thread(t);
			} while (t != p);
			spin_unlock_irqrestore(&p->sighand->siglock, flags);
			cputime_to_timeval(utime, &r->ru_utime);
			cputime_to_timeval(stime, &r->ru_stime);
			break;
		default:
			BUG();
	}
}

int getrusage(struct task_struct *p, int who, struct rusage __user *ru)
{
	struct rusage r;
	read_lock(&tasklist_lock);
	k_getrusage(p, who, &r);
	read_unlock(&tasklist_lock);
	return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0;
}

asmlinkage long sys_getrusage(int who, struct rusage __user *ru)
{
	if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN)
		return -EINVAL;
	return getrusage(current, who, ru);
}

asmlinkage long sys_umask(int mask)
{
	mask = xchg(&current->fs->umask, mask & S_IRWXUGO);
	return mask;
}
    
asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
			  unsigned long arg4, unsigned long arg5)
{
	long error;
	int sig;

	error = security_task_prctl(option, arg2, arg3, arg4, arg5);
	if (error)
		return error;

	switch (option) {
		case PR_SET_PDEATHSIG:
			sig = arg2;
			if (!valid_signal(sig)) {
				error = -EINVAL;
				break;
			}
			current->pdeath_signal = sig;
			break;
		case PR_GET_PDEATHSIG:
			error = put_user(current->pdeath_signal, (int __user *)arg2);
			break;
		case PR_GET_DUMPABLE:
			if (current->mm->dumpable)
				error = 1;
			break;
		case PR_SET_DUMPABLE:
			if (arg2 < 0 || arg2 > 2) {
				error = -EINVAL;
				break;
			}
			current->mm->dumpable = arg2;
			break;

		case PR_SET_UNALIGN:
			error = SET_UNALIGN_CTL(current, arg2);
			break;
		case PR_GET_UNALIGN:
			error = GET_UNALIGN_CTL(current, arg2);
			break;
		case PR_SET_FPEMU:
			error = SET_FPEMU_CTL(current, arg2);
			break;
		case PR_GET_FPEMU:
			error = GET_FPEMU_CTL(current, arg2);
			break;
		case PR_SET_FPEXC:
			error = SET_FPEXC_CTL(current, arg2);
			break;
		case PR_GET_FPEXC:
			error = GET_FPEXC_CTL(current, arg2);
			break;
		case PR_GET_TIMING:
			error = PR_TIMING_STATISTICAL;
			break;
		case PR_SET_TIMING:
			if (arg2 == PR_TIMING_STATISTICAL)
				error = 0;
			else
				error = -EINVAL;
			break;

		case PR_GET_KEEPCAPS:
			if (current->keep_capabilities)
				error = 1;
			break;
		case PR_SET_KEEPCAPS:
			if (arg2 != 0 && arg2 != 1) {
				error = -EINVAL;
				break;
			}
			current->keep_capabilities = arg2;
			break;
		case PR_SET_NAME: {
			struct task_struct *me = current;
			unsigned char ncomm[sizeof(me->comm)];

			ncomm[sizeof(me->comm)-1] = 0;
			if (strncpy_from_user(ncomm, (char __user *)arg2,
						sizeof(me->comm)-1) < 0)
				return -EFAULT;
			set_task_comm(me, ncomm);
			return 0;
		}
		case PR_GET_NAME: {
			struct task_struct *me = current;
			unsigned char tcomm[sizeof(me->comm)];

			get_task_comm(tcomm, me);
			if (copy_to_user((char __user *)arg2, tcomm, sizeof(tcomm)))
				return -EFAULT;
			return 0;
		}
		default:
			error = -EINVAL;
			break;
	}
	return error;
}