#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/uaccess.h>
#include <linux/writeback.h>
#include <linux/buffer_head.h>
+#include <linux/falloc.h>
#include <asm/ioctls.h>
* @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.
{
int error = -ENOTTY;
- if (!filp->f_op)
+ if (!filp->f_op || !filp->f_op->unlocked_ioctl)
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();
- }
-
+ error = filp->f_op->unlocked_ioctl(filp, cmd, arg);
+ if (error == -ENOIOCTLCMD)
+ error = -ENOTTY;
out:
return error;
}
res = get_user(block, p);
if (res)
return res;
- lock_kernel();
res = mapping->a_ops->bmap(mapping, block);
- unlock_kernel();
return put_user(res, p);
}
u64 phys, u64 len, u32 flags)
{
struct fiemap_extent extent;
- struct fiemap_extent *dest = fieinfo->fi_extents_start;
+ struct fiemap_extent __user *dest = fieinfo->fi_extents_start;
/* only count the extents */
if (fieinfo->fi_extents_max == 0) {
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 > sb->s_maxbytes)
+ if (start > 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;
+ 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;
if (!inode->i_op->fiemap)
return -EOPNOTSUPP;
- if (copy_from_user(&fiemap, (struct fiemap __user *)arg,
- sizeof(struct fiemap)))
+ if (copy_from_user(&fiemap, ufiemap, sizeof(fiemap)))
return -EFAULT;
if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS)
fieinfo.fi_flags = fiemap.fm_flags;
fieinfo.fi_extents_max = fiemap.fm_extent_count;
- fieinfo.fi_extents_start = (struct fiemap_extent *)(arg + sizeof(fiemap));
+ fieinfo.fi_extents_start = ufiemap->fm_extents;
if (fiemap.fm_extent_count != 0 &&
!access_ok(VERIFY_WRITE, fieinfo.fi_extents_start,
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)))
+ if (copy_to_user(ufiemap, &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);
+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
- * @arg - the pointer to userspace where we copy everything to
- * @get_block - the fs's get_block function
+ * @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
*/
int __generic_block_fiemap(struct inode *inode,
- struct fiemap_extent_info *fieinfo, u64 start,
- u64 len, get_block_t *get_block)
+ struct fiemap_extent_info *fieinfo, loff_t start,
+ loff_t len, get_block_t *get_block)
{
- struct buffer_head tmp;
- unsigned int start_blk;
- long long length = 0, map_len = 0;
+ 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;
- if ((ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC)))
+ ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
+ if (ret)
return ret;
- start_blk = logical_to_blk(inode, start);
+ /*
+ * 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);
- length = (long long)min_t(u64, len, i_size_read(inode));
- map_len = length;
+ 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(&tmp, 0, sizeof(struct buffer_head));
- tmp.b_size = map_len;
+ memset(&map_bh, 0, sizeof(struct buffer_head));
+ map_bh.b_size = len;
- ret = get_block(inode, start_blk, &tmp, 0);
+ ret = get_block(inode, start_blk, &map_bh, 0);
if (ret)
break;
/* HOLE */
- if (!buffer_mapped(&tmp)) {
+ 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
+ * First hole after going past the EOF, this is our
* last extent
*/
- if (length <= 0) {
+ if (past_eof && size) {
flags = FIEMAP_EXTENT_MERGED|FIEMAP_EXTENT_LAST;
ret = fiemap_fill_next_extent(fieinfo, logical,
phys, size,
flags);
- break;
+ } else if (size) {
+ ret = fiemap_fill_next_extent(fieinfo, logical,
+ phys, size, flags);
+ size = 0;
}
- length -= blk_to_logical(inode, 1);
-
/* if we have holes up to/past EOF then we're done */
- if (length <= 0)
+ if (start_blk > last_blk || past_eof || ret)
break;
-
- start_blk++;
} else {
- if (length <= 0 && size) {
+ /*
+ * 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);
}
logical = blk_to_logical(inode, start_blk);
- phys = blk_to_logical(inode, tmp.b_blocknr);
- size = tmp.b_size;
+ phys = blk_to_logical(inode, map_bh.b_blocknr);
+ size = map_bh.b_size;
flags = FIEMAP_EXTENT_MERGED;
- length -= tmp.b_size;
start_blk += logical_to_blk(inode, size);
/*
- * if we are past the EOF we need to loop again to see
- * if there is a hole so we can mark this extent as the
- * last one, and if not keep mapping things until we
- * find a hole, or we run out of slots in the extent
- * array
+ * 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 (length <= 0)
- continue;
-
- ret = fiemap_fill_next_extent(fieinfo, logical, phys,
- size, flags);
- if (ret)
- break;
+ 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 is 1 then we just hit the end of the extent array */
if (ret == 1)
ret = 0;
#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)
{
switch (cmd) {
case FIBMAP:
return ioctl_fibmap(filp, p);
- case FS_IOC_FIEMAP:
- return ioctl_fiemap(filp, arg);
- case FIGETBSZ:
- return put_user(inode->i_sb->s_blocksize, 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);
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;
}
/* 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;
}
- if (error)
- return error;
+ return error < 0 ? error : 0;
+}
- if (on)
- filp->f_flags |= FASYNC;
- else
- filp->f_flags &= ~FASYNC;
- return error;
+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);
}
/*
{
int error = 0;
int __user *argp = (int __user *)arg;
+ struct inode *inode = filp->f_path.dentry->d_inode;
switch (cmd) {
case FIOCLEX:
break;
case FIONBIO:
- /* BKL needed to avoid races tweaking f_flags */
- lock_kernel();
error = ioctl_fionbio(filp, argp);
- unlock_kernel();
break;
case FIOASYNC:
- /* BKL needed to avoid races tweaking f_flags */
- lock_kernel();
error = ioctl_fioasync(fd, filp, argp);
- unlock_kernel();
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;
+ 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(filp->f_path.dentry->d_inode->i_mode))
+ if (S_ISREG(inode->i_mode))
error = file_ioctl(filp, cmd, arg);
else
error = vfs_ioctl(filp, cmd, arg);
return error;
}
-asmlinkage long sys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg)
+SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
{
struct file *filp;
int error = -EBADF;