linux32.c

来自「linux-2.4.29操作系统的源码」· C语言 代码 · 共 2,612 行 · 第 1/5 页

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) {
			sec = timeout / HZ;
			usec = timeout % HZ;
			usec *= (1000000/HZ);
		}
		put_user(sec, &tvp->tv_sec);
		put_user(usec, &tvp->tv_usec);
	}

	if (ret < 0)
		goto out;
	if (!ret) {
		ret = -ERESTARTNOHAND;
		if (signal_pending(current))
			goto out;
		ret = 0;
	}

	set_fd_set32(nn, inp, fds.res_in);
	set_fd_set32(nn, outp, fds.res_out);
	set_fd_set32(nn, exp, fds.res_ex);

out:
	kfree(bits);
out_nofds:
	return ret;
}



struct timespec32 {
	int 	tv_sec;
	int	tv_nsec;
};

extern asmlinkage int sys_sched_rr_get_interval(pid_t pid,
						struct timespec *interval);

asmlinkage int
sys32_sched_rr_get_interval(__kernel_pid_t32 pid, struct timespec32 *interval)
{
	struct timespec t;
	int ret;
	mm_segment_t old_fs = get_fs ();

	set_fs (KERNEL_DS);
	ret = sys_sched_rr_get_interval(pid, &t);
	set_fs (old_fs);
	if (put_user (t.tv_sec, &interval->tv_sec) ||
	    __put_user (t.tv_nsec, &interval->tv_nsec))
		return -EFAULT;
	return ret;
}


extern asmlinkage int sys_nanosleep(struct timespec *rqtp,
				    struct timespec *rmtp);

asmlinkage int
sys32_nanosleep(struct timespec32 *rqtp, struct timespec32 *rmtp)
{
	struct timespec t;
	int ret;
	mm_segment_t old_fs = get_fs ();

	if (get_user (t.tv_sec, &rqtp->tv_sec) ||
	    __get_user (t.tv_nsec, &rqtp->tv_nsec))
		return -EFAULT;

	set_fs (KERNEL_DS);
	ret = sys_nanosleep(&t, rmtp ? &t : NULL);
	set_fs (old_fs);
	if (rmtp && ret == -EINTR) {
		if (__put_user (t.tv_sec, &rmtp->tv_sec) ||
	    	    __put_user (t.tv_nsec, &rmtp->tv_nsec))
			return -EFAULT;
	}
	return ret;
}

struct tms32 {
	int tms_utime;
	int tms_stime;
	int tms_cutime;
	int tms_cstime;
};

extern asmlinkage long sys_times(struct tms * tbuf);
asmlinkage long sys32_times(struct tms32 *tbuf)
{
	struct tms t;
	long ret;
	mm_segment_t old_fs = get_fs();
	int err;

	set_fs(KERNEL_DS);
	ret = sys_times(tbuf ? &t : NULL);
	set_fs(old_fs);
	if (tbuf) {
		err = put_user (t.tms_utime, &tbuf->tms_utime);
		err |= __put_user (t.tms_stime, &tbuf->tms_stime);
		err |= __put_user (t.tms_cutime, &tbuf->tms_cutime);
		err |= __put_user (t.tms_cstime, &tbuf->tms_cstime);
		if (err)
			ret = -EFAULT;
	}
	return ret;
}

static int do_set_attach_filter(int fd, int level, int optname,
				char *optval, int optlen)
{
	struct sock_fprog32 {
		__u16 len;
		__u32 filter;
	} *fprog32 = (struct sock_fprog32 *)optval;
	struct sock_fprog kfprog;
	struct sock_filter *kfilter;
	unsigned int fsize;
	mm_segment_t old_fs;
	__u32 uptr;
	int ret;

	if (get_user(kfprog.len, &fprog32->len) ||
	    __get_user(uptr, &fprog32->filter))
		return -EFAULT;

	kfprog.filter = (struct sock_filter *)A(uptr);
	fsize = kfprog.len * sizeof(struct sock_filter);

	kfilter = (struct sock_filter *)kmalloc(fsize, GFP_KERNEL);
	if (kfilter == NULL)
		return -ENOMEM;

	if (copy_from_user(kfilter, kfprog.filter, fsize)) {
		kfree(kfilter);
		return -EFAULT;
	}

	kfprog.filter = kfilter;

	old_fs = get_fs();
	set_fs(KERNEL_DS);
	ret = sys_setsockopt(fd, level, optname,
			     (char *)&kfprog, sizeof(kfprog));
	set_fs(old_fs);

	kfree(kfilter);

	return ret;
}

static int do_set_icmpv6_filter(int fd, int level, int optname,
				char *optval, int optlen)
{
	struct icmp6_filter kfilter;
	mm_segment_t old_fs;
	int ret, i;

	if (copy_from_user(&kfilter, optval, sizeof(kfilter)))
		return -EFAULT;


	for (i = 0; i < 8; i += 2) {
		u32 tmp = kfilter.data[i];

		kfilter.data[i] = kfilter.data[i + 1];
		kfilter.data[i + 1] = tmp;
	}

	old_fs = get_fs();
	set_fs(KERNEL_DS);
	ret = sys_setsockopt(fd, level, optname,
			     (char *) &kfilter, sizeof(kfilter));
	set_fs(old_fs);

	return ret;
}