kernel-ark/fs/fhandle.c
Linus Torvalds 982197277c Merge branch 'for-3.8' of git://linux-nfs.org/~bfields/linux
Pull nfsd update from Bruce Fields:
 "Included this time:

   - more nfsd containerization work from Stanislav Kinsbursky: we're
     not quite there yet, but should be by 3.9.

   - NFSv4.1 progress: implementation of basic backchannel security
     negotiation and the mandatory BACKCHANNEL_CTL operation.  See

       http://wiki.linux-nfs.org/wiki/index.php/Server_4.0_and_4.1_issues

     for remaining TODO's

   - Fixes for some bugs that could be triggered by unusual compounds.
     Our xdr code wasn't designed with v4 compounds in mind, and it
     shows.  A more thorough rewrite is still a todo.

   - If you've ever seen "RPC: multiple fragments per record not
     supported" logged while using some sort of odd userland NFS client,
     that should now be fixed.

   - Further work from Jeff Layton on our mechanism for storing
     information about NFSv4 clients across reboots.

   - Further work from Bryan Schumaker on his fault-injection mechanism
     (which allows us to discard selective NFSv4 state, to excercise
     rarely-taken recovery code paths in the client.)

   - The usual mix of miscellaneous bugs and cleanup.

  Thanks to everyone who tested or contributed this cycle."

* 'for-3.8' of git://linux-nfs.org/~bfields/linux: (111 commits)
  nfsd4: don't leave freed stateid hashed
  nfsd4: free_stateid can use the current stateid
  nfsd4: cleanup: replace rq_resused count by rq_next_page pointer
  nfsd: warn on odd reply state in nfsd_vfs_read
  nfsd4: fix oops on unusual readlike compound
  nfsd4: disable zero-copy on non-final read ops
  svcrpc: fix some printks
  NFSD: Correct the size calculation in fault_inject_write
  NFSD: Pass correct buffer size to rpc_ntop
  nfsd: pass proper net to nfsd_destroy() from NFSd kthreads
  nfsd: simplify service shutdown
  nfsd: replace boolean nfsd_up flag by users counter
  nfsd: simplify NFSv4 state init and shutdown
  nfsd: introduce helpers for generic resources init and shutdown
  nfsd: make NFSd service structure allocated per net
  nfsd: make NFSd service boot time per-net
  nfsd: per-net NFSd up flag introduced
  nfsd: move per-net startup code to separated function
  nfsd: pass net to __write_ports() and down
  nfsd: pass net to nfsd_set_nrthreads()
  ...
2012-12-20 14:04:11 -08:00

266 lines
6.5 KiB
C

#include <linux/syscalls.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/exportfs.h>
#include <linux/fs_struct.h>
#include <linux/fsnotify.h>
#include <linux/personality.h>
#include <asm/uaccess.h>
#include "internal.h"
#include "mount.h"
static long do_sys_name_to_handle(struct path *path,
struct file_handle __user *ufh,
int __user *mnt_id)
{
long retval;
struct file_handle f_handle;
int handle_dwords, handle_bytes;
struct file_handle *handle = NULL;
/*
* We need to make sure whether the file system
* support decoding of the file handle
*/
if (!path->dentry->d_sb->s_export_op ||
!path->dentry->d_sb->s_export_op->fh_to_dentry)
return -EOPNOTSUPP;
if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle)))
return -EFAULT;
if (f_handle.handle_bytes > MAX_HANDLE_SZ)
return -EINVAL;
handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes,
GFP_KERNEL);
if (!handle)
return -ENOMEM;
/* convert handle size to multiple of sizeof(u32) */
handle_dwords = f_handle.handle_bytes >> 2;
/* we ask for a non connected handle */
retval = exportfs_encode_fh(path->dentry,
(struct fid *)handle->f_handle,
&handle_dwords, 0);
handle->handle_type = retval;
/* convert handle size to bytes */
handle_bytes = handle_dwords * sizeof(u32);
handle->handle_bytes = handle_bytes;
if ((handle->handle_bytes > f_handle.handle_bytes) ||
(retval == FILEID_INVALID) || (retval == -ENOSPC)) {
/* As per old exportfs_encode_fh documentation
* we could return ENOSPC to indicate overflow
* But file system returned 255 always. So handle
* both the values
*/
/*
* set the handle size to zero so we copy only
* non variable part of the file_handle
*/
handle_bytes = 0;
retval = -EOVERFLOW;
} else
retval = 0;
/* copy the mount id */
if (copy_to_user(mnt_id, &real_mount(path->mnt)->mnt_id,
sizeof(*mnt_id)) ||
copy_to_user(ufh, handle,
sizeof(struct file_handle) + handle_bytes))
retval = -EFAULT;
kfree(handle);
return retval;
}
/**
* sys_name_to_handle_at: convert name to handle
* @dfd: directory relative to which name is interpreted if not absolute
* @name: name that should be converted to handle.
* @handle: resulting file handle
* @mnt_id: mount id of the file system containing the file
* @flag: flag value to indicate whether to follow symlink or not
*
* @handle->handle_size indicate the space available to store the
* variable part of the file handle in bytes. If there is not
* enough space, the field is updated to return the minimum
* value required.
*/
SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name,
struct file_handle __user *, handle, int __user *, mnt_id,
int, flag)
{
struct path path;
int lookup_flags;
int err;
if ((flag & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0)
return -EINVAL;
lookup_flags = (flag & AT_SYMLINK_FOLLOW) ? LOOKUP_FOLLOW : 0;
if (flag & AT_EMPTY_PATH)
lookup_flags |= LOOKUP_EMPTY;
err = user_path_at(dfd, name, lookup_flags, &path);
if (!err) {
err = do_sys_name_to_handle(&path, handle, mnt_id);
path_put(&path);
}
return err;
}
static struct vfsmount *get_vfsmount_from_fd(int fd)
{
struct vfsmount *mnt;
if (fd == AT_FDCWD) {
struct fs_struct *fs = current->fs;
spin_lock(&fs->lock);
mnt = mntget(fs->pwd.mnt);
spin_unlock(&fs->lock);
} else {
struct fd f = fdget(fd);
if (!f.file)
return ERR_PTR(-EBADF);
mnt = mntget(f.file->f_path.mnt);
fdput(f);
}
return mnt;
}
static int vfs_dentry_acceptable(void *context, struct dentry *dentry)
{
return 1;
}
static int do_handle_to_path(int mountdirfd, struct file_handle *handle,
struct path *path)
{
int retval = 0;
int handle_dwords;
path->mnt = get_vfsmount_from_fd(mountdirfd);
if (IS_ERR(path->mnt)) {
retval = PTR_ERR(path->mnt);
goto out_err;
}
/* change the handle size to multiple of sizeof(u32) */
handle_dwords = handle->handle_bytes >> 2;
path->dentry = exportfs_decode_fh(path->mnt,
(struct fid *)handle->f_handle,
handle_dwords, handle->handle_type,
vfs_dentry_acceptable, NULL);
if (IS_ERR(path->dentry)) {
retval = PTR_ERR(path->dentry);
goto out_mnt;
}
return 0;
out_mnt:
mntput(path->mnt);
out_err:
return retval;
}
static int handle_to_path(int mountdirfd, struct file_handle __user *ufh,
struct path *path)
{
int retval = 0;
struct file_handle f_handle;
struct file_handle *handle = NULL;
/*
* With handle we don't look at the execute bit on the
* the directory. Ideally we would like CAP_DAC_SEARCH.
* But we don't have that
*/
if (!capable(CAP_DAC_READ_SEARCH)) {
retval = -EPERM;
goto out_err;
}
if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle))) {
retval = -EFAULT;
goto out_err;
}
if ((f_handle.handle_bytes > MAX_HANDLE_SZ) ||
(f_handle.handle_bytes == 0)) {
retval = -EINVAL;
goto out_err;
}
handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes,
GFP_KERNEL);
if (!handle) {
retval = -ENOMEM;
goto out_err;
}
/* copy the full handle */
if (copy_from_user(handle, ufh,
sizeof(struct file_handle) +
f_handle.handle_bytes)) {
retval = -EFAULT;
goto out_handle;
}
retval = do_handle_to_path(mountdirfd, handle, path);
out_handle:
kfree(handle);
out_err:
return retval;
}
long do_handle_open(int mountdirfd,
struct file_handle __user *ufh, int open_flag)
{
long retval = 0;
struct path path;
struct file *file;
int fd;
retval = handle_to_path(mountdirfd, ufh, &path);
if (retval)
return retval;
fd = get_unused_fd_flags(open_flag);
if (fd < 0) {
path_put(&path);
return fd;
}
file = file_open_root(path.dentry, path.mnt, "", open_flag);
if (IS_ERR(file)) {
put_unused_fd(fd);
retval = PTR_ERR(file);
} else {
retval = fd;
fsnotify_open(file);
fd_install(fd, file);
}
path_put(&path);
return retval;
}
/**
* sys_open_by_handle_at: Open the file handle
* @mountdirfd: directory file descriptor
* @handle: file handle to be opened
* @flag: open flags.
*
* @mountdirfd indicate the directory file descriptor
* of the mount point. file handle is decoded relative
* to the vfsmount pointed by the @mountdirfd. @flags
* value is same as the open(2) flags.
*/
SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd,
struct file_handle __user *, handle,
int, flags)
{
long ret;
if (force_o_largefile())
flags |= O_LARGEFILE;
ret = do_handle_open(mountdirfd, handle, flags);
return ret;
}