sys.c

linux 2.6.19 kernel source code before patching

			}
			GROUP_AT(group_info, right) = tmp;
		}
		stride /= 3;
	}
}

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

	if (!group_info)
		return 0;

	left = 0;
	right = group_info->ngroups;
	while (left < right) {
		unsigned 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 */
	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:
	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)
		retval = groups_search(current->group_info, grp);
	return retval;
}

EXPORT_SYMBOL(in_group_p);

int in_egroup_p(gid_t grp)
{
	int retval = 1;
	if (grp != current->egid)
		retval = groups_search(current->group_info, grp);
	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, 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(utsname()->nodename, tmp, len);
		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(utsname()->nodename);
	if (i > len)
		i = len;
	errno = 0;
	if (copy_to_user(name, 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(utsname()->domainname, tmp, len);
		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;
	unsigned long it_prof_secs;
	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;

	if (resource == RLIMIT_CPU && new_rlim.rlim_cur == 0) {
		/*
		 * The caller is asking for an immediate RLIMIT_CPU
		 * expiry.  But we use the zero value to mean "it was
		 * never set".  So let's cheat and make it one second
		 * instead
		 */
		new_rlim.rlim_cur = 1;
	}

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

	if (resource != RLIMIT_CPU)
		goto out;

	/*
	 * RLIMIT_CPU handling.   Note that the kernel fails to return an error
	 * code if it rejected the user's attempt to set RLIMIT_CPU.  This is a
	 * very long-standing error, and fixing it now risks breakage of
	 * applications, so we live with it
	 */
	if (new_rlim.rlim_cur == RLIM_INFINITY)
		goto out;

	it_prof_secs = cputime_to_secs(current->signal->it_prof_expires);
	if (it_prof_secs == 0 || new_rlim.rlim_cur <= it_prof_secs) {
		unsigned long rlim_cur = new_rlim.rlim_cur;
		cputime_t cputime;

		cputime = secs_to_cputime(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);
	}
out:
	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).
 *
 * 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.
 *
 * Locking:
 * We need to take the siglock for CHILDEREN, SELF and BOTH
 * for  the cases current multithreaded, non-current single threaded
 * non-current multithreaded.  Thread traversal is now safe with
 * the siglock held.
 * Strictly speaking, we donot need to take the siglock if we are current and
 * single threaded,  as no one else can take our signal_struct away, no one
 * else can  reap the  children to update signal->c* counters, and no one else
 * can race with the signal-> fields. If we do not take any lock, the
 * signal-> fields could be read out of order while another thread was just
 * exiting. So we should  place a read memory barrier when we avoid the lock.
 * On the writer side,  write memory barrier is implied in  __exit_signal
 * as __exit_signal releases  the siglock spinlock after updating the signal->
 * fields. But we don't do this yet to keep things simple.
 *
 */

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);
	utime = stime = cputime_zero;

	rcu_read_lock();
	if (!lock_task_sighand(p, &flags)) {
		rcu_read_unlock();
		return;
	}

	switch (who) {
		case RUSAGE_BOTH:
		case RUSAGE_CHILDREN:
			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;
			r->ru_inblock = p->signal->cinblock;
			r->ru_oublock = p->signal->coublock;

			if (who == RUSAGE_CHILDREN)
				break;

		case RUSAGE_SELF:
			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;
			r->ru_inblock += p->signal->inblock;
			r->ru_oublock += p->signal->oublock;
			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;
				r->ru_inblock += task_io_get_inblock(t);
				r->ru_oublock += task_io_get_oublock(t);
				t = next_thread(t);
			} while (t != p);
			break;

		default:
			BUG();
	}

	unlock_task_sighand(p, &flags);
	rcu_read_unlock();

	cputime_to_timeval(utime, &r->ru_utime);
	cputime_to_timeval(stime, &r->ru_stime);
}

int getrusage(struct task_struct *p, int who, struct rusage __user *ru)
{
	struct rusage r;
	k_getrusage(p, who, &r);
	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;

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

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

		default:
			error = -EINVAL;
			break;
	}
	return error;
}

asmlinkage long sys_getcpu(unsigned __user *cpup, unsigned __user *nodep,
	   		   struct getcpu_cache __user *cache)
{
	int err = 0;
	int cpu = raw_smp_processor_id();
	if (cpup)
		err |= put_user(cpu, cpup);
	if (nodep)
		err |= put_user(cpu_to_node(cpu), nodep);
	if (cache) {
		/*
		 * The cache is not needed for this implementation,
		 * but make sure user programs pass something
		 * valid. vsyscall implementations can instead make
		 * good use of the cache. Only use t0 and t1 because
		 * these are available in both 32bit and 64bit ABI (no
		 * need for a compat_getcpu). 32bit has enough
		 * padding
		 */
		unsigned long t0, t1;
		get_user(t0, &cache->blob[0]);
		get_user(t1, &cache->blob[1]);
		t0++;
		t1++;
		put_user(t0, &cache->blob[0]);
		put_user(t1, &cache->blob[1]);
	}
	return err ? -EFAULT : 0;
}