iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
linux/fs/cifs/cifsfs.c
Linus Torvalds 7d6beb71da idmapped-mounts-v5.12 
-----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQRAhzRXHqcMeLMyaSiRxhvAZXjcogUCYCegywAKCRCRxhvAZXjc
 ouJ6AQDlf+7jCQlQdeKKoN9QDFfMzG1ooemat36EpRRTONaGuAD8D9A4sUsG4+5f
 4IU5Lj9oY4DEmF8HenbWK2ZHsesL2Qg=
 =yPaw
 -----END PGP SIGNATURE-----

Merge tag 'idmapped-mounts-v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux

Pull idmapped mounts from Christian Brauner:
 "This introduces idmapped mounts which has been in the making for some
  time. Simply put, different mounts can expose the same file or
  directory with different ownership. This initial implementation comes
  with ports for fat, ext4 and with Christoph's port for xfs with more
  filesystems being actively worked on by independent people and
  maintainers.

  Idmapping mounts handle a wide range of long standing use-cases. Here
  are just a few:

   - Idmapped mounts make it possible to easily share files between
     multiple users or multiple machines especially in complex
     scenarios. For example, idmapped mounts will be used in the
     implementation of portable home directories in
     systemd-homed.service(8) where they allow users to move their home
     directory to an external storage device and use it on multiple
     computers where they are assigned different uids and gids. This
     effectively makes it possible to assign random uids and gids at
     login time.

   - It is possible to share files from the host with unprivileged
     containers without having to change ownership permanently through
     chown(2).

   - It is possible to idmap a container's rootfs and without having to
     mangle every file. For example, Chromebooks use it to share the
     user's Download folder with their unprivileged containers in their
     Linux subsystem.

   - It is possible to share files between containers with
     non-overlapping idmappings.

   - Filesystem that lack a proper concept of ownership such as fat can
     use idmapped mounts to implement discretionary access (DAC)
     permission checking.

   - They allow users to efficiently changing ownership on a per-mount
     basis without having to (recursively) chown(2) all files. In
     contrast to chown (2) changing ownership of large sets of files is
     instantenous with idmapped mounts. This is especially useful when
     ownership of a whole root filesystem of a virtual machine or
     container is changed. With idmapped mounts a single syscall
     mount_setattr syscall will be sufficient to change the ownership of
     all files.

   - Idmapped mounts always take the current ownership into account as
     idmappings specify what a given uid or gid is supposed to be mapped
     to. This contrasts with the chown(2) syscall which cannot by itself
     take the current ownership of the files it changes into account. It
     simply changes the ownership to the specified uid and gid. This is
     especially problematic when recursively chown(2)ing a large set of
     files which is commong with the aforementioned portable home
     directory and container and vm scenario.

   - Idmapped mounts allow to change ownership locally, restricting it
     to specific mounts, and temporarily as the ownership changes only
     apply as long as the mount exists.

  Several userspace projects have either already put up patches and
  pull-requests for this feature or will do so should you decide to pull
  this:

   - systemd: In a wide variety of scenarios but especially right away
     in their implementation of portable home directories.

         https://systemd.io/HOME_DIRECTORY/

   - container runtimes: containerd, runC, LXD:To share data between
     host and unprivileged containers, unprivileged and privileged
     containers, etc. The pull request for idmapped mounts support in
     containerd, the default Kubernetes runtime is already up for quite
     a while now: https://github.com/containerd/containerd/pull/4734

   - The virtio-fs developers and several users have expressed interest
     in using this feature with virtual machines once virtio-fs is
     ported.

   - ChromeOS: Sharing host-directories with unprivileged containers.

  I've tightly synced with all those projects and all of those listed
  here have also expressed their need/desire for this feature on the
  mailing list. For more info on how people use this there's a bunch of
  talks about this too. Here's just two recent ones:

      https://www.cncf.io/wp-content/uploads/2020/12/Rootless-Containers-in-Gitpod.pdf
      https://fosdem.org/2021/schedule/event/containers_idmap/

  This comes with an extensive xfstests suite covering both ext4 and
  xfs:

      https://git.kernel.org/brauner/xfstests-dev/h/idmapped_mounts

  It covers truncation, creation, opening, xattrs, vfscaps, setid
  execution, setgid inheritance and more both with idmapped and
  non-idmapped mounts. It already helped to discover an unrelated xfs
  setgid inheritance bug which has since been fixed in mainline. It will
  be sent for inclusion with the xfstests project should you decide to
  merge this.

  In order to support per-mount idmappings vfsmounts are marked with
  user namespaces. The idmapping of the user namespace will be used to
  map the ids of vfs objects when they are accessed through that mount.
  By default all vfsmounts are marked with the initial user namespace.
  The initial user namespace is used to indicate that a mount is not
  idmapped. All operations behave as before and this is verified in the
  testsuite.

  Based on prior discussions we want to attach the whole user namespace
  and not just a dedicated idmapping struct. This allows us to reuse all
  the helpers that already exist for dealing with idmappings instead of
  introducing a whole new range of helpers. In addition, if we decide in
  the future that we are confident enough to enable unprivileged users
  to setup idmapped mounts the permission checking can take into account
  whether the caller is privileged in the user namespace the mount is
  currently marked with.

  The user namespace the mount will be marked with can be specified by
  passing a file descriptor refering to the user namespace as an
  argument to the new mount_setattr() syscall together with the new
  MOUNT_ATTR_IDMAP flag. The system call follows the openat2() pattern
  of extensibility.

  The following conditions must be met in order to create an idmapped
  mount:

   - The caller must currently have the CAP_SYS_ADMIN capability in the
     user namespace the underlying filesystem has been mounted in.

   - The underlying filesystem must support idmapped mounts.

   - The mount must not already be idmapped. This also implies that the
     idmapping of a mount cannot be altered once it has been idmapped.

   - The mount must be a detached/anonymous mount, i.e. it must have
     been created by calling open_tree() with the OPEN_TREE_CLONE flag
     and it must not already have been visible in the filesystem.

  The last two points guarantee easier semantics for userspace and the
  kernel and make the implementation significantly simpler.

  By default vfsmounts are marked with the initial user namespace and no
  behavioral or performance changes are observed.

  The manpage with a detailed description can be found here:

      1d7b902e28

  In order to support idmapped mounts, filesystems need to be changed
  and mark themselves with the FS_ALLOW_IDMAP flag in fs_flags. The
  patches to convert individual filesystem are not very large or
  complicated overall as can be seen from the included fat, ext4, and
  xfs ports. Patches for other filesystems are actively worked on and
  will be sent out separately. The xfstestsuite can be used to verify
  that port has been done correctly.

  The mount_setattr() syscall is motivated independent of the idmapped
  mounts patches and it's been around since July 2019. One of the most
  valuable features of the new mount api is the ability to perform
  mounts based on file descriptors only.

  Together with the lookup restrictions available in the openat2()
  RESOLVE_* flag namespace which we added in v5.6 this is the first time
  we are close to hardened and race-free (e.g. symlinks) mounting and
  path resolution.

  While userspace has started porting to the new mount api to mount
  proper filesystems and create new bind-mounts it is currently not
  possible to change mount options of an already existing bind mount in
  the new mount api since the mount_setattr() syscall is missing.

  With the addition of the mount_setattr() syscall we remove this last
  restriction and userspace can now fully port to the new mount api,
  covering every use-case the old mount api could. We also add the
  crucial ability to recursively change mount options for a whole mount
  tree, both removing and adding mount options at the same time. This
  syscall has been requested multiple times by various people and
  projects.

  There is a simple tool available at

      https://github.com/brauner/mount-idmapped

  that allows to create idmapped mounts so people can play with this
  patch series. I'll add support for the regular mount binary should you
  decide to pull this in the following weeks:

  Here's an example to a simple idmapped mount of another user's home
  directory:

	u1001@f2-vm:/$ sudo ./mount --idmap both:1000:1001:1 /home/ubuntu/ /mnt

	u1001@f2-vm:/$ ls -al /home/ubuntu/
	total 28
	drwxr-xr-x 2 ubuntu ubuntu 4096 Oct 28 22:07 .
	drwxr-xr-x 4 root   root   4096 Oct 28 04:00 ..
	-rw------- 1 ubuntu ubuntu 3154 Oct 28 22:12 .bash_history
	-rw-r--r-- 1 ubuntu ubuntu  220 Feb 25  2020 .bash_logout
	-rw-r--r-- 1 ubuntu ubuntu 3771 Feb 25  2020 .bashrc
	-rw-r--r-- 1 ubuntu ubuntu  807 Feb 25  2020 .profile
	-rw-r--r-- 1 ubuntu ubuntu    0 Oct 16 16:11 .sudo_as_admin_successful
	-rw------- 1 ubuntu ubuntu 1144 Oct 28 00:43 .viminfo

	u1001@f2-vm:/$ ls -al /mnt/
	total 28
	drwxr-xr-x  2 u1001 u1001 4096 Oct 28 22:07 .
	drwxr-xr-x 29 root  root  4096 Oct 28 22:01 ..
	-rw-------  1 u1001 u1001 3154 Oct 28 22:12 .bash_history
	-rw-r--r--  1 u1001 u1001  220 Feb 25  2020 .bash_logout
	-rw-r--r--  1 u1001 u1001 3771 Feb 25  2020 .bashrc
	-rw-r--r--  1 u1001 u1001  807 Feb 25  2020 .profile
	-rw-r--r--  1 u1001 u1001    0 Oct 16 16:11 .sudo_as_admin_successful
	-rw-------  1 u1001 u1001 1144 Oct 28 00:43 .viminfo

	u1001@f2-vm:/$ touch /mnt/my-file

	u1001@f2-vm:/$ setfacl -m u:1001:rwx /mnt/my-file

	u1001@f2-vm:/$ sudo setcap -n 1001 cap_net_raw+ep /mnt/my-file

	u1001@f2-vm:/$ ls -al /mnt/my-file
	-rw-rwxr--+ 1 u1001 u1001 0 Oct 28 22:14 /mnt/my-file

	u1001@f2-vm:/$ ls -al /home/ubuntu/my-file
	-rw-rwxr--+ 1 ubuntu ubuntu 0 Oct 28 22:14 /home/ubuntu/my-file

	u1001@f2-vm:/$ getfacl /mnt/my-file
	getfacl: Removing leading '/' from absolute path names
	# file: mnt/my-file
	# owner: u1001
	# group: u1001
	user::rw-
	user:u1001:rwx
	group::rw-
	mask::rwx
	other::r--

	u1001@f2-vm:/$ getfacl /home/ubuntu/my-file
	getfacl: Removing leading '/' from absolute path names
	# file: home/ubuntu/my-file
	# owner: ubuntu
	# group: ubuntu
	user::rw-
	user:ubuntu:rwx
	group::rw-
	mask::rwx
	other::r--"

* tag 'idmapped-mounts-v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux: (41 commits)
  xfs: remove the possibly unused mp variable in xfs_file_compat_ioctl
  xfs: support idmapped mounts
  ext4: support idmapped mounts
  fat: handle idmapped mounts
  tests: add mount_setattr() selftests
  fs: introduce MOUNT_ATTR_IDMAP
  fs: add mount_setattr()
  fs: add attr_flags_to_mnt_flags helper
  fs: split out functions to hold writers
  namespace: only take read lock in do_reconfigure_mnt()
  mount: make {lock,unlock}_mount_hash() static
  namespace: take lock_mount_hash() directly when changing flags
  nfs: do not export idmapped mounts
  overlayfs: do not mount on top of idmapped mounts
  ecryptfs: do not mount on top of idmapped mounts
  ima: handle idmapped mounts
  apparmor: handle idmapped mounts
  fs: make helpers idmap mount aware
  exec: handle idmapped mounts
  would_dump: handle idmapped mounts
  ...
2021-02-23 13:39:45 -08:00

1728 lines
47 KiB
C
Raw Blame History

/*
* fs/cifs/cifsfs.c
*
* Copyright (C) International Business Machines Corp., 2002,2008
* Author(s): Steve French (sfrench@us.ibm.com)
*
* Common Internet FileSystem (CIFS) client
*
* This library is free software; you can redistribute it and/or modify
* it under the terms of the GNU Lesser General Public License as published
* by the Free Software Foundation; either version 2.1 of the License, or
* (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
* the GNU Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public License
* along with this library; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
/* Note that BB means BUGBUG (ie something to fix eventually) */
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/seq_file.h>
#include <linux/vfs.h>
#include <linux/mempool.h>
#include <linux/delay.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/namei.h>
#include <linux/random.h>
#include <linux/uuid.h>
#include <linux/xattr.h>
#include <net/ipv6.h>
#include "cifsfs.h"
#include "cifspdu.h"
#define DECLARE_GLOBALS_HERE
#include "cifsglob.h"
#include "cifsproto.h"
#include "cifs_debug.h"
#include "cifs_fs_sb.h"
#include <linux/mm.h>
#include <linux/key-type.h>
#include "cifs_spnego.h"
#include "fscache.h"
#include "smb2pdu.h"
#ifdef CONFIG_CIFS_DFS_UPCALL
#include "dfs_cache.h"
#endif
#ifdef CONFIG_CIFS_SWN_UPCALL
#include "netlink.h"
#endif
#include "fs_context.h"
/*
* DOS dates from 1980/1/1 through 2107/12/31
* Protocol specifications indicate the range should be to 119, which
* limits maximum year to 2099. But this range has not been checked.
*/
#define SMB_DATE_MAX (127<<9 | 12<<5 | 31)
#define SMB_DATE_MIN (0<<9 | 1<<5 | 1)
#define SMB_TIME_MAX (23<<11 | 59<<5 | 29)
int cifsFYI = 0;
bool traceSMB;
bool enable_oplocks = true;
bool linuxExtEnabled = true;
bool lookupCacheEnabled = true;
bool disable_legacy_dialects; /* false by default */
bool enable_gcm_256; /* false by default, change when more servers support it */
bool require_gcm_256; /* false by default */
unsigned int global_secflags = CIFSSEC_DEF;
/* unsigned int ntlmv2_support = 0; */
unsigned int sign_CIFS_PDUs = 1;
static const struct super_operations cifs_super_ops;
unsigned int CIFSMaxBufSize = CIFS_MAX_MSGSIZE;
module_param(CIFSMaxBufSize, uint, 0444);
MODULE_PARM_DESC(CIFSMaxBufSize, "Network buffer size (not including header) "
"for CIFS requests. "
"Default: 16384 Range: 8192 to 130048");
unsigned int cifs_min_rcv = CIFS_MIN_RCV_POOL;
module_param(cifs_min_rcv, uint, 0444);
MODULE_PARM_DESC(cifs_min_rcv, "Network buffers in pool. Default: 4 Range: "
"1 to 64");
unsigned int cifs_min_small = 30;
module_param(cifs_min_small, uint, 0444);
MODULE_PARM_DESC(cifs_min_small, "Small network buffers in pool. Default: 30 "
"Range: 2 to 256");
unsigned int cifs_max_pending = CIFS_MAX_REQ;
module_param(cifs_max_pending, uint, 0444);
MODULE_PARM_DESC(cifs_max_pending, "Simultaneous requests to server for "
"CIFS/SMB1 dialect (N/A for SMB3) "
"Default: 32767 Range: 2 to 32767.");
#ifdef CONFIG_CIFS_STATS2
unsigned int slow_rsp_threshold = 1;
module_param(slow_rsp_threshold, uint, 0644);
MODULE_PARM_DESC(slow_rsp_threshold, "Amount of time (in seconds) to wait "
"before logging that a response is delayed. "
"Default: 1 (if set to 0 disables msg).");
#endif /* STATS2 */
module_param(enable_oplocks, bool, 0644);
MODULE_PARM_DESC(enable_oplocks, "Enable or disable oplocks. Default: y/Y/1");
module_param(enable_gcm_256, bool, 0644);
MODULE_PARM_DESC(enable_gcm_256, "Enable requesting strongest (256 bit) GCM encryption. Default: n/N/0");
module_param(require_gcm_256, bool, 0644);
MODULE_PARM_DESC(require_gcm_256, "Require strongest (256 bit) GCM encryption. Default: n/N/0");
module_param(disable_legacy_dialects, bool, 0644);
MODULE_PARM_DESC(disable_legacy_dialects, "To improve security it may be "
"helpful to restrict the ability to "
"override the default dialects (SMB2.1, "
"SMB3 and SMB3.02) on mount with old "
"dialects (CIFS/SMB1 and SMB2) since "
"vers=1.0 (CIFS/SMB1) and vers=2.0 are weaker"
" and less secure. Default: n/N/0");
extern mempool_t *cifs_sm_req_poolp;
extern mempool_t *cifs_req_poolp;
extern mempool_t *cifs_mid_poolp;
struct workqueue_struct *cifsiod_wq;
struct workqueue_struct *decrypt_wq;
struct workqueue_struct *fileinfo_put_wq;
struct workqueue_struct *cifsoplockd_wq;
__u32 cifs_lock_secret;
/*
* Bumps refcount for cifs super block.
* Note that it should be only called if a referece to VFS super block is
* already held, e.g. in open-type syscalls context. Otherwise it can race with
* atomic_dec_and_test in deactivate_locked_super.
*/
void
cifs_sb_active(struct super_block *sb)
{
struct cifs_sb_info *server = CIFS_SB(sb);
if (atomic_inc_return(&server->active) == 1)
atomic_inc(&sb->s_active);
}
void
cifs_sb_deactive(struct super_block *sb)
{
struct cifs_sb_info *server = CIFS_SB(sb);
if (atomic_dec_and_test(&server->active))
deactivate_super(sb);
}
static int
cifs_read_super(struct super_block *sb)
{
struct inode *inode;
struct cifs_sb_info *cifs_sb;
struct cifs_tcon *tcon;
struct timespec64 ts;
int rc = 0;
cifs_sb = CIFS_SB(sb);
tcon = cifs_sb_master_tcon(cifs_sb);
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIXACL)
sb->s_flags |= SB_POSIXACL;
if (tcon->snapshot_time)
sb->s_flags |= SB_RDONLY;
if (tcon->ses->capabilities & tcon->ses->server->vals->cap_large_files)
sb->s_maxbytes = MAX_LFS_FILESIZE;
else
sb->s_maxbytes = MAX_NON_LFS;
/*
* Some very old servers like DOS and OS/2 used 2 second granularity
* (while all current servers use 100ns granularity - see MS-DTYP)
* but 1 second is the maximum allowed granularity for the VFS
* so for old servers set time granularity to 1 second while for
* everything else (current servers) set it to 100ns.
*/
if ((tcon->ses->server->vals->protocol_id == SMB10_PROT_ID) &&
((tcon->ses->capabilities &
tcon->ses->server->vals->cap_nt_find) == 0) &&
!tcon->unix_ext) {
sb->s_time_gran = 1000000000; /* 1 second is max allowed gran */
ts = cnvrtDosUnixTm(cpu_to_le16(SMB_DATE_MIN), 0, 0);
sb->s_time_min = ts.tv_sec;
ts = cnvrtDosUnixTm(cpu_to_le16(SMB_DATE_MAX),
cpu_to_le16(SMB_TIME_MAX), 0);
sb->s_time_max = ts.tv_sec;
} else {
/*
* Almost every server, including all SMB2+, uses DCE TIME
* ie 100 nanosecond units, since 1601. See MS-DTYP and MS-FSCC
*/
sb->s_time_gran = 100;
ts = cifs_NTtimeToUnix(0);
sb->s_time_min = ts.tv_sec;
ts = cifs_NTtimeToUnix(cpu_to_le64(S64_MAX));
sb->s_time_max = ts.tv_sec;
}
sb->s_magic = CIFS_MAGIC_NUMBER;
sb->s_op = &cifs_super_ops;
sb->s_xattr = cifs_xattr_handlers;
rc = super_setup_bdi(sb);
if (rc)
goto out_no_root;
/* tune readahead according to rsize */
sb->s_bdi->ra_pages = cifs_sb->ctx->rsize / PAGE_SIZE;
sb->s_blocksize = CIFS_MAX_MSGSIZE;
sb->s_blocksize_bits = 14; /* default 2**14 = CIFS_MAX_MSGSIZE */
inode = cifs_root_iget(sb);
if (IS_ERR(inode)) {
rc = PTR_ERR(inode);
goto out_no_root;
}
if (tcon->nocase)
sb->s_d_op = &cifs_ci_dentry_ops;
else
sb->s_d_op = &cifs_dentry_ops;
sb->s_root = d_make_root(inode);
if (!sb->s_root) {
rc = -ENOMEM;
goto out_no_root;
}
#ifdef CONFIG_CIFS_NFSD_EXPORT
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) {
cifs_dbg(FYI, "export ops supported\n");
sb->s_export_op = &cifs_export_ops;
}
#endif /* CONFIG_CIFS_NFSD_EXPORT */
return 0;
out_no_root:
cifs_dbg(VFS, "%s: get root inode failed\n", __func__);
return rc;
}
static void cifs_kill_sb(struct super_block *sb)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
kill_anon_super(sb);
cifs_umount(cifs_sb);
}
static int
cifs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
struct TCP_Server_Info *server = tcon->ses->server;
unsigned int xid;
int rc = 0;
xid = get_xid();
if (le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength) > 0)
buf->f_namelen =
le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength);
else
buf->f_namelen = PATH_MAX;
buf->f_fsid.val[0] = tcon->vol_serial_number;
/* are using part of create time for more randomness, see man statfs */
buf->f_fsid.val[1] = (int)le64_to_cpu(tcon->vol_create_time);
buf->f_files = 0; /* undefined */
buf->f_ffree = 0; /* unlimited */
if (server->ops->queryfs)
rc = server->ops->queryfs(xid, tcon, cifs_sb, buf);
free_xid(xid);
return 0;
}
static long cifs_fallocate(struct file *file, int mode, loff_t off, loff_t len)
{
struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file);
struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
struct TCP_Server_Info *server = tcon->ses->server;
if (server->ops->fallocate)
return server->ops->fallocate(file, tcon, mode, off, len);
return -EOPNOTSUPP;
}
static int cifs_permission(struct user_namespace *mnt_userns,
struct inode *inode, int mask)
{
struct cifs_sb_info *cifs_sb;
cifs_sb = CIFS_SB(inode->i_sb);
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) {
if ((mask & MAY_EXEC) && !execute_ok(inode))
return -EACCES;
else
return 0;
} else /* file mode might have been restricted at mount time
on the client (above and beyond ACL on servers) for
servers which do not support setting and viewing mode bits,
so allowing client to check permissions is useful */
return generic_permission(&init_user_ns, inode, mask);
}
static struct kmem_cache *cifs_inode_cachep;
static struct kmem_cache *cifs_req_cachep;
static struct kmem_cache *cifs_mid_cachep;
static struct kmem_cache *cifs_sm_req_cachep;
mempool_t *cifs_sm_req_poolp;
mempool_t *cifs_req_poolp;
mempool_t *cifs_mid_poolp;
static struct inode *
cifs_alloc_inode(struct super_block *sb)
{
struct cifsInodeInfo *cifs_inode;
cifs_inode = kmem_cache_alloc(cifs_inode_cachep, GFP_KERNEL);
if (!cifs_inode)
return NULL;
cifs_inode->cifsAttrs = 0x20; /* default */
cifs_inode->time = 0;
/*
* Until the file is open and we have gotten oplock info back from the
* server, can not assume caching of file data or metadata.
*/
cifs_set_oplock_level(cifs_inode, 0);
cifs_inode->flags = 0;
spin_lock_init(&cifs_inode->writers_lock);
cifs_inode->writers = 0;
cifs_inode->vfs_inode.i_blkbits = 14; /* 2**14 = CIFS_MAX_MSGSIZE */
cifs_inode->server_eof = 0;
cifs_inode->uniqueid = 0;
cifs_inode->createtime = 0;
cifs_inode->epoch = 0;
spin_lock_init(&cifs_inode->open_file_lock);
generate_random_uuid(cifs_inode->lease_key);
/*
* Can not set i_flags here - they get immediately overwritten to zero
* by the VFS.
*/
/* cifs_inode->vfs_inode.i_flags = S_NOATIME | S_NOCMTIME; */
INIT_LIST_HEAD(&cifs_inode->openFileList);
INIT_LIST_HEAD(&cifs_inode->llist);
return &cifs_inode->vfs_inode;
}
static void
cifs_free_inode(struct inode *inode)
{
kmem_cache_free(cifs_inode_cachep, CIFS_I(inode));
}
static void
cifs_evict_inode(struct inode *inode)
{
truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
cifs_fscache_release_inode_cookie(inode);
}
static void
cifs_show_address(struct seq_file *s, struct TCP_Server_Info *server)
{
struct sockaddr_in *sa = (struct sockaddr_in *) &server->dstaddr;
struct sockaddr_in6 *sa6 = (struct sockaddr_in6 *) &server->dstaddr;
seq_puts(s, ",addr=");
switch (server->dstaddr.ss_family) {
case AF_INET:
seq_printf(s, "%pI4", &sa->sin_addr.s_addr);
break;
case AF_INET6:
seq_printf(s, "%pI6", &sa6->sin6_addr.s6_addr);
if (sa6->sin6_scope_id)
seq_printf(s, "%%%u", sa6->sin6_scope_id);
break;
default:
seq_puts(s, "(unknown)");
}
if (server->rdma)
seq_puts(s, ",rdma");
}
static void
cifs_show_security(struct seq_file *s, struct cifs_ses *ses)
{
if (ses->sectype == Unspecified) {
if (ses->user_name == NULL)
seq_puts(s, ",sec=none");
return;
}
seq_puts(s, ",sec=");
switch (ses->sectype) {
case LANMAN:
seq_puts(s, "lanman");
break;
case NTLMv2:
seq_puts(s, "ntlmv2");
break;
case NTLM:
seq_puts(s, "ntlm");
break;
case Kerberos:
seq_puts(s, "krb5");
break;
case RawNTLMSSP:
seq_puts(s, "ntlmssp");
break;
default:
/* shouldn't ever happen */
seq_puts(s, "unknown");
break;
}
if (ses->sign)
seq_puts(s, "i");
if (ses->sectype == Kerberos)
seq_printf(s, ",cruid=%u",
from_kuid_munged(&init_user_ns, ses->cred_uid));
}
static void
cifs_show_cache_flavor(struct seq_file *s, struct cifs_sb_info *cifs_sb)
{
seq_puts(s, ",cache=");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO)
seq_puts(s, "strict");
else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO)
seq_puts(s, "none");
else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RW_CACHE)
seq_puts(s, "singleclient"); /* assume only one client access */
else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RO_CACHE)
seq_puts(s, "ro"); /* read only caching assumed */
else
seq_puts(s, "loose");
}
/*
* cifs_show_devname() is used so we show the mount device name with correct
* format (e.g. forward slashes vs. back slashes) in /proc/mounts
*/
static int cifs_show_devname(struct seq_file *m, struct dentry *root)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(root->d_sb);
char *devname = kstrdup(cifs_sb->ctx->source, GFP_KERNEL);
if (devname == NULL)
seq_puts(m, "none");
else {
convert_delimiter(devname, '/');
seq_puts(m, devname);
kfree(devname);
}
return 0;
}
/*
* cifs_show_options() is for displaying mount options in /proc/mounts.
* Not all settable options are displayed but most of the important
* ones are.
*/
static int
cifs_show_options(struct seq_file *s, struct dentry *root)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(root->d_sb);
struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
struct sockaddr *srcaddr;
srcaddr = (struct sockaddr *)&tcon->ses->server->srcaddr;
seq_show_option(s, "vers", tcon->ses->server->vals->version_string);
cifs_show_security(s, tcon->ses);
cifs_show_cache_flavor(s, cifs_sb);
if (tcon->no_lease)
seq_puts(s, ",nolease");
if (cifs_sb->ctx->multiuser)
seq_puts(s, ",multiuser");
else if (tcon->ses->user_name)
seq_show_option(s, "username", tcon->ses->user_name);
if (tcon->ses->domainName && tcon->ses->domainName[0] != 0)
seq_show_option(s, "domain", tcon->ses->domainName);
if (srcaddr->sa_family != AF_UNSPEC) {
struct sockaddr_in *saddr4;
struct sockaddr_in6 *saddr6;
saddr4 = (struct sockaddr_in *)srcaddr;
saddr6 = (struct sockaddr_in6 *)srcaddr;
if (srcaddr->sa_family == AF_INET6)
seq_printf(s, ",srcaddr=%pI6c",
&saddr6->sin6_addr);
else if (srcaddr->sa_family == AF_INET)
seq_printf(s, ",srcaddr=%pI4",
&saddr4->sin_addr.s_addr);
else
seq_printf(s, ",srcaddr=BAD-AF:%i",
(int)(srcaddr->sa_family));
}
seq_printf(s, ",uid=%u",
from_kuid_munged(&init_user_ns, cifs_sb->ctx->linux_uid));
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID)
seq_puts(s, ",forceuid");
else
seq_puts(s, ",noforceuid");
seq_printf(s, ",gid=%u",
from_kgid_munged(&init_user_ns, cifs_sb->ctx->linux_gid));
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID)
seq_puts(s, ",forcegid");
else
seq_puts(s, ",noforcegid");
cifs_show_address(s, tcon->ses->server);
if (!tcon->unix_ext)
seq_printf(s, ",file_mode=0%ho,dir_mode=0%ho",
cifs_sb->ctx->file_mode,
cifs_sb->ctx->dir_mode);
if (cifs_sb->ctx->iocharset)
seq_printf(s, ",iocharset=%s", cifs_sb->ctx->iocharset);
if (tcon->seal)
seq_puts(s, ",seal");
else if (tcon->ses->server->ignore_signature)
seq_puts(s, ",signloosely");
if (tcon->nocase)
seq_puts(s, ",nocase");
if (tcon->nodelete)
seq_puts(s, ",nodelete");
if (tcon->local_lease)
seq_puts(s, ",locallease");
if (tcon->retry)
seq_puts(s, ",hard");
else
seq_puts(s, ",soft");
if (tcon->use_persistent)
seq_puts(s, ",persistenthandles");
else if (tcon->use_resilient)
seq_puts(s, ",resilienthandles");
if (tcon->posix_extensions)
seq_puts(s, ",posix");
else if (tcon->unix_ext)
seq_puts(s, ",unix");
else
seq_puts(s, ",nounix");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS)
seq_puts(s, ",nodfs");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)
seq_puts(s, ",posixpaths");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)
seq_puts(s, ",setuids");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UID_FROM_ACL)
seq_puts(s, ",idsfromsid");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)
seq_puts(s, ",serverino");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
seq_puts(s, ",rwpidforward");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL)
seq_puts(s, ",forcemand");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
seq_puts(s, ",nouser_xattr");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR)
seq_puts(s, ",mapchars");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SFM_CHR)
seq_puts(s, ",mapposix");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)
seq_puts(s, ",sfu");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
seq_puts(s, ",nobrl");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_HANDLE_CACHE)
seq_puts(s, ",nohandlecache");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID)
seq_puts(s, ",modefromsid");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL)
seq_puts(s, ",cifsacl");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)
seq_puts(s, ",dynperm");
if (root->d_sb->s_flags & SB_POSIXACL)
seq_puts(s, ",acl");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS)
seq_puts(s, ",mfsymlinks");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_FSCACHE)
seq_puts(s, ",fsc");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)
seq_puts(s, ",nostrictsync");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM)
seq_puts(s, ",noperm");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPUID)
seq_printf(s, ",backupuid=%u",
from_kuid_munged(&init_user_ns,
cifs_sb->ctx->backupuid));
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPGID)
seq_printf(s, ",backupgid=%u",
from_kgid_munged(&init_user_ns,
cifs_sb->ctx->backupgid));
seq_printf(s, ",rsize=%u", cifs_sb->ctx->rsize);
seq_printf(s, ",wsize=%u", cifs_sb->ctx->wsize);
seq_printf(s, ",bsize=%u", cifs_sb->ctx->bsize);
if (tcon->ses->server->min_offload)
seq_printf(s, ",esize=%u", tcon->ses->server->min_offload);
seq_printf(s, ",echo_interval=%lu",
tcon->ses->server->echo_interval / HZ);
/* Only display max_credits if it was overridden on mount */
if (tcon->ses->server->max_credits != SMB2_MAX_CREDITS_AVAILABLE)
seq_printf(s, ",max_credits=%u", tcon->ses->server->max_credits);
if (tcon->snapshot_time)
seq_printf(s, ",snapshot=%llu", tcon->snapshot_time);
if (tcon->handle_timeout)
seq_printf(s, ",handletimeout=%u", tcon->handle_timeout);
/* convert actimeo and display it in seconds */
seq_printf(s, ",actimeo=%lu", cifs_sb->ctx->actimeo / HZ);
if (tcon->ses->chan_max > 1)
seq_printf(s, ",multichannel,max_channels=%zu",
tcon->ses->chan_max);
#ifdef CONFIG_CIFS_SWN_UPCALL
if (tcon->use_witness)
seq_puts(s, ",witness");
#endif
return 0;
}
static void cifs_umount_begin(struct super_block *sb)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
struct cifs_tcon *tcon;
if (cifs_sb == NULL)
return;
tcon = cifs_sb_master_tcon(cifs_sb);
spin_lock(&cifs_tcp_ses_lock);
if ((tcon->tc_count > 1) || (tcon->tidStatus == CifsExiting)) {
/* we have other mounts to same share or we have
already tried to force umount this and woken up
all waiting network requests, nothing to do */
spin_unlock(&cifs_tcp_ses_lock);
return;
} else if (tcon->tc_count == 1)
tcon->tidStatus = CifsExiting;
spin_unlock(&cifs_tcp_ses_lock);
/* cancel_brl_requests(tcon); */ /* BB mark all brl mids as exiting */
/* cancel_notify_requests(tcon); */
if (tcon->ses && tcon->ses->server) {
cifs_dbg(FYI, "wake up tasks now - umount begin not complete\n");
wake_up_all(&tcon->ses->server->request_q);
wake_up_all(&tcon->ses->server->response_q);
msleep(1); /* yield */
/* we have to kick the requests once more */
wake_up_all(&tcon->ses->server->response_q);
msleep(1);
}
return;
}
#ifdef CONFIG_CIFS_STATS2
static int cifs_show_stats(struct seq_file *s, struct dentry *root)
{
/* BB FIXME */
return 0;
}
#endif
static int cifs_drop_inode(struct inode *inode)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
/* no serverino => unconditional eviction */
return !(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) ||
generic_drop_inode(inode);
}
static const struct super_operations cifs_super_ops = {
.statfs = cifs_statfs,
.alloc_inode = cifs_alloc_inode,
.free_inode = cifs_free_inode,
.drop_inode = cifs_drop_inode,
.evict_inode = cifs_evict_inode,
/* .show_path = cifs_show_path, */ /* Would we ever need show path? */
.show_devname = cifs_show_devname,
/* .delete_inode = cifs_delete_inode, */ /* Do not need above
function unless later we add lazy close of inodes or unless the
kernel forgets to call us with the same number of releases (closes)
as opens */
.show_options = cifs_show_options,
.umount_begin = cifs_umount_begin,
#ifdef CONFIG_CIFS_STATS2
.show_stats = cifs_show_stats,
#endif
};
/*
* Get root dentry from superblock according to prefix path mount option.
* Return dentry with refcount + 1 on success and NULL otherwise.
*/
static struct dentry *
cifs_get_root(struct smb3_fs_context *ctx, struct super_block *sb)
{
struct dentry *dentry;
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
char *full_path = NULL;
char *s, *p;
char sep;
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH)
return dget(sb->s_root);
full_path = cifs_build_path_to_root(ctx, cifs_sb,
cifs_sb_master_tcon(cifs_sb), 0);
if (full_path == NULL)
return ERR_PTR(-ENOMEM);
cifs_dbg(FYI, "Get root dentry for %s\n", full_path);
sep = CIFS_DIR_SEP(cifs_sb);
dentry = dget(sb->s_root);
p = s = full_path;
do {
struct inode *dir = d_inode(dentry);
struct dentry *child;
if (!S_ISDIR(dir->i_mode)) {
dput(dentry);
dentry = ERR_PTR(-ENOTDIR);
break;
}
/* skip separators */
while (*s == sep)
s++;
if (!*s)
break;
p = s++;
/* next separator */
while (*s && *s != sep)
s++;
child = lookup_positive_unlocked(p, dentry, s - p);
dput(dentry);
dentry = child;
} while (!IS_ERR(dentry));
kfree(full_path);
return dentry;
}
static int cifs_set_super(struct super_block *sb, void *data)
{
struct cifs_mnt_data *mnt_data = data;
sb->s_fs_info = mnt_data->cifs_sb;
return set_anon_super(sb, NULL);
}
struct dentry *
cifs_smb3_do_mount(struct file_system_type *fs_type,
int flags, struct smb3_fs_context *old_ctx)
{
int rc;
struct super_block *sb;
struct cifs_sb_info *cifs_sb = NULL;
struct cifs_mnt_data mnt_data;
struct dentry *root;
/*
* Prints in Kernel / CIFS log the attempted mount operation
* If CIFS_DEBUG && cifs_FYI
*/
if (cifsFYI)
cifs_dbg(FYI, "Devname: %s flags: %d\n", old_ctx->UNC, flags);
else
cifs_info("Attempting to mount %s\n", old_ctx->UNC);
cifs_sb = kzalloc(sizeof(struct cifs_sb_info), GFP_KERNEL);
if (cifs_sb == NULL) {
root = ERR_PTR(-ENOMEM);
goto out;
}
cifs_sb->ctx = kzalloc(sizeof(struct smb3_fs_context), GFP_KERNEL);
if (!cifs_sb->ctx) {
root = ERR_PTR(-ENOMEM);
goto out;
}
rc = smb3_fs_context_dup(cifs_sb->ctx, old_ctx);
if (rc) {
root = ERR_PTR(rc);
goto out;
}
rc = cifs_setup_volume_info(cifs_sb->ctx, NULL, old_ctx->UNC);
if (rc) {
root = ERR_PTR(rc);
goto out;
}
rc = cifs_setup_cifs_sb(cifs_sb);
if (rc) {
root = ERR_PTR(rc);
goto out;
}
rc = cifs_mount(cifs_sb, cifs_sb->ctx);
if (rc) {
if (!(flags & SB_SILENT))
cifs_dbg(VFS, "cifs_mount failed w/return code = %d\n",
rc);
root = ERR_PTR(rc);
goto out;
}
mnt_data.ctx = cifs_sb->ctx;
mnt_data.cifs_sb = cifs_sb;
mnt_data.flags = flags;
/* BB should we make this contingent on mount parm? */
flags |= SB_NODIRATIME | SB_NOATIME;
sb = sget(fs_type, cifs_match_super, cifs_set_super, flags, &mnt_data);
if (IS_ERR(sb)) {
root = ERR_CAST(sb);
cifs_umount(cifs_sb);
cifs_sb = NULL;
goto out;
}
if (sb->s_root) {
cifs_dbg(FYI, "Use existing superblock\n");
cifs_umount(cifs_sb);
cifs_sb = NULL;
} else {
rc = cifs_read_super(sb);
if (rc) {
root = ERR_PTR(rc);
goto out_super;
}
sb->s_flags |= SB_ACTIVE;
}
root = cifs_get_root(cifs_sb ? cifs_sb->ctx : old_ctx, sb);
if (IS_ERR(root))
goto out_super;
cifs_dbg(FYI, "dentry root is: %p\n", root);
return root;
out_super:
deactivate_locked_super(sb);
out:
if (cifs_sb) {
kfree(cifs_sb->prepath);
smb3_cleanup_fs_context(cifs_sb->ctx);
kfree(cifs_sb);
}
return root;
}
static ssize_t
cifs_loose_read_iter(struct kiocb *iocb, struct iov_iter *iter)
{
ssize_t rc;
struct inode *inode = file_inode(iocb->ki_filp);
if (iocb->ki_filp->f_flags & O_DIRECT)
return cifs_user_readv(iocb, iter);
rc = cifs_revalidate_mapping(inode);
if (rc)
return rc;
return generic_file_read_iter(iocb, iter);
}
static ssize_t cifs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct inode *inode = file_inode(iocb->ki_filp);
struct cifsInodeInfo *cinode = CIFS_I(inode);
ssize_t written;
int rc;
if (iocb->ki_filp->f_flags & O_DIRECT) {
written = cifs_user_writev(iocb, from);
if (written > 0 && CIFS_CACHE_READ(cinode)) {
cifs_zap_mapping(inode);
cifs_dbg(FYI,
"Set no oplock for inode=%p after a write operation\n",
inode);
cinode->oplock = 0;
}
return written;
}
written = cifs_get_writer(cinode);
if (written)
return written;
written = generic_file_write_iter(iocb, from);
if (CIFS_CACHE_WRITE(CIFS_I(inode)))
goto out;
rc = filemap_fdatawrite(inode->i_mapping);
if (rc)
cifs_dbg(FYI, "cifs_file_write_iter: %d rc on %p inode\n",
rc, inode);
out:
cifs_put_writer(cinode);
return written;
}
static loff_t cifs_llseek(struct file *file, loff_t offset, int whence)
{
struct cifsFileInfo *cfile = file->private_data;
struct cifs_tcon *tcon;
/*
* whence == SEEK_END || SEEK_DATA || SEEK_HOLE => we must revalidate
* the cached file length
*/
if (whence != SEEK_SET && whence != SEEK_CUR) {
int rc;
struct inode *inode = file_inode(file);
/*
* We need to be sure that all dirty pages are written and the
* server has the newest file length.
*/
if (!CIFS_CACHE_READ(CIFS_I(inode)) && inode->i_mapping &&
inode->i_mapping->nrpages != 0) {
rc = filemap_fdatawait(inode->i_mapping);
if (rc) {
mapping_set_error(inode->i_mapping, rc);
return rc;
}
}
/*
* Some applications poll for the file length in this strange
* way so we must seek to end on non-oplocked files by
* setting the revalidate time to zero.
*/
CIFS_I(inode)->time = 0;
rc = cifs_revalidate_file_attr(file);
if (rc < 0)
return (loff_t)rc;
}
if (cfile && cfile->tlink) {
tcon = tlink_tcon(cfile->tlink);
if (tcon->ses->server->ops->llseek)
return tcon->ses->server->ops->llseek(file, tcon,
offset, whence);
}
return generic_file_llseek(file, offset, whence);
}
static int
cifs_setlease(struct file *file, long arg, struct file_lock **lease, void **priv)
{
/*
* Note that this is called by vfs setlease with i_lock held to
* protect *lease from going away.
*/
struct inode *inode = file_inode(file);
struct cifsFileInfo *cfile = file->private_data;
if (!(S_ISREG(inode->i_mode)))
return -EINVAL;
/* Check if file is oplocked if this is request for new lease */
if (arg == F_UNLCK ||
((arg == F_RDLCK) && CIFS_CACHE_READ(CIFS_I(inode))) ||
((arg == F_WRLCK) && CIFS_CACHE_WRITE(CIFS_I(inode))))
return generic_setlease(file, arg, lease, priv);
else if (tlink_tcon(cfile->tlink)->local_lease &&
!CIFS_CACHE_READ(CIFS_I(inode)))
/*
* If the server claims to support oplock on this file, then we
* still need to check oplock even if the local_lease mount
* option is set, but there are servers which do not support
* oplock for which this mount option may be useful if the user
* knows that the file won't be changed on the server by anyone
* else.
*/
return generic_setlease(file, arg, lease, priv);
else
return -EAGAIN;
}
struct file_system_type cifs_fs_type = {
.owner = THIS_MODULE,
.name = "cifs",
.init_fs_context = smb3_init_fs_context,
.parameters = smb3_fs_parameters,
.kill_sb = cifs_kill_sb,
.fs_flags = FS_RENAME_DOES_D_MOVE,
};
MODULE_ALIAS_FS("cifs");
static struct file_system_type smb3_fs_type = {
.owner = THIS_MODULE,
.name = "smb3",
.init_fs_context = smb3_init_fs_context,
.parameters = smb3_fs_parameters,
.kill_sb = cifs_kill_sb,
.fs_flags = FS_RENAME_DOES_D_MOVE,
};
MODULE_ALIAS_FS("smb3");
MODULE_ALIAS("smb3");
const struct inode_operations cifs_dir_inode_ops = {
.create = cifs_create,
.atomic_open = cifs_atomic_open,
.lookup = cifs_lookup,
.getattr = cifs_getattr,
.unlink = cifs_unlink,
.link = cifs_hardlink,
.mkdir = cifs_mkdir,
.rmdir = cifs_rmdir,
.rename = cifs_rename2,
.permission = cifs_permission,
.setattr = cifs_setattr,
.symlink = cifs_symlink,
.mknod = cifs_mknod,
.listxattr = cifs_listxattr,
};
const struct inode_operations cifs_file_inode_ops = {
.setattr = cifs_setattr,
.getattr = cifs_getattr,
.permission = cifs_permission,
.listxattr = cifs_listxattr,
.fiemap = cifs_fiemap,
};
const struct inode_operations cifs_symlink_inode_ops = {
.get_link = cifs_get_link,
.permission = cifs_permission,
.listxattr = cifs_listxattr,
};
static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
struct file *dst_file, loff_t destoff, loff_t len,
unsigned int remap_flags)
{
struct inode *src_inode = file_inode(src_file);
struct inode *target_inode = file_inode(dst_file);
struct cifsFileInfo *smb_file_src = src_file->private_data;
struct cifsFileInfo *smb_file_target;
struct cifs_tcon *target_tcon;
unsigned int xid;
int rc;
if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY))
return -EINVAL;
cifs_dbg(FYI, "clone range\n");
xid = get_xid();
if (!src_file->private_data || !dst_file->private_data) {
rc = -EBADF;
cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
goto out;
}
smb_file_target = dst_file->private_data;
target_tcon = tlink_tcon(smb_file_target->tlink);
/*
* Note: cifs case is easier than btrfs since server responsible for
* checks for proper open modes and file type and if it wants
* server could even support copy of range where source = target
*/
lock_two_nondirectories(target_inode, src_inode);
if (len == 0)
len = src_inode->i_size - off;
cifs_dbg(FYI, "about to flush pages\n");
/* should we flush first and last page first */
truncate_inode_pages_range(&target_inode->i_data, destoff,
PAGE_ALIGN(destoff + len)-1);
if (target_tcon->ses->server->ops->duplicate_extents)
rc = target_tcon->ses->server->ops->duplicate_extents(xid,
smb_file_src, smb_file_target, off, len, destoff);
else
rc = -EOPNOTSUPP;
/* force revalidate of size and timestamps of target file now
that target is updated on the server */
CIFS_I(target_inode)->time = 0;
/* although unlocking in the reverse order from locking is not
strictly necessary here it is a little cleaner to be consistent */
unlock_two_nondirectories(src_inode, target_inode);
out:
free_xid(xid);
return rc < 0 ? rc : len;
}
ssize_t cifs_file_copychunk_range(unsigned int xid,
struct file *src_file, loff_t off,
struct file *dst_file, loff_t destoff,
size_t len, unsigned int flags)
{
struct inode *src_inode = file_inode(src_file);
struct inode *target_inode = file_inode(dst_file);
struct cifsFileInfo *smb_file_src;
struct cifsFileInfo *smb_file_target;
struct cifs_tcon *src_tcon;
struct cifs_tcon *target_tcon;
ssize_t rc;
cifs_dbg(FYI, "copychunk range\n");
if (!src_file->private_data || !dst_file->private_data) {
rc = -EBADF;
cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
goto out;
}
rc = -EXDEV;
smb_file_target = dst_file->private_data;
smb_file_src = src_file->private_data;
src_tcon = tlink_tcon(smb_file_src->tlink);
target_tcon = tlink_tcon(smb_file_target->tlink);
if (src_tcon->ses != target_tcon->ses) {
cifs_dbg(VFS, "source and target of copy not on same server\n");
goto out;
}
rc = -EOPNOTSUPP;
if (!target_tcon->ses->server->ops->copychunk_range)
goto out;
/*
* Note: cifs case is easier than btrfs since server responsible for
* checks for proper open modes and file type and if it wants
* server could even support copy of range where source = target
*/
lock_two_nondirectories(target_inode, src_inode);
cifs_dbg(FYI, "about to flush pages\n");
/* should we flush first and last page first */
truncate_inode_pages(&target_inode->i_data, 0);
rc = file_modified(dst_file);
if (!rc)
rc = target_tcon->ses->server->ops->copychunk_range(xid,
smb_file_src, smb_file_target, off, len, destoff);
file_accessed(src_file);
/* force revalidate of size and timestamps of target file now
* that target is updated on the server
*/
CIFS_I(target_inode)->time = 0;
/* although unlocking in the reverse order from locking is not
* strictly necessary here it is a little cleaner to be consistent
*/
unlock_two_nondirectories(src_inode, target_inode);
out:
return rc;
}
/*
* Directory operations under CIFS/SMB2/SMB3 are synchronous, so fsync()
* is a dummy operation.
*/
static int cifs_dir_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
cifs_dbg(FYI, "Sync directory - name: %pD datasync: 0x%x\n",
file, datasync);
return 0;
}
static ssize_t cifs_copy_file_range(struct file *src_file, loff_t off,
struct file *dst_file, loff_t destoff,
size_t len, unsigned int flags)
{
unsigned int xid = get_xid();
ssize_t rc;
struct cifsFileInfo *cfile = dst_file->private_data;
if (cfile->swapfile)
return -EOPNOTSUPP;
rc = cifs_file_copychunk_range(xid, src_file, off, dst_file, destoff,
len, flags);
free_xid(xid);
if (rc == -EOPNOTSUPP || rc == -EXDEV)
rc = generic_copy_file_range(src_file, off, dst_file,
destoff, len, flags);
return rc;
}
const struct file_operations cifs_file_ops = {
.read_iter = cifs_loose_read_iter,
.write_iter = cifs_file_write_iter,
.open = cifs_open,
.release = cifs_close,
.lock = cifs_lock,
.flock = cifs_flock,
.fsync = cifs_fsync,
.flush = cifs_flush,
.mmap = cifs_file_mmap,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.llseek = cifs_llseek,
.unlocked_ioctl = cifs_ioctl,
.copy_file_range = cifs_copy_file_range,
.remap_file_range = cifs_remap_file_range,
.setlease = cifs_setlease,
.fallocate = cifs_fallocate,
};
const struct file_operations cifs_file_strict_ops = {
.read_iter = cifs_strict_readv,
.write_iter = cifs_strict_writev,
.open = cifs_open,
.release = cifs_close,
.lock = cifs_lock,
.flock = cifs_flock,
.fsync = cifs_strict_fsync,
.flush = cifs_flush,
.mmap = cifs_file_strict_mmap,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.llseek = cifs_llseek,
.unlocked_ioctl = cifs_ioctl,
.copy_file_range = cifs_copy_file_range,
.remap_file_range = cifs_remap_file_range,
.setlease = cifs_setlease,
.fallocate = cifs_fallocate,
};
const struct file_operations cifs_file_direct_ops = {
.read_iter = cifs_direct_readv,
.write_iter = cifs_direct_writev,
.open = cifs_open,
.release = cifs_close,
.lock = cifs_lock,
.flock = cifs_flock,
.fsync = cifs_fsync,
.flush = cifs_flush,
.mmap = cifs_file_mmap,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.unlocked_ioctl = cifs_ioctl,
.copy_file_range = cifs_copy_file_range,
.remap_file_range = cifs_remap_file_range,
.llseek = cifs_llseek,
.setlease = cifs_setlease,
.fallocate = cifs_fallocate,
};
const struct file_operations cifs_file_nobrl_ops = {
.read_iter = cifs_loose_read_iter,
.write_iter = cifs_file_write_iter,
.open = cifs_open,
.release = cifs_close,
.fsync = cifs_fsync,
.flush = cifs_flush,
.mmap = cifs_file_mmap,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.llseek = cifs_llseek,
.unlocked_ioctl = cifs_ioctl,
.copy_file_range = cifs_copy_file_range,
.remap_file_range = cifs_remap_file_range,
.setlease = cifs_setlease,
.fallocate = cifs_fallocate,
};
const struct file_operations cifs_file_strict_nobrl_ops = {
.read_iter = cifs_strict_readv,
.write_iter = cifs_strict_writev,
.open = cifs_open,
.release = cifs_close,
.fsync = cifs_strict_fsync,
.flush = cifs_flush,
.mmap = cifs_file_strict_mmap,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.llseek = cifs_llseek,
.unlocked_ioctl = cifs_ioctl,
.copy_file_range = cifs_copy_file_range,
.remap_file_range = cifs_remap_file_range,
.setlease = cifs_setlease,
.fallocate = cifs_fallocate,
};
const struct file_operations cifs_file_direct_nobrl_ops = {
.read_iter = cifs_direct_readv,
.write_iter = cifs_direct_writev,
.open = cifs_open,
.release = cifs_close,
.fsync = cifs_fsync,
.flush = cifs_flush,
.mmap = cifs_file_mmap,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.unlocked_ioctl = cifs_ioctl,
.copy_file_range = cifs_copy_file_range,
.remap_file_range = cifs_remap_file_range,
.llseek = cifs_llseek,
.setlease = cifs_setlease,
.fallocate = cifs_fallocate,
};
const struct file_operations cifs_dir_ops = {
.iterate_shared = cifs_readdir,
.release = cifs_closedir,
.read = generic_read_dir,
.unlocked_ioctl = cifs_ioctl,
.copy_file_range = cifs_copy_file_range,
.remap_file_range = cifs_remap_file_range,
.llseek = generic_file_llseek,
.fsync = cifs_dir_fsync,
};
static void
cifs_init_once(void *inode)
{
struct cifsInodeInfo *cifsi = inode;
inode_init_once(&cifsi->vfs_inode);
init_rwsem(&cifsi->lock_sem);
}
static int __init
cifs_init_inodecache(void)
{
cifs_inode_cachep = kmem_cache_create("cifs_inode_cache",
sizeof(struct cifsInodeInfo),
0, (SLAB_RECLAIM_ACCOUNT|
SLAB_MEM_SPREAD|SLAB_ACCOUNT),
cifs_init_once);
if (cifs_inode_cachep == NULL)
return -ENOMEM;
return 0;
}
static void
cifs_destroy_inodecache(void)
{
/*
* Make sure all delayed rcu free inodes are flushed before we
* destroy cache.
*/
rcu_barrier();
kmem_cache_destroy(cifs_inode_cachep);
}
static int
cifs_init_request_bufs(void)
{
/*
* SMB2 maximum header size is bigger than CIFS one - no problems to
* allocate some more bytes for CIFS.
*/
size_t max_hdr_size = MAX_SMB2_HDR_SIZE;
if (CIFSMaxBufSize < 8192) {
/* Buffer size can not be smaller than 2 * PATH_MAX since maximum
Unicode path name has to fit in any SMB/CIFS path based frames */
CIFSMaxBufSize = 8192;
} else if (CIFSMaxBufSize > 1024*127) {
CIFSMaxBufSize = 1024 * 127;
} else {
CIFSMaxBufSize &= 0x1FE00; /* Round size to even 512 byte mult*/
}
/*
cifs_dbg(VFS, "CIFSMaxBufSize %d 0x%x\n",
CIFSMaxBufSize, CIFSMaxBufSize);
*/
cifs_req_cachep = kmem_cache_create_usercopy("cifs_request",
CIFSMaxBufSize + max_hdr_size, 0,
SLAB_HWCACHE_ALIGN, 0,
CIFSMaxBufSize + max_hdr_size,
NULL);
if (cifs_req_cachep == NULL)
return -ENOMEM;
if (cifs_min_rcv < 1)
cifs_min_rcv = 1;
else if (cifs_min_rcv > 64) {
cifs_min_rcv = 64;
cifs_dbg(VFS, "cifs_min_rcv set to maximum (64)\n");
}
cifs_req_poolp = mempool_create_slab_pool(cifs_min_rcv,
cifs_req_cachep);
if (cifs_req_poolp == NULL) {
kmem_cache_destroy(cifs_req_cachep);
return -ENOMEM;
}
/* MAX_CIFS_SMALL_BUFFER_SIZE bytes is enough for most SMB responses and
almost all handle based requests (but not write response, nor is it
sufficient for path based requests). A smaller size would have
been more efficient (compacting multiple slab items on one 4k page)
for the case in which debug was on, but this larger size allows
more SMBs to use small buffer alloc and is still much more
efficient to alloc 1 per page off the slab compared to 17K (5page)
alloc of large cifs buffers even when page debugging is on */
cifs_sm_req_cachep = kmem_cache_create_usercopy("cifs_small_rq",
MAX_CIFS_SMALL_BUFFER_SIZE, 0, SLAB_HWCACHE_ALIGN,
0, MAX_CIFS_SMALL_BUFFER_SIZE, NULL);
if (cifs_sm_req_cachep == NULL) {
mempool_destroy(cifs_req_poolp);
kmem_cache_destroy(cifs_req_cachep);
return -ENOMEM;
}
if (cifs_min_small < 2)
cifs_min_small = 2;
else if (cifs_min_small > 256) {
cifs_min_small = 256;
cifs_dbg(FYI, "cifs_min_small set to maximum (256)\n");
}
cifs_sm_req_poolp = mempool_create_slab_pool(cifs_min_small,
cifs_sm_req_cachep);
if (cifs_sm_req_poolp == NULL) {
mempool_destroy(cifs_req_poolp);
kmem_cache_destroy(cifs_req_cachep);
kmem_cache_destroy(cifs_sm_req_cachep);
return -ENOMEM;
}
return 0;
}
static void
cifs_destroy_request_bufs(void)
{
mempool_destroy(cifs_req_poolp);
kmem_cache_destroy(cifs_req_cachep);
mempool_destroy(cifs_sm_req_poolp);
kmem_cache_destroy(cifs_sm_req_cachep);
}
static int
cifs_init_mids(void)
{
cifs_mid_cachep = kmem_cache_create("cifs_mpx_ids",
sizeof(struct mid_q_entry), 0,
SLAB_HWCACHE_ALIGN, NULL);
if (cifs_mid_cachep == NULL)
return -ENOMEM;
/* 3 is a reasonable minimum number of simultaneous operations */
cifs_mid_poolp = mempool_create_slab_pool(3, cifs_mid_cachep);
if (cifs_mid_poolp == NULL) {
kmem_cache_destroy(cifs_mid_cachep);
return -ENOMEM;
}
return 0;
}
static void
cifs_destroy_mids(void)
{
mempool_destroy(cifs_mid_poolp);
kmem_cache_destroy(cifs_mid_cachep);
}
static int __init
init_cifs(void)
{
int rc = 0;
cifs_proc_init();
INIT_LIST_HEAD(&cifs_tcp_ses_list);
#ifdef CONFIG_CIFS_DNOTIFY_EXPERIMENTAL /* unused temporarily */
INIT_LIST_HEAD(&GlobalDnotifyReqList);
INIT_LIST_HEAD(&GlobalDnotifyRsp_Q);
#endif /* was needed for dnotify, and will be needed for inotify when VFS fix */
/*
* Initialize Global counters
*/
atomic_set(&sesInfoAllocCount, 0);
atomic_set(&tconInfoAllocCount, 0);
atomic_set(&tcpSesAllocCount, 0);
atomic_set(&tcpSesReconnectCount, 0);
atomic_set(&tconInfoReconnectCount, 0);
atomic_set(&bufAllocCount, 0);
atomic_set(&smBufAllocCount, 0);
#ifdef CONFIG_CIFS_STATS2
atomic_set(&totBufAllocCount, 0);
atomic_set(&totSmBufAllocCount, 0);
if (slow_rsp_threshold < 1)
cifs_dbg(FYI, "slow_response_threshold msgs disabled\n");
else if (slow_rsp_threshold > 32767)
cifs_dbg(VFS,
"slow response threshold set higher than recommended (0 to 32767)\n");
#endif /* CONFIG_CIFS_STATS2 */
atomic_set(&midCount, 0);
GlobalCurrentXid = 0;
GlobalTotalActiveXid = 0;
GlobalMaxActiveXid = 0;
spin_lock_init(&cifs_tcp_ses_lock);
spin_lock_init(&GlobalMid_Lock);
cifs_lock_secret = get_random_u32();
if (cifs_max_pending < 2) {
cifs_max_pending = 2;
cifs_dbg(FYI, "cifs_max_pending set to min of 2\n");
} else if (cifs_max_pending > CIFS_MAX_REQ) {
cifs_max_pending = CIFS_MAX_REQ;
cifs_dbg(FYI, "cifs_max_pending set to max of %u\n",
CIFS_MAX_REQ);
}
cifsiod_wq = alloc_workqueue("cifsiod", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
if (!cifsiod_wq) {
rc = -ENOMEM;
goto out_clean_proc;
}
/*
* Consider in future setting limit!=0 maybe to min(num_of_cores - 1, 3)
* so that we don't launch too many worker threads but
* Documentation/core-api/workqueue.rst recommends setting it to 0
*/
/* WQ_UNBOUND allows decrypt tasks to run on any CPU */
decrypt_wq = alloc_workqueue("smb3decryptd",
WQ_UNBOUND|WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
if (!decrypt_wq) {
rc = -ENOMEM;
goto out_destroy_cifsiod_wq;
}
fileinfo_put_wq = alloc_workqueue("cifsfileinfoput",
WQ_UNBOUND|WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
if (!fileinfo_put_wq) {
rc = -ENOMEM;
goto out_destroy_decrypt_wq;
}
cifsoplockd_wq = alloc_workqueue("cifsoplockd",
WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
if (!cifsoplockd_wq) {
rc = -ENOMEM;
goto out_destroy_fileinfo_put_wq;
}
rc = cifs_fscache_register();
if (rc)
goto out_destroy_cifsoplockd_wq;
rc = cifs_init_inodecache();
if (rc)
goto out_unreg_fscache;
rc = cifs_init_mids();
if (rc)
goto out_destroy_inodecache;
rc = cifs_init_request_bufs();
if (rc)
goto out_destroy_mids;
#ifdef CONFIG_CIFS_DFS_UPCALL
rc = dfs_cache_init();
if (rc)
goto out_destroy_request_bufs;
#endif /* CONFIG_CIFS_DFS_UPCALL */
#ifdef CONFIG_CIFS_UPCALL
rc = init_cifs_spnego();
if (rc)
goto out_destroy_dfs_cache;
#endif /* CONFIG_CIFS_UPCALL */
#ifdef CONFIG_CIFS_SWN_UPCALL
rc = cifs_genl_init();
if (rc)
goto out_register_key_type;
#endif /* CONFIG_CIFS_SWN_UPCALL */
rc = init_cifs_idmap();
if (rc)
goto out_cifs_swn_init;
rc = register_filesystem(&cifs_fs_type);
if (rc)
goto out_init_cifs_idmap;
rc = register_filesystem(&smb3_fs_type);
if (rc) {
unregister_filesystem(&cifs_fs_type);
goto out_init_cifs_idmap;
}
return 0;
out_init_cifs_idmap:
exit_cifs_idmap();
out_cifs_swn_init:
#ifdef CONFIG_CIFS_SWN_UPCALL
cifs_genl_exit();
out_register_key_type:
#endif
#ifdef CONFIG_CIFS_UPCALL
exit_cifs_spnego();
out_destroy_dfs_cache:
#endif
#ifdef CONFIG_CIFS_DFS_UPCALL
dfs_cache_destroy();
out_destroy_request_bufs:
#endif
cifs_destroy_request_bufs();
out_destroy_mids:
cifs_destroy_mids();
out_destroy_inodecache:
cifs_destroy_inodecache();
out_unreg_fscache:
cifs_fscache_unregister();
out_destroy_cifsoplockd_wq:
destroy_workqueue(cifsoplockd_wq);
out_destroy_fileinfo_put_wq:
destroy_workqueue(fileinfo_put_wq);
out_destroy_decrypt_wq:
destroy_workqueue(decrypt_wq);
out_destroy_cifsiod_wq:
destroy_workqueue(cifsiod_wq);
out_clean_proc:
cifs_proc_clean();
return rc;
}
static void __exit
exit_cifs(void)
{
cifs_dbg(NOISY, "exit_smb3\n");
unregister_filesystem(&cifs_fs_type);
unregister_filesystem(&smb3_fs_type);
cifs_dfs_release_automount_timer();
exit_cifs_idmap();
#ifdef CONFIG_CIFS_SWN_UPCALL
cifs_genl_exit();
#endif
#ifdef CONFIG_CIFS_UPCALL
exit_cifs_spnego();
#endif
#ifdef CONFIG_CIFS_DFS_UPCALL
dfs_cache_destroy();
#endif
cifs_destroy_request_bufs();
cifs_destroy_mids();
cifs_destroy_inodecache();
cifs_fscache_unregister();
destroy_workqueue(cifsoplockd_wq);
destroy_workqueue(decrypt_wq);
destroy_workqueue(fileinfo_put_wq);
destroy_workqueue(cifsiod_wq);
cifs_proc_clean();
}
MODULE_AUTHOR("Steve French");
MODULE_LICENSE("GPL"); /* combination of LGPL + GPL source behaves as GPL */
MODULE_DESCRIPTION
("VFS to access SMB3 servers e.g. Samba, Macs, Azure and Windows (and "
"also older servers complying with the SNIA CIFS Specification)");
MODULE_VERSION(CIFS_VERSION);
MODULE_SOFTDEP("ecb");
MODULE_SOFTDEP("hmac");
MODULE_SOFTDEP("md4");
MODULE_SOFTDEP("md5");
MODULE_SOFTDEP("nls");
MODULE_SOFTDEP("aes");
MODULE_SOFTDEP("cmac");
MODULE_SOFTDEP("sha256");
MODULE_SOFTDEP("sha512");
MODULE_SOFTDEP("aead2");
MODULE_SOFTDEP("ccm");
MODULE_SOFTDEP("gcm");
module_init(init_cifs)
module_exit(exit_cifs)
Reference in New Issue View Git Blame Copy Permalink