[linux.git] / fs / ioctl.c

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

#include <linux/syscalls.h>
#include <linux/mm.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
 * 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 || !filp->f_op->unlocked_ioctl)
		goto out;

	error = filp->f_op->unlocked_ioctl(filp, cmd, arg);
	if (error == -ENOIOCTLCMD)
		error = -EINVAL;
 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 __user *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)
{
	u64 maxbytes = (u64) sb->s_maxbytes;

	*new_len = len;

	if (len == 0)
		return -EINVAL;

	if (start > maxbytes)
		return -EFBIG;

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

	return 0;
}

static int ioctl_fiemap(struct file *filp, unsigned long arg)
{
	struct fiemap fiemap;
	struct fiemap __user *ufiemap = (struct fiemap __user *) arg;
	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, ufiemap, sizeof(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 = ufiemap->fm_extents;

	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(ufiemap, &fiemap, sizeof(fiemap)))
		error = -EFAULT;

	return error;
}

#ifdef CONFIG_BLOCK

static inline sector_t logical_to_blk(struct inode *inode, loff_t offset)
{
	return (offset >> inode->i_blkbits);
}

static inline loff_t blk_to_logical(struct inode *inode, sector_t blk)
{
	return (blk << inode->i_blkbits);
}

/**
 * __generic_block_fiemap - FIEMAP for block based inodes (no locking)
 * @inode: the inode to map
 * @fieinfo: the fiemap info struct that will be passed back to userspace
 * @start: where to start mapping in the inode
 * @len: how much space to map
 * @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, loff_t start,
			   loff_t len, get_block_t *get_block)
{
	struct buffer_head map_bh;
	sector_t start_blk, last_blk;
	loff_t isize = i_size_read(inode);
	u64 logical = 0, phys = 0, size = 0;
	u32 flags = FIEMAP_EXTENT_MERGED;
	bool past_eof = false, whole_file = false;
	int ret = 0;

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

	/*
	 * Either the i_mutex or other appropriate locking needs to be held
	 * since we expect isize to not change at all through the duration of
	 * this call.
	 */
	if (len >= isize) {
		whole_file = true;
		len = isize;
	}

	start_blk = logical_to_blk(inode, start);
	last_blk = logical_to_blk(inode, start + len - 1);

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

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

		/* HOLE */
		if (!buffer_mapped(&map_bh)) {
			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) >= isize)
				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);
			} else if (size) {
				ret = fiemap_fill_next_extent(fieinfo, logical,
							      phys, size, flags);
				size = 0;
			}

			/* if we have holes up to/past EOF then we're done */
			if (start_blk > last_blk || past_eof || ret)
				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 (start_blk > last_blk && !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, map_bh.b_blocknr);
			size = map_bh.b_size;
			flags = FIEMAP_EXTENT_MERGED;

			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 >= isize)
				past_eof = true;
		}
		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;

	/* Freeze */
	return freeze_super(sb);
}

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;

	/* Thaw */
	return thaw_super(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>
1da177e4 LT	8	#include <linux/mm.h>
16f7e0fe	9	#include <linux/capability.h>
1da177e4 LT	10	#include <linux/file.h>
	11	#include <linux/fs.h>
	12	#include <linux/security.h>
	13	#include <linux/module.h>
c9845ff1	14	#include <linux/uaccess.h>
68c9d702 JB	15	#include <linux/writeback.h>
68c9d702 JB	16	#include <linux/buffer_head.h>
3e63cbb1	17	#include <linux/falloc.h>
1da177e4	18
1da177e4 LT	19	#include <asm/ioctls.h>
1da177e4 LT	20
c4b929b8 MF	21	/* So that the fiemap access checks can't overflow on 32 bit machines. */
	22	#define FIEMAP_MAX_EXTENTS (UINT_MAX / sizeof(struct fiemap_extent))
	23
deb21db7 EZ	24	/**
deb21db7 EZ	25	* vfs_ioctl - call filesystem specific ioctl methods
f6a4c8bd CH	26	* @filp: open file to invoke ioctl method on
	27	* @cmd: ioctl command to execute
	28	* @arg: command-specific argument for ioctl
deb21db7 EZ	29	*
deb21db7 EZ	30	* Invokes filesystem specific ->unlocked_ioctl, if one exists; otherwise
deb21db7 EZ	31	* returns -ENOTTY.
	32	*
	33	* Returns 0 on success, -errno on error.
	34	*/
67cde595 AB	35	static long vfs_ioctl(struct file *filp, unsigned int cmd,
67cde595 AB	36	unsigned long arg)
1da177e4 LT	37	{
	38	int error = -ENOTTY;
	39
b19dd42f	40	if (!filp->f_op \|\| !filp->f_op->unlocked_ioctl)
1da177e4 LT	41	goto out;
1da177e4 LT	42
b19dd42f AB	43	error = filp->f_op->unlocked_ioctl(filp, cmd, arg);
	44	if (error == -ENOIOCTLCMD)
	45	error = -EINVAL;
1da177e4 LT	46	out:
	47	return error;
	48	}
	49
aa81a7c7 EZ	50	static int ioctl_fibmap(struct file filp, int __user p)
	51	{
	52	struct address_space *mapping = filp->f_mapping;
	53	int res, block;
	54
	55	/* do we support this mess? */
	56	if (!mapping->a_ops->bmap)
	57	return -EINVAL;
	58	if (!capable(CAP_SYS_RAWIO))
	59	return -EPERM;
	60	res = get_user(block, p);
	61	if (res)
	62	return res;
aa81a7c7	63	res = mapping->a_ops->bmap(mapping, block);
aa81a7c7 EZ	64	return put_user(res, p);
	65	}
	66
c4b929b8 MF	67	/**
	68	* fiemap_fill_next_extent - Fiemap helper function
	69	* @fieinfo: Fiemap context passed into ->fiemap
	70	* @logical: Extent logical start offset, in bytes
	71	* @phys: Extent physical start offset, in bytes
	72	* @len: Extent length, in bytes
	73	* @flags: FIEMAP_EXTENT flags that describe this extent
	74	*
	75	* Called from file system ->fiemap callback. Will populate extent
	76	* info as passed in via arguments and copy to user memory. On
	77	* success, extent count on fieinfo is incremented.
	78	*
	79	* Returns 0 on success, -errno on error, 1 if this was the last
	80	* extent that will fit in user array.
	81	*/
	82	#define SET_UNKNOWN_FLAGS (FIEMAP_EXTENT_DELALLOC)
	83	#define SET_NO_UNMOUNTED_IO_FLAGS (FIEMAP_EXTENT_DATA_ENCRYPTED)
	84	#define SET_NOT_ALIGNED_FLAGS (FIEMAP_EXTENT_DATA_TAIL\|FIEMAP_EXTENT_DATA_INLINE)
	85	int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical,
	86	u64 phys, u64 len, u32 flags)
	87	{
	88	struct fiemap_extent extent;
ecf5632d	89	struct fiemap_extent __user *dest = fieinfo->fi_extents_start;
c4b929b8 MF	90
	91	/* only count the extents */
	92	if (fieinfo->fi_extents_max == 0) {
	93	fieinfo->fi_extents_mapped++;
	94	return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
	95	}
	96
	97	if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max)
	98	return 1;
	99
	100	if (flags & SET_UNKNOWN_FLAGS)
	101	flags \|= FIEMAP_EXTENT_UNKNOWN;
	102	if (flags & SET_NO_UNMOUNTED_IO_FLAGS)
	103	flags \|= FIEMAP_EXTENT_ENCODED;
	104	if (flags & SET_NOT_ALIGNED_FLAGS)
	105	flags \|= FIEMAP_EXTENT_NOT_ALIGNED;
	106
	107	memset(&extent, 0, sizeof(extent));
	108	extent.fe_logical = logical;
	109	extent.fe_physical = phys;
	110	extent.fe_length = len;
	111	extent.fe_flags = flags;
	112
	113	dest += fieinfo->fi_extents_mapped;
	114	if (copy_to_user(dest, &extent, sizeof(extent)))
	115	return -EFAULT;
	116
	117	fieinfo->fi_extents_mapped++;
	118	if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max)
	119	return 1;
	120	return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
	121	}
	122	EXPORT_SYMBOL(fiemap_fill_next_extent);
	123
	124	/**
	125	* fiemap_check_flags - check validity of requested flags for fiemap
	126	* @fieinfo: Fiemap context passed into ->fiemap
	127	* @fs_flags: Set of fiemap flags that the file system understands
	128	*
	129	* Called from file system ->fiemap callback. This will compute the
	130	* intersection of valid fiemap flags and those that the fs supports. That
	131	* value is then compared against the user supplied flags. In case of bad user
	132	* flags, the invalid values will be written into the fieinfo structure, and
	133	* -EBADR is returned, which tells ioctl_fiemap() to return those values to
	134	* userspace. For this reason, a return code of -EBADR should be preserved.
	135	*
	136	* Returns 0 on success, -EBADR on bad flags.
	137	*/
	138	int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags)
	139	{
	140	u32 incompat_flags;
	141
	142	incompat_flags = fieinfo->fi_flags & ~(FIEMAP_FLAGS_COMPAT & fs_flags);
	143	if (incompat_flags) {
	144	fieinfo->fi_flags = incompat_flags;
	145	return -EBADR;
	146	}
	147	return 0;
	148	}
	149	EXPORT_SYMBOL(fiemap_check_flags);
	150
	151	static int fiemap_check_ranges(struct super_block *sb,
	152	u64 start, u64 len, u64 *new_len)
	153	{
5aa98b70 JL	154	u64 maxbytes = (u64) sb->s_maxbytes;
5aa98b70 JL	155
c4b929b8 MF	156	*new_len = len;
	157
	158	if (len == 0)
	159	return -EINVAL;
	160
5aa98b70	161	if (start > maxbytes)
c4b929b8 MF	162	return -EFBIG;
	163
	164	/*
	165	* Shrink request scope to what the fs can actually handle.
	166	*/
5aa98b70 JL	167	if (len > maxbytes \|\| (maxbytes - len) < start)
5aa98b70 JL	168	*new_len = maxbytes - start;
c4b929b8 MF	169
	170	return 0;
	171	}
	172
	173	static int ioctl_fiemap(struct file *filp, unsigned long arg)
	174	{
	175	struct fiemap fiemap;
ecf5632d	176	struct fiemap __user ufiemap = (struct fiemap __user ) arg;
c4b929b8 MF	177	struct fiemap_extent_info fieinfo = { 0, };
	178	struct inode *inode = filp->f_path.dentry->d_inode;
	179	struct super_block *sb = inode->i_sb;
	180	u64 len;
	181	int error;
	182
	183	if (!inode->i_op->fiemap)
	184	return -EOPNOTSUPP;
	185
ecf5632d	186	if (copy_from_user(&fiemap, ufiemap, sizeof(fiemap)))
c4b929b8 MF	187	return -EFAULT;
	188
	189	if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS)
	190	return -EINVAL;
	191
	192	error = fiemap_check_ranges(sb, fiemap.fm_start, fiemap.fm_length,
	193	&len);
	194	if (error)
	195	return error;
	196
	197	fieinfo.fi_flags = fiemap.fm_flags;
	198	fieinfo.fi_extents_max = fiemap.fm_extent_count;
ecf5632d	199	fieinfo.fi_extents_start = ufiemap->fm_extents;
c4b929b8 MF	200
	201	if (fiemap.fm_extent_count != 0 &&
	202	!access_ok(VERIFY_WRITE, fieinfo.fi_extents_start,
	203	fieinfo.fi_extents_max * sizeof(struct fiemap_extent)))
	204	return -EFAULT;
	205
	206	if (fieinfo.fi_flags & FIEMAP_FLAG_SYNC)
	207	filemap_write_and_wait(inode->i_mapping);
	208
	209	error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start, len);
	210	fiemap.fm_flags = fieinfo.fi_flags;
	211	fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped;
ecf5632d	212	if (copy_to_user(ufiemap, &fiemap, sizeof(fiemap)))
c4b929b8 MF	213	error = -EFAULT;
	214
	215	return error;
	216	}
	217
06270d5d AB	218	#ifdef CONFIG_BLOCK
06270d5d AB	219
3a3076f4 JB	220	static inline sector_t logical_to_blk(struct inode *inode, loff_t offset)
	221	{
	222	return (offset >> inode->i_blkbits);
	223	}
	224
	225	static inline loff_t blk_to_logical(struct inode *inode, sector_t blk)
	226	{
	227	return (blk << inode->i_blkbits);
	228	}
68c9d702	229
e9079cce SW	230	/**
e9079cce SW	231	* __generic_block_fiemap - FIEMAP for block based inodes (no locking)
3a3076f4 JB	232	* @inode: the inode to map
	233	* @fieinfo: the fiemap info struct that will be passed back to userspace
	234	* @start: where to start mapping in the inode
	235	* @len: how much space to map
	236	* @get_block: the fs's get_block function
68c9d702 JB	237	*
	238	* This does FIEMAP for block based inodes. Basically it will just loop
	239	* through get_block until we hit the number of extents we want to map, or we
	240	* go past the end of the file and hit a hole.
	241	*
	242	* If it is possible to have data blocks beyond a hole past @inode->i_size, then
	243	* please do not use this function, it will stop at the first unmapped block
e9079cce SW	244	* beyond i_size.
	245	*
	246	* If you use this function directly, you need to do your own locking. Use
	247	* generic_block_fiemap if you want the locking done for you.
68c9d702	248	*/
e9079cce SW	249
e9079cce SW	250	int __generic_block_fiemap(struct inode *inode,
3a3076f4 JB	251	struct fiemap_extent_info *fieinfo, loff_t start,
3a3076f4 JB	252	loff_t len, get_block_t *get_block)
68c9d702	253	{
3a3076f4 JB	254	struct buffer_head map_bh;
	255	sector_t start_blk, last_blk;
	256	loff_t isize = i_size_read(inode);
68c9d702 JB	257	u64 logical = 0, phys = 0, size = 0;
68c9d702 JB	258	u32 flags = FIEMAP_EXTENT_MERGED;
3a3076f4 JB	259	bool past_eof = false, whole_file = false;
3a3076f4 JB	260	int ret = 0;
68c9d702	261
3a3076f4 JB	262	ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
3a3076f4 JB	263	if (ret)
68c9d702 JB	264	return ret;
68c9d702 JB	265
3a3076f4 JB	266	/*
	267	* Either the i_mutex or other appropriate locking needs to be held
	268	* since we expect isize to not change at all through the duration of
	269	* this call.
	270	*/
	271	if (len >= isize) {
	272	whole_file = true;
	273	len = isize;
	274	}
df3935ff	275
3a3076f4 JB	276	start_blk = logical_to_blk(inode, start);
3a3076f4 JB	277	last_blk = logical_to_blk(inode, start + len - 1);
68c9d702 JB	278
	279	do {
	280	/*
	281	* we set b_size to the total size we want so it will map as
	282	* many contiguous blocks as possible at once
	283	*/
3a3076f4 JB	284	memset(&map_bh, 0, sizeof(struct buffer_head));
3a3076f4 JB	285	map_bh.b_size = len;
68c9d702	286
3a3076f4	287	ret = get_block(inode, start_blk, &map_bh, 0);
68c9d702 JB	288	if (ret)
	289	break;
	290
	291	/* HOLE */
3a3076f4	292	if (!buffer_mapped(&map_bh)) {
df3935ff JB	293	start_blk++;
	294
	295	/*
3a3076f4	296	* We want to handle the case where there is an
df3935ff JB	297	* allocated block at the front of the file, and then
	298	* nothing but holes up to the end of the file properly,
	299	* to make sure that extent at the front gets properly
	300	* marked with FIEMAP_EXTENT_LAST
	301	*/
	302	if (!past_eof &&
3a3076f4	303	blk_to_logical(inode, start_blk) >= isize)
df3935ff JB	304	past_eof = 1;
df3935ff JB	305
68c9d702	306	/*
3a3076f4	307	* First hole after going past the EOF, this is our
68c9d702 JB	308	* last extent
68c9d702 JB	309	*/
df3935ff	310	if (past_eof && size) {
68c9d702 JB	311	flags = FIEMAP_EXTENT_MERGED\|FIEMAP_EXTENT_LAST;
	312	ret = fiemap_fill_next_extent(fieinfo, logical,
	313	phys, size,
	314	flags);
3a3076f4 JB	315	} else if (size) {
	316	ret = fiemap_fill_next_extent(fieinfo, logical,
	317	phys, size, flags);
	318	size = 0;
68c9d702 JB	319	}
68c9d702 JB	320
68c9d702	321	/* if we have holes up to/past EOF then we're done */
3a3076f4	322	if (start_blk > last_blk \|\| past_eof \|\| ret)
68c9d702	323	break;
68c9d702	324	} else {
df3935ff	325	/*
3a3076f4	326	* We have gone over the length of what we wanted to
df3935ff JB	327	* map, and it wasn't the entire file, so add the extent
	328	* we got last time and exit.
	329	*
	330	* This is for the case where say we want to map all the
	331	* way up to the second to the last block in a file, but
	332	* the last block is a hole, making the second to last
	333	* block FIEMAP_EXTENT_LAST. In this case we want to
	334	* see if there is a hole after the second to last block
	335	* so we can mark it properly. If we found data after
	336	* we exceeded the length we were requesting, then we
	337	* are good to go, just add the extent to the fieinfo
	338	* and break
	339	*/
3a3076f4	340	if (start_blk > last_blk && !whole_file) {
df3935ff JB	341	ret = fiemap_fill_next_extent(fieinfo, logical,
	342	phys, size,
	343	flags);
	344	break;
	345	}
	346
	347	/*
	348	* if size != 0 then we know we already have an extent
	349	* to add, so add it.
	350	*/
	351	if (size) {
68c9d702 JB	352	ret = fiemap_fill_next_extent(fieinfo, logical,
	353	phys, size,
	354	flags);
	355	if (ret)
	356	break;
	357	}
	358
	359	logical = blk_to_logical(inode, start_blk);
3a3076f4 JB	360	phys = blk_to_logical(inode, map_bh.b_blocknr);
3a3076f4 JB	361	size = map_bh.b_size;
68c9d702 JB	362	flags = FIEMAP_EXTENT_MERGED;
68c9d702 JB	363
68c9d702 JB	364	start_blk += logical_to_blk(inode, size);
	365
	366	/*
df3935ff JB	367	* If we are past the EOF, then we need to make sure as
	368	* soon as we find a hole that the last extent we found
	369	* is marked with FIEMAP_EXTENT_LAST
68c9d702	370	*/
3a3076f4 JB	371	if (!past_eof && logical + size >= isize)
3a3076f4 JB	372	past_eof = true;
68c9d702 JB	373	}
	374	cond_resched();
	375	} while (1);
	376
3a3076f4	377	/* If ret is 1 then we just hit the end of the extent array */
68c9d702 JB	378	if (ret == 1)
	379	ret = 0;
	380
	381	return ret;
	382	}
e9079cce SW	383	EXPORT_SYMBOL(__generic_block_fiemap);
	384
	385	/**
	386	* generic_block_fiemap - FIEMAP for block based inodes
	387	* @inode: The inode to map
	388	* @fieinfo: The mapping information
	389	* @start: The initial block to map
	390	* @len: The length of the extect to attempt to map
	391	* @get_block: The block mapping function for the fs
	392	*
	393	* Calls __generic_block_fiemap to map the inode, after taking
	394	* the inode's mutex lock.
	395	*/
	396
	397	int generic_block_fiemap(struct inode *inode,
	398	struct fiemap_extent_info *fieinfo, u64 start,
	399	u64 len, get_block_t *get_block)
	400	{
	401	int ret;
	402	mutex_lock(&inode->i_mutex);
	403	ret = __generic_block_fiemap(inode, fieinfo, start, len, get_block);
	404	mutex_unlock(&inode->i_mutex);
	405	return ret;
	406	}
68c9d702 JB	407	EXPORT_SYMBOL(generic_block_fiemap);
68c9d702 JB	408
06270d5d AB	409	#endif /* CONFIG_BLOCK */
06270d5d AB	410
3e63cbb1 AJ	411	/*
	412	* This provides compatibility with legacy XFS pre-allocation ioctls
	413	* which predate the fallocate syscall.
	414	*
	415	* Only the l_start, l_len and l_whence fields of the 'struct space_resv'
	416	* are used here, rest are ignored.
	417	*/
	418	int ioctl_preallocate(struct file filp, void __user argp)
	419	{
	420	struct inode *inode = filp->f_path.dentry->d_inode;
	421	struct space_resv sr;
	422
	423	if (copy_from_user(&sr, argp, sizeof(sr)))
	424	return -EFAULT;
	425
	426	switch (sr.l_whence) {
	427	case SEEK_SET:
	428	break;
	429	case SEEK_CUR:
	430	sr.l_start += filp->f_pos;
	431	break;
	432	case SEEK_END:
	433	sr.l_start += i_size_read(inode);
	434	break;
	435	default:
	436	return -EINVAL;
	437	}
	438
	439	return do_fallocate(filp, FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len);
	440	}
	441
1da177e4 LT	442	static int file_ioctl(struct file *filp, unsigned int cmd,
	443	unsigned long arg)
	444	{
c9845ff1	445	struct inode *inode = filp->f_path.dentry->d_inode;
1da177e4 LT	446	int __user p = (int __user )arg;
	447
	448	switch (cmd) {
c9845ff1	449	case FIBMAP:
aa81a7c7	450	return ioctl_fibmap(filp, p);
c9845ff1 EZ	451	case FIONREAD:
c9845ff1 EZ	452	return put_user(i_size_read(inode) - filp->f_pos, p);
3e63cbb1 AJ	453	case FS_IOC_RESVSP:
	454	case FS_IOC_RESVSP64:
	455	return ioctl_preallocate(filp, p);
1da177e4 LT	456	}
1da177e4 LT	457
deb21db7	458	return vfs_ioctl(filp, cmd, arg);
1da177e4 LT	459	}
1da177e4 LT	460
aa81a7c7 EZ	461	static int ioctl_fionbio(struct file filp, int __user argp)
	462	{
	463	unsigned int flag;
	464	int on, error;
	465
	466	error = get_user(on, argp);
	467	if (error)
	468	return error;
	469	flag = O_NONBLOCK;
	470	#ifdef __sparc__
	471	/* SunOS compatibility item. */
	472	if (O_NONBLOCK != O_NDELAY)
	473	flag \|= O_NDELAY;
	474	#endif
db1dd4d3	475	spin_lock(&filp->f_lock);
aa81a7c7 EZ	476	if (on)
	477	filp->f_flags \|= flag;
	478	else
	479	filp->f_flags &= ~flag;
db1dd4d3	480	spin_unlock(&filp->f_lock);
aa81a7c7 EZ	481	return error;
	482	}
	483
	484	static int ioctl_fioasync(unsigned int fd, struct file *filp,
	485	int __user *argp)
	486	{
	487	unsigned int flag;
	488	int on, error;
	489
	490	error = get_user(on, argp);
	491	if (error)
	492	return error;
	493	flag = on ? FASYNC : 0;
	494
	495	/* Did FASYNC state change ? */
	496	if ((flag ^ filp->f_flags) & FASYNC) {
218d11a8	497	if (filp->f_op && filp->f_op->fasync)
76398425	498	/* fasync() adjusts filp->f_flags */
aa81a7c7	499	error = filp->f_op->fasync(fd, filp, on);
218d11a8	500	else
aa81a7c7 EZ	501	error = -ENOTTY;
aa81a7c7 EZ	502	}
60aa4924	503	return error < 0 ? error : 0;
aa81a7c7 EZ	504	}
aa81a7c7 EZ	505
fcccf502 TS	506	static int ioctl_fsfreeze(struct file *filp)
	507	{
	508	struct super_block *sb = filp->f_path.dentry->d_inode->i_sb;
	509
	510	if (!capable(CAP_SYS_ADMIN))
	511	return -EPERM;
	512
	513	/* If filesystem doesn't support freeze feature, return. */
	514	if (sb->s_op->freeze_fs == NULL)
	515	return -EOPNOTSUPP;
	516
fcccf502	517	/* Freeze */
18e9e510	518	return freeze_super(sb);
fcccf502 TS	519	}
	520
	521	static int ioctl_fsthaw(struct file *filp)
	522	{
	523	struct super_block *sb = filp->f_path.dentry->d_inode->i_sb;
	524
	525	if (!capable(CAP_SYS_ADMIN))
	526	return -EPERM;
	527
fcccf502	528	/* Thaw */
18e9e510	529	return thaw_super(sb);
fcccf502 TS	530	}
fcccf502 TS	531
1da177e4 LT	532	/*
	533	* When you add any new common ioctls to the switches above and below
	534	* please update compat_sys_ioctl() too.
	535	*
deb21db7	536	* do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d.
1da177e4 LT	537	* It's just a simple helper for sys_ioctl and compat_sys_ioctl.
1da177e4 LT	538	*/
deb21db7 EZ	539	int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
deb21db7 EZ	540	unsigned long arg)
1da177e4	541	{
aa81a7c7 EZ	542	int error = 0;
aa81a7c7 EZ	543	int __user argp = (int __user )arg;
1da177e4 LT	544
1da177e4 LT	545	switch (cmd) {
c9845ff1 EZ	546	case FIOCLEX:
	547	set_close_on_exec(fd, 1);
	548	break;
1da177e4	549
c9845ff1 EZ	550	case FIONCLEX:
	551	set_close_on_exec(fd, 0);
	552	break;
1da177e4	553
c9845ff1	554	case FIONBIO:
aa81a7c7	555	error = ioctl_fionbio(filp, argp);
c9845ff1 EZ	556	break;
	557
	558	case FIOASYNC:
aa81a7c7	559	error = ioctl_fioasync(fd, filp, argp);
c9845ff1 EZ	560	break;
	561
	562	case FIOQSIZE:
	563	if (S_ISDIR(filp->f_path.dentry->d_inode->i_mode) \|\|
	564	S_ISREG(filp->f_path.dentry->d_inode->i_mode) \|\|
	565	S_ISLNK(filp->f_path.dentry->d_inode->i_mode)) {
	566	loff_t res =
	567	inode_get_bytes(filp->f_path.dentry->d_inode);
	568	error = copy_to_user((loff_t __user *)arg, &res,
	569	sizeof(res)) ? -EFAULT : 0;
	570	} else
	571	error = -ENOTTY;
	572	break;
fcccf502 TS	573
	574	case FIFREEZE:
	575	error = ioctl_fsfreeze(filp);
	576	break;
	577
	578	case FITHAW:
	579	error = ioctl_fsthaw(filp);
	580	break;
	581
19ba0559 AK	582	case FS_IOC_FIEMAP:
	583	return ioctl_fiemap(filp, arg);
	584
	585	case FIGETBSZ:
	586	{
	587	struct inode *inode = filp->f_path.dentry->d_inode;
	588	int __user p = (int __user )arg;
	589	return put_user(inode->i_sb->s_blocksize, p);
	590	}
	591
c9845ff1 EZ	592	default:
	593	if (S_ISREG(filp->f_path.dentry->d_inode->i_mode))
	594	error = file_ioctl(filp, cmd, arg);
	595	else
deb21db7	596	error = vfs_ioctl(filp, cmd, arg);
c9845ff1	597	break;
1da177e4 LT	598	}
	599	return error;
	600	}
	601
a26eab24	602	SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
1da177e4	603	{
c9845ff1	604	struct file *filp;
1da177e4 LT	605	int error = -EBADF;
	606	int fput_needed;
	607
	608	filp = fget_light(fd, &fput_needed);
	609	if (!filp)
	610	goto out;
	611
	612	error = security_file_ioctl(filp, cmd, arg);
	613	if (error)
	614	goto out_fput;
	615
deb21db7	616	error = do_vfs_ioctl(filp, fd, cmd, arg);
1da177e4 LT	617	out_fput:
	618	fput_light(filp, fput_needed);
	619	out:
	620	return error;
	621	}