[net-next-2.6.git] / fs / ioctl.c

/*
 *  linux/fs/ioctl.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

#include <linux/syscalls.h>
#include <linux/mm.h>
#include <linux/smp_lock.h>
#include <linux/capability.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/security.h>
#include <linux/module.h>
#include <linux/uaccess.h>
#include <linux/writeback.h>
#include <linux/buffer_head.h>
#include <linux/falloc.h>

#include <asm/ioctls.h>

/* So that the fiemap access checks can't overflow on 32 bit machines. */
#define FIEMAP_MAX_EXTENTS	(UINT_MAX / sizeof(struct fiemap_extent))

/**
 * vfs_ioctl - call filesystem specific ioctl methods
 * @filp:	open file to invoke ioctl method on
 * @cmd:	ioctl command to execute
 * @arg:	command-specific argument for ioctl
 *
 * Invokes filesystem specific ->unlocked_ioctl, if one exists; otherwise
 * invokes filesystem specific ->ioctl method.  If neither method exists,
 * returns -ENOTTY.
 *
 * Returns 0 on success, -errno on error.
 */
static long vfs_ioctl(struct file *filp, unsigned int cmd,
		      unsigned long arg)
{
	int error = -ENOTTY;

	if (!filp->f_op)
		goto out;

	if (filp->f_op->unlocked_ioctl) {
		error = filp->f_op->unlocked_ioctl(filp, cmd, arg);
		if (error == -ENOIOCTLCMD)
			error = -EINVAL;
		goto out;
	} else if (filp->f_op->ioctl) {
		lock_kernel();
		error = filp->f_op->ioctl(filp->f_path.dentry->d_inode,
					  filp, cmd, arg);
		unlock_kernel();
	}

 out:
	return error;
}

static int ioctl_fibmap(struct file *filp, int __user *p)
{
	struct address_space *mapping = filp->f_mapping;
	int res, block;

	/* do we support this mess? */
	if (!mapping->a_ops->bmap)
		return -EINVAL;
	if (!capable(CAP_SYS_RAWIO))
		return -EPERM;
	res = get_user(block, p);
	if (res)
		return res;
	res = mapping->a_ops->bmap(mapping, block);
	return put_user(res, p);
}

/**
 * fiemap_fill_next_extent - Fiemap helper function
 * @fieinfo:	Fiemap context passed into ->fiemap
 * @logical:	Extent logical start offset, in bytes
 * @phys:	Extent physical start offset, in bytes
 * @len:	Extent length, in bytes
 * @flags:	FIEMAP_EXTENT flags that describe this extent
 *
 * Called from file system ->fiemap callback. Will populate extent
 * info as passed in via arguments and copy to user memory. On
 * success, extent count on fieinfo is incremented.
 *
 * Returns 0 on success, -errno on error, 1 if this was the last
 * extent that will fit in user array.
 */
#define SET_UNKNOWN_FLAGS	(FIEMAP_EXTENT_DELALLOC)
#define SET_NO_UNMOUNTED_IO_FLAGS	(FIEMAP_EXTENT_DATA_ENCRYPTED)
#define SET_NOT_ALIGNED_FLAGS	(FIEMAP_EXTENT_DATA_TAIL|FIEMAP_EXTENT_DATA_INLINE)
int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical,
			    u64 phys, u64 len, u32 flags)
{
	struct fiemap_extent extent;
	struct fiemap_extent *dest = fieinfo->fi_extents_start;

	/* only count the extents */
	if (fieinfo->fi_extents_max == 0) {
		fieinfo->fi_extents_mapped++;
		return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
	}

	if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max)
		return 1;

	if (flags & SET_UNKNOWN_FLAGS)
		flags |= FIEMAP_EXTENT_UNKNOWN;
	if (flags & SET_NO_UNMOUNTED_IO_FLAGS)
		flags |= FIEMAP_EXTENT_ENCODED;
	if (flags & SET_NOT_ALIGNED_FLAGS)
		flags |= FIEMAP_EXTENT_NOT_ALIGNED;

	memset(&extent, 0, sizeof(extent));
	extent.fe_logical = logical;
	extent.fe_physical = phys;
	extent.fe_length = len;
	extent.fe_flags = flags;

	dest += fieinfo->fi_extents_mapped;
	if (copy_to_user(dest, &extent, sizeof(extent)))
		return -EFAULT;

	fieinfo->fi_extents_mapped++;
	if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max)
		return 1;
	return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
}
EXPORT_SYMBOL(fiemap_fill_next_extent);

/**
 * fiemap_check_flags - check validity of requested flags for fiemap
 * @fieinfo:	Fiemap context passed into ->fiemap
 * @fs_flags:	Set of fiemap flags that the file system understands
 *
 * Called from file system ->fiemap callback. This will compute the
 * intersection of valid fiemap flags and those that the fs supports. That
 * value is then compared against the user supplied flags. In case of bad user
 * flags, the invalid values will be written into the fieinfo structure, and
 * -EBADR is returned, which tells ioctl_fiemap() to return those values to
 * userspace. For this reason, a return code of -EBADR should be preserved.
 *
 * Returns 0 on success, -EBADR on bad flags.
 */
int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags)
{
	u32 incompat_flags;

	incompat_flags = fieinfo->fi_flags & ~(FIEMAP_FLAGS_COMPAT & fs_flags);
	if (incompat_flags) {
		fieinfo->fi_flags = incompat_flags;
		return -EBADR;
	}
	return 0;
}
EXPORT_SYMBOL(fiemap_check_flags);

static int fiemap_check_ranges(struct super_block *sb,
			       u64 start, u64 len, u64 *new_len)
{
	*new_len = len;

	if (len == 0)
		return -EINVAL;

	if (start > sb->s_maxbytes)
		return -EFBIG;

	/*
	 * Shrink request scope to what the fs can actually handle.
	 */
	if ((len > sb->s_maxbytes) ||
	    (sb->s_maxbytes - len) < start)
		*new_len = sb->s_maxbytes - start;

	return 0;
}

static int ioctl_fiemap(struct file *filp, unsigned long arg)
{
	struct fiemap fiemap;
	struct fiemap_extent_info fieinfo = { 0, };
	struct inode *inode = filp->f_path.dentry->d_inode;
	struct super_block *sb = inode->i_sb;
	u64 len;
	int error;

	if (!inode->i_op->fiemap)
		return -EOPNOTSUPP;

	if (copy_from_user(&fiemap, (struct fiemap __user *)arg,
			   sizeof(struct fiemap)))
		return -EFAULT;

	if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS)
		return -EINVAL;

	error = fiemap_check_ranges(sb, fiemap.fm_start, fiemap.fm_length,
				    &len);
	if (error)
		return error;

	fieinfo.fi_flags = fiemap.fm_flags;
	fieinfo.fi_extents_max = fiemap.fm_extent_count;
	fieinfo.fi_extents_start = (struct fiemap_extent *)(arg + sizeof(fiemap));

	if (fiemap.fm_extent_count != 0 &&
	    !access_ok(VERIFY_WRITE, fieinfo.fi_extents_start,
		       fieinfo.fi_extents_max * sizeof(struct fiemap_extent)))
		return -EFAULT;

	if (fieinfo.fi_flags & FIEMAP_FLAG_SYNC)
		filemap_write_and_wait(inode->i_mapping);

	error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start, len);
	fiemap.fm_flags = fieinfo.fi_flags;
	fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped;
	if (copy_to_user((char *)arg, &fiemap, sizeof(fiemap)))
		error = -EFAULT;

	return error;
}

#ifdef CONFIG_BLOCK

#define blk_to_logical(inode, blk) (blk << (inode)->i_blkbits)
#define logical_to_blk(inode, offset) (offset >> (inode)->i_blkbits);

/**
 * __generic_block_fiemap - FIEMAP for block based inodes (no locking)
 * @inode - the inode to map
 * @arg - the pointer to userspace where we copy everything to
 * @get_block - the fs's get_block function
 *
 * This does FIEMAP for block based inodes.  Basically it will just loop
 * through get_block until we hit the number of extents we want to map, or we
 * go past the end of the file and hit a hole.
 *
 * If it is possible to have data blocks beyond a hole past @inode->i_size, then
 * please do not use this function, it will stop at the first unmapped block
 * beyond i_size.
 *
 * If you use this function directly, you need to do your own locking. Use
 * generic_block_fiemap if you want the locking done for you.
 */

int __generic_block_fiemap(struct inode *inode,
			   struct fiemap_extent_info *fieinfo, u64 start,
			   u64 len, get_block_t *get_block)
{
	struct buffer_head tmp;
	unsigned int start_blk;
	long long length = 0, map_len = 0;
	u64 logical = 0, phys = 0, size = 0;
	u32 flags = FIEMAP_EXTENT_MERGED;
	int ret = 0, past_eof = 0, whole_file = 0;

	if ((ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC)))
		return ret;

	start_blk = logical_to_blk(inode, start);

	length = (long long)min_t(u64, len, i_size_read(inode));
	if (length < len)
		whole_file = 1;

	map_len = length;

	do {
		/*
		 * we set b_size to the total size we want so it will map as
		 * many contiguous blocks as possible at once
		 */
		memset(&tmp, 0, sizeof(struct buffer_head));
		tmp.b_size = map_len;

		ret = get_block(inode, start_blk, &tmp, 0);
		if (ret)
			break;

		/* HOLE */
		if (!buffer_mapped(&tmp)) {
			length -= blk_to_logical(inode, 1);
			start_blk++;

			/*
			 * we want to handle the case where there is an
			 * allocated block at the front of the file, and then
			 * nothing but holes up to the end of the file properly,
			 * to make sure that extent at the front gets properly
			 * marked with FIEMAP_EXTENT_LAST
			 */
			if (!past_eof &&
			    blk_to_logical(inode, start_blk) >=
			    blk_to_logical(inode, 0)+i_size_read(inode))
				past_eof = 1;

			/*
			 * first hole after going past the EOF, this is our
			 * last extent
			 */
			if (past_eof && size) {
				flags = FIEMAP_EXTENT_MERGED|FIEMAP_EXTENT_LAST;
				ret = fiemap_fill_next_extent(fieinfo, logical,
							      phys, size,
							      flags);
				break;
			}

			/* if we have holes up to/past EOF then we're done */
			if (length <= 0 || past_eof)
				break;
		} else {
			/*
			 * we have gone over the length of what we wanted to
			 * map, and it wasn't the entire file, so add the extent
			 * we got last time and exit.
			 *
			 * This is for the case where say we want to map all the
			 * way up to the second to the last block in a file, but
			 * the last block is a hole, making the second to last
			 * block FIEMAP_EXTENT_LAST.  In this case we want to
			 * see if there is a hole after the second to last block
			 * so we can mark it properly.  If we found data after
			 * we exceeded the length we were requesting, then we
			 * are good to go, just add the extent to the fieinfo
			 * and break
			 */
			if (length <= 0 && !whole_file) {
				ret = fiemap_fill_next_extent(fieinfo, logical,
							      phys, size,
							      flags);
				break;
			}

			/*
			 * if size != 0 then we know we already have an extent
			 * to add, so add it.
			 */
			if (size) {
				ret = fiemap_fill_next_extent(fieinfo, logical,
							      phys, size,
							      flags);
				if (ret)
					break;
			}

			logical = blk_to_logical(inode, start_blk);
			phys = blk_to_logical(inode, tmp.b_blocknr);
			size = tmp.b_size;
			flags = FIEMAP_EXTENT_MERGED;

			length -= tmp.b_size;
			start_blk += logical_to_blk(inode, size);

			/*
			 * If we are past the EOF, then we need to make sure as
			 * soon as we find a hole that the last extent we found
			 * is marked with FIEMAP_EXTENT_LAST
			 */
			if (!past_eof &&
			    logical+size >=
			    blk_to_logical(inode, 0)+i_size_read(inode))
				past_eof = 1;
		}
		cond_resched();
	} while (1);

	/* if ret is 1 then we just hit the end of the extent array */
	if (ret == 1)
		ret = 0;

	return ret;
}
EXPORT_SYMBOL(__generic_block_fiemap);

/**
 * generic_block_fiemap - FIEMAP for block based inodes
 * @inode: The inode to map
 * @fieinfo: The mapping information
 * @start: The initial block to map
 * @len: The length of the extect to attempt to map
 * @get_block: The block mapping function for the fs
 *
 * Calls __generic_block_fiemap to map the inode, after taking
 * the inode's mutex lock.
 */

int generic_block_fiemap(struct inode *inode,
			 struct fiemap_extent_info *fieinfo, u64 start,
			 u64 len, get_block_t *get_block)
{
	int ret;
	mutex_lock(&inode->i_mutex);
	ret = __generic_block_fiemap(inode, fieinfo, start, len, get_block);
	mutex_unlock(&inode->i_mutex);
	return ret;
}
EXPORT_SYMBOL(generic_block_fiemap);

#endif  /*  CONFIG_BLOCK  */

/*
 * This provides compatibility with legacy XFS pre-allocation ioctls
 * which predate the fallocate syscall.
 *
 * Only the l_start, l_len and l_whence fields of the 'struct space_resv'
 * are used here, rest are ignored.
 */
int ioctl_preallocate(struct file *filp, void __user *argp)
{
	struct inode *inode = filp->f_path.dentry->d_inode;
	struct space_resv sr;

	if (copy_from_user(&sr, argp, sizeof(sr)))
		return -EFAULT;

	switch (sr.l_whence) {
	case SEEK_SET:
		break;
	case SEEK_CUR:
		sr.l_start += filp->f_pos;
		break;
	case SEEK_END:
		sr.l_start += i_size_read(inode);
		break;
	default:
		return -EINVAL;
	}

	return do_fallocate(filp, FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len);
}

static int file_ioctl(struct file *filp, unsigned int cmd,
		unsigned long arg)
{
	struct inode *inode = filp->f_path.dentry->d_inode;
	int __user *p = (int __user *)arg;

	switch (cmd) {
	case FIBMAP:
		return ioctl_fibmap(filp, p);
	case FIONREAD:
		return put_user(i_size_read(inode) - filp->f_pos, p);
	case FS_IOC_RESVSP:
	case FS_IOC_RESVSP64:
		return ioctl_preallocate(filp, p);
	}

	return vfs_ioctl(filp, cmd, arg);
}

static int ioctl_fionbio(struct file *filp, int __user *argp)
{
	unsigned int flag;
	int on, error;

	error = get_user(on, argp);
	if (error)
		return error;
	flag = O_NONBLOCK;
#ifdef __sparc__
	/* SunOS compatibility item. */
	if (O_NONBLOCK != O_NDELAY)
		flag |= O_NDELAY;
#endif
	spin_lock(&filp->f_lock);
	if (on)
		filp->f_flags |= flag;
	else
		filp->f_flags &= ~flag;
	spin_unlock(&filp->f_lock);
	return error;
}

static int ioctl_fioasync(unsigned int fd, struct file *filp,
			  int __user *argp)
{
	unsigned int flag;
	int on, error;

	error = get_user(on, argp);
	if (error)
		return error;
	flag = on ? FASYNC : 0;

	/* Did FASYNC state change ? */
	if ((flag ^ filp->f_flags) & FASYNC) {
		if (filp->f_op && filp->f_op->fasync)
			/* fasync() adjusts filp->f_flags */
			error = filp->f_op->fasync(fd, filp, on);
		else
			error = -ENOTTY;
	}
	return error < 0 ? error : 0;
}

static int ioctl_fsfreeze(struct file *filp)
{
	struct super_block *sb = filp->f_path.dentry->d_inode->i_sb;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	/* If filesystem doesn't support freeze feature, return. */
	if (sb->s_op->freeze_fs == NULL)
		return -EOPNOTSUPP;

	/* If a blockdevice-backed filesystem isn't specified, return. */
	if (sb->s_bdev == NULL)
		return -EINVAL;

	/* Freeze */
	sb = freeze_bdev(sb->s_bdev);
	if (IS_ERR(sb))
		return PTR_ERR(sb);
	return 0;
}

static int ioctl_fsthaw(struct file *filp)
{
	struct super_block *sb = filp->f_path.dentry->d_inode->i_sb;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	/* If a blockdevice-backed filesystem isn't specified, return EINVAL. */
	if (sb->s_bdev == NULL)
		return -EINVAL;

	/* Thaw */
	return thaw_bdev(sb->s_bdev, sb);
}

/*
 * When you add any new common ioctls to the switches above and below
 * please update compat_sys_ioctl() too.
 *
 * do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d.
 * It's just a simple helper for sys_ioctl and compat_sys_ioctl.
 */
int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
	     unsigned long arg)
{
	int error = 0;
	int __user *argp = (int __user *)arg;

	switch (cmd) {
	case FIOCLEX:
		set_close_on_exec(fd, 1);
		break;

	case FIONCLEX:
		set_close_on_exec(fd, 0);
		break;

	case FIONBIO:
		error = ioctl_fionbio(filp, argp);
		break;

	case FIOASYNC:
		error = ioctl_fioasync(fd, filp, argp);
		break;

	case FIOQSIZE:
		if (S_ISDIR(filp->f_path.dentry->d_inode->i_mode) ||
		    S_ISREG(filp->f_path.dentry->d_inode->i_mode) ||
		    S_ISLNK(filp->f_path.dentry->d_inode->i_mode)) {
			loff_t res =
				inode_get_bytes(filp->f_path.dentry->d_inode);
			error = copy_to_user((loff_t __user *)arg, &res,
					     sizeof(res)) ? -EFAULT : 0;
		} else
			error = -ENOTTY;
		break;

	case FIFREEZE:
		error = ioctl_fsfreeze(filp);
		break;

	case FITHAW:
		error = ioctl_fsthaw(filp);
		break;

	case FS_IOC_FIEMAP:
		return ioctl_fiemap(filp, arg);

	case FIGETBSZ:
	{
		struct inode *inode = filp->f_path.dentry->d_inode;
		int __user *p = (int __user *)arg;
		return put_user(inode->i_sb->s_blocksize, p);
	}

	default:
		if (S_ISREG(filp->f_path.dentry->d_inode->i_mode))
			error = file_ioctl(filp, cmd, arg);
		else
			error = vfs_ioctl(filp, cmd, arg);
		break;
	}
	return error;
}

SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
{
	struct file *filp;
	int error = -EBADF;
	int fput_needed;

	filp = fget_light(fd, &fput_needed);
	if (!filp)
		goto out;

	error = security_file_ioctl(filp, cmd, arg);
	if (error)
		goto out_fput;

	error = do_vfs_ioctl(filp, fd, cmd, arg);
 out_fput:
	fput_light(filp, fput_needed);
 out:
	return error;
}
Commit	Line	Data
1da177e4 LT	1	/*
	2	* linux/fs/ioctl.c
	3	*
	4	* Copyright (C) 1991, 1992 Linus Torvalds
	5	*/
	6
1da177e4 LT	7	#include <linux/syscalls.h>
	8	#include <linux/mm.h>
	9	#include <linux/smp_lock.h>
16f7e0fe	10	#include <linux/capability.h>
1da177e4 LT	11	#include <linux/file.h>
	12	#include <linux/fs.h>
	13	#include <linux/security.h>
	14	#include <linux/module.h>
c9845ff1	15	#include <linux/uaccess.h>
68c9d702 JB	16	#include <linux/writeback.h>
68c9d702 JB	17	#include <linux/buffer_head.h>
3e63cbb1	18	#include <linux/falloc.h>
1da177e4	19
1da177e4 LT	20	#include <asm/ioctls.h>
1da177e4 LT	21
c4b929b8 MF	22	/* So that the fiemap access checks can't overflow on 32 bit machines. */
	23	#define FIEMAP_MAX_EXTENTS (UINT_MAX / sizeof(struct fiemap_extent))
	24
deb21db7 EZ	25	/**
deb21db7 EZ	26	* vfs_ioctl - call filesystem specific ioctl methods
f6a4c8bd CH	27	* @filp: open file to invoke ioctl method on
	28	* @cmd: ioctl command to execute
	29	* @arg: command-specific argument for ioctl
deb21db7 EZ	30	*
deb21db7 EZ	31	* Invokes filesystem specific ->unlocked_ioctl, if one exists; otherwise
f6a4c8bd	32	* invokes filesystem specific ->ioctl method. If neither method exists,
deb21db7 EZ	33	* returns -ENOTTY.
	34	*
	35	* Returns 0 on success, -errno on error.
	36	*/
67cde595 AB	37	static long vfs_ioctl(struct file *filp, unsigned int cmd,
67cde595 AB	38	unsigned long arg)
1da177e4 LT	39	{
	40	int error = -ENOTTY;
	41
	42	if (!filp->f_op)
	43	goto out;
	44
	45	if (filp->f_op->unlocked_ioctl) {
	46	error = filp->f_op->unlocked_ioctl(filp, cmd, arg);
	47	if (error == -ENOIOCTLCMD)
	48	error = -EINVAL;
	49	goto out;
64d67d21	50	} else if (filp->f_op->ioctl) {
1da177e4	51	lock_kernel();
64d67d21 AM	52	error = filp->f_op->ioctl(filp->f_path.dentry->d_inode,
64d67d21 AM	53	filp, cmd, arg);
1da177e4 LT	54	unlock_kernel();
	55	}
	56
	57	out:
	58	return error;
	59	}
	60
aa81a7c7 EZ	61	static int ioctl_fibmap(struct file filp, int __user p)
	62	{
	63	struct address_space *mapping = filp->f_mapping;
	64	int res, block;
	65
	66	/* do we support this mess? */
	67	if (!mapping->a_ops->bmap)
	68	return -EINVAL;
	69	if (!capable(CAP_SYS_RAWIO))
	70	return -EPERM;
	71	res = get_user(block, p);
	72	if (res)
	73	return res;
aa81a7c7	74	res = mapping->a_ops->bmap(mapping, block);
aa81a7c7 EZ	75	return put_user(res, p);
	76	}
	77
c4b929b8 MF	78	/**
	79	* fiemap_fill_next_extent - Fiemap helper function
	80	* @fieinfo: Fiemap context passed into ->fiemap
	81	* @logical: Extent logical start offset, in bytes
	82	* @phys: Extent physical start offset, in bytes
	83	* @len: Extent length, in bytes
	84	* @flags: FIEMAP_EXTENT flags that describe this extent
	85	*
	86	* Called from file system ->fiemap callback. Will populate extent
	87	* info as passed in via arguments and copy to user memory. On
	88	* success, extent count on fieinfo is incremented.
	89	*
	90	* Returns 0 on success, -errno on error, 1 if this was the last
	91	* extent that will fit in user array.
	92	*/
	93	#define SET_UNKNOWN_FLAGS (FIEMAP_EXTENT_DELALLOC)
	94	#define SET_NO_UNMOUNTED_IO_FLAGS (FIEMAP_EXTENT_DATA_ENCRYPTED)
	95	#define SET_NOT_ALIGNED_FLAGS (FIEMAP_EXTENT_DATA_TAIL\|FIEMAP_EXTENT_DATA_INLINE)
	96	int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical,
	97	u64 phys, u64 len, u32 flags)
	98	{
	99	struct fiemap_extent extent;
	100	struct fiemap_extent *dest = fieinfo->fi_extents_start;
	101
	102	/* only count the extents */
	103	if (fieinfo->fi_extents_max == 0) {
	104	fieinfo->fi_extents_mapped++;
	105	return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
	106	}
	107
	108	if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max)
	109	return 1;
	110
	111	if (flags & SET_UNKNOWN_FLAGS)
	112	flags \|= FIEMAP_EXTENT_UNKNOWN;
	113	if (flags & SET_NO_UNMOUNTED_IO_FLAGS)
	114	flags \|= FIEMAP_EXTENT_ENCODED;
	115	if (flags & SET_NOT_ALIGNED_FLAGS)
	116	flags \|= FIEMAP_EXTENT_NOT_ALIGNED;
	117
	118	memset(&extent, 0, sizeof(extent));
	119	extent.fe_logical = logical;
	120	extent.fe_physical = phys;
	121	extent.fe_length = len;
	122	extent.fe_flags = flags;
	123
	124	dest += fieinfo->fi_extents_mapped;
	125	if (copy_to_user(dest, &extent, sizeof(extent)))
	126	return -EFAULT;
	127
	128	fieinfo->fi_extents_mapped++;
	129	if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max)
	130	return 1;
	131	return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
	132	}
	133	EXPORT_SYMBOL(fiemap_fill_next_extent);
	134
	135	/**
	136	* fiemap_check_flags - check validity of requested flags for fiemap
	137	* @fieinfo: Fiemap context passed into ->fiemap
	138	* @fs_flags: Set of fiemap flags that the file system understands
	139	*
	140	* Called from file system ->fiemap callback. This will compute the
	141	* intersection of valid fiemap flags and those that the fs supports. That
142	* value is then compared against the user supplied flags. In case of bad user
143	* flags, the invalid values will be written into the fieinfo structure, and
144	* -EBADR is returned, which tells ioctl_fiemap() to return those values to
145	* userspace. For this reason, a return code of -EBADR should be preserved.
146	*
147	* Returns 0 on success, -EBADR on bad flags.
148	*/
149	int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags)
150	{
151	u32 incompat_flags;
152
153	incompat_flags = fieinfo->fi_flags & ~(FIEMAP_FLAGS_COMPAT & fs_flags);
154	if (incompat_flags) {
155	fieinfo->fi_flags = incompat_flags;
156	return -EBADR;
157	}
158	return 0;
159	}
160	EXPORT_SYMBOL(fiemap_check_flags);
161
162	static int fiemap_check_ranges(struct super_block *sb,
163	u64 start, u64 len, u64 *new_len)
164	{
165	*new_len = len;
166
167	if (len == 0)
168	return -EINVAL;
169
170	if (start > sb->s_maxbytes)
171	return -EFBIG;
172
173	/*
174	* Shrink request scope to what the fs can actually handle.
175	*/
176	if ((len > sb->s_maxbytes) \|\|
177	(sb->s_maxbytes - len) < start)
178	*new_len = sb->s_maxbytes - start;
179
180	return 0;
181	}
182
183	static int ioctl_fiemap(struct file *filp, unsigned long arg)
184	{
185	struct fiemap fiemap;
186	struct fiemap_extent_info fieinfo = { 0, };
187	struct inode *inode = filp->f_path.dentry->d_inode;
188	struct super_block *sb = inode->i_sb;
189	u64 len;
190	int error;
191
192	if (!inode->i_op->fiemap)
193	return -EOPNOTSUPP;
194
195	if (copy_from_user(&fiemap, (struct fiemap __user *)arg,
196	sizeof(struct fiemap)))
197	return -EFAULT;
198
199	if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS)
200	return -EINVAL;
201
202	error = fiemap_check_ranges(sb, fiemap.fm_start, fiemap.fm_length,
203	&len);
204	if (error)
205	return error;
206
207	fieinfo.fi_flags = fiemap.fm_flags;
208	fieinfo.fi_extents_max = fiemap.fm_extent_count;
209	fieinfo.fi_extents_start = (struct fiemap_extent *)(arg + sizeof(fiemap));
210
211	if (fiemap.fm_extent_count != 0 &&
212	!access_ok(VERIFY_WRITE, fieinfo.fi_extents_start,
213	fieinfo.fi_extents_max * sizeof(struct fiemap_extent)))
214	return -EFAULT;
215
216	if (fieinfo.fi_flags & FIEMAP_FLAG_SYNC)
217	filemap_write_and_wait(inode->i_mapping);
218
219	error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start, len);
220	fiemap.fm_flags = fieinfo.fi_flags;
221	fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped;
222	if (copy_to_user((char *)arg, &fiemap, sizeof(fiemap)))
223	error = -EFAULT;
224
225	return error;
226	}
227
06270d5d AB	228	#ifdef CONFIG_BLOCK
06270d5d AB	229
68c9d702 JB	230	#define blk_to_logical(inode, blk) (blk << (inode)->i_blkbits)
	231	#define logical_to_blk(inode, offset) (offset >> (inode)->i_blkbits);
	232
e9079cce SW	233	/**
e9079cce SW	234	* __generic_block_fiemap - FIEMAP for block based inodes (no locking)
68c9d702 JB	235	* @inode - the inode to map
	236	* @arg - the pointer to userspace where we copy everything to
	237	* @get_block - the fs's get_block function
	238	*
	239	* This does FIEMAP for block based inodes. Basically it will just loop
	240	* through get_block until we hit the number of extents we want to map, or we
	241	* go past the end of the file and hit a hole.
	242	*
	243	* If it is possible to have data blocks beyond a hole past @inode->i_size, then
	244	* please do not use this function, it will stop at the first unmapped block
e9079cce SW	245	* beyond i_size.
	246	*
	247	* If you use this function directly, you need to do your own locking. Use
	248	* generic_block_fiemap if you want the locking done for you.
68c9d702	249	*/
e9079cce SW	250
	251	int __generic_block_fiemap(struct inode *inode,
	252	struct fiemap_extent_info *fieinfo, u64 start,
	253	u64 len, get_block_t *get_block)
68c9d702 JB	254	{
	255	struct buffer_head tmp;
	256	unsigned int start_blk;
	257	long long length = 0, map_len = 0;
	258	u64 logical = 0, phys = 0, size = 0;
	259	u32 flags = FIEMAP_EXTENT_MERGED;
df3935ff	260	int ret = 0, past_eof = 0, whole_file = 0;
68c9d702 JB	261
	262	if ((ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC)))
	263	return ret;
	264
	265	start_blk = logical_to_blk(inode, start);
	266
68c9d702	267	length = (long long)min_t(u64, len, i_size_read(inode));
df3935ff JB	268	if (length < len)
	269	whole_file = 1;
	270
68c9d702 JB	271	map_len = length;
	272
	273	do {
	274	/*
	275	* we set b_size to the total size we want so it will map as
	276	* many contiguous blocks as possible at once
	277	*/
	278	memset(&tmp, 0, sizeof(struct buffer_head));
	279	tmp.b_size = map_len;
	280
	281	ret = get_block(inode, start_blk, &tmp, 0);
	282	if (ret)
	283	break;
	284
	285	/* HOLE */
	286	if (!buffer_mapped(&tmp)) {
df3935ff JB	287	length -= blk_to_logical(inode, 1);
	288	start_blk++;
	289
	290	/*
	291	* we want to handle the case where there is an
	292	* allocated block at the front of the file, and then
	293	* nothing but holes up to the end of the file properly,
	294	* to make sure that extent at the front gets properly
	295	* marked with FIEMAP_EXTENT_LAST
	296	*/
	297	if (!past_eof &&
	298	blk_to_logical(inode, start_blk) >=
	299	blk_to_logical(inode, 0)+i_size_read(inode))
	300	past_eof = 1;
	301
68c9d702 JB	302	/*
	303	* first hole after going past the EOF, this is our
	304	* last extent
	305	*/
df3935ff	306	if (past_eof && size) {
68c9d702 JB	307	flags = FIEMAP_EXTENT_MERGED\|FIEMAP_EXTENT_LAST;
	308	ret = fiemap_fill_next_extent(fieinfo, logical,
	309	phys, size,
	310	flags);
	311	break;
	312	}
	313
68c9d702	314	/* if we have holes up to/past EOF then we're done */
df3935ff	315	if (length <= 0 \|\| past_eof)
68c9d702	316	break;
68c9d702	317	} else {
df3935ff JB	318	/*
	319	* we have gone over the length of what we wanted to
	320	* map, and it wasn't the entire file, so add the extent
	321	* we got last time and exit.
	322	*
	323	* This is for the case where say we want to map all the
	324	* way up to the second to the last block in a file, but
	325	* the last block is a hole, making the second to last
	326	* block FIEMAP_EXTENT_LAST. In this case we want to
	327	* see if there is a hole after the second to last block
	328	* so we can mark it properly. If we found data after
	329	* we exceeded the length we were requesting, then we
	330	* are good to go, just add the extent to the fieinfo
	331	* and break
	332	*/
	333	if (length <= 0 && !whole_file) {
	334	ret = fiemap_fill_next_extent(fieinfo, logical,
	335	phys, size,
	336	flags);
	337	break;
	338	}
	339
	340	/*
	341	* if size != 0 then we know we already have an extent
	342	* to add, so add it.
	343	*/
	344	if (size) {
68c9d702 JB	345	ret = fiemap_fill_next_extent(fieinfo, logical,
	346	phys, size,
	347	flags);
	348	if (ret)
	349	break;
	350	}
	351
	352	logical = blk_to_logical(inode, start_blk);
	353	phys = blk_to_logical(inode, tmp.b_blocknr);
	354	size = tmp.b_size;
	355	flags = FIEMAP_EXTENT_MERGED;
	356
	357	length -= tmp.b_size;
	358	start_blk += logical_to_blk(inode, size);
	359
	360	/*
df3935ff JB	361	* If we are past the EOF, then we need to make sure as
	362	* soon as we find a hole that the last extent we found
	363	* is marked with FIEMAP_EXTENT_LAST
68c9d702	364	*/
df3935ff JB	365	if (!past_eof &&
	366	logical+size >=
	367	blk_to_logical(inode, 0)+i_size_read(inode))
	368	past_eof = 1;
68c9d702 JB	369	}
	370	cond_resched();
	371	} while (1);
	372
68c9d702 JB	373	/* if ret is 1 then we just hit the end of the extent array */
	374	if (ret == 1)
	375	ret = 0;
	376
	377	return ret;
	378	}
e9079cce SW	379	EXPORT_SYMBOL(__generic_block_fiemap);
	380
	381	/**
	382	* generic_block_fiemap - FIEMAP for block based inodes
	383	* @inode: The inode to map
	384	* @fieinfo: The mapping information
	385	* @start: The initial block to map
	386	* @len: The length of the extect to attempt to map
	387	* @get_block: The block mapping function for the fs
	388	*
	389	* Calls __generic_block_fiemap to map the inode, after taking
	390	* the inode's mutex lock.
	391	*/
	392
	393	int generic_block_fiemap(struct inode *inode,
	394	struct fiemap_extent_info *fieinfo, u64 start,
	395	u64 len, get_block_t *get_block)
	396	{
	397	int ret;
	398	mutex_lock(&inode->i_mutex);
	399	ret = __generic_block_fiemap(inode, fieinfo, start, len, get_block);
	400	mutex_unlock(&inode->i_mutex);
	401	return ret;
	402	}
68c9d702 JB	403	EXPORT_SYMBOL(generic_block_fiemap);
68c9d702 JB	404
06270d5d AB	405	#endif /* CONFIG_BLOCK */
06270d5d AB	406
3e63cbb1 AJ	407	/*
	408	* This provides compatibility with legacy XFS pre-allocation ioctls
	409	* which predate the fallocate syscall.
	410	*
	411	* Only the l_start, l_len and l_whence fields of the 'struct space_resv'
	412	* are used here, rest are ignored.
	413	*/
	414	int ioctl_preallocate(struct file filp, void __user argp)
	415	{
	416	struct inode *inode = filp->f_path.dentry->d_inode;
	417	struct space_resv sr;
	418
	419	if (copy_from_user(&sr, argp, sizeof(sr)))
	420	return -EFAULT;
	421
	422	switch (sr.l_whence) {
	423	case SEEK_SET:
	424	break;
	425	case SEEK_CUR:
	426	sr.l_start += filp->f_pos;
	427	break;
	428	case SEEK_END:
	429	sr.l_start += i_size_read(inode);
	430	break;
	431	default:
	432	return -EINVAL;
	433	}
	434
	435	return do_fallocate(filp, FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len);
	436	}
	437
1da177e4 LT	438	static int file_ioctl(struct file *filp, unsigned int cmd,
	439	unsigned long arg)
	440	{
c9845ff1	441	struct inode *inode = filp->f_path.dentry->d_inode;
1da177e4 LT	442	int __user p = (int __user )arg;
	443
	444	switch (cmd) {
c9845ff1	445	case FIBMAP:
aa81a7c7	446	return ioctl_fibmap(filp, p);
c9845ff1 EZ	447	case FIONREAD:
c9845ff1 EZ	448	return put_user(i_size_read(inode) - filp->f_pos, p);
3e63cbb1 AJ	449	case FS_IOC_RESVSP:
	450	case FS_IOC_RESVSP64:
	451	return ioctl_preallocate(filp, p);
1da177e4 LT	452	}
1da177e4 LT	453
deb21db7	454	return vfs_ioctl(filp, cmd, arg);
1da177e4 LT	455	}
1da177e4 LT	456
aa81a7c7 EZ	457	static int ioctl_fionbio(struct file filp, int __user argp)
	458	{
	459	unsigned int flag;
	460	int on, error;
	461
	462	error = get_user(on, argp);
	463	if (error)
	464	return error;
	465	flag = O_NONBLOCK;
	466	#ifdef __sparc__
	467	/* SunOS compatibility item. */
	468	if (O_NONBLOCK != O_NDELAY)
	469	flag \|= O_NDELAY;
	470	#endif
db1dd4d3	471	spin_lock(&filp->f_lock);
aa81a7c7 EZ	472	if (on)
	473	filp->f_flags \|= flag;
	474	else
	475	filp->f_flags &= ~flag;
db1dd4d3	476	spin_unlock(&filp->f_lock);
aa81a7c7 EZ	477	return error;
	478	}
	479
	480	static int ioctl_fioasync(unsigned int fd, struct file *filp,
	481	int __user *argp)
	482	{
	483	unsigned int flag;
	484	int on, error;
	485
	486	error = get_user(on, argp);
	487	if (error)
	488	return error;
	489	flag = on ? FASYNC : 0;
	490
	491	/* Did FASYNC state change ? */
	492	if ((flag ^ filp->f_flags) & FASYNC) {
218d11a8	493	if (filp->f_op && filp->f_op->fasync)
76398425	494	/* fasync() adjusts filp->f_flags */
aa81a7c7	495	error = filp->f_op->fasync(fd, filp, on);
218d11a8	496	else
aa81a7c7 EZ	497	error = -ENOTTY;
aa81a7c7 EZ	498	}
60aa4924	499	return error < 0 ? error : 0;
aa81a7c7 EZ	500	}
aa81a7c7 EZ	501
fcccf502 TS	502	static int ioctl_fsfreeze(struct file *filp)
	503	{
	504	struct super_block *sb = filp->f_path.dentry->d_inode->i_sb;
	505
	506	if (!capable(CAP_SYS_ADMIN))
	507	return -EPERM;
	508
	509	/* If filesystem doesn't support freeze feature, return. */
	510	if (sb->s_op->freeze_fs == NULL)
	511	return -EOPNOTSUPP;
	512
	513	/* If a blockdevice-backed filesystem isn't specified, return. */
	514	if (sb->s_bdev == NULL)
	515	return -EINVAL;
	516
	517	/* Freeze */
	518	sb = freeze_bdev(sb->s_bdev);
	519	if (IS_ERR(sb))
	520	return PTR_ERR(sb);
	521	return 0;
	522	}
	523
	524	static int ioctl_fsthaw(struct file *filp)
	525	{
	526	struct super_block *sb = filp->f_path.dentry->d_inode->i_sb;
	527
	528	if (!capable(CAP_SYS_ADMIN))
	529	return -EPERM;
	530
	531	/* If a blockdevice-backed filesystem isn't specified, return EINVAL. */
	532	if (sb->s_bdev == NULL)
	533	return -EINVAL;
	534
	535	/* Thaw */
	536	return thaw_bdev(sb->s_bdev, sb);
	537	}
	538
1da177e4 LT	539	/*
	540	* When you add any new common ioctls to the switches above and below
	541	* please update compat_sys_ioctl() too.
	542	*
deb21db7	543	* do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d.
1da177e4 LT	544	* It's just a simple helper for sys_ioctl and compat_sys_ioctl.
1da177e4 LT	545	*/
deb21db7 EZ	546	int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
deb21db7 EZ	547	unsigned long arg)
1da177e4	548	{
aa81a7c7 EZ	549	int error = 0;
aa81a7c7 EZ	550	int __user argp = (int __user )arg;
1da177e4 LT	551
1da177e4 LT	552	switch (cmd) {
c9845ff1 EZ	553	case FIOCLEX:
	554	set_close_on_exec(fd, 1);
	555	break;
1da177e4	556
c9845ff1 EZ	557	case FIONCLEX:
	558	set_close_on_exec(fd, 0);
	559	break;
1da177e4	560
c9845ff1	561	case FIONBIO:
aa81a7c7	562	error = ioctl_fionbio(filp, argp);
c9845ff1 EZ	563	break;
	564
	565	case FIOASYNC:
aa81a7c7	566	error = ioctl_fioasync(fd, filp, argp);
c9845ff1 EZ	567	break;
	568
	569	case FIOQSIZE:
	570	if (S_ISDIR(filp->f_path.dentry->d_inode->i_mode) \|\|
	571	S_ISREG(filp->f_path.dentry->d_inode->i_mode) \|\|
	572	S_ISLNK(filp->f_path.dentry->d_inode->i_mode)) {
	573	loff_t res =
	574	inode_get_bytes(filp->f_path.dentry->d_inode);
	575	error = copy_to_user((loff_t __user *)arg, &res,
	576	sizeof(res)) ? -EFAULT : 0;
	577	} else
	578	error = -ENOTTY;
	579	break;
fcccf502 TS	580
	581	case FIFREEZE:
	582	error = ioctl_fsfreeze(filp);
	583	break;
	584
	585	case FITHAW:
	586	error = ioctl_fsthaw(filp);
	587	break;
	588
19ba0559 AK	589	case FS_IOC_FIEMAP:
	590	return ioctl_fiemap(filp, arg);
	591
	592	case FIGETBSZ:
	593	{
	594	struct inode *inode = filp->f_path.dentry->d_inode;
	595	int __user p = (int __user )arg;
	596	return put_user(inode->i_sb->s_blocksize, p);
	597	}
	598
c9845ff1 EZ	599	default:
	600	if (S_ISREG(filp->f_path.dentry->d_inode->i_mode))
	601	error = file_ioctl(filp, cmd, arg);
	602	else
deb21db7	603	error = vfs_ioctl(filp, cmd, arg);
c9845ff1	604	break;
1da177e4 LT	605	}
	606	return error;
	607	}
	608
a26eab24	609	SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
1da177e4	610	{
c9845ff1	611	struct file *filp;
1da177e4 LT	612	int error = -EBADF;
	613	int fput_needed;
	614
	615	filp = fget_light(fd, &fput_needed);
	616	if (!filp)
	617	goto out;
	618
	619	error = security_file_ioctl(filp, cmd, arg);
	620	if (error)
	621	goto out_fput;
	622
deb21db7	623	error = do_vfs_ioctl(filp, fd, cmd, arg);
1da177e4 LT	624	out_fput:
	625	fput_light(filp, fput_needed);
	626	out:
	627	return error;
	628	}