linux/fs/compat.c

/*
 *  linux/fs/compat.c
 *
 *  Kernel compatibililty routines for e.g. 32 bit syscall support
 *  on 64 bit kernels.
 *
 *  Copyright (C) 2002       Stephen Rothwell, IBM Corporation
 *  Copyright (C) 1997-2000  Jakub Jelinek  (jakub@redhat.com)
 *  Copyright (C) 1998       Eddie C. Dost  (ecd@skynet.be)
 *  Copyright (C) 2001,2002  Andi Kleen, SuSE Labs 
 *  Copyright (C) 2003       Pavel Machek (pavel@ucw.cz)
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License version 2 as
 *  published by the Free Software Foundation.
 */

#include <linux/stddef.h>
#include <linux/kernel.h>
#include <linux/linkage.h>
#include <linux/compat.h>
#include <linux/errno.h>
#include <linux/time.h>
#include <linux/cred.h>
#include <linux/fs.h>
#include <linux/fcntl.h>
#include <linux/namei.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/vfs.h>
#include <linux/ioctl.h>
#include <linux/init.h>
#include <linux/ncp_mount.h>
#include <linux/nfs4_mount.h>
#include <linux/syscalls.h>
#include <linux/ctype.h>
#include <linux/dirent.h>
#include <linux/fsnotify.h>
#include <linux/highuid.h>
#include <linux/personality.h>
#include <linux/rwsem.h>
#include <linux/tsacct_kern.h>
#include <linux/security.h>
#include <linux/highmem.h>
#include <linux/signal.h>
#include <linux/mm.h>
#include <linux/fs_struct.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/aio.h>

#include <linux/uaccess.h>
#include <asm/mmu_context.h>
#include <asm/ioctls.h>
#include "internal.h"

static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf)
{
	struct compat_stat tmp;

	if (!old_valid_dev(stat->dev) || !old_valid_dev(stat->rdev))
		return -EOVERFLOW;

	memset(&tmp, 0, sizeof(tmp));
	tmp.st_dev = old_encode_dev(stat->dev);
	tmp.st_ino = stat->ino;
	if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
		return -EOVERFLOW;
	tmp.st_mode = stat->mode;
	tmp.st_nlink = stat->nlink;
	if (tmp.st_nlink != stat->nlink)
		return -EOVERFLOW;
	SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid));
	SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid));
	tmp.st_rdev = old_encode_dev(stat->rdev);
	if ((u64) stat->size > MAX_NON_LFS)
		return -EOVERFLOW;
	tmp.st_size = stat->size;
	tmp.st_atime = stat->atime.tv_sec;
	tmp.st_atime_nsec = stat->atime.tv_nsec;
	tmp.st_mtime = stat->mtime.tv_sec;
	tmp.st_mtime_nsec = stat->mtime.tv_nsec;
	tmp.st_ctime = stat->ctime.tv_sec;
	tmp.st_ctime_nsec = stat->ctime.tv_nsec;
	tmp.st_blocks = stat->blocks;
	tmp.st_blksize = stat->blksize;
	return copy_to_user(ubuf, &tmp, sizeof(tmp)) ? -EFAULT : 0;
}

COMPAT_SYSCALL_DEFINE2(newstat, const char __user *, filename,
		       struct compat_stat __user *, statbuf)
{
	struct kstat stat;
	int error;

	error = vfs_stat(filename, &stat);
	if (error)
		return error;
	return cp_compat_stat(&stat, statbuf);
}

COMPAT_SYSCALL_DEFINE2(newlstat, const char __user *, filename,
		       struct compat_stat __user *, statbuf)
{
	struct kstat stat;
	int error;

	error = vfs_lstat(filename, &stat);
	if (error)
		return error;
	return cp_compat_stat(&stat, statbuf);
}

#ifndef __ARCH_WANT_STAT64
COMPAT_SYSCALL_DEFINE4(newfstatat, unsigned int, dfd,
		       const char __user *, filename,
		       struct compat_stat __user *, statbuf, int, flag)
{
	struct kstat stat;
	int error;

	error = vfs_fstatat(dfd, filename, &stat, flag);
	if (error)
		return error;
	return cp_compat_stat(&stat, statbuf);
}
#endif

COMPAT_SYSCALL_DEFINE2(newfstat, unsigned int, fd,
		       struct compat_stat __user *, statbuf)
{
	struct kstat stat;
	int error = vfs_fstat(fd, &stat);

	if (!error)
		error = cp_compat_stat(&stat, statbuf);
	return error;
}

static int get_compat_flock(struct flock *kfl, struct compat_flock __user *ufl)
{
	if (!access_ok(VERIFY_READ, ufl, sizeof(*ufl)) ||
	    __get_user(kfl->l_type, &ufl->l_type) ||
	    __get_user(kfl->l_whence, &ufl->l_whence) ||
	    __get_user(kfl->l_start, &ufl->l_start) ||
	    __get_user(kfl->l_len, &ufl->l_len) ||
	    __get_user(kfl->l_pid, &ufl->l_pid))
		return -EFAULT;
	return 0;
}

static int put_compat_flock(struct flock *kfl, struct compat_flock __user *ufl)
{
	if (!access_ok(VERIFY_WRITE, ufl, sizeof(*ufl)) ||
	    __put_user(kfl->l_type, &ufl->l_type) ||
	    __put_user(kfl->l_whence, &ufl->l_whence) ||
	    __put_user(kfl->l_start, &ufl->l_start) ||
	    __put_user(kfl->l_len, &ufl->l_len) ||
	    __put_user(kfl->l_pid, &ufl->l_pid))
		return -EFAULT;
	return 0;
}

#ifndef HAVE_ARCH_GET_COMPAT_FLOCK64
static int get_compat_flock64(struct flock *kfl, struct compat_flock64 __user *ufl)
{
	if (!access_ok(VERIFY_READ, ufl, sizeof(*ufl)) ||
	    __get_user(kfl->l_type, &ufl->l_type) ||
	    __get_user(kfl->l_whence, &ufl->l_whence) ||
	    __get_user(kfl->l_start, &ufl->l_start) ||
	    __get_user(kfl->l_len, &ufl->l_len) ||
	    __get_user(kfl->l_pid, &ufl->l_pid))
		return -EFAULT;
	return 0;
}
#endif

#ifndef HAVE_ARCH_PUT_COMPAT_FLOCK64
static int put_compat_flock64(struct flock *kfl, struct compat_flock64 __user *ufl)
{
	if (!access_ok(VERIFY_WRITE, ufl, sizeof(*ufl)) ||
	    __put_user(kfl->l_type, &ufl->l_type) ||
	    __put_user(kfl->l_whence, &ufl->l_whence) ||
	    __put_user(kfl->l_start, &ufl->l_start) ||
	    __put_user(kfl->l_len, &ufl->l_len) ||
	    __put_user(kfl->l_pid, &ufl->l_pid))
		return -EFAULT;
	return 0;
}
#endif

static unsigned int
convert_fcntl_cmd(unsigned int cmd)
{
	switch (cmd) {
	case F_GETLK64:
		return F_GETLK;
	case F_SETLK64:
		return F_SETLK;
	case F_SETLKW64:
		return F_SETLKW;
	}

	return cmd;
}

COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
		       compat_ulong_t, arg)
{
	mm_segment_t old_fs;
	struct flock f;
	long ret;
	unsigned int conv_cmd;

	switch (cmd) {
	case F_GETLK:
	case F_SETLK:
	case F_SETLKW:
		ret = get_compat_flock(&f, compat_ptr(arg));
		if (ret != 0)
			break;
		old_fs = get_fs();
		set_fs(KERNEL_DS);
		ret = sys_fcntl(fd, cmd, (unsigned long)&f);
		set_fs(old_fs);
		if (cmd == F_GETLK && ret == 0) {
			/* GETLK was successful and we need to return the data...
			 * but it needs to fit in the compat structure.
			 * l_start shouldn't be too big, unless the original
			 * start + end is greater than COMPAT_OFF_T_MAX, in which
			 * case the app was asking for trouble, so we return
			 * -EOVERFLOW in that case.
			 * l_len could be too big, in which case we just truncate it,
			 * and only allow the app to see that part of the conflicting
			 * lock that might make sense to it anyway
			 */

			if (f.l_start > COMPAT_OFF_T_MAX)
				ret = -EOVERFLOW;
			if (f.l_len > COMPAT_OFF_T_MAX)
				f.l_len = COMPAT_OFF_T_MAX;
			if (ret == 0)
				ret = put_compat_flock(&f, compat_ptr(arg));
		}
		break;

	case F_GETLK64:
	case F_SETLK64:
	case F_SETLKW64:
	case F_OFD_GETLK:
	case F_OFD_SETLK:
	case F_OFD_SETLKW:
		ret = get_compat_flock64(&f, compat_ptr(arg));
		if (ret != 0)
			break;
		old_fs = get_fs();
		set_fs(KERNEL_DS);
		conv_cmd = convert_fcntl_cmd(cmd);
		ret = sys_fcntl(fd, conv_cmd, (unsigned long)&f);
		set_fs(old_fs);
		if ((conv_cmd == F_GETLK || conv_cmd == F_OFD_GETLK) && ret == 0) {
			/* need to return lock information - see above for commentary */
			if (f.l_start > COMPAT_LOFF_T_MAX)
				ret = -EOVERFLOW;
			if (f.l_len > COMPAT_LOFF_T_MAX)
				f.l_len = COMPAT_LOFF_T_MAX;
			if (ret == 0)
				ret = put_compat_flock64(&f, compat_ptr(arg));
		}
		break;

	default:
		ret = sys_fcntl(fd, cmd, arg);
		break;
	}
	return ret;
}

COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd,
		       compat_ulong_t, arg)
{
	switch (cmd) {
	case F_GETLK64:
	case F_SETLK64:
	case F_SETLKW64:
	case F_OFD_GETLK:
	case F_OFD_SETLK:
	case F_OFD_SETLKW:
		return -EINVAL;
	}
	return compat_sys_fcntl64(fd, cmd, arg);
}

/* A write operation does a read from user space and vice versa */
#define vrfy_dir(type) ((type) == READ ? VERIFY_WRITE : VERIFY_READ)

ssize_t compat_rw_copy_check_uvector(int type,
		const struct compat_iovec __user *uvector, unsigned long nr_segs,
		unsigned long fast_segs, struct iovec *fast_pointer,
		struct iovec **ret_pointer)
{
	compat_ssize_t tot_len;
	struct iovec *iov = *ret_pointer = fast_pointer;
	ssize_t ret = 0;
	int seg;

	/*
	 * SuS says "The readv() function *may* fail if the iovcnt argument
	 * was less than or equal to 0, or greater than {IOV_MAX}.  Linux has
	 * traditionally returned zero for zero segments, so...
	 */
	if (nr_segs == 0)
		goto out;

	ret = -EINVAL;
	if (nr_segs > UIO_MAXIOV)
		goto out;
	if (nr_segs > fast_segs) {
		ret = -ENOMEM;
		iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL);
		if (iov == NULL)
			goto out;
	}
	*ret_pointer = iov;

	ret = -EFAULT;
	if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector)))
		goto out;

	/*
	 * Single unix specification:
	 * We should -EINVAL if an element length is not >= 0 and fitting an
	 * ssize_t.
	 *
	 * In Linux, the total length is limited to MAX_RW_COUNT, there is
	 * no overflow possibility.
	 */
	tot_len = 0;
	ret = -EINVAL;
	for (seg = 0; seg < nr_segs; seg++) {
		compat_uptr_t buf;
		compat_ssize_t len;

		if (__get_user(len, &uvector->iov_len) ||
		   __get_user(buf, &uvector->iov_base)) {
			ret = -EFAULT;
			goto out;
		}
		if (len < 0)	/* size_t not fitting in compat_ssize_t .. */
			goto out;
		if (type >= 0 &&
		    !access_ok(vrfy_dir(type), compat_ptr(buf), len)) {
			ret = -EFAULT;
			goto out;
		}
		if (len > MAX_RW_COUNT - tot_len)
			len = MAX_RW_COUNT - tot_len;
		tot_len += len;
		iov->iov_base = compat_ptr(buf);
		iov->iov_len = (compat_size_t) len;
		uvector++;
		iov++;
	}
	ret = tot_len;

out:
	return ret;
}

struct compat_ncp_mount_data {
	compat_int_t version;
	compat_uint_t ncp_fd;
	__compat_uid_t mounted_uid;
	compat_pid_t wdog_pid;
	unsigned char mounted_vol[NCP_VOLNAME_LEN + 1];
	compat_uint_t time_out;
	compat_uint_t retry_count;
	compat_uint_t flags;
	__compat_uid_t uid;
	__compat_gid_t gid;
	compat_mode_t file_mode;
	compat_mode_t dir_mode;
};

struct compat_ncp_mount_data_v4 {
	compat_int_t version;
	compat_ulong_t flags;
	compat_ulong_t mounted_uid;
	compat_long_t wdog_pid;
	compat_uint_t ncp_fd;
	compat_uint_t time_out;
	compat_uint_t retry_count;
	compat_ulong_t uid;
	compat_ulong_t gid;
	compat_ulong_t file_mode;
	compat_ulong_t dir_mode;
};

static void *do_ncp_super_data_conv(void *raw_data)
{
	int version = *(unsigned int *)raw_data;

	if (version == 3) {
		struct compat_ncp_mount_data *c_n = raw_data;
		struct ncp_mount_data *n = raw_data;

		n->dir_mode = c_n->dir_mode;
		n->file_mode = c_n->file_mode;
		n->gid = c_n->gid;
		n->uid = c_n->uid;
		memmove (n->mounted_vol, c_n->mounted_vol, (sizeof (c_n->mounted_vol) + 3 * sizeof (unsigned int)));
		n->wdog_pid = c_n->wdog_pid;
		n->mounted_uid = c_n->mounted_uid;
	} else if (version == 4) {
		struct compat_ncp_mount_data_v4 *c_n = raw_data;
		struct ncp_mount_data_v4 *n = raw_data;

		n->dir_mode = c_n->dir_mode;
		n->file_mode = c_n->file_mode;
		n->gid = c_n->gid;
		n->uid = c_n->uid;
		n->retry_count = c_n->retry_count;
		n->time_out = c_n->time_out;
		n->ncp_fd = c_n->ncp_fd;
		n->wdog_pid = c_n->wdog_pid;
		n->mounted_uid = c_n->mounted_uid;
		n->flags = c_n->flags;
	} else if (version != 5) {
		return NULL;
	}

	return raw_data;
}


struct compat_nfs_string {
	compat_uint_t len;
	compat_uptr_t data;
};

static inline void compat_nfs_string(struct nfs_string *dst,
				     struct compat_nfs_string *src)
{
	dst->data = compat_ptr(src->data);
	dst->len = src->len;
}

struct compat_nfs4_mount_data_v1 {
	compat_int_t version;
	compat_int_t flags;
	compat_int_t rsize;
	compat_int_t wsize;
	compat_int_t timeo;
	compat_int_t retrans;
	compat_int_t acregmin;
	compat_int_t acregmax;
	compat_int_t acdirmin;
	compat_int_t acdirmax;
	struct compat_nfs_string client_addr;
	struct compat_nfs_string mnt_path;
	struct compat_nfs_string hostname;
	compat_uint_t host_addrlen;
	compat_uptr_t host_addr;
	compat_int_t proto;
	compat_int_t auth_flavourlen;
	compat_uptr_t auth_flavours;
};

static int do_nfs4_super_data_conv(void *raw_data)
{
	int version = *(compat_uint_t *) raw_data;

	if (version == 1) {
		struct compat_nfs4_mount_data_v1 *raw = raw_data;
		struct nfs4_mount_data *real = raw_data;

		/* copy the fields backwards */
		real->auth_flavours = compat_ptr(raw->auth_flavours);
		real->auth_flavourlen = raw->auth_flavourlen;
		real->proto = raw->proto;
		real->host_addr = compat_ptr(raw->host_addr);
		real->host_addrlen = raw->host_addrlen;
		compat_nfs_string(&real->hostname, &raw->hostname);
		compat_nfs_string(&real->mnt_path, &raw->mnt_path);
		compat_nfs_string(&real->client_addr, &raw->client_addr);
		real->acdirmax = raw->acdirmax;
		real->acdirmin = raw->acdirmin;
		real->acregmax = raw->acregmax;
		real->acregmin = raw->acregmin;
		real->retrans = raw->retrans;
		real->timeo = raw->timeo;
		real->wsize = raw->wsize;
		real->rsize = raw->rsize;
		real->flags = raw->flags;
		real->version = raw->version;
	}

	return 0;
}

#define NCPFS_NAME      "ncpfs"
#define NFS4_NAME	"nfs4"

COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name,
		       const char __user *, dir_name,
		       const char __user *, type, compat_ulong_t, flags,
		       const void __user *, data)
{
	char *kernel_type;
	void *options;
	char *kernel_dev;
	int retval;

	kernel_type = copy_mount_string(type);
	retval = PTR_ERR(kernel_type);
	if (IS_ERR(kernel_type))
		goto out;

	kernel_dev = copy_mount_string(dev_name);
	retval = PTR_ERR(kernel_dev);
	if (IS_ERR(kernel_dev))
		goto out1;

	options = copy_mount_options(data);
	retval = PTR_ERR(options);
	if (IS_ERR(options))
		goto out2;

	if (kernel_type && options) {
		if (!strcmp(kernel_type, NCPFS_NAME)) {
			do_ncp_super_data_conv(options);
		} else if (!strcmp(kernel_type, NFS4_NAME)) {
			retval = -EINVAL;
			if (do_nfs4_super_data_conv(options))
				goto out3;
		}
	}

	retval = do_mount(kernel_dev, dir_name, kernel_type, flags, options);

 out3:
	kfree(options);
 out2:
	kfree(kernel_dev);
 out1:
	kfree(kernel_type);
 out:
	return retval;
}

/*
 * Exactly like fs/open.c:sys_open(), except that it doesn't set the
 * O_LARGEFILE flag.
 */
COMPAT_SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode)
{
	return do_sys_open(AT_FDCWD, filename, flags, mode);
}

/*
 * Exactly like fs/open.c:sys_openat(), except that it doesn't set the
 * O_LARGEFILE flag.
 */
COMPAT_SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode)
{
	return do_sys_open(dfd, filename, flags, mode);
}

#ifdef CONFIG_FHANDLE
/*
 * Exactly like fs/open.c:sys_open_by_handle_at(), except that it
 * doesn't set the O_LARGEFILE flag.
 */
COMPAT_SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd,
			     struct file_handle __user *, handle, int, flags)
{
	return do_handle_open(mountdirfd, handle, flags);
}
#endif