linux32.c

该文件是rt_linux

{
	return sys32_wait4(pid, stat_addr, options, NULL);
}

#define RLIM_INFINITY32	0x7fffffff
#define RESOURCE32(x) ((x > RLIM_INFINITY32) ? RLIM_INFINITY32 : x)

struct rlimit32 {
	int	rlim_cur;
	int	rlim_max;
};

extern asmlinkage int sys_old_getrlimit(unsigned int resource, struct rlimit *rlim);

asmlinkage int
sys32_getrlimit(unsigned int resource, struct rlimit32 *rlim)
{
	struct rlimit r;
	int ret;
	mm_segment_t old_fs = get_fs ();

	set_fs (KERNEL_DS);
	ret = sys_old_getrlimit(resource, &r);
	set_fs (old_fs);
	if (!ret) {
		ret = put_user (RESOURCE32(r.rlim_cur), &rlim->rlim_cur);
		ret |= __put_user (RESOURCE32(r.rlim_max), &rlim->rlim_max);
	}
	return ret;
}

extern asmlinkage int sys_setrlimit(unsigned int resource, struct rlimit *rlim);

asmlinkage int
sys32_setrlimit(unsigned int resource, struct rlimit32 *rlim)
{
	struct rlimit r;
	int ret;
	mm_segment_t old_fs = get_fs ();

	if (resource >= RLIM_NLIMITS) return -EINVAL;
	if (get_user (r.rlim_cur, &rlim->rlim_cur) ||
	    __get_user (r.rlim_max, &rlim->rlim_max))
		return -EFAULT;
	if (r.rlim_cur == RLIM_INFINITY32)
		r.rlim_cur = RLIM_INFINITY;
	if (r.rlim_max == RLIM_INFINITY32)
		r.rlim_max = RLIM_INFINITY;
	set_fs (KERNEL_DS);
	ret = sys_setrlimit(resource, &r);
	set_fs (old_fs);
	return ret;
}

struct statfs32 {
	int	f_type;
	int	f_bsize;
	int	f_frsize;
	int	f_blocks;
	int	f_bfree;
	int	f_files;
	int	f_ffree;
	int	f_bavail;
	__kernel_fsid_t32	f_fsid;
	int	f_namelen;
	int	f_spare[6];
};

static inline int
put_statfs (struct statfs32 *ubuf, struct statfs *kbuf)
{
	int err;

	err = put_user (kbuf->f_type, &ubuf->f_type);
	err |= __put_user (kbuf->f_bsize, &ubuf->f_bsize);
	err |= __put_user (kbuf->f_blocks, &ubuf->f_blocks);
	err |= __put_user (kbuf->f_bfree, &ubuf->f_bfree);
	err |= __put_user (kbuf->f_bavail, &ubuf->f_bavail);
	err |= __put_user (kbuf->f_files, &ubuf->f_files);
	err |= __put_user (kbuf->f_ffree, &ubuf->f_ffree);
	err |= __put_user (kbuf->f_namelen, &ubuf->f_namelen);
	err |= __put_user (kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]);
	err |= __put_user (kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]);
	return err;
}

extern asmlinkage int sys_statfs(const char * path, struct statfs * buf);

asmlinkage int
sys32_statfs(const char * path, struct statfs32 *buf)
{
	int ret;
	struct statfs s;
	mm_segment_t old_fs = get_fs();

	set_fs (KERNEL_DS);
	ret = sys_statfs((const char *)path, &s);
	set_fs (old_fs);
	if (put_statfs(buf, &s))
		return -EFAULT;
	return ret;
}

extern asmlinkage int sys_fstatfs(unsigned int fd, struct statfs * buf);

asmlinkage int
sys32_fstatfs(unsigned int fd, struct statfs32 *buf)
{
	int ret;
	struct statfs s;
	mm_segment_t old_fs = get_fs();

	set_fs (KERNEL_DS);
	ret = sys_fstatfs(fd, &s);
	set_fs (old_fs);
	if (put_statfs(buf, &s))
		return -EFAULT;
	return ret;
}

extern asmlinkage int
sys_getrusage(int who, struct rusage *ru);

asmlinkage int
sys32_getrusage(int who, struct rusage32 *ru)
{
	struct rusage r;
	int ret;
	mm_segment_t old_fs = get_fs();

	set_fs (KERNEL_DS);
	ret = sys_getrusage(who, &r);
	set_fs (old_fs);
	if (put_rusage (ru, &r))
		return -EFAULT;

	return ret;
}

static inline long
get_tv32(struct timeval *o, struct timeval32 *i)
{
	return (!access_ok(VERIFY_READ, i, sizeof(*i)) ||
		(__get_user(o->tv_sec, &i->tv_sec) |
		 __get_user(o->tv_usec, &i->tv_usec)));
}

static inline long
get_it32(struct itimerval *o, struct itimerval32 *i)
{
	return (!access_ok(VERIFY_READ, i, sizeof(*i)) ||
		(__get_user(o->it_interval.tv_sec, &i->it_interval.tv_sec) |
		 __get_user(o->it_interval.tv_usec, &i->it_interval.tv_usec) |
		 __get_user(o->it_value.tv_sec, &i->it_value.tv_sec) |
		 __get_user(o->it_value.tv_usec, &i->it_value.tv_usec)));
}

static inline long
put_tv32(struct timeval32 *o, struct timeval *i)
{
	return (!access_ok(VERIFY_WRITE, o, sizeof(*o)) ||
		(__put_user(i->tv_sec, &o->tv_sec) |
		 __put_user(i->tv_usec, &o->tv_usec)));
}

static inline long
put_it32(struct itimerval32 *o, struct itimerval *i)
{
	return (!access_ok(VERIFY_WRITE, o, sizeof(*o)) ||
		(__put_user(i->it_interval.tv_sec, &o->it_interval.tv_sec) |
		 __put_user(i->it_interval.tv_usec, &o->it_interval.tv_usec) |
		 __put_user(i->it_value.tv_sec, &o->it_value.tv_sec) |
		 __put_user(i->it_value.tv_usec, &o->it_value.tv_usec)));
}

extern int do_getitimer(int which, struct itimerval *value);

asmlinkage int
sys32_getitimer(int which, struct itimerval32 *it)
{
	struct itimerval kit;
	int error;

	error = do_getitimer(which, &kit);
	if (!error && put_it32(it, &kit))
		error = -EFAULT;

	return error;
}

extern int do_setitimer(int which, struct itimerval *, struct itimerval *);


asmlinkage int
sys32_setitimer(int which, struct itimerval32 *in, struct itimerval32 *out)
{
	struct itimerval kin, kout;
	int error;

	if (in) {
		if (get_it32(&kin, in))
			return -EFAULT;
	} else
		memset(&kin, 0, sizeof(kin));

	error = do_setitimer(which, &kin, out ? &kout : NULL);
	if (error || !out)
		return error;
	if (put_it32(out, &kout))
		return -EFAULT;

	return 0;

}
asmlinkage unsigned long
sys32_alarm(unsigned int seconds)
{
	struct itimerval it_new, it_old;
	unsigned int oldalarm;

	it_new.it_interval.tv_sec = it_new.it_interval.tv_usec = 0;
	it_new.it_value.tv_sec = seconds;
	it_new.it_value.tv_usec = 0;
	do_setitimer(ITIMER_REAL, &it_new, &it_old);
	oldalarm = it_old.it_value.tv_sec;
	/* ehhh.. We can't return 0 if we have an alarm pending.. */
	/* And we'd better return too much than too little anyway */
	if (it_old.it_value.tv_usec)
		oldalarm++;

	return oldalarm;
}

/* Translations due to time_t size differences.  Which affects all
   sorts of things, like timeval and itimerval.  */


extern struct timezone sys_tz;
extern int do_sys_settimeofday(struct timeval *tv, struct timezone *tz);

asmlinkage int
sys32_gettimeofday(struct timeval32 *tv, struct timezone *tz)
{
	if (tv) {
		struct timeval ktv;
		do_gettimeofday(&ktv);
		if (put_tv32(tv, &ktv))
			return -EFAULT;
	}
	if (tz) {
		if (copy_to_user(tz, &sys_tz, sizeof(sys_tz)))
			return -EFAULT;
	}
	return 0;
}

asmlinkage int
sys32_settimeofday(struct timeval32 *tv, struct timezone *tz)
{
	struct timeval ktv;
	struct timezone ktz;

 	if (tv) {
		if (get_tv32(&ktv, tv))
			return -EFAULT;
	}
	if (tz) {
		if (copy_from_user(&ktz, tz, sizeof(ktz)))
			return -EFAULT;
	}

	return do_sys_settimeofday(tv ? &ktv : NULL, tz ? &ktz : NULL);
}

extern asmlinkage long sys_llseek(unsigned int fd, unsigned long offset_high,
			          unsigned long offset_low, loff_t * result,
			          unsigned int origin);

asmlinkage int sys32_llseek(unsigned int fd, unsigned int offset_high,
			    unsigned int offset_low, loff_t * result,
			    unsigned int origin)
{
	return sys_llseek(fd, offset_high, offset_low, result, origin);
}

struct iovec32 { unsigned int iov_base; int iov_len; };

typedef ssize_t (*IO_fn_t)(struct file *, char *, size_t, loff_t *);

static long
do_readv_writev32(int type, struct file *file, const struct iovec32 *vector,
		  u32 count)
{
	unsigned long tot_len;
	struct iovec iovstack[UIO_FASTIOV];
	struct iovec *iov=iovstack, *ivp;
	struct inode *inode;
	long retval, i;
	IO_fn_t fn;

	/* First get the "struct iovec" from user memory and
	 * verify all the pointers
	 */
	if (!count)
		return 0;
	if(verify_area(VERIFY_READ, vector, sizeof(struct iovec32)*count))
		return -EFAULT;
	if (count > UIO_MAXIOV)
		return -EINVAL;
	if (count > UIO_FASTIOV) {
		iov = kmalloc(count*sizeof(struct iovec), GFP_KERNEL);
		if (!iov)
			return -ENOMEM;
	}

	tot_len = 0;
	i = count;
	ivp = iov;
	while (i > 0) {
		u32 len;
		u32 buf;

		__get_user(len, &vector->iov_len);
		__get_user(buf, &vector->iov_base);
		tot_len += len;
		ivp->iov_base = (void *)A(buf);
		ivp->iov_len = (__kernel_size_t) len;
		vector++;
		ivp++;
		i--;
	}

	inode = file->f_dentry->d_inode;
	/* VERIFY_WRITE actually means a read, as we write to user space */
	retval = locks_verify_area((type == VERIFY_WRITE
				    ? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE),
				   inode, file, file->f_pos, tot_len);
	if (retval) {
		if (iov != iovstack)
			kfree(iov);
		return retval;
	}

	/* Then do the actual IO.  Note that sockets need to be handled
	 * specially as they have atomicity guarantees and can handle
	 * iovec's natively
	 */
	if (inode->i_sock) {
		int err;
		err = sock_readv_writev(type, inode, file, iov, count, tot_len);
		if (iov != iovstack)
			kfree(iov);
		return err;
	}

	if (!file->f_op) {
		if (iov != iovstack)
			kfree(iov);
		return -EINVAL;
	}
	/* VERIFY_WRITE actually means a read, as we write to user space */
	fn = file->f_op->read;
	if (type == VERIFY_READ)
		fn = (IO_fn_t) file->f_op->write;
	ivp = iov;
	while (count > 0) {
		void * base;
		int len, nr;

		base = ivp->iov_base;
		len = ivp->iov_len;
		ivp++;
		count--;
		nr = fn(file, base, len, &file->f_pos);
		if (nr < 0) {
			if (retval)
				break;
			retval = nr;
			break;
		}
		retval += nr;
		if (nr != len)
			break;
	}
	if (iov != iovstack)
		kfree(iov);

	return retval;
}

asmlinkage long
sys32_readv(int fd, struct iovec32 *vector, u32 count)
{
	struct file *file;
	ssize_t ret;

	ret = -EBADF;
	file = fget(fd);
	if (!file)
		goto bad_file;
	if (file->f_op && (file->f_mode & FMODE_READ) &&
	    (file->f_op->readv || file->f_op->read))
		ret = do_readv_writev32(VERIFY_WRITE, file, vector, count);

	fput(file);

bad_file:
	return ret;
}

asmlinkage long
sys32_writev(int fd, struct iovec32 *vector, u32 count)
{
	struct file *file;
	ssize_t ret;

	ret = -EBADF;
	file = fget(fd);
	if(!file)
		goto bad_file;
	if (file->f_op && (file->f_mode & FMODE_WRITE) &&
	    (file->f_op->writev || file->f_op->write))
	        ret = do_readv_writev32(VERIFY_READ, file, vector, count);
	fput(file);

bad_file:
	return ret;
}

/* From the Single Unix Spec: pread & pwrite act like lseek to pos + op +
   lseek back to original location.  They fail just like lseek does on
   non-seekable files.  */

asmlinkage ssize_t sys32_pread(unsigned int fd, char * buf,
			       size_t count, u32 unused, u64 a4, u64 a5)
{
	ssize_t ret;
	struct file * file;
	ssize_t (*read)(struct file *, char *, size_t, loff_t *);
	loff_t pos;

	ret = -EBADF;
	file = fget(fd);
	if (!file)
		goto bad_file;
	if (!(file->f_mode & FMODE_READ))
		goto out;
	pos = merge_64(a4, a5);
	ret = locks_verify_area(FLOCK_VERIFY_READ, file->f_dentry->d_inode,
				file, pos, count);
	if (ret)
		goto out;
	ret = -EINVAL;
	if (!file->f_op || !(read = file->f_op->read))
		goto out;
	if (pos < 0)
		goto out;
	ret = read(file, buf, count, &pos);
	if (ret > 0)
		dnotify_parent(file->f_dentry, DN_ACCESS);
out:
	fput(file);
bad_file:
	return ret;
}

asmlinkage ssize_t sys32_pwrite(unsigned int fd, const char * buf,
			        size_t count, u32 unused, u64 a4, u64 a5)
{
	ssize_t ret;
	struct file * file;
	ssize_t (*write)(struct file *, const char *, size_t, loff_t *);
	loff_t pos;

	ret = -EBADF;
	file = fget(fd);
	if (!file)
		goto bad_file;
	if (!(file->f_mode & FMODE_WRITE))
		goto out;
	pos = merge_64(a4, a5);
	ret = locks_verify_area(FLOCK_VERIFY_WRITE, file->f_dentry->d_inode,
				file, pos, count);
	if (ret)
		goto out;
	ret = -EINVAL;
	if (!file->f_op || !(write = file->f_op->write))
		goto out;
	if (pos < 0)
		goto out;

	ret = write(file, buf, count, &pos);
	if (ret > 0)
		dnotify_parent(file->f_dentry, DN_MODIFY);
out:
	fput(file);
bad_file:
	return ret;
}
/*
 * Ooo, nasty.  We need here to frob 32-bit unsigned longs to
 * 64-bit unsigned longs.
 */

static inline int
get_fd_set32(unsigned long n, unsigned long *fdset, u32 *ufdset)
{
	if (ufdset) {
		unsigned long odd;

		if (verify_area(VERIFY_WRITE, ufdset, n*sizeof(u32)))
			return -EFAULT;

		odd = n & 1UL;
		n &= ~1UL;
		while (n) {
			unsigned long h, l;
			__get_user(l, ufdset);
			__get_user(h, ufdset+1);
			ufdset += 2;
			*fdset++ = h << 32 | l;
			n -= 2;
		}
		if (odd)
			__get_user(*fdset, ufdset);
	} else {
		/* Tricky, must clear full unsigned long in the
		 * kernel fdset at the end, this makes sure that
		 * actually happens.
		 */
		memset(fdset, 0, ((n + 1) & ~1)*sizeof(u32));
	}
	return 0;
}

static inline void
set_fd_set32(unsigned long n, u32 *ufdset, unsigned long *fdset)
{
	unsigned long odd;

	if (!ufdset)
		return;

	odd = n & 1UL;
	n &= ~1UL;
	while (n) {
		unsigned long h, l;
		l = *fdset++;
		h = l >> 32;
		__put_user(l, ufdset);
		__put_user(h, ufdset+1);
		ufdset += 2;
		n -= 2;
	}
	if (odd)
		__put_user(*fdset, ufdset);
}

/*
 * We can actually return ERESTARTSYS instead of EINTR, but I'd
 * like to be certain this leads to no problems. So I return
 * EINTR just for safety.
 *
 * Update: ERESTARTSYS breaks at least the xview clock binary, so
 * I'm trying ERESTARTNOHAND which restart only when you want to.
 */
#define MAX_SELECT_SECONDS \
	((unsigned long) (MAX_SCHEDULE_TIMEOUT / HZ)-1)

asmlinkage int sys32_select(int n, u32 *inp, u32 *outp, u32 *exp, struct timeval32 *tvp)
{
	fd_set_bits fds;
	char *bits;
	unsigned long nn;
	long timeout;
	int ret, size;

	timeout = MAX_SCHEDULE_TIMEOUT;
	if (tvp) {
		time_t sec, usec;

		if ((ret = verify_area(VERIFY_READ, tvp, sizeof(*tvp)))
		    || (ret = __get_user(sec, &tvp->tv_sec))
		    || (ret = __get_user(usec, &tvp->tv_usec)))
			goto out_nofds;

		ret = -EINVAL;
		if(sec < 0 || usec < 0)
			goto out_nofds;

		if ((unsigned long) sec < MAX_SELECT_SECONDS) {
			timeout = (usec + 1000000/HZ - 1) / (1000000/HZ);
			timeout += sec * (unsigned long) HZ;
		}
	}

	ret = -EINVAL;
	if (n < 0)
		goto out_nofds;
	if (n > current->files->max_fdset)
		n = current->files->max_fdset;

	/*
	 * We need 6 bitmaps (in/out/ex for both incoming and outgoing),
	 * since we used fdset we need to allocate memory in units of
	 * long-words.
	 */
	ret = -ENOMEM;
	size = FDS_BYTES(n);
	bits = kmalloc(6 * size, GFP_KERNEL);
	if (!bits)
		goto out_nofds;
	fds.in      = (unsigned long *)  bits;
	fds.out     = (unsigned long *) (bits +   size);
	fds.ex      = (unsigned long *) (bits + 2*size);
	fds.res_in  = (unsigned long *) (bits + 3*size);
	fds.res_out = (unsigned long *) (bits + 4*size);
	fds.res_ex  = (unsigned long *) (bits + 5*size);

	nn = (n + 8*sizeof(u32) - 1) / (8*sizeof(u32));
	if ((ret = get_fd_set32(nn, fds.in, inp)) ||
	    (ret = get_fd_set32(nn, fds.out, outp)) ||
	    (ret = get_fd_set32(nn, fds.ex, exp)))
		goto out;
	zero_fd_set(n, fds.res_in);
	zero_fd_set(n, fds.res_out);
	zero_fd_set(n, fds.res_ex);

	ret = do_select(n, &fds, &timeout);

	if (tvp && !(current->personality & STICKY_TIMEOUTS)) {
		time_t sec = 0, usec = 0;
		if (timeout) {