ioctl.c

Go to the documentation of this file.

/*
 *  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/export.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))

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 = -ENOTTY;
 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);
}

#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);

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);
}

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;
    }

    /*
     * Some filesystems can't deal with being asked to map less than
     * blocksize, so make sure our len is at least block length.
     */
    if (logical_to_blk(inode, len) == 0)
        len = blk_to_logical(inode, 1);

    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);

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;
    struct inode *inode = filp->f_path.dentry->d_inode;

    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(inode->i_mode) || S_ISREG(inode->i_mode) ||
            S_ISLNK(inode->i_mode)) {
            loff_t res = inode_get_bytes(inode);
            error = copy_to_user(argp, &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:
        return put_user(inode->i_sb->s_blocksize, argp);

    default:
        if (S_ISREG(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)
{
    int error;
    struct fd f = fdget(fd);

    if (!f.file)
        return -EBADF;
    error = security_file_ioctl(f.file, cmd, arg);
    if (!error)
        error = do_vfs_ioctl(f.file, fd, cmd, arg);
    fdput(f);
    return error;
}