/*
 *  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/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/poll.h>
#include <linux/mm.h>
#include <linux/fs_struct.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/aio.h>

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

int compat_log = 1;

int compat_printk(const char *fmt, ...)
{
	va_list ap;
	int ret;
	if (!compat_log)
		return 0;
	va_start(ap, fmt);
	ret = vprintk(fmt, ap);
	va_end(ap);
	return ret;
}

/*
 * Not all architectures have sys_utime, so implement this in terms
 * of sys_utimes.
 */
COMPAT_SYSCALL_DEFINE2(utime, const char __user *, filename,
		       struct compat_utimbuf __user *, t)
{
	struct timespec tv[2];

	if (t) {
		if (get_user(tv[0].tv_sec, &t->actime) ||
		    get_user(tv[1].tv_sec, &t->modtime))
			return -EFAULT;
		tv[0].tv_nsec = 0;
		tv[1].tv_nsec = 0;
	}
	return do_utimes(AT_FDCWD, filename, t ? tv : NULL, 0);
}

COMPAT_SYSCALL_DEFINE4(utimensat, unsigned int, dfd, const char __user *, filename, struct compat_timespec __user *, t, int, flags)
{
	struct timespec tv[2];

	if  (t) {
		if (compat_get_timespec(&tv[0], &t[0]) ||
		    compat_get_timespec(&tv[1], &t[1]))
			return -EFAULT;

		if (tv[0].tv_nsec == UTIME_OMIT && tv[1].tv_nsec == UTIME_OMIT)
			return 0;
	}
	return do_utimes(dfd, filename, t ? tv : NULL, flags);
}

COMPAT_SYSCALL_DEFINE3(futimesat, unsigned int, dfd, const char __user *, filename, struct compat_timeval __user *, t)
{
	struct timespec tv[2];

	if (t) {
		if (get_user(tv[0].tv_sec, &t[0].tv_sec) ||
		    get_user(tv[0].tv_nsec, &t[0].tv_usec) ||
		    get_user(tv[1].tv_sec, &t[1].tv_sec) ||
		    get_user(tv[1].tv_nsec, &t[1].tv_usec))
			return -EFAULT;
		if (tv[0].tv_nsec >= 1000000 || tv[0].tv_nsec < 0 ||
		    tv[1].tv_nsec >= 1000000 || tv[1].tv_nsec < 0)
			return -EINVAL;
		tv[0].tv_nsec *= 1000;
		tv[1].tv_nsec *= 1000;
	}
	return do_utimes(dfd, filename, t ? tv : NULL, 0);
}

COMPAT_SYSCALL_DEFINE2(utimes, const char __user *, filename, struct compat_timeval __user *, t)
{
	return compat_sys_futimesat(AT_FDCWD, filename, t);
}

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 put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs *kbuf)
{
	
	if (sizeof ubuf->f_blocks == 4) {
		if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail |
		     kbuf->f_bsize | kbuf->f_frsize) & 0xffffffff00000000ULL)
			return -EOVERFLOW;
		/* f_files and f_ffree may be -1; it's okay
		 * to stuff that into 32 bits */
		if (kbuf->f_files != 0xffffffffffffffffULL
		 && (kbuf->f_files & 0xffffffff00000000ULL))
			return -EOVERFLOW;
		if (kbuf->f_ffree != 0xffffffffffffffffULL
		 && (kbuf->f_ffree & 0xffffffff00000000ULL))
			return -EOVERFLOW;
	}
	if (!access_ok(VERIFY_WRITE, ubuf, sizeof(*ubuf)) ||
	    __put_user(kbuf->f_type, &ubuf->f_type) ||
	    __put_user(kbuf->f_bsize, &ubuf->f_bsize) ||
	    __put_user(kbuf->f_blocks, &ubuf->f_blocks) ||
	    __put_user(kbuf->f_bfree, &ubuf->f_bfree) ||
	    __put_user(kbuf->f_bavail, &ubuf->f_bavail) ||
	    __put_user(kbuf->f_files, &ubuf->f_files) ||
	    __put_user(kbuf->f_ffree, &ubuf->f_ffree) ||
	    __put_user(kbuf->f_namelen, &ubuf->f_namelen) ||
	    __put_user(kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]) ||
	    __put_user(kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]) ||
	    __put_user(kbuf->f_frsize, &ubuf->f_frsize) ||
	    __put_user(kbuf->f_flags, &ubuf->f_flags) ||
	    __clear_user(ubuf->f_spare, sizeof(ubuf->f_spare)))
		return -EFAULT;
	return 0;
}

/*
 * The following statfs calls are copies of code from fs/statfs.c and
 * should be checked against those from time to time
 */
COMPAT_SYSCALL_DEFINE2(statfs, const char __user *, pathname, struct compat_statfs __user *, buf)
{
	struct kstatfs tmp;
	int error = user_statfs(pathname, &tmp);
	if (!error)
		error = put_compat_statfs(buf, &tmp);
	return error;
}

COMPAT_SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct compat_statfs __user *, buf)
{
	struct kstatfs tmp;
	int error = fd_statfs(fd, &tmp);
	if (!error)
		error = put_compat_statfs(buf, &tmp);
	return error;
}

static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstatfs *kbuf)
{
	if (sizeof ubuf->f_blocks == 4) {
		if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail |
		     kbuf->f_bsize | kbuf->f_frsize) & 0xffffffff00000000ULL)
			return -EOVERFLOW;
		/* f_files and f_ffree may be -1; it's okay
		 * to stuff that into 32 bits */
		if (kbuf->f_files != 0xffffffffffffffffULL
		 && (kbuf->f_files & 0xffffffff00000000ULL))
			return -EOVERFLOW;
		if (kbuf->f_ffree != 0xffffffffffffffffULL
		 && (kbuf->f_ffree & 0xffffffff00000000ULL))
			return -EOVERFLOW;
	}
	if (!access_ok(VERIFY_WRITE, ubuf, sizeof(*ubuf)) ||
	    __put_user(kbuf->f_type, &ubuf->f_type) ||
	    __put_user(kbuf->f_bsize, &ubuf->f_bsize) ||
	    __put_user(kbuf->f_blocks, &ubuf->f_blocks) ||
	    __put_user(kbuf->f_bfree, &ubuf->f_bfree) ||
	    __put_user(kbuf->f_bavail, &ubuf->f_bavail) ||
	    __put_user(kbuf->f_files, &ubuf->f_files) ||
	    __put_user(kbuf->f_ffree, &ubuf->f_ffree) ||
	    __put_user(kbuf->f_namelen, &ubuf->f_namelen) ||
	    __put_user(kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]) ||
	    __put_user(kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]) ||
	    __put_user(kbuf->f_frsize, &ubuf->f_frsize) ||
	    __put_user(kbuf->f_flags, &ubuf->f_flags) ||
	    __clear_user(ubuf->f_spare, sizeof(ubuf->f_spare)))
		return -EFAULT;
	return 0;
}

COMPAT_SYSCALL_DEFINE3(statfs64, const char __user *, pathname, compat_size_t, sz, struct compat_statfs64 __user *, buf)
{
	struct kstatfs tmp;
	int error;

	if (sz != sizeof(*buf))
		return -EINVAL;

	error = user_statfs(pathname, &tmp);
	if (!error)
		error = put_compat_statfs64(buf, &tmp);
	return error;
}

COMPAT_SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, compat_size_t, sz, struct compat_statfs64 __user *, buf)
{
	struct kstatfs tmp;
	int error;

	if (sz != sizeof(*buf))
		return -EINVAL;

	error = fd_statfs(fd, &tmp);
	if (!error)
		error = put_compat_statfs64(buf, &tmp);
	return error;
}

/*
 * This is a copy of sys_ustat, just dealing with a structure layout.
 * Given how simple this syscall is that apporach is more maintainable
 * than the various conversion hacks.
 */
COMPAT_SYSCALL_DEFINE2(ustat, unsigned, dev, struct compat_ustat __user *, u)
{
	struct compat_ustat tmp;
	struct kstatfs sbuf;
	int err = vfs_ustat(new_decode_dev(dev), &sbuf);
	if (err)
		return err;

	memset(&tmp, 0, sizeof(struct compat_ustat));
	tmp.f_tfree = sbuf.f_bfree;
	tmp.f_tinode = sbuf.f_ffree;
	if (copy_to_user(u, &tmp, sizeof(struct compat_ustat)))
		return -EFAULT;
	return 0;
}

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);
}

COMPAT_SYSCALL_DEFINE2(io_setup, unsigned, nr_reqs, u32 __user *, ctx32p)
{
	long ret;
	aio_context_t ctx64;

	mm_segment_t oldfs = get_fs();
	if (unlikely(get_user(ctx64, ctx32p)))
		return -EFAULT;

	set_fs(KERNEL_DS);
	/* The __user pointer cast is valid because of the set_fs() */
	ret = sys_io_setup(nr_reqs, (aio_context_t __user *) &ctx64);
	set_fs(oldfs);
	/* truncating is ok because it's a user address */
	if (!ret)
		ret = put_user((u32) ctx64, ctx32p);
	return ret;
}

COMPAT_SYSCALL_DEFINE5(io_getevents, compat_aio_context_t, ctx_id,
		       compat_long_t, min_nr,
		       compat_long_t, nr,
		       struct io_event __user *, events,
		       struct compat_timespec __user *, timeout)
{
	struct timespec t;
	struct timespec __user *ut = NULL;

	if (timeout) {
		if (compat_get_timespec(&t, timeout))
			return -EFAULT;

		ut = compat_alloc_user_space(sizeof(*ut));
		if (copy_to_user(ut, &t, sizeof(t)) )
			return -EFAULT;
	} 
	return sys_io_getevents(ctx_id, min_nr, nr, events, ut);
}

/* 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 || nr_segs < 0)
		goto out;
	if (nr_segs > fast_segs) {
		ret = -ENOMEM;