[mirror_ubuntu-artful-kernel.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
 * 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 *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_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

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>
	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
deb21db7 EZ	32	* returns -ENOTTY.
	33	*
	34	* Returns 0 on success, -errno on error.
	35	*/
67cde595 AB	36	static long vfs_ioctl(struct file *filp, unsigned int cmd,
67cde595 AB	37	unsigned long arg)
1da177e4 LT	38	{
	39	int error = -ENOTTY;
	40
b19dd42f	41	if (!filp->f_op \|\| !filp->f_op->unlocked_ioctl)
1da177e4 LT	42	goto out;
1da177e4 LT	43
b19dd42f AB	44	error = filp->f_op->unlocked_ioctl(filp, cmd, arg);
	45	if (error == -ENOIOCTLCMD)
	46	error = -EINVAL;
1da177e4 LT	47	out:
	48	return error;
	49	}
	50
aa81a7c7 EZ	51	static int ioctl_fibmap(struct file filp, int __user p)
	52	{
	53	struct address_space *mapping = filp->f_mapping;
	54	int res, block;
	55
	56	/* do we support this mess? */
	57	if (!mapping->a_ops->bmap)
	58	return -EINVAL;
	59	if (!capable(CAP_SYS_RAWIO))
	60	return -EPERM;
	61	res = get_user(block, p);
	62	if (res)
	63	return res;
aa81a7c7	64	res = mapping->a_ops->bmap(mapping, block);
aa81a7c7 EZ	65	return put_user(res, p);
	66	}
	67
c4b929b8 MF	68	/**
	69	* fiemap_fill_next_extent - Fiemap helper function
	70	* @fieinfo: Fiemap context passed into ->fiemap
	71	* @logical: Extent logical start offset, in bytes
	72	* @phys: Extent physical start offset, in bytes
	73	* @len: Extent length, in bytes
	74	* @flags: FIEMAP_EXTENT flags that describe this extent
	75	*
	76	* Called from file system ->fiemap callback. Will populate extent
	77	* info as passed in via arguments and copy to user memory. On
	78	* success, extent count on fieinfo is incremented.
	79	*
	80	* Returns 0 on success, -errno on error, 1 if this was the last
	81	* extent that will fit in user array.
	82	*/
	83	#define SET_UNKNOWN_FLAGS (FIEMAP_EXTENT_DELALLOC)
	84	#define SET_NO_UNMOUNTED_IO_FLAGS (FIEMAP_EXTENT_DATA_ENCRYPTED)
	85	#define SET_NOT_ALIGNED_FLAGS (FIEMAP_EXTENT_DATA_TAIL\|FIEMAP_EXTENT_DATA_INLINE)
	86	int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical,
	87	u64 phys, u64 len, u32 flags)
	88	{
	89	struct fiemap_extent extent;
	90	struct fiemap_extent *dest = fieinfo->fi_extents_start;
	91
	92	/* only count the extents */
	93	if (fieinfo->fi_extents_max == 0) {
	94	fieinfo->fi_extents_mapped++;
	95	return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
	96	}
	97
	98	if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max)
	99	return 1;
	100
	101	if (flags & SET_UNKNOWN_FLAGS)
	102	flags \|= FIEMAP_EXTENT_UNKNOWN;
	103	if (flags & SET_NO_UNMOUNTED_IO_FLAGS)
	104	flags \|= FIEMAP_EXTENT_ENCODED;
	105	if (flags & SET_NOT_ALIGNED_FLAGS)
	106	flags \|= FIEMAP_EXTENT_NOT_ALIGNED;
	107
	108	memset(&extent, 0, sizeof(extent));
	109	extent.fe_logical = logical;
	110	extent.fe_physical = phys;
	111	extent.fe_length = len;
	112	extent.fe_flags = flags;
	113
	114	dest += fieinfo->fi_extents_mapped;
	115	if (copy_to_user(dest, &extent, sizeof(extent)))
	116	return -EFAULT;
	117
	118	fieinfo->fi_extents_mapped++;
	119	if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max)
	120	return 1;
	121	return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
	122	}
	123	EXPORT_SYMBOL(fiemap_fill_next_extent);
	124
	125	/**
	126	* fiemap_check_flags - check validity of requested flags for fiemap
	127	* @fieinfo: Fiemap context passed into ->fiemap
	128	* @fs_flags: Set of fiemap flags that the file system understands
	129	*
	130	* Called from file system ->fiemap callback. This will compute the
	131	* intersection of valid fiemap flags and those that the fs supports. That
132	* value is then compared against the user supplied flags. In case of bad user
133	* flags, the invalid values will be written into the fieinfo structure, and
134	* -EBADR is returned, which tells ioctl_fiemap() to return those values to
135	* userspace. For this reason, a return code of -EBADR should be preserved.
136	*
137	* Returns 0 on success, -EBADR on bad flags.
138	*/
139	int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags)
140	{
141	u32 incompat_flags;
142
143	incompat_flags = fieinfo->fi_flags & ~(FIEMAP_FLAGS_COMPAT & fs_flags);
144	if (incompat_flags) {
145	fieinfo->fi_flags = incompat_flags;
146	return -EBADR;
147	}
148	return 0;
149	}
150	EXPORT_SYMBOL(fiemap_check_flags);
151
152	static int fiemap_check_ranges(struct super_block *sb,
153	u64 start, u64 len, u64 *new_len)
154	{
5aa98b70 JL	155	u64 maxbytes = (u64) sb->s_maxbytes;
5aa98b70 JL	156
c4b929b8 MF	157	*new_len = len;
	158
	159	if (len == 0)
	160	return -EINVAL;
	161
5aa98b70	162	if (start > maxbytes)
c4b929b8 MF	163	return -EFBIG;
	164
	165	/*
	166	* Shrink request scope to what the fs can actually handle.
	167	*/
5aa98b70 JL	168	if (len > maxbytes \|\| (maxbytes - len) < start)
5aa98b70 JL	169	*new_len = maxbytes - start;
c4b929b8 MF	170
	171	return 0;
	172	}
	173
	174	static int ioctl_fiemap(struct file *filp, unsigned long arg)
	175	{
	176	struct fiemap fiemap;
	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
	186	if (copy_from_user(&fiemap, (struct fiemap __user *)arg,
	187	sizeof(struct fiemap)))
	188	return -EFAULT;
	189
	190	if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS)
	191	return -EINVAL;
	192
	193	error = fiemap_check_ranges(sb, fiemap.fm_start, fiemap.fm_length,
	194	&len);
	195	if (error)
	196	return error;
	197
	198	fieinfo.fi_flags = fiemap.fm_flags;
	199	fieinfo.fi_extents_max = fiemap.fm_extent_count;
	200	fieinfo.fi_extents_start = (struct fiemap_extent *)(arg + sizeof(fiemap));
	201
	202	if (fiemap.fm_extent_count != 0 &&
	203	!access_ok(VERIFY_WRITE, fieinfo.fi_extents_start,
	204	fieinfo.fi_extents_max * sizeof(struct fiemap_extent)))
	205	return -EFAULT;
	206
	207	if (fieinfo.fi_flags & FIEMAP_FLAG_SYNC)
	208	filemap_write_and_wait(inode->i_mapping);
	209
	210	error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start, len);
	211	fiemap.fm_flags = fieinfo.fi_flags;
	212	fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped;
	213	if (copy_to_user((char *)arg, &fiemap, sizeof(fiemap)))
	214	error = -EFAULT;
	215
	216	return error;
	217	}
	218
06270d5d AB	219	#ifdef CONFIG_BLOCK
06270d5d AB	220
3a3076f4 JB	221	static inline sector_t logical_to_blk(struct inode *inode, loff_t offset)
	222	{
	223	return (offset >> inode->i_blkbits);
	224	}
	225
	226	static inline loff_t blk_to_logical(struct inode *inode, sector_t blk)
	227	{
	228	return (blk << inode->i_blkbits);
	229	}
68c9d702	230
e9079cce SW	231	/**
e9079cce SW	232	* __generic_block_fiemap - FIEMAP for block based inodes (no locking)
3a3076f4 JB	233	* @inode: the inode to map
	234	* @fieinfo: the fiemap info struct that will be passed back to userspace
	235	* @start: where to start mapping in the inode
	236	* @len: how much space to map
	237	* @get_block: the fs's get_block function
68c9d702 JB	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
e9079cce SW	251	int __generic_block_fiemap(struct inode *inode,
3a3076f4 JB	252	struct fiemap_extent_info *fieinfo, loff_t start,
3a3076f4 JB	253	loff_t len, get_block_t *get_block)
68c9d702	254	{
3a3076f4 JB	255	struct buffer_head map_bh;
	256	sector_t start_blk, last_blk;
	257	loff_t isize = i_size_read(inode);
68c9d702 JB	258	u64 logical = 0, phys = 0, size = 0;
68c9d702 JB	259	u32 flags = FIEMAP_EXTENT_MERGED;
3a3076f4 JB	260	bool past_eof = false, whole_file = false;
3a3076f4 JB	261	int ret = 0;
68c9d702	262
3a3076f4 JB	263	ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
3a3076f4 JB	264	if (ret)
68c9d702 JB	265	return ret;
68c9d702 JB	266
3a3076f4 JB	267	/*
	268	* Either the i_mutex or other appropriate locking needs to be held
	269	* since we expect isize to not change at all through the duration of
	270	* this call.
	271	*/
	272	if (len >= isize) {
	273	whole_file = true;
	274	len = isize;
	275	}
df3935ff	276
3a3076f4 JB	277	start_blk = logical_to_blk(inode, start);
3a3076f4 JB	278	last_blk = logical_to_blk(inode, start + len - 1);
68c9d702 JB	279
	280	do {
	281	/*
	282	* we set b_size to the total size we want so it will map as
	283	* many contiguous blocks as possible at once
	284	*/
3a3076f4 JB	285	memset(&map_bh, 0, sizeof(struct buffer_head));
3a3076f4 JB	286	map_bh.b_size = len;
68c9d702	287
3a3076f4	288	ret = get_block(inode, start_blk, &map_bh, 0);
68c9d702 JB	289	if (ret)
	290	break;
	291
	292	/* HOLE */
3a3076f4	293	if (!buffer_mapped(&map_bh)) {
df3935ff JB	294	start_blk++;
	295
	296	/*
3a3076f4	297	* We want to handle the case where there is an
df3935ff JB	298	* allocated block at the front of the file, and then
	299	* nothing but holes up to the end of the file properly,
	300	* to make sure that extent at the front gets properly
	301	* marked with FIEMAP_EXTENT_LAST
	302	*/
	303	if (!past_eof &&
3a3076f4	304	blk_to_logical(inode, start_blk) >= isize)
df3935ff JB	305	past_eof = 1;
df3935ff JB	306
68c9d702	307	/*
3a3076f4	308	* First hole after going past the EOF, this is our
68c9d702 JB	309	* last extent
68c9d702 JB	310	*/
df3935ff	311	if (past_eof && size) {
68c9d702 JB	312	flags = FIEMAP_EXTENT_MERGED\|FIEMAP_EXTENT_LAST;
	313	ret = fiemap_fill_next_extent(fieinfo, logical,
	314	phys, size,
	315	flags);
3a3076f4 JB	316	} else if (size) {
	317	ret = fiemap_fill_next_extent(fieinfo, logical,
	318	phys, size, flags);
	319	size = 0;
68c9d702 JB	320	}
68c9d702 JB	321
68c9d702	322	/* if we have holes up to/past EOF then we're done */
3a3076f4	323	if (start_blk > last_blk \|\| past_eof \|\| ret)
68c9d702	324	break;
68c9d702	325	} else {
df3935ff	326	/*
3a3076f4	327	* We have gone over the length of what we wanted to
df3935ff JB	328	* map, and it wasn't the entire file, so add the extent
	329	* we got last time and exit.
	330	*
	331	* This is for the case where say we want to map all the
	332	* way up to the second to the last block in a file, but
	333	* the last block is a hole, making the second to last
	334	* block FIEMAP_EXTENT_LAST. In this case we want to
	335	* see if there is a hole after the second to last block
	336	* so we can mark it properly. If we found data after
	337	* we exceeded the length we were requesting, then we
	338	* are good to go, just add the extent to the fieinfo
	339	* and break
	340	*/
3a3076f4	341	if (start_blk > last_blk && !whole_file) {
df3935ff JB	342	ret = fiemap_fill_next_extent(fieinfo, logical,
	343	phys, size,
	344	flags);
	345	break;
	346	}
	347
	348	/*
	349	* if size != 0 then we know we already have an extent
	350	* to add, so add it.
	351	*/
	352	if (size) {
68c9d702 JB	353	ret = fiemap_fill_next_extent(fieinfo, logical,
	354	phys, size,
	355	flags);
	356	if (ret)
	357	break;
	358	}
	359
	360	logical = blk_to_logical(inode, start_blk);
3a3076f4 JB	361	phys = blk_to_logical(inode, map_bh.b_blocknr);
3a3076f4 JB	362	size = map_bh.b_size;
68c9d702 JB	363	flags = FIEMAP_EXTENT_MERGED;
68c9d702 JB	364
68c9d702 JB	365	start_blk += logical_to_blk(inode, size);
	366
	367	/*
df3935ff JB	368	* If we are past the EOF, then we need to make sure as
	369	* soon as we find a hole that the last extent we found
	370	* is marked with FIEMAP_EXTENT_LAST
68c9d702	371	*/
3a3076f4 JB	372	if (!past_eof && logical + size >= isize)
3a3076f4 JB	373	past_eof = true;
68c9d702 JB	374	}
	375	cond_resched();
	376	} while (1);
	377
3a3076f4	378	/* If ret is 1 then we just hit the end of the extent array */
68c9d702 JB	379	if (ret == 1)
	380	ret = 0;
	381
	382	return ret;
	383	}
e9079cce SW	384	EXPORT_SYMBOL(__generic_block_fiemap);
	385
	386	/**
	387	* generic_block_fiemap - FIEMAP for block based inodes
	388	* @inode: The inode to map
	389	* @fieinfo: The mapping information
	390	* @start: The initial block to map
	391	* @len: The length of the extect to attempt to map
	392	* @get_block: The block mapping function for the fs
	393	*
	394	* Calls __generic_block_fiemap to map the inode, after taking
	395	* the inode's mutex lock.
	396	*/
	397
	398	int generic_block_fiemap(struct inode *inode,
	399	struct fiemap_extent_info *fieinfo, u64 start,
	400	u64 len, get_block_t *get_block)
	401	{
	402	int ret;
	403	mutex_lock(&inode->i_mutex);
	404	ret = __generic_block_fiemap(inode, fieinfo, start, len, get_block);
	405	mutex_unlock(&inode->i_mutex);
	406	return ret;
	407	}
68c9d702 JB	408	EXPORT_SYMBOL(generic_block_fiemap);
68c9d702 JB	409
06270d5d AB	410	#endif /* CONFIG_BLOCK */
06270d5d AB	411
3e63cbb1 AJ	412	/*
	413	* This provides compatibility with legacy XFS pre-allocation ioctls
	414	* which predate the fallocate syscall.
	415	*
	416	* Only the l_start, l_len and l_whence fields of the 'struct space_resv'
	417	* are used here, rest are ignored.
	418	*/
	419	int ioctl_preallocate(struct file filp, void __user argp)
	420	{
	421	struct inode *inode = filp->f_path.dentry->d_inode;
	422	struct space_resv sr;
	423
	424	if (copy_from_user(&sr, argp, sizeof(sr)))
	425	return -EFAULT;
	426
	427	switch (sr.l_whence) {
	428	case SEEK_SET:
	429	break;
	430	case SEEK_CUR:
	431	sr.l_start += filp->f_pos;
	432	break;
	433	case SEEK_END:
	434	sr.l_start += i_size_read(inode);
	435	break;
	436	default:
	437	return -EINVAL;
	438	}
	439
	440	return do_fallocate(filp, FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len);
	441	}
	442
1da177e4 LT	443	static int file_ioctl(struct file *filp, unsigned int cmd,
	444	unsigned long arg)
	445	{
c9845ff1	446	struct inode *inode = filp->f_path.dentry->d_inode;
1da177e4 LT	447	int __user p = (int __user )arg;
	448
	449	switch (cmd) {
c9845ff1	450	case FIBMAP:
aa81a7c7	451	return ioctl_fibmap(filp, p);
c9845ff1 EZ	452	case FIONREAD:
c9845ff1 EZ	453	return put_user(i_size_read(inode) - filp->f_pos, p);
3e63cbb1 AJ	454	case FS_IOC_RESVSP:
	455	case FS_IOC_RESVSP64:
	456	return ioctl_preallocate(filp, p);
1da177e4 LT	457	}
1da177e4 LT	458
deb21db7	459	return vfs_ioctl(filp, cmd, arg);
1da177e4 LT	460	}
1da177e4 LT	461
aa81a7c7 EZ	462	static int ioctl_fionbio(struct file filp, int __user argp)
	463	{
	464	unsigned int flag;
	465	int on, error;
	466
	467	error = get_user(on, argp);
	468	if (error)
	469	return error;
	470	flag = O_NONBLOCK;
	471	#ifdef __sparc__
	472	/* SunOS compatibility item. */
	473	if (O_NONBLOCK != O_NDELAY)
	474	flag \|= O_NDELAY;
	475	#endif
db1dd4d3	476	spin_lock(&filp->f_lock);
aa81a7c7 EZ	477	if (on)
	478	filp->f_flags \|= flag;
	479	else
	480	filp->f_flags &= ~flag;
db1dd4d3	481	spin_unlock(&filp->f_lock);
aa81a7c7 EZ	482	return error;
	483	}
	484
	485	static int ioctl_fioasync(unsigned int fd, struct file *filp,
	486	int __user *argp)
	487	{
	488	unsigned int flag;
	489	int on, error;
	490
	491	error = get_user(on, argp);
	492	if (error)
	493	return error;
	494	flag = on ? FASYNC : 0;
	495
	496	/* Did FASYNC state change ? */
	497	if ((flag ^ filp->f_flags) & FASYNC) {
218d11a8	498	if (filp->f_op && filp->f_op->fasync)
76398425	499	/* fasync() adjusts filp->f_flags */
aa81a7c7	500	error = filp->f_op->fasync(fd, filp, on);
218d11a8	501	else
aa81a7c7 EZ	502	error = -ENOTTY;
aa81a7c7 EZ	503	}
60aa4924	504	return error < 0 ? error : 0;
aa81a7c7 EZ	505	}
aa81a7c7 EZ	506
fcccf502 TS	507	static int ioctl_fsfreeze(struct file *filp)
	508	{
	509	struct super_block *sb = filp->f_path.dentry->d_inode->i_sb;
	510
	511	if (!capable(CAP_SYS_ADMIN))
	512	return -EPERM;
	513
	514	/* If filesystem doesn't support freeze feature, return. */
	515	if (sb->s_op->freeze_fs == NULL)
	516	return -EOPNOTSUPP;
	517
fcccf502	518	/* Freeze */
18e9e510	519	return freeze_super(sb);
fcccf502 TS	520	}
	521
	522	static int ioctl_fsthaw(struct file *filp)
	523	{
	524	struct super_block *sb = filp->f_path.dentry->d_inode->i_sb;
	525
	526	if (!capable(CAP_SYS_ADMIN))
	527	return -EPERM;
	528
fcccf502	529	/* Thaw */
18e9e510	530	return thaw_super(sb);
fcccf502 TS	531	}
fcccf502 TS	532
1da177e4 LT	533	/*
	534	* When you add any new common ioctls to the switches above and below
	535	* please update compat_sys_ioctl() too.
	536	*
deb21db7	537	* do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d.
1da177e4 LT	538	* It's just a simple helper for sys_ioctl and compat_sys_ioctl.
1da177e4 LT	539	*/
deb21db7 EZ	540	int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
deb21db7 EZ	541	unsigned long arg)
1da177e4	542	{
aa81a7c7 EZ	543	int error = 0;
aa81a7c7 EZ	544	int __user argp = (int __user )arg;
1da177e4 LT	545
1da177e4 LT	546	switch (cmd) {
c9845ff1 EZ	547	case FIOCLEX:
	548	set_close_on_exec(fd, 1);
	549	break;
1da177e4	550
c9845ff1 EZ	551	case FIONCLEX:
	552	set_close_on_exec(fd, 0);
	553	break;
1da177e4	554
c9845ff1	555	case FIONBIO:
aa81a7c7	556	error = ioctl_fionbio(filp, argp);
c9845ff1 EZ	557	break;
	558
	559	case FIOASYNC:
aa81a7c7	560	error = ioctl_fioasync(fd, filp, argp);
c9845ff1 EZ	561	break;
	562
	563	case FIOQSIZE:
	564	if (S_ISDIR(filp->f_path.dentry->d_inode->i_mode) \|\|
	565	S_ISREG(filp->f_path.dentry->d_inode->i_mode) \|\|
	566	S_ISLNK(filp->f_path.dentry->d_inode->i_mode)) {
	567	loff_t res =
	568	inode_get_bytes(filp->f_path.dentry->d_inode);
	569	error = copy_to_user((loff_t __user *)arg, &res,
	570	sizeof(res)) ? -EFAULT : 0;
	571	} else
	572	error = -ENOTTY;
	573	break;
fcccf502 TS	574
	575	case FIFREEZE:
	576	error = ioctl_fsfreeze(filp);
	577	break;
	578
	579	case FITHAW:
	580	error = ioctl_fsthaw(filp);
	581	break;
	582
19ba0559 AK	583	case FS_IOC_FIEMAP:
	584	return ioctl_fiemap(filp, arg);
	585
	586	case FIGETBSZ:
	587	{
	588	struct inode *inode = filp->f_path.dentry->d_inode;
	589	int __user p = (int __user )arg;
	590	return put_user(inode->i_sb->s_blocksize, p);
	591	}
	592
c9845ff1 EZ	593	default:
	594	if (S_ISREG(filp->f_path.dentry->d_inode->i_mode))
	595	error = file_ioctl(filp, cmd, arg);
	596	else
deb21db7	597	error = vfs_ioctl(filp, cmd, arg);
c9845ff1	598	break;
1da177e4 LT	599	}
	600	return error;
	601	}
	602
a26eab24	603	SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
1da177e4	604	{
c9845ff1	605	struct file *filp;
1da177e4 LT	606	int error = -EBADF;
	607	int fput_needed;
	608
	609	filp = fget_light(fd, &fput_needed);
	610	if (!filp)
	611	goto out;
	612
	613	error = security_file_ioctl(filp, cmd, arg);
	614	if (error)
	615	goto out_fput;
	616
deb21db7	617	error = do_vfs_ioctl(filp, fd, cmd, arg);
1da177e4 LT	618	out_fput:
	619	fput_light(filp, fput_needed);
	620	out:
	621	return error;
	622	}