Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-26 06:02:05 +00:00
Code Issues Packages Projects Releases Wiki Activity
f96d44743a
linux/fs/f2fs/file.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

4599 lines
108 KiB
C
Raw Blame History

// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/file.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include <linux/stat.h>
#include <linux/buffer_head.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/falloc.h>
#include <linux/types.h>
#include <linux/compat.h>
#include <linux/uaccess.h>
#include <linux/mount.h>
#include <linux/pagevec.h>
#include <linux/uio.h>
#include <linux/uuid.h>
#include <linux/file.h>
#include <linux/nls.h>
#include <linux/sched/signal.h>
#include "f2fs.h"
#include "node.h"
#include "segment.h"
#include "xattr.h"
#include "acl.h"
#include "gc.h"
#include <trace/events/f2fs.h>
#include <uapi/linux/f2fs.h>
static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf)
{
struct inode *inode = file_inode(vmf->vma->vm_file);
vm_fault_t ret;
down_read(&F2FS_I(inode)->i_mmap_sem);
ret = filemap_fault(vmf);
up_read(&F2FS_I(inode)->i_mmap_sem);
if (!ret)
f2fs_update_iostat(F2FS_I_SB(inode), APP_MAPPED_READ_IO,
F2FS_BLKSIZE);
trace_f2fs_filemap_fault(inode, vmf->pgoff, (unsigned long)ret);
return ret;
}
static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = file_inode(vmf->vma->vm_file);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
bool need_alloc = true;
int err = 0;
if (unlikely(IS_IMMUTABLE(inode)))
return VM_FAULT_SIGBUS;
if (unlikely(f2fs_cp_error(sbi))) {
err = -EIO;
goto err;
}
if (!f2fs_is_checkpoint_ready(sbi)) {
err = -ENOSPC;
goto err;
}
err = f2fs_convert_inline_inode(inode);
if (err)
goto err;
#ifdef CONFIG_F2FS_FS_COMPRESSION
if (f2fs_compressed_file(inode)) {
int ret = f2fs_is_compressed_cluster(inode, page->index);
if (ret < 0) {
err = ret;
goto err;
} else if (ret) {
if (ret < F2FS_I(inode)->i_cluster_size) {
err = -EAGAIN;
goto err;
}
need_alloc = false;
}
}
#endif
/* should do out of any locked page */
if (need_alloc)
f2fs_balance_fs(sbi, true);
sb_start_pagefault(inode->i_sb);
f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
file_update_time(vmf->vma->vm_file);
down_read(&F2FS_I(inode)->i_mmap_sem);
lock_page(page);
if (unlikely(page->mapping != inode->i_mapping ||
page_offset(page) > i_size_read(inode) ||
!PageUptodate(page))) {
unlock_page(page);
err = -EFAULT;
goto out_sem;
}
if (need_alloc) {
/* block allocation */
f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true);
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = f2fs_get_block(&dn, page->index);
f2fs_put_dnode(&dn);
f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false);
}
#ifdef CONFIG_F2FS_FS_COMPRESSION
if (!need_alloc) {
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = f2fs_get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
f2fs_put_dnode(&dn);
}
#endif
if (err) {
unlock_page(page);
goto out_sem;
}
f2fs_wait_on_page_writeback(page, DATA, false, true);
/* wait for GCed page writeback via META_MAPPING */
f2fs_wait_on_block_writeback(inode, dn.data_blkaddr);
/*
* check to see if the page is mapped already (no holes)
*/
if (PageMappedToDisk(page))
goto out_sem;
/* page is wholly or partially inside EOF */
if (((loff_t)(page->index + 1) << PAGE_SHIFT) >
i_size_read(inode)) {
loff_t offset;
offset = i_size_read(inode) & ~PAGE_MASK;
zero_user_segment(page, offset, PAGE_SIZE);
}
set_page_dirty(page);
if (!PageUptodate(page))
SetPageUptodate(page);
f2fs_update_iostat(sbi, APP_MAPPED_IO, F2FS_BLKSIZE);
f2fs_update_time(sbi, REQ_TIME);
trace_f2fs_vm_page_mkwrite(page, DATA);
out_sem:
up_read(&F2FS_I(inode)->i_mmap_sem);
sb_end_pagefault(inode->i_sb);
err:
return block_page_mkwrite_return(err);
}
static const struct vm_operations_struct f2fs_file_vm_ops = {
.fault = f2fs_filemap_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = f2fs_vm_page_mkwrite,
};
static int get_parent_ino(struct inode *inode, nid_t *pino)
{
struct dentry *dentry;
/*
* Make sure to get the non-deleted alias. The alias associated with
* the open file descriptor being fsync()'ed may be deleted already.
*/
dentry = d_find_alias(inode);
if (!dentry)
return 0;
*pino = parent_ino(dentry);
dput(dentry);
return 1;
}
static inline enum cp_reason_type need_do_checkpoint(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
enum cp_reason_type cp_reason = CP_NO_NEEDED;
if (!S_ISREG(inode->i_mode))
cp_reason = CP_NON_REGULAR;
else if (f2fs_compressed_file(inode))
cp_reason = CP_COMPRESSED;
else if (inode->i_nlink != 1)
cp_reason = CP_HARDLINK;
else if (is_sbi_flag_set(sbi, SBI_NEED_CP))
cp_reason = CP_SB_NEED_CP;
else if (file_wrong_pino(inode))
cp_reason = CP_WRONG_PINO;
else if (!f2fs_space_for_roll_forward(sbi))
cp_reason = CP_NO_SPC_ROLL;
else if (!f2fs_is_checkpointed_node(sbi, F2FS_I(inode)->i_pino))
cp_reason = CP_NODE_NEED_CP;
else if (test_opt(sbi, FASTBOOT))
cp_reason = CP_FASTBOOT_MODE;
else if (F2FS_OPTION(sbi).active_logs == 2)
cp_reason = CP_SPEC_LOG_NUM;
else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT &&
f2fs_need_dentry_mark(sbi, inode->i_ino) &&
f2fs_exist_written_data(sbi, F2FS_I(inode)->i_pino,
TRANS_DIR_INO))
cp_reason = CP_RECOVER_DIR;
return cp_reason;
}
static bool need_inode_page_update(struct f2fs_sb_info *sbi, nid_t ino)
{
struct page *i = find_get_page(NODE_MAPPING(sbi), ino);
bool ret = false;
/* But we need to avoid that there are some inode updates */
if ((i && PageDirty(i)) || f2fs_need_inode_block_update(sbi, ino))
ret = true;
f2fs_put_page(i, 0);
return ret;
}
static void try_to_fix_pino(struct inode *inode)
{
struct f2fs_inode_info *fi = F2FS_I(inode);
nid_t pino;
down_write(&fi->i_sem);
if (file_wrong_pino(inode) && inode->i_nlink == 1 &&
get_parent_ino(inode, &pino)) {
f2fs_i_pino_write(inode, pino);
file_got_pino(inode);
}
up_write(&fi->i_sem);
}
static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
int datasync, bool atomic)
{
struct inode *inode = file->f_mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
nid_t ino = inode->i_ino;
int ret = 0;
enum cp_reason_type cp_reason = 0;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.for_reclaim = 0,
};
unsigned int seq_id = 0;
if (unlikely(f2fs_readonly(inode->i_sb) ||
is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
return 0;
trace_f2fs_sync_file_enter(inode);
if (S_ISDIR(inode->i_mode))
goto go_write;
/* if fdatasync is triggered, let's do in-place-update */
if (datasync || get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
set_inode_flag(inode, FI_NEED_IPU);
ret = file_write_and_wait_range(file, start, end);
clear_inode_flag(inode, FI_NEED_IPU);
if (ret) {
trace_f2fs_sync_file_exit(inode, cp_reason, datasync, ret);
return ret;
}
/* if the inode is dirty, let's recover all the time */
if (!f2fs_skip_inode_update(inode, datasync)) {
f2fs_write_inode(inode, NULL);
goto go_write;
}
/*
* if there is no written data, don't waste time to write recovery info.
*/
if (!is_inode_flag_set(inode, FI_APPEND_WRITE) &&
!f2fs_exist_written_data(sbi, ino, APPEND_INO)) {
/* it may call write_inode just prior to fsync */
if (need_inode_page_update(sbi, ino))
goto go_write;
if (is_inode_flag_set(inode, FI_UPDATE_WRITE) ||
f2fs_exist_written_data(sbi, ino, UPDATE_INO))
goto flush_out;
goto out;
}
go_write:
/*
* Both of fdatasync() and fsync() are able to be recovered from
* sudden-power-off.
*/
down_read(&F2FS_I(inode)->i_sem);
cp_reason = need_do_checkpoint(inode);
up_read(&F2FS_I(inode)->i_sem);
if (cp_reason) {
/* all the dirty node pages should be flushed for POR */
ret = f2fs_sync_fs(inode->i_sb, 1);
/*
* We've secured consistency through sync_fs. Following pino
* will be used only for fsynced inodes after checkpoint.
*/
try_to_fix_pino(inode);
clear_inode_flag(inode, FI_APPEND_WRITE);
clear_inode_flag(inode, FI_UPDATE_WRITE);
goto out;
}
sync_nodes:
atomic_inc(&sbi->wb_sync_req[NODE]);
ret = f2fs_fsync_node_pages(sbi, inode, &wbc, atomic, &seq_id);
atomic_dec(&sbi->wb_sync_req[NODE]);
if (ret)
goto out;
/* if cp_error was enabled, we should avoid infinite loop */
if (unlikely(f2fs_cp_error(sbi))) {
ret = -EIO;
goto out;
}
if (f2fs_need_inode_block_update(sbi, ino)) {
f2fs_mark_inode_dirty_sync(inode, true);
f2fs_write_inode(inode, NULL);
goto sync_nodes;
}
/*
* If it's atomic_write, it's just fine to keep write ordering. So
* here we don't need to wait for node write completion, since we use
* node chain which serializes node blocks. If one of node writes are
* reordered, we can see simply broken chain, resulting in stopping
* roll-forward recovery. It means we'll recover all or none node blocks
* given fsync mark.
*/
if (!atomic) {
ret = f2fs_wait_on_node_pages_writeback(sbi, seq_id);
if (ret)
goto out;
}
/* once recovery info is written, don't need to tack this */
f2fs_remove_ino_entry(sbi, ino, APPEND_INO);
clear_inode_flag(inode, FI_APPEND_WRITE);
flush_out:
if (!atomic && F2FS_OPTION(sbi).fsync_mode != FSYNC_MODE_NOBARRIER)
ret = f2fs_issue_flush(sbi, inode->i_ino);
if (!ret) {
f2fs_remove_ino_entry(sbi, ino, UPDATE_INO);
clear_inode_flag(inode, FI_UPDATE_WRITE);
f2fs_remove_ino_entry(sbi, ino, FLUSH_INO);
}
f2fs_update_time(sbi, REQ_TIME);
out:
trace_f2fs_sync_file_exit(inode, cp_reason, datasync, ret);
return ret;
}
int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(file)))))
return -EIO;
return f2fs_do_sync_file(file, start, end, datasync, false);
}
static bool __found_offset(struct address_space *mapping, block_t blkaddr,
pgoff_t index, int whence)
{
switch (whence) {
case SEEK_DATA:
if (__is_valid_data_blkaddr(blkaddr))
return true;
if (blkaddr == NEW_ADDR &&
xa_get_mark(&mapping->i_pages, index, PAGECACHE_TAG_DIRTY))
return true;
break;
case SEEK_HOLE:
if (blkaddr == NULL_ADDR)
return true;
break;
}
return false;
}
static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
{
struct inode *inode = file->f_mapping->host;
loff_t maxbytes = inode->i_sb->s_maxbytes;
struct dnode_of_data dn;
pgoff_t pgofs, end_offset;
loff_t data_ofs = offset;
loff_t isize;
int err = 0;
inode_lock(inode);
isize = i_size_read(inode);
if (offset >= isize)
goto fail;
/* handle inline data case */
if (f2fs_has_inline_data(inode)) {
if (whence == SEEK_HOLE) {
data_ofs = isize;
goto found;
} else if (whence == SEEK_DATA) {
data_ofs = offset;
goto found;
}
}
pgofs = (pgoff_t)(offset >> PAGE_SHIFT);
for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_SHIFT) {
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = f2fs_get_dnode_of_data(&dn, pgofs, LOOKUP_NODE);
if (err && err != -ENOENT) {
goto fail;
} else if (err == -ENOENT) {
/* direct node does not exists */
if (whence == SEEK_DATA) {
pgofs = f2fs_get_next_page_offset(&dn, pgofs);
continue;
} else {
goto found;
}
}
end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
/* find data/hole in dnode block */
for (; dn.ofs_in_node < end_offset;
dn.ofs_in_node++, pgofs++,
data_ofs = (loff_t)pgofs << PAGE_SHIFT) {
block_t blkaddr;
blkaddr = f2fs_data_blkaddr(&dn);
if (__is_valid_data_blkaddr(blkaddr) &&
!f2fs_is_valid_blkaddr(F2FS_I_SB(inode),
blkaddr, DATA_GENERIC_ENHANCE)) {
f2fs_put_dnode(&dn);
goto fail;
}
if (__found_offset(file->f_mapping, blkaddr,
pgofs, whence)) {
f2fs_put_dnode(&dn);
goto found;
}
}
f2fs_put_dnode(&dn);
}
if (whence == SEEK_DATA)
goto fail;
found:
if (whence == SEEK_HOLE && data_ofs > isize)
data_ofs = isize;
inode_unlock(inode);
return vfs_setpos(file, data_ofs, maxbytes);
fail:
inode_unlock(inode);
return -ENXIO;
}
static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence)
{
struct inode *inode = file->f_mapping->host;
loff_t maxbytes = inode->i_sb->s_maxbytes;
if (f2fs_compressed_file(inode))
maxbytes = max_file_blocks(inode) << F2FS_BLKSIZE_BITS;
switch (whence) {
case SEEK_SET:
case SEEK_CUR:
case SEEK_END:
return generic_file_llseek_size(file, offset, whence,
maxbytes, i_size_read(inode));
case SEEK_DATA:
case SEEK_HOLE:
if (offset < 0)
return -ENXIO;
return f2fs_seek_block(file, offset, whence);
}
return -EINVAL;
}
static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
struct inode *inode = file_inode(file);
if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
return -EIO;
if (!f2fs_is_compress_backend_ready(inode))
return -EOPNOTSUPP;
file_accessed(file);
vma->vm_ops = &f2fs_file_vm_ops;
set_inode_flag(inode, FI_MMAP_FILE);
return 0;
}
static int f2fs_file_open(struct inode *inode, struct file *filp)
{
int err = fscrypt_file_open(inode, filp);
if (err)
return err;
if (!f2fs_is_compress_backend_ready(inode))
return -EOPNOTSUPP;
err = fsverity_file_open(inode, filp);
if (err)
return err;
filp->f_mode |= FMODE_NOWAIT;
return dquot_file_open(inode, filp);
}
void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct f2fs_node *raw_node;
int nr_free = 0, ofs = dn->ofs_in_node, len = count;
__le32 *addr;
int base = 0;
bool compressed_cluster = false;
int cluster_index = 0, valid_blocks = 0;
int cluster_size = F2FS_I(dn->inode)->i_cluster_size;
bool released = !atomic_read(&F2FS_I(dn->inode)->i_compr_blocks);
if (IS_INODE(dn->node_page) && f2fs_has_extra_attr(dn->inode))
base = get_extra_isize(dn->inode);
raw_node = F2FS_NODE(dn->node_page);
addr = blkaddr_in_node(raw_node) + base + ofs;
/* Assumption: truncateion starts with cluster */
for (; count > 0; count--, addr++, dn->ofs_in_node++, cluster_index++) {
block_t blkaddr = le32_to_cpu(*addr);
if (f2fs_compressed_file(dn->inode) &&
!(cluster_index & (cluster_size - 1))) {
if (compressed_cluster)
f2fs_i_compr_blocks_update(dn->inode,
valid_blocks, false);
compressed_cluster = (blkaddr == COMPRESS_ADDR);
valid_blocks = 0;
}
if (blkaddr == NULL_ADDR)
continue;
dn->data_blkaddr = NULL_ADDR;
f2fs_set_data_blkaddr(dn);
if (__is_valid_data_blkaddr(blkaddr)) {
if (!f2fs_is_valid_blkaddr(sbi, blkaddr,
DATA_GENERIC_ENHANCE))
continue;
if (compressed_cluster)
valid_blocks++;
}
if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page))
clear_inode_flag(dn->inode, FI_FIRST_BLOCK_WRITTEN);
f2fs_invalidate_blocks(sbi, blkaddr);
if (!released || blkaddr != COMPRESS_ADDR)
nr_free++;
}
if (compressed_cluster)
f2fs_i_compr_blocks_update(dn->inode, valid_blocks, false);
if (nr_free) {
pgoff_t fofs;
/*
* once we invalidate valid blkaddr in range [ofs, ofs + count],
* we will invalidate all blkaddr in the whole range.
*/
fofs = f2fs_start_bidx_of_node(ofs_of_node(dn->node_page),
dn->inode) + ofs;
f2fs_update_extent_cache_range(dn, fofs, 0, len);
dec_valid_block_count(sbi, dn->inode, nr_free);
}
dn->ofs_in_node = ofs;
f2fs_update_time(sbi, REQ_TIME);
trace_f2fs_truncate_data_blocks_range(dn->inode, dn->nid,
dn->ofs_in_node, nr_free);
}
void f2fs_truncate_data_blocks(struct dnode_of_data *dn)
{
f2fs_truncate_data_blocks_range(dn, ADDRS_PER_BLOCK(dn->inode));
}
static int truncate_partial_data_page(struct inode *inode, u64 from,
bool cache_only)
{
loff_t offset = from & (PAGE_SIZE - 1);
pgoff_t index = from >> PAGE_SHIFT;
struct address_space *mapping = inode->i_mapping;
struct page *page;
if (!offset && !cache_only)
return 0;
if (cache_only) {
page = find_lock_page(mapping, index);
if (page && PageUptodate(page))
goto truncate_out;
f2fs_put_page(page, 1);
return 0;
}
page = f2fs_get_lock_data_page(inode, index, true);
if (IS_ERR(page))
return PTR_ERR(page) == -ENOENT ? 0 : PTR_ERR(page);
truncate_out:
f2fs_wait_on_page_writeback(page, DATA, true, true);
zero_user(page, offset, PAGE_SIZE - offset);
/* An encrypted inode should have a key and truncate the last page. */
f2fs_bug_on(F2FS_I_SB(inode), cache_only && IS_ENCRYPTED(inode));
if (!cache_only)
set_page_dirty(page);
f2fs_put_page(page, 1);
return 0;
}
int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
pgoff_t free_from;
int count = 0, err = 0;
struct page *ipage;
bool truncate_page = false;
trace_f2fs_truncate_blocks_enter(inode, from);
free_from = (pgoff_t)F2FS_BLK_ALIGN(from);
if (free_from >= max_file_blocks(inode))
goto free_partial;
if (lock)
f2fs_lock_op(sbi);
ipage = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto out;
}
if (f2fs_has_inline_data(inode)) {
f2fs_truncate_inline_inode(inode, ipage, from);
f2fs_put_page(ipage, 1);
truncate_page = true;
goto out;
}
set_new_dnode(&dn, inode, ipage, NULL, 0);
err = f2fs_get_dnode_of_data(&dn, free_from, LOOKUP_NODE_RA);
if (err) {
if (err == -ENOENT)
goto free_next;
goto out;
}
count = ADDRS_PER_PAGE(dn.node_page, inode);
count -= dn.ofs_in_node;
f2fs_bug_on(sbi, count < 0);
if (dn.ofs_in_node || IS_INODE(dn.node_page)) {
f2fs_truncate_data_blocks_range(&dn, count);
free_from += count;
}
f2fs_put_dnode(&dn);
free_next:
err = f2fs_truncate_inode_blocks(inode, free_from);
out:
if (lock)
f2fs_unlock_op(sbi);
free_partial:
/* lastly zero out the first data page */
if (!err)
err = truncate_partial_data_page(inode, from, truncate_page);
trace_f2fs_truncate_blocks_exit(inode, err);
return err;
}
int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock)
{
u64 free_from = from;
int err;
#ifdef CONFIG_F2FS_FS_COMPRESSION
/*
* for compressed file, only support cluster size
* aligned truncation.
*/
if (f2fs_compressed_file(inode))
free_from = round_up(from,
F2FS_I(inode)->i_cluster_size << PAGE_SHIFT);
#endif
err = f2fs_do_truncate_blocks(inode, free_from, lock);
if (err)
return err;
#ifdef CONFIG_F2FS_FS_COMPRESSION
if (from != free_from) {
err = f2fs_truncate_partial_cluster(inode, from, lock);
if (err)
return err;
}
#endif
return 0;
}
int f2fs_truncate(struct inode *inode)
{
int err;
if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
return -EIO;
if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
S_ISLNK(inode->i_mode)))
return 0;
trace_f2fs_truncate(inode);
if (time_to_inject(F2FS_I_SB(inode), FAULT_TRUNCATE)) {
f2fs_show_injection_info(F2FS_I_SB(inode), FAULT_TRUNCATE);
return -EIO;
}
err = dquot_initialize(inode);
if (err)
return err;
/* we should check inline_data size */
if (!f2fs_may_inline_data(inode)) {
err = f2fs_convert_inline_inode(inode);
if (err)
return err;
}
err = f2fs_truncate_blocks(inode, i_size_read(inode), true);
if (err)
return err;
inode->i_mtime = inode->i_ctime = current_time(inode);
f2fs_mark_inode_dirty_sync(inode, false);
return 0;
}
int f2fs_getattr(struct user_namespace *mnt_userns, const struct path *path,
struct kstat *stat, u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_inode *ri;
unsigned int flags;
if (f2fs_has_extra_attr(inode) &&
f2fs_sb_has_inode_crtime(F2FS_I_SB(inode)) &&
F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_crtime)) {
stat->result_mask |= STATX_BTIME;
stat->btime.tv_sec = fi->i_crtime.tv_sec;
stat->btime.tv_nsec = fi->i_crtime.tv_nsec;
}
flags = fi->i_flags;
if (flags & F2FS_COMPR_FL)
stat->attributes |= STATX_ATTR_COMPRESSED;
if (flags & F2FS_APPEND_FL)
stat->attributes |= STATX_ATTR_APPEND;
if (IS_ENCRYPTED(inode))
stat->attributes |= STATX_ATTR_ENCRYPTED;
if (flags & F2FS_IMMUTABLE_FL)
stat->attributes |= STATX_ATTR_IMMUTABLE;
if (flags & F2FS_NODUMP_FL)
stat->attributes |= STATX_ATTR_NODUMP;
if (IS_VERITY(inode))
stat->attributes |= STATX_ATTR_VERITY;
stat->attributes_mask |= (STATX_ATTR_COMPRESSED |
STATX_ATTR_APPEND |
STATX_ATTR_ENCRYPTED |
STATX_ATTR_IMMUTABLE |
STATX_ATTR_NODUMP |
STATX_ATTR_VERITY);
generic_fillattr(&init_user_ns, inode, stat);
/* we need to show initial sectors used for inline_data/dentries */
if ((S_ISREG(inode->i_mode) && f2fs_has_inline_data(inode)) ||
f2fs_has_inline_dentry(inode))
stat->blocks += (stat->size + 511) >> 9;
return 0;
}
#ifdef CONFIG_F2FS_FS_POSIX_ACL
static void __setattr_copy(struct user_namespace *mnt_userns,
struct inode *inode, const struct iattr *attr)
{
unsigned int ia_valid = attr->ia_valid;
if (ia_valid & ATTR_UID)
inode->i_uid = attr->ia_uid;
if (ia_valid & ATTR_GID)
inode->i_gid = attr->ia_gid;
if (ia_valid & ATTR_ATIME)
inode->i_atime = attr->ia_atime;
if (ia_valid & ATTR_MTIME)
inode->i_mtime = attr->ia_mtime;
if (ia_valid & ATTR_CTIME)
inode->i_ctime = attr->ia_ctime;
if (ia_valid & ATTR_MODE) {
umode_t mode = attr->ia_mode;
kgid_t kgid = i_gid_into_mnt(mnt_userns, inode);
if (!in_group_p(kgid) && !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID))
mode &= ~S_ISGID;
set_acl_inode(inode, mode);
}
}
#else
#define __setattr_copy setattr_copy
#endif
int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
int err;
if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
return -EIO;
if (unlikely(IS_IMMUTABLE(inode)))
return -EPERM;
if (unlikely(IS_APPEND(inode) &&
(attr->ia_valid & (ATTR_MODE | ATTR_UID |
ATTR_GID | ATTR_TIMES_SET))))
return -EPERM;
if ((attr->ia_valid & ATTR_SIZE) &&
!f2fs_is_compress_backend_ready(inode))
return -EOPNOTSUPP;
err = setattr_prepare(&init_user_ns, dentry, attr);
if (err)
return err;
err = fscrypt_prepare_setattr(dentry, attr);
if (err)
return err;
err = fsverity_prepare_setattr(dentry, attr);
if (err)
return err;
if (is_quota_modification(inode, attr)) {
err = dquot_initialize(inode);
if (err)
return err;
}
if ((attr->ia_valid & ATTR_UID &&
!uid_eq(attr->ia_uid, inode->i_uid)) ||
(attr->ia_valid & ATTR_GID &&
!gid_eq(attr->ia_gid, inode->i_gid))) {
f2fs_lock_op(F2FS_I_SB(inode));
err = dquot_transfer(inode, attr);
if (err) {
set_sbi_flag(F2FS_I_SB(inode),
SBI_QUOTA_NEED_REPAIR);
f2fs_unlock_op(F2FS_I_SB(inode));
return err;
}
/*
* update uid/gid under lock_op(), so that dquot and inode can
* be updated atomically.
*/
if (attr->ia_valid & ATTR_UID)
inode->i_uid = attr->ia_uid;
if (attr->ia_valid & ATTR_GID)
inode->i_gid = attr->ia_gid;
f2fs_mark_inode_dirty_sync(inode, true);
f2fs_unlock_op(F2FS_I_SB(inode));
}
if (attr->ia_valid & ATTR_SIZE) {
loff_t old_size = i_size_read(inode);
if (attr->ia_size > MAX_INLINE_DATA(inode)) {
/*
* should convert inline inode before i_size_write to
* keep smaller than inline_data size with inline flag.
*/
err = f2fs_convert_inline_inode(inode);
if (err)
return err;
}
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
down_write(&F2FS_I(inode)->i_mmap_sem);
truncate_setsize(inode, attr->ia_size);
if (attr->ia_size <= old_size)
err = f2fs_truncate(inode);
/*
* do not trim all blocks after i_size if target size is
* larger than i_size.
*/
up_write(&F2FS_I(inode)->i_mmap_sem);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
if (err)
return err;
spin_lock(&F2FS_I(inode)->i_size_lock);
inode->i_mtime = inode->i_ctime = current_time(inode);
F2FS_I(inode)->last_disk_size = i_size_read(inode);
spin_unlock(&F2FS_I(inode)->i_size_lock);
}
__setattr_copy(&init_user_ns, inode, attr);
if (attr->ia_valid & ATTR_MODE) {
err = posix_acl_chmod(&init_user_ns, inode, f2fs_get_inode_mode(inode));
if (is_inode_flag_set(inode, FI_ACL_MODE)) {
if (!err)
inode->i_mode = F2FS_I(inode)->i_acl_mode;
clear_inode_flag(inode, FI_ACL_MODE);
}
}
/* file size may changed here */
f2fs_mark_inode_dirty_sync(inode, true);
/* inode change will produce dirty node pages flushed by checkpoint */
f2fs_balance_fs(F2FS_I_SB(inode), true);
return err;
}
const struct inode_operations f2fs_file_inode_operations = {
.getattr = f2fs_getattr,
.setattr = f2fs_setattr,
.get_acl = f2fs_get_acl,
.set_acl = f2fs_set_acl,
.listxattr = f2fs_listxattr,
.fiemap = f2fs_fiemap,
};
static int fill_zero(struct inode *inode, pgoff_t index,
loff_t start, loff_t len)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *page;
if (!len)
return 0;
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
page = f2fs_get_new_data_page(inode, NULL, index, false);
f2fs_unlock_op(sbi);
if (IS_ERR(page))
return PTR_ERR(page);
f2fs_wait_on_page_writeback(page, DATA, true, true);
zero_user(page, start, len);
set_page_dirty(page);
f2fs_put_page(page, 1);
return 0;
}
int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
{
int err;
while (pg_start < pg_end) {
struct dnode_of_data dn;
pgoff_t end_offset, count;
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = f2fs_get_dnode_of_data(&dn, pg_start, LOOKUP_NODE);
if (err) {
if (err == -ENOENT) {
pg_start = f2fs_get_next_page_offset(&dn,
pg_start);
continue;
}
return err;
}
end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
count = min(end_offset - dn.ofs_in_node, pg_end - pg_start);
f2fs_bug_on(F2FS_I_SB(inode), count == 0 || count > end_offset);
f2fs_truncate_data_blocks_range(&dn, count);
f2fs_put_dnode(&dn);
pg_start += count;
}
return 0;
}
static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
{
pgoff_t pg_start, pg_end;
loff_t off_start, off_end;
int ret;
ret = f2fs_convert_inline_inode(inode);
if (ret)
return ret;
pg_start = ((unsigned long long) offset) >> PAGE_SHIFT;
pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT;
off_start = offset & (PAGE_SIZE - 1);
off_end = (offset + len) & (PAGE_SIZE - 1);
if (pg_start == pg_end) {
ret = fill_zero(inode, pg_start, off_start,
off_end - off_start);
if (ret)
return ret;
} else {
if (off_start) {
ret = fill_zero(inode, pg_start++, off_start,
PAGE_SIZE - off_start);
if (ret)
return ret;
}
if (off_end) {
ret = fill_zero(inode, pg_end, 0, off_end);
if (ret)
return ret;
}
if (pg_start < pg_end) {
struct address_space *mapping = inode->i_mapping;
loff_t blk_start, blk_end;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
f2fs_balance_fs(sbi, true);
blk_start = (loff_t)pg_start << PAGE_SHIFT;
blk_end = (loff_t)pg_end << PAGE_SHIFT;
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
down_write(&F2FS_I(inode)->i_mmap_sem);
truncate_inode_pages_range(mapping, blk_start,
blk_end - 1);
f2fs_lock_op(sbi);
ret = f2fs_truncate_hole(inode, pg_start, pg_end);
f2fs_unlock_op(sbi);
up_write(&F2FS_I(inode)->i_mmap_sem);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
}
}
return ret;
}
static int __read_out_blkaddrs(struct inode *inode, block_t *blkaddr,
int *do_replace, pgoff_t off, pgoff_t len)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
int ret, done, i;
next_dnode:
set_new_dnode(&dn, inode, NULL, NULL, 0);
ret = f2fs_get_dnode_of_data(&dn, off, LOOKUP_NODE_RA);
if (ret && ret != -ENOENT) {
return ret;
} else if (ret == -ENOENT) {
if (dn.max_level == 0)
return -ENOENT;
done = min((pgoff_t)ADDRS_PER_BLOCK(inode) -
dn.ofs_in_node, len);
blkaddr += done;
do_replace += done;
goto next;
}
done = min((pgoff_t)ADDRS_PER_PAGE(dn.node_page, inode) -
dn.ofs_in_node, len);
for (i = 0; i < done; i++, blkaddr++, do_replace++, dn.ofs_in_node++) {
*blkaddr = f2fs_data_blkaddr(&dn);
if (__is_valid_data_blkaddr(*blkaddr) &&
!f2fs_is_valid_blkaddr(sbi, *blkaddr,
DATA_GENERIC_ENHANCE)) {
f2fs_put_dnode(&dn);
return -EFSCORRUPTED;
}
if (!f2fs_is_checkpointed_data(sbi, *blkaddr)) {
if (f2fs_lfs_mode(sbi)) {
f2fs_put_dnode(&dn);
return -EOPNOTSUPP;
}
/* do not invalidate this block address */
f2fs_update_data_blkaddr(&dn, NULL_ADDR);
*do_replace = 1;
}
}
f2fs_put_dnode(&dn);
next:
len -= done;
off += done;
if (len)
goto next_dnode;
return 0;
}
static int __roll_back_blkaddrs(struct inode *inode, block_t *blkaddr,
int *do_replace, pgoff_t off, int len)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
int ret, i;
for (i = 0; i < len; i++, do_replace++, blkaddr++) {
if (*do_replace == 0)
continue;
set_new_dnode(&dn, inode, NULL, NULL, 0);
ret = f2fs_get_dnode_of_data(&dn, off + i, LOOKUP_NODE_RA);
if (ret) {
dec_valid_block_count(sbi, inode, 1);
f2fs_invalidate_blocks(sbi, *blkaddr);
} else {
f2fs_update_data_blkaddr(&dn, *blkaddr);
}
f2fs_put_dnode(&dn);
}
return 0;
}
static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
block_t *blkaddr, int *do_replace,
pgoff_t src, pgoff_t dst, pgoff_t len, bool full)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(src_inode);
pgoff_t i = 0;
int ret;
while (i < len) {
if (blkaddr[i] == NULL_ADDR && !full) {
i++;
continue;
}
if (do_replace[i] || blkaddr[i] == NULL_ADDR) {
struct dnode_of_data dn;
struct node_info ni;
size_t new_size;
pgoff_t ilen;
set_new_dnode(&dn, dst_inode, NULL, NULL, 0);
ret = f2fs_get_dnode_of_data(&dn, dst + i, ALLOC_NODE);
if (ret)
return ret;
ret = f2fs_get_node_info(sbi, dn.nid, &ni);
if (ret) {
f2fs_put_dnode(&dn);
return ret;
}
ilen = min((pgoff_t)
ADDRS_PER_PAGE(dn.node_page, dst_inode) -
dn.ofs_in_node, len - i);
do {
dn.data_blkaddr = f2fs_data_blkaddr(&dn);
f2fs_truncate_data_blocks_range(&dn, 1);
if (do_replace[i]) {
f2fs_i_blocks_write(src_inode,
1, false, false);
f2fs_i_blocks_write(dst_inode,
1, true, false);
f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
blkaddr[i], ni.version, true, false);
do_replace[i] = 0;
}
dn.ofs_in_node++;
i++;
new_size = (loff_t)(dst + i) << PAGE_SHIFT;
if (dst_inode->i_size < new_size)
f2fs_i_size_write(dst_inode, new_size);
} while (--ilen && (do_replace[i] || blkaddr[i] == NULL_ADDR));
f2fs_put_dnode(&dn);
} else {
struct page *psrc, *pdst;
psrc = f2fs_get_lock_data_page(src_inode,
src + i, true);
if (IS_ERR(psrc))
return PTR_ERR(psrc);
pdst = f2fs_get_new_data_page(dst_inode, NULL, dst + i,
true);
if (IS_ERR(pdst)) {
f2fs_put_page(psrc, 1);
return PTR_ERR(pdst);
}
f2fs_copy_page(psrc, pdst);
set_page_dirty(pdst);
f2fs_put_page(pdst, 1);
f2fs_put_page(psrc, 1);
ret = f2fs_truncate_hole(src_inode,
src + i, src + i + 1);
if (ret)
return ret;
i++;
}
}
return 0;
}
static int __exchange_data_block(struct inode *src_inode,
struct inode *dst_inode, pgoff_t src, pgoff_t dst,
pgoff_t len, bool full)
{
block_t *src_blkaddr;
int *do_replace;
pgoff_t olen;
int ret;
while (len) {
olen = min((pgoff_t)4 * ADDRS_PER_BLOCK(src_inode), len);
src_blkaddr = f2fs_kvzalloc(F2FS_I_SB(src_inode),
array_size(olen, sizeof(block_t)),
GFP_NOFS);
if (!src_blkaddr)
return -ENOMEM;
do_replace = f2fs_kvzalloc(F2FS_I_SB(src_inode),
array_size(olen, sizeof(int)),
GFP_NOFS);
if (!do_replace) {
kvfree(src_blkaddr);
return -ENOMEM;
}
ret = __read_out_blkaddrs(src_inode, src_blkaddr,
do_replace, src, olen);
if (ret)
goto roll_back;
ret = __clone_blkaddrs(src_inode, dst_inode, src_blkaddr,
do_replace, src, dst, olen, full);
if (ret)
goto roll_back;
src += olen;
dst += olen;
len -= olen;
kvfree(src_blkaddr);
kvfree(do_replace);
}
return 0;
roll_back:
__roll_back_blkaddrs(src_inode, src_blkaddr, do_replace, src, olen);
kvfree(src_blkaddr);
kvfree(do_replace);
return ret;
}
static int f2fs_do_collapse(struct inode *inode, loff_t offset, loff_t len)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
pgoff_t nrpages = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
pgoff_t start = offset >> PAGE_SHIFT;
pgoff_t end = (offset + len) >> PAGE_SHIFT;
int ret;
f2fs_balance_fs(sbi, true);
/* avoid gc operation during block exchange */
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
down_write(&F2FS_I(inode)->i_mmap_sem);
f2fs_lock_op(sbi);
f2fs_drop_extent_tree(inode);
truncate_pagecache(inode, offset);
ret = __exchange_data_block(inode, inode, end, start, nrpages - end, true);
f2fs_unlock_op(sbi);
up_write(&F2FS_I(inode)->i_mmap_sem);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
return ret;
}
static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
{
loff_t new_size;
int ret;
if (offset + len >= i_size_read(inode))
return -EINVAL;
/* collapse range should be aligned to block size of f2fs. */
if (offset & (F2FS_BLKSIZE - 1) || len & (F2FS_BLKSIZE - 1))
return -EINVAL;
ret = f2fs_convert_inline_inode(inode);
if (ret)
return ret;
/* write out all dirty pages from offset */
ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
if (ret)
return ret;
ret = f2fs_do_collapse(inode, offset, len);
if (ret)
return ret;
/* write out all moved pages, if possible */
down_write(&F2FS_I(inode)->i_mmap_sem);
filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
truncate_pagecache(inode, offset);
new_size = i_size_read(inode) - len;
ret = f2fs_truncate_blocks(inode, new_size, true);
up_write(&F2FS_I(inode)->i_mmap_sem);
if (!ret)
f2fs_i_size_write(inode, new_size);
return ret;
}
static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start,
pgoff_t end)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
pgoff_t index = start;
unsigned int ofs_in_node = dn->ofs_in_node;
blkcnt_t count = 0;
int ret;
for (; index < end; index++, dn->ofs_in_node++) {
if (f2fs_data_blkaddr(dn) == NULL_ADDR)
count++;
}
dn->ofs_in_node = ofs_in_node;
ret = f2fs_reserve_new_blocks(dn, count);
if (ret)
return ret;
dn->ofs_in_node = ofs_in_node;
for (index = start; index < end; index++, dn->ofs_in_node++) {
dn->data_blkaddr = f2fs_data_blkaddr(dn);
/*
* f2fs_reserve_new_blocks will not guarantee entire block
* allocation.
*/
if (dn->data_blkaddr == NULL_ADDR) {
ret = -ENOSPC;
break;
}
if (dn->data_blkaddr != NEW_ADDR) {
f2fs_invalidate_blocks(sbi, dn->data_blkaddr);
dn->data_blkaddr = NEW_ADDR;
f2fs_set_data_blkaddr(dn);
}
}
f2fs_update_extent_cache_range(dn, start, 0, index - start);
return ret;
}
static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
int mode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct address_space *mapping = inode->i_mapping;
pgoff_t index, pg_start, pg_end;
loff_t new_size = i_size_read(inode);
loff_t off_start, off_end;
int ret = 0;
ret = inode_newsize_ok(inode, (len + offset));
if (ret)
return ret;
ret = f2fs_convert_inline_inode(inode);
if (ret)
return ret;
ret = filemap_write_and_wait_range(mapping, offset, offset + len - 1);
if (ret)
return ret;
pg_start = ((unsigned long long) offset) >> PAGE_SHIFT;
pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT;
off_start = offset & (PAGE_SIZE - 1);
off_end = (offset + len) & (PAGE_SIZE - 1);
if (pg_start == pg_end) {
ret = fill_zero(inode, pg_start, off_start,
off_end - off_start);
if (ret)
return ret;
new_size = max_t(loff_t, new_size, offset + len);
} else {
if (off_start) {
ret = fill_zero(inode, pg_start++, off_start,
PAGE_SIZE - off_start);
if (ret)
return ret;
new_size = max_t(loff_t, new_size,
(loff_t)pg_start << PAGE_SHIFT);
}
for (index = pg_start; index < pg_end;) {
struct dnode_of_data dn;
unsigned int end_offset;
pgoff_t end;
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
down_write(&F2FS_I(inode)->i_mmap_sem);
truncate_pagecache_range(inode,
(loff_t)index << PAGE_SHIFT,
((loff_t)pg_end << PAGE_SHIFT) - 1);
f2fs_lock_op(sbi);
set_new_dnode(&dn, inode, NULL, NULL, 0);
ret = f2fs_get_dnode_of_data(&dn, index, ALLOC_NODE);
if (ret) {
f2fs_unlock_op(sbi);
up_write(&F2FS_I(inode)->i_mmap_sem);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
goto out;
}
end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
end = min(pg_end, end_offset - dn.ofs_in_node + index);
ret = f2fs_do_zero_range(&dn, index, end);
f2fs_put_dnode(&dn);
f2fs_unlock_op(sbi);
up_write(&F2FS_I(inode)->i_mmap_sem);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
f2fs_balance_fs(sbi, dn.node_changed);
if (ret)
goto out;
index = end;
new_size = max_t(loff_t, new_size,
(loff_t)index << PAGE_SHIFT);
}
if (off_end) {
ret = fill_zero(inode, pg_end, 0, off_end);
if (ret)
goto out;
new_size = max_t(loff_t, new_size, offset + len);
}
}
out:
if (new_size > i_size_read(inode)) {
if (mode & FALLOC_FL_KEEP_SIZE)
file_set_keep_isize(inode);
else
f2fs_i_size_write(inode, new_size);
}
return ret;
}
static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
pgoff_t nr, pg_start, pg_end, delta, idx;
loff_t new_size;
int ret = 0;
new_size = i_size_read(inode) + len;
ret = inode_newsize_ok(inode, new_size);
if (ret)
return ret;
if (offset >= i_size_read(inode))
return -EINVAL;
/* insert range should be aligned to block size of f2fs. */
if (offset & (F2FS_BLKSIZE - 1) || len & (F2FS_BLKSIZE - 1))
return -EINVAL;
ret = f2fs_convert_inline_inode(inode);
if (ret)
return ret;
f2fs_balance_fs(sbi, true);
down_write(&F2FS_I(inode)->i_mmap_sem);
ret = f2fs_truncate_blocks(inode, i_size_read(inode), true);
up_write(&F2FS_I(inode)->i_mmap_sem);
if (ret)
return ret;
/* write out all dirty pages from offset */
ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
if (ret)
return ret;
pg_start = offset >> PAGE_SHIFT;
pg_end = (offset + len) >> PAGE_SHIFT;
delta = pg_end - pg_start;
idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
/* avoid gc operation during block exchange */
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
down_write(&F2FS_I(inode)->i_mmap_sem);
truncate_pagecache(inode, offset);
while (!ret && idx > pg_start) {
nr = idx - pg_start;
if (nr > delta)
nr = delta;
idx -= nr;
f2fs_lock_op(sbi);
f2fs_drop_extent_tree(inode);
ret = __exchange_data_block(inode, inode, idx,
idx + delta, nr, false);
f2fs_unlock_op(sbi);
}
up_write(&F2FS_I(inode)->i_mmap_sem);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
/* write out all moved pages, if possible */
down_write(&F2FS_I(inode)->i_mmap_sem);
filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
truncate_pagecache(inode, offset);
up_write(&F2FS_I(inode)->i_mmap_sem);
if (!ret)
f2fs_i_size_write(inode, new_size);
return ret;
}
static int expand_inode_data(struct inode *inode, loff_t offset,
loff_t len, int mode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_map_blocks map = { .m_next_pgofs = NULL,
.m_next_extent = NULL, .m_seg_type = NO_CHECK_TYPE,
.m_may_create = true };
pgoff_t pg_end;
loff_t new_size = i_size_read(inode);
loff_t off_end;
int err;
err = inode_newsize_ok(inode, (len + offset));
if (err)
return err;
err = f2fs_convert_inline_inode(inode);
if (err)
return err;
f2fs_balance_fs(sbi, true);
pg_end = ((unsigned long long)offset + len) >> PAGE_SHIFT;
off_end = (offset + len) & (PAGE_SIZE - 1);
map.m_lblk = ((unsigned long long)offset) >> PAGE_SHIFT;
map.m_len = pg_end - map.m_lblk;
if (off_end)
map.m_len++;
if (!map.m_len)
return 0;
if (f2fs_is_pinned_file(inode)) {
block_t len = (map.m_len >> sbi->log_blocks_per_seg) <<
sbi->log_blocks_per_seg;
block_t done = 0;
if (map.m_len % sbi->blocks_per_seg)
len += sbi->blocks_per_seg;
map.m_len = sbi->blocks_per_seg;
next_alloc:
if (has_not_enough_free_secs(sbi, 0,
GET_SEC_FROM_SEG(sbi, overprovision_segments(sbi)))) {
down_write(&sbi->gc_lock);
err = f2fs_gc(sbi, true, false, NULL_SEGNO);
if (err && err != -ENODATA && err != -EAGAIN)
goto out_err;
}
down_write(&sbi->pin_sem);
f2fs_lock_op(sbi);
f2fs_allocate_new_segment(sbi, CURSEG_COLD_DATA_PINNED);
f2fs_unlock_op(sbi);
map.m_seg_type = CURSEG_COLD_DATA_PINNED;
err = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_DIO);
up_write(&sbi->pin_sem);
done += map.m_len;
len -= map.m_len;
map.m_lblk += map.m_len;
if (!err && len)
goto next_alloc;
map.m_len = done;
} else {
err = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO);
}
out_err:
if (err) {
pgoff_t last_off;
if (!map.m_len)
return err;
last_off = map.m_lblk + map.m_len - 1;
/* update new size to the failed position */
new_size = (last_off == pg_end) ? offset + len :
(loff_t)(last_off + 1) << PAGE_SHIFT;
} else {
new_size = ((loff_t)pg_end << PAGE_SHIFT) + off_end;
}
if (new_size > i_size_read(inode)) {
if (mode & FALLOC_FL_KEEP_SIZE)
file_set_keep_isize(inode);
else
f2fs_i_size_write(inode, new_size);
}
return err;
}
static long f2fs_fallocate(struct file *file, int mode,
loff_t offset, loff_t len)
{
struct inode *inode = file_inode(file);
long ret = 0;
if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
return -EIO;
if (!f2fs_is_checkpoint_ready(F2FS_I_SB(inode)))
return -ENOSPC;
if (!f2fs_is_compress_backend_ready(inode))
return -EOPNOTSUPP;
/* f2fs only support ->fallocate for regular file */
if (!S_ISREG(inode->i_mode))
return -EINVAL;
if (IS_ENCRYPTED(inode) &&
(mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE)))
return -EOPNOTSUPP;
if (f2fs_compressed_file(inode) &&
(mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE |
FALLOC_FL_ZERO_RANGE | FALLOC_FL_INSERT_RANGE)))
return -EOPNOTSUPP;
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |
FALLOC_FL_INSERT_RANGE))
return -EOPNOTSUPP;
inode_lock(inode);
if (mode & FALLOC_FL_PUNCH_HOLE) {
if (offset >= inode->i_size)
goto out;
ret = punch_hole(inode, offset, len);
} else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
ret = f2fs_collapse_range(inode, offset, len);
} else if (mode & FALLOC_FL_ZERO_RANGE) {
ret = f2fs_zero_range(inode, offset, len, mode);
} else if (mode & FALLOC_FL_INSERT_RANGE) {
ret = f2fs_insert_range(inode, offset, len);
} else {
ret = expand_inode_data(inode, offset, len, mode);
}
if (!ret) {
inode->i_mtime = inode->i_ctime = current_time(inode);
f2fs_mark_inode_dirty_sync(inode, false);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
}
out:
inode_unlock(inode);
trace_f2fs_fallocate(inode, mode, offset, len, ret);
return ret;
}
static int f2fs_release_file(struct inode *inode, struct file *filp)
{
/*
* f2fs_relase_file is called at every close calls. So we should
* not drop any inmemory pages by close called by other process.
*/
if (!(filp->f_mode & FMODE_WRITE) ||
atomic_read(&inode->i_writecount) != 1)
return 0;
/* some remained atomic pages should discarded */
if (f2fs_is_atomic_file(inode))
f2fs_drop_inmem_pages(inode);
if (f2fs_is_volatile_file(inode)) {
set_inode_flag(inode, FI_DROP_CACHE);
filemap_fdatawrite(inode->i_mapping);
clear_inode_flag(inode, FI_DROP_CACHE);
clear_inode_flag(inode, FI_VOLATILE_FILE);
stat_dec_volatile_write(inode);
}
return 0;
}
static int f2fs_file_flush(struct file *file, fl_owner_t id)
{
struct inode *inode = file_inode(file);
/*
* If the process doing a transaction is crashed, we should do
* roll-back. Otherwise, other reader/write can see corrupted database
* until all the writers close its file. Since this should be done
* before dropping file lock, it needs to do in ->flush.
*/
if (f2fs_is_atomic_file(inode) &&
F2FS_I(inode)->inmem_task == current)
f2fs_drop_inmem_pages(inode);
return 0;
}
static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask)
{
struct f2fs_inode_info *fi = F2FS_I(inode);
u32 masked_flags = fi->i_flags & mask;
f2fs_bug_on(F2FS_I_SB(inode), (iflags & ~mask));
/* Is it quota file? Do not allow user to mess with it */
if (IS_NOQUOTA(inode))
return -EPERM;
if ((iflags ^ masked_flags) & F2FS_CASEFOLD_FL) {
if (!f2fs_sb_has_casefold(F2FS_I_SB(inode)))
return -EOPNOTSUPP;
if (!f2fs_empty_dir(inode))
return -ENOTEMPTY;
}
if (iflags & (F2FS_COMPR_FL | F2FS_NOCOMP_FL)) {
if (!f2fs_sb_has_compression(F2FS_I_SB(inode)))
return -EOPNOTSUPP;
if ((iflags & F2FS_COMPR_FL) && (iflags & F2FS_NOCOMP_FL))
return -EINVAL;
}
if ((iflags ^ masked_flags) & F2FS_COMPR_FL) {
if (masked_flags & F2FS_COMPR_FL) {
if (!f2fs_disable_compressed_file(inode))
return -EINVAL;
}
if (iflags & F2FS_NOCOMP_FL)
return -EINVAL;
if (iflags & F2FS_COMPR_FL) {
if (!f2fs_may_compress(inode))
return -EINVAL;
if (S_ISREG(inode->i_mode) && inode->i_size)
return -EINVAL;
set_compress_context(inode);
}
}
if ((iflags ^ masked_flags) & F2FS_NOCOMP_FL) {
if (masked_flags & F2FS_COMPR_FL)
return -EINVAL;
}
fi->i_flags = iflags | (fi->i_flags & ~mask);
f2fs_bug_on(F2FS_I_SB(inode), (fi->i_flags & F2FS_COMPR_FL) &&
(fi->i_flags & F2FS_NOCOMP_FL));
if (fi->i_flags & F2FS_PROJINHERIT_FL)
set_inode_flag(inode, FI_PROJ_INHERIT);
else
clear_inode_flag(inode, FI_PROJ_INHERIT);
inode->i_ctime = current_time(inode);
f2fs_set_inode_flags(inode);
f2fs_mark_inode_dirty_sync(inode, true);
return 0;
}
/* FS_IOC_GETFLAGS and FS_IOC_SETFLAGS support */
/*
* To make a new on-disk f2fs i_flag gettable via FS_IOC_GETFLAGS, add an entry
* for it to f2fs_fsflags_map[], and add its FS_*_FL equivalent to
* F2FS_GETTABLE_FS_FL. To also make it settable via FS_IOC_SETFLAGS, also add
* its FS_*_FL equivalent to F2FS_SETTABLE_FS_FL.
*/
static const struct {
u32 iflag;
u32 fsflag;
} f2fs_fsflags_map[] = {
{ F2FS_COMPR_FL, FS_COMPR_FL },
{ F2FS_SYNC_FL, FS_SYNC_FL },
{ F2FS_IMMUTABLE_FL, FS_IMMUTABLE_FL },
{ F2FS_APPEND_FL, FS_APPEND_FL },
{ F2FS_NODUMP_FL, FS_NODUMP_FL },
{ F2FS_NOATIME_FL, FS_NOATIME_FL },
{ F2FS_NOCOMP_FL, FS_NOCOMP_FL },
{ F2FS_INDEX_FL, FS_INDEX_FL },
{ F2FS_DIRSYNC_FL, FS_DIRSYNC_FL },
{ F2FS_PROJINHERIT_FL, FS_PROJINHERIT_FL },
{ F2FS_CASEFOLD_FL, FS_CASEFOLD_FL },
};
#define F2FS_GETTABLE_FS_FL ( \
FS_COMPR_FL | \
FS_SYNC_FL | \
FS_IMMUTABLE_FL | \
FS_APPEND_FL | \
FS_NODUMP_FL | \
FS_NOATIME_FL | \
FS_NOCOMP_FL | \
FS_INDEX_FL | \
FS_DIRSYNC_FL | \
FS_PROJINHERIT_FL | \
FS_ENCRYPT_FL | \
FS_INLINE_DATA_FL | \
FS_NOCOW_FL | \
FS_VERITY_FL | \
FS_CASEFOLD_FL)
#define F2FS_SETTABLE_FS_FL ( \
FS_COMPR_FL | \
FS_SYNC_FL | \
FS_IMMUTABLE_FL | \
FS_APPEND_FL | \
FS_NODUMP_FL | \
FS_NOATIME_FL | \
FS_NOCOMP_FL | \
FS_DIRSYNC_FL | \
FS_PROJINHERIT_FL | \
FS_CASEFOLD_FL)
/* Convert f2fs on-disk i_flags to FS_IOC_{GET,SET}FLAGS flags */
static inline u32 f2fs_iflags_to_fsflags(u32 iflags)
{
u32 fsflags = 0;
int i;
for (i = 0; i < ARRAY_SIZE(f2fs_fsflags_map); i++)
if (iflags & f2fs_fsflags_map[i].iflag)
fsflags |= f2fs_fsflags_map[i].fsflag;
return fsflags;
}
/* Convert FS_IOC_{GET,SET}FLAGS flags to f2fs on-disk i_flags */
static inline u32 f2fs_fsflags_to_iflags(u32 fsflags)
{
u32 iflags = 0;
int i;
for (i = 0; i < ARRAY_SIZE(f2fs_fsflags_map); i++)
if (fsflags & f2fs_fsflags_map[i].fsflag)
iflags |= f2fs_fsflags_map[i].iflag;
return iflags;
}
static int f2fs_ioc_getflags(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_inode_info *fi = F2FS_I(inode);
u32 fsflags = f2fs_iflags_to_fsflags(fi->i_flags);
if (IS_ENCRYPTED(inode))
fsflags |= FS_ENCRYPT_FL;
if (IS_VERITY(inode))
fsflags |= FS_VERITY_FL;
if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode))
fsflags |= FS_INLINE_DATA_FL;
if (is_inode_flag_set(inode, FI_PIN_FILE))
fsflags |= FS_NOCOW_FL;
fsflags &= F2FS_GETTABLE_FS_FL;
return put_user(fsflags, (int __user *)arg);
}
static int f2fs_ioc_setflags(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_inode_info *fi = F2FS_I(inode);
u32 fsflags, old_fsflags;
u32 iflags;
int ret;
if (!inode_owner_or_capable(&init_user_ns, inode))
return -EACCES;
if (get_user(fsflags, (int __user *)arg))
return -EFAULT;
if (fsflags & ~F2FS_GETTABLE_FS_FL)
return -EOPNOTSUPP;
fsflags &= F2FS_SETTABLE_FS_FL;
iflags = f2fs_fsflags_to_iflags(fsflags);
if (f2fs_mask_flags(inode->i_mode, iflags) != iflags)
return -EOPNOTSUPP;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
inode_lock(inode);
old_fsflags = f2fs_iflags_to_fsflags(fi->i_flags);
ret = vfs_ioc_setflags_prepare(inode, old_fsflags, fsflags);
if (ret)
goto out;
ret = f2fs_setflags_common(inode, iflags,
f2fs_fsflags_to_iflags(F2FS_SETTABLE_FS_FL));
out:
inode_unlock(inode);
mnt_drop_write_file(filp);
return ret;
}
static int f2fs_ioc_getversion(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
return put_user(inode->i_generation, (int __user *)arg);
}
static int f2fs_ioc_start_atomic_write(struct file *filp)
{
struct inode *inode = file_inode(filp);
struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
int ret;
if (!inode_owner_or_capable(&init_user_ns, inode))
return -EACCES;
if (!S_ISREG(inode->i_mode))
return -EINVAL;
if (filp->f_flags & O_DIRECT)
return -EINVAL;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
inode_lock(inode);
f2fs_disable_compressed_file(inode);
if (f2fs_is_atomic_file(inode)) {
if (is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST))
ret = -EINVAL;
goto out;
}
ret = f2fs_convert_inline_inode(inode);
if (ret)
goto out;
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
/*
* Should wait end_io to count F2FS_WB_CP_DATA correctly by
* f2fs_is_atomic_file.
*/
if (get_dirty_pages(inode))
f2fs_warn(F2FS_I_SB(inode), "Unexpected flush for atomic writes: ino=%lu, npages=%u",
inode->i_ino, get_dirty_pages(inode));
ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX);
if (ret) {
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
goto out;
}
spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
if (list_empty(&fi->inmem_ilist))
list_add_tail(&fi->inmem_ilist, &sbi->inode_list[ATOMIC_FILE]);
sbi->atomic_files++;
spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
/* add inode in inmem_list first and set atomic_file */
set_inode_flag(inode, FI_ATOMIC_FILE);
clear_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
F2FS_I(inode)->inmem_task = current;
stat_update_max_atomic_write(inode);
out:
inode_unlock(inode);
mnt_drop_write_file(filp);
return ret;
}
static int f2fs_ioc_commit_atomic_write(struct file *filp)
{
struct inode *inode = file_inode(filp);
int ret;
if (!inode_owner_or_capable(&init_user_ns, inode))
return -EACCES;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
f2fs_balance_fs(F2FS_I_SB(inode), true);
inode_lock(inode);
if (f2fs_is_volatile_file(inode)) {
ret = -EINVAL;
goto err_out;
}
if (f2fs_is_atomic_file(inode)) {
ret = f2fs_commit_inmem_pages(inode);
if (ret)
goto err_out;
ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
if (!ret)
f2fs_drop_inmem_pages(inode);
} else {
ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 1, false);
}
err_out:
if (is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST)) {
clear_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST);
ret = -EINVAL;
}
inode_unlock(inode);
mnt_drop_write_file(filp);
return ret;
}
static int f2fs_ioc_start_volatile_write(struct file *filp)
{
struct inode *inode = file_inode(filp);
int ret;
if (!inode_owner_or_capable(&init_user_ns, inode))
return -EACCES;
if (!S_ISREG(inode->i_mode))
return -EINVAL;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
inode_lock(inode);
if (f2fs_is_volatile_file(inode))
goto out;
ret = f2fs_convert_inline_inode(inode);
if (ret)
goto out;
stat_inc_volatile_write(inode);
stat_update_max_volatile_write(inode);
set_inode_flag(inode, FI_VOLATILE_FILE);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
out:
inode_unlock(inode);
mnt_drop_write_file(filp);
return ret;
}
static int f2fs_ioc_release_volatile_write(struct file *filp)
{
struct inode *inode = file_inode(filp);
int ret;
if (!inode_owner_or_capable(&init_user_ns, inode))
return -EACCES;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
inode_lock(inode);
if (!f2fs_is_volatile_file(inode))
goto out;
if (!f2fs_is_first_block_written(inode)) {
ret = truncate_partial_data_page(inode, 0, true);
goto out;
}
ret = punch_hole(inode, 0, F2FS_BLKSIZE);
out:
inode_unlock(inode);
mnt_drop_write_file(filp);
return ret;
}
static int f2fs_ioc_abort_volatile_write(struct file *filp)
{
struct inode *inode = file_inode(filp);
int ret;
if (!inode_owner_or_capable(&init_user_ns, inode))
return -EACCES;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
inode_lock(inode);
if (f2fs_is_atomic_file(inode))
f2fs_drop_inmem_pages(inode);
if (f2fs_is_volatile_file(inode)) {
clear_inode_flag(inode, FI_VOLATILE_FILE);
stat_dec_volatile_write(inode);
ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
}
clear_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST);
inode_unlock(inode);
mnt_drop_write_file(filp);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return ret;
}
static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct super_block *sb = sbi->sb;
__u32 in;
int ret = 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (get_user(in, (__u32 __user *)arg))
return -EFAULT;
if (in != F2FS_GOING_DOWN_FULLSYNC) {
ret = mnt_want_write_file(filp);
if (ret) {
if (ret == -EROFS) {
ret = 0;
f2fs_stop_checkpoint(sbi, false);
set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
trace_f2fs_shutdown(sbi, in, ret);
}
return ret;
}
}
switch (in) {
case F2FS_GOING_DOWN_FULLSYNC:
ret = freeze_bdev(sb->s_bdev);
if (ret)
goto out;
f2fs_stop_checkpoint(sbi, false);
set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
thaw_bdev(sb->s_bdev);
break;
case F2FS_GOING_DOWN_METASYNC:
/* do checkpoint only */
ret = f2fs_sync_fs(sb, 1);
if (ret)
goto out;
f2fs_stop_checkpoint(sbi, false);
set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
break;
case F2FS_GOING_DOWN_NOSYNC:
f2fs_stop_checkpoint(sbi, false);
set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
break;
case F2FS_GOING_DOWN_METAFLUSH:
f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_META_IO);
f2fs_stop_checkpoint(sbi, false);
set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
break;
case F2FS_GOING_DOWN_NEED_FSCK:
set_sbi_flag(sbi, SBI_NEED_FSCK);
set_sbi_flag(sbi, SBI_CP_DISABLED_QUICK);
set_sbi_flag(sbi, SBI_IS_DIRTY);
/* do checkpoint only */
ret = f2fs_sync_fs(sb, 1);
goto out;
default:
ret = -EINVAL;
goto out;
}
f2fs_stop_gc_thread(sbi);
f2fs_stop_discard_thread(sbi);
f2fs_drop_discard_cmd(sbi);
clear_opt(sbi, DISCARD);
f2fs_update_time(sbi, REQ_TIME);
out:
if (in != F2FS_GOING_DOWN_FULLSYNC)
mnt_drop_write_file(filp);
trace_f2fs_shutdown(sbi, in, ret);
return ret;
}
static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
struct request_queue *q = bdev_get_queue(sb->s_bdev);
struct fstrim_range range;
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!f2fs_hw_support_discard(F2FS_SB(sb)))
return -EOPNOTSUPP;
if (copy_from_user(&range, (struct fstrim_range __user *)arg,
sizeof(range)))
return -EFAULT;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
range.minlen = max((unsigned int)range.minlen,
q->limits.discard_granularity);
ret = f2fs_trim_fs(F2FS_SB(sb), &range);
mnt_drop_write_file(filp);
if (ret < 0)
return ret;
if (copy_to_user((struct fstrim_range __user *)arg, &range,
sizeof(range)))
return -EFAULT;
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return 0;
}
static bool uuid_is_nonzero(__u8 u[16])
{
int i;
for (i = 0; i < 16; i++)
if (u[i])
return true;
return false;
}
static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
if (!f2fs_sb_has_encrypt(F2FS_I_SB(inode)))
return -EOPNOTSUPP;
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return fscrypt_ioctl_set_policy(filp, (const void __user *)arg);
}
static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg)
{
if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp))))
return -EOPNOTSUPP;
return fscrypt_ioctl_get_policy(filp, (void __user *)arg);
}
static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
int err;
if (!f2fs_sb_has_encrypt(sbi))
return -EOPNOTSUPP;
err = mnt_want_write_file(filp);
if (err)
return err;
down_write(&sbi->sb_lock);
if (uuid_is_nonzero(sbi->raw_super->encrypt_pw_salt))
goto got_it;
/* update superblock with uuid */
generate_random_uuid(sbi->raw_super->encrypt_pw_salt);
err = f2fs_commit_super(sbi, false);
if (err) {
/* undo new data */
memset(sbi->raw_super->encrypt_pw_salt, 0, 16);
goto out_err;
}
got_it:
if (copy_to_user((__u8 __user *)arg, sbi->raw_super->encrypt_pw_salt,
16))
err = -EFAULT;
out_err:
up_write(&sbi->sb_lock);
mnt_drop_write_file(filp);
return err;
}
static int f2fs_ioc_get_encryption_policy_ex(struct file *filp,
unsigned long arg)
{
if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp))))
return -EOPNOTSUPP;
return fscrypt_ioctl_get_policy_ex(filp, (void __user *)arg);
}
static int f2fs_ioc_add_encryption_key(struct file *filp, unsigned long arg)
{
if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp))))
return -EOPNOTSUPP;
return fscrypt_ioctl_add_key(filp, (void __user *)arg);
}
static int f2fs_ioc_remove_encryption_key(struct file *filp, unsigned long arg)
{
if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp))))
return -EOPNOTSUPP;
return fscrypt_ioctl_remove_key(filp, (void __user *)arg);
}
static int f2fs_ioc_remove_encryption_key_all_users(struct file *filp,
unsigned long arg)
{
if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp))))
return -EOPNOTSUPP;
return fscrypt_ioctl_remove_key_all_users(filp, (void __user *)arg);
}
static int f2fs_ioc_get_encryption_key_status(struct file *filp,
unsigned long arg)
{
if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp))))
return -EOPNOTSUPP;
return fscrypt_ioctl_get_key_status(filp, (void __user *)arg);
}
static int f2fs_ioc_get_encryption_nonce(struct file *filp, unsigned long arg)
{
if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp))))
return -EOPNOTSUPP;
return fscrypt_ioctl_get_nonce(filp, (void __user *)arg);
}
static int f2fs_ioc_gc(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
__u32 sync;
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (get_user(sync, (__u32 __user *)arg))
return -EFAULT;
if (f2fs_readonly(sbi->sb))
return -EROFS;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
if (!sync) {
if (!down_write_trylock(&sbi->gc_lock)) {
ret = -EBUSY;
goto out;
}
} else {
down_write(&sbi->gc_lock);
}
ret = f2fs_gc(sbi, sync, true, NULL_SEGNO);
out:
mnt_drop_write_file(filp);
return ret;
}
static int __f2fs_ioc_gc_range(struct file *filp, struct f2fs_gc_range *range)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(file_inode(filp));
u64 end;
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (f2fs_readonly(sbi->sb))
return -EROFS;
end = range->start + range->len;
if (end < range->start || range->start < MAIN_BLKADDR(sbi) ||
end >= MAX_BLKADDR(sbi))
return -EINVAL;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
do_more:
if (!range->sync) {
if (!down_write_trylock(&sbi->gc_lock)) {
ret = -EBUSY;
goto out;
}
} else {
down_write(&sbi->gc_lock);
}
ret = f2fs_gc(sbi, range->sync, true, GET_SEGNO(sbi, range->start));
if (ret) {
if (ret == -EBUSY)
ret = -EAGAIN;
goto out;
}
range->start += BLKS_PER_SEC(sbi);
if (range->start <= end)
goto do_more;
out:
mnt_drop_write_file(filp);
return ret;
}
static int f2fs_ioc_gc_range(struct file *filp, unsigned long arg)
{
struct f2fs_gc_range range;
if (copy_from_user(&range, (struct f2fs_gc_range __user *)arg,
sizeof(range)))
return -EFAULT;
return __f2fs_ioc_gc_range(filp, &range);
}
static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (f2fs_readonly(sbi->sb))
return -EROFS;
if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
f2fs_info(sbi, "Skipping Checkpoint. Checkpoints currently disabled.");
return -EINVAL;
}
ret = mnt_want_write_file(filp);
if (ret)
return ret;
ret = f2fs_sync_fs(sbi->sb, 1);
mnt_drop_write_file(filp);
return ret;
}
static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
struct file *filp,
struct f2fs_defragment *range)
{
struct inode *inode = file_inode(filp);
struct f2fs_map_blocks map = { .m_next_extent = NULL,
.m_seg_type = NO_CHECK_TYPE ,
.m_may_create = false };
struct extent_info ei = {0, 0, 0};
pgoff_t pg_start, pg_end, next_pgofs;
unsigned int blk_per_seg = sbi->blocks_per_seg;
unsigned int total = 0, sec_num;
block_t blk_end = 0;
bool fragmented = false;
int err;
/* if in-place-update policy is enabled, don't waste time here */
if (f2fs_should_update_inplace(inode, NULL))
return -EINVAL;
pg_start = range->start >> PAGE_SHIFT;
pg_end = (range->start + range->len) >> PAGE_SHIFT;
f2fs_balance_fs(sbi, true);
inode_lock(inode);
/* writeback all dirty pages in the range */
err = filemap_write_and_wait_range(inode->i_mapping, range->start,
range->start + range->len - 1);
if (err)
goto out;
/*
* lookup mapping info in extent cache, skip defragmenting if physical
* block addresses are continuous.
*/
if (f2fs_lookup_extent_cache(inode, pg_start, &ei)) {
if (ei.fofs + ei.len >= pg_end)
goto out;
}
map.m_lblk = pg_start;
map.m_next_pgofs = &next_pgofs;
/*
* lookup mapping info in dnode page cache, skip defragmenting if all
* physical block addresses are continuous even if there are hole(s)
* in logical blocks.
*/
while (map.m_lblk < pg_end) {
map.m_len = pg_end - map.m_lblk;
err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT);
if (err)
goto out;
if (!(map.m_flags & F2FS_MAP_FLAGS)) {
map.m_lblk = next_pgofs;
continue;
}
if (blk_end && blk_end != map.m_pblk)
fragmented = true;
/* record total count of block that we're going to move */
total += map.m_len;
blk_end = map.m_pblk + map.m_len;
map.m_lblk += map.m_len;
}
if (!fragmented) {
total = 0;
goto out;
}
sec_num = DIV_ROUND_UP(total, BLKS_PER_SEC(sbi));
/*
* make sure there are enough free section for LFS allocation, this can
* avoid defragment running in SSR mode when free section are allocated
* intensively
*/
if (has_not_enough_free_secs(sbi, 0, sec_num)) {
err = -EAGAIN;
goto out;
}
map.m_lblk = pg_start;
map.m_len = pg_end - pg_start;
total = 0;
while (map.m_lblk < pg_end) {
pgoff_t idx;
int cnt = 0;
do_map:
map.m_len = pg_end - map.m_lblk;
err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT);
if (err)
goto clear_out;
if (!(map.m_flags & F2FS_MAP_FLAGS)) {
map.m_lblk = next_pgofs;
goto check;
}
set_inode_flag(inode, FI_DO_DEFRAG);
idx = map.m_lblk;
while (idx < map.m_lblk + map.m_len && cnt < blk_per_seg) {
struct page *page;
page = f2fs_get_lock_data_page(inode, idx, true);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto clear_out;
}
set_page_dirty(page);
f2fs_put_page(page, 1);
idx++;
cnt++;
total++;
}
map.m_lblk = idx;
check:
if (map.m_lblk < pg_end && cnt < blk_per_seg)
goto do_map;
clear_inode_flag(inode, FI_DO_DEFRAG);
err = filemap_fdatawrite(inode->i_mapping);
if (err)
goto out;
}
clear_out:
clear_inode_flag(inode, FI_DO_DEFRAG);
out:
inode_unlock(inode);
if (!err)
range->len = (u64)total << PAGE_SHIFT;
return err;
}
static int f2fs_ioc_defragment(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_defragment range;
int err;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!S_ISREG(inode->i_mode) || f2fs_is_atomic_file(inode))
return -EINVAL;
if (f2fs_readonly(sbi->sb))
return -EROFS;
if (copy_from_user(&range, (struct f2fs_defragment __user *)arg,
sizeof(range)))
return -EFAULT;
/* verify alignment of offset & size */
if (range.start & (F2FS_BLKSIZE - 1) || range.len & (F2FS_BLKSIZE - 1))
return -EINVAL;
if (unlikely((range.start + range.len) >> PAGE_SHIFT >
max_file_blocks(inode)))
return -EINVAL;
err = mnt_want_write_file(filp);
if (err)
return err;
err = f2fs_defragment_range(sbi, filp, &range);
mnt_drop_write_file(filp);
f2fs_update_time(sbi, REQ_TIME);
if (err < 0)
return err;
if (copy_to_user((struct f2fs_defragment __user *)arg, &range,
sizeof(range)))
return -EFAULT;
return 0;
}
static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out, size_t len)
{
struct inode *src = file_inode(file_in);
struct inode *dst = file_inode(file_out);
struct f2fs_sb_info *sbi = F2FS_I_SB(src);
size_t olen = len, dst_max_i_size = 0;
size_t dst_osize;
int ret;
if (file_in->f_path.mnt != file_out->f_path.mnt ||
src->i_sb != dst->i_sb)
return -EXDEV;
if (unlikely(f2fs_readonly(src->i_sb)))
return -EROFS;
if (!S_ISREG(src->i_mode) || !S_ISREG(dst->i_mode))
return -EINVAL;
if (IS_ENCRYPTED(src) || IS_ENCRYPTED(dst))
return -EOPNOTSUPP;
if (pos_out < 0 || pos_in < 0)
return -EINVAL;
if (src == dst) {
if (pos_in == pos_out)
return 0;
if (pos_out > pos_in && pos_out < pos_in + len)
return -EINVAL;
}
inode_lock(src);
if (src != dst) {
ret = -EBUSY;
if (!inode_trylock(dst))
goto out;
}
ret = -EINVAL;
if (pos_in + len > src->i_size || pos_in + len < pos_in)
goto out_unlock;
if (len == 0)
olen = len = src->i_size - pos_in;
if (pos_in + len == src->i_size)
len = ALIGN(src->i_size, F2FS_BLKSIZE) - pos_in;
if (len == 0) {
ret = 0;
goto out_unlock;
}
dst_osize = dst->i_size;
if (pos_out + olen > dst->i_size)
dst_max_i_size = pos_out + olen;
/* verify the end result is block aligned */
if (!IS_ALIGNED(pos_in, F2FS_BLKSIZE) ||
!IS_ALIGNED(pos_in + len, F2FS_BLKSIZE) ||
!IS_ALIGNED(pos_out, F2FS_BLKSIZE))
goto out_unlock;
ret = f2fs_convert_inline_inode(src);
if (ret)
goto out_unlock;
ret = f2fs_convert_inline_inode(dst);
if (ret)
goto out_unlock;
/* write out all dirty pages from offset */
ret = filemap_write_and_wait_range(src->i_mapping,
pos_in, pos_in + len);
if (ret)
goto out_unlock;
ret = filemap_write_and_wait_range(dst->i_mapping,
pos_out, pos_out + len);
if (ret)
goto out_unlock;
f2fs_balance_fs(sbi, true);
down_write(&F2FS_I(src)->i_gc_rwsem[WRITE]);
if (src != dst) {
ret = -EBUSY;
if (!down_write_trylock(&F2FS_I(dst)->i_gc_rwsem[WRITE]))
goto out_src;
}
f2fs_lock_op(sbi);
ret = __exchange_data_block(src, dst, pos_in >> F2FS_BLKSIZE_BITS,
pos_out >> F2FS_BLKSIZE_BITS,
len >> F2FS_BLKSIZE_BITS, false);
if (!ret) {
if (dst_max_i_size)
f2fs_i_size_write(dst, dst_max_i_size);
else if (dst_osize != dst->i_size)
f2fs_i_size_write(dst, dst_osize);
}
f2fs_unlock_op(sbi);
if (src != dst)
up_write(&F2FS_I(dst)->i_gc_rwsem[WRITE]);
out_src:
up_write(&F2FS_I(src)->i_gc_rwsem[WRITE]);
out_unlock:
if (src != dst)
inode_unlock(dst);
out:
inode_unlock(src);
return ret;
}
static int __f2fs_ioc_move_range(struct file *filp,
struct f2fs_move_range *range)
{
struct fd dst;
int err;
if (!(filp->f_mode & FMODE_READ) ||
!(filp->f_mode & FMODE_WRITE))
return -EBADF;
dst = fdget(range->dst_fd);
if (!dst.file)
return -EBADF;
if (!(dst.file->f_mode & FMODE_WRITE)) {
err = -EBADF;
goto err_out;
}
err = mnt_want_write_file(filp);
if (err)
goto err_out;
err = f2fs_move_file_range(filp, range->pos_in, dst.file,
range->pos_out, range->len);
mnt_drop_write_file(filp);
err_out:
fdput(dst);
return err;
}
static int f2fs_ioc_move_range(struct file *filp, unsigned long arg)
{
struct f2fs_move_range range;
if (copy_from_user(&range, (struct f2fs_move_range __user *)arg,
sizeof(range)))
return -EFAULT;
return __f2fs_ioc_move_range(filp, &range);
}
static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct sit_info *sm = SIT_I(sbi);
unsigned int start_segno = 0, end_segno = 0;
unsigned int dev_start_segno = 0, dev_end_segno = 0;
struct f2fs_flush_device range;
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (f2fs_readonly(sbi->sb))
return -EROFS;
if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
return -EINVAL;
if (copy_from_user(&range, (struct f2fs_flush_device __user *)arg,
sizeof(range)))
return -EFAULT;
if (!f2fs_is_multi_device(sbi) || sbi->s_ndevs - 1 <= range.dev_num ||
__is_large_section(sbi)) {
f2fs_warn(sbi, "Can't flush %u in %d for segs_per_sec %u != 1",
range.dev_num, sbi->s_ndevs, sbi->segs_per_sec);
return -EINVAL;
}
ret = mnt_want_write_file(filp);
if (ret)
return ret;
if (range.dev_num != 0)
dev_start_segno = GET_SEGNO(sbi, FDEV(range.dev_num).start_blk);
dev_end_segno = GET_SEGNO(sbi, FDEV(range.dev_num).end_blk);
start_segno = sm->last_victim[FLUSH_DEVICE];
if (start_segno < dev_start_segno || start_segno >= dev_end_segno)
start_segno = dev_start_segno;
end_segno = min(start_segno + range.segments, dev_end_segno);
while (start_segno < end_segno) {
if (!down_write_trylock(&sbi->gc_lock)) {
ret = -EBUSY;
goto out;
}
sm->last_victim[GC_CB] = end_segno + 1;
sm->last_victim[GC_GREEDY] = end_segno + 1;
sm->last_victim[ALLOC_NEXT] = end_segno + 1;
ret = f2fs_gc(sbi, true, true, start_segno);
if (ret == -EAGAIN)
ret = 0;
else if (ret < 0)
break;
start_segno++;
}
out:
mnt_drop_write_file(filp);
return ret;
}
static int f2fs_ioc_get_features(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
u32 sb_feature = le32_to_cpu(F2FS_I_SB(inode)->raw_super->feature);
/* Must validate to set it with SQLite behavior in Android. */
sb_feature |= F2FS_FEATURE_ATOMIC_WRITE;
return put_user(sb_feature, (u32 __user *)arg);
}
#ifdef CONFIG_QUOTA
int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid)
{
struct dquot *transfer_to[MAXQUOTAS] = {};
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct super_block *sb = sbi->sb;
int err = 0;
transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid));
if (!IS_ERR(transfer_to[PRJQUOTA])) {
err = __dquot_transfer(inode, transfer_to);
if (err)
set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR);
dqput(transfer_to[PRJQUOTA]);
}
return err;
}
static int f2fs_ioc_setproject(struct file *filp, __u32 projid)
{
struct inode *inode = file_inode(filp);
struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *ipage;
kprojid_t kprojid;
int err;
if (!f2fs_sb_has_project_quota(sbi)) {
if (projid != F2FS_DEF_PROJID)
return -EOPNOTSUPP;
else
return 0;
}
if (!f2fs_has_extra_attr(inode))
return -EOPNOTSUPP;
kprojid = make_kprojid(&init_user_ns, (projid_t)projid);
if (projid_eq(kprojid, F2FS_I(inode)->i_projid))
return 0;
err = -EPERM;
/* Is it quota file? Do not allow user to mess with it */
if (IS_NOQUOTA(inode))
return err;
ipage = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
if (!F2FS_FITS_IN_INODE(F2FS_INODE(ipage), fi->i_extra_isize,
i_projid)) {
err = -EOVERFLOW;
f2fs_put_page(ipage, 1);
return err;
}
f2fs_put_page(ipage, 1);
err = dquot_initialize(inode);
if (err)
return err;
f2fs_lock_op(sbi);
err = f2fs_transfer_project_quota(inode, kprojid);
if (err)
goto out_unlock;
F2FS_I(inode)->i_projid = kprojid;
inode->i_ctime = current_time(inode);
f2fs_mark_inode_dirty_sync(inode, true);
out_unlock:
f2fs_unlock_op(sbi);
return err;
}
#else
int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid)
{
return 0;
}
static int f2fs_ioc_setproject(struct file *filp, __u32 projid)
{
if (projid != F2FS_DEF_PROJID)
return -EOPNOTSUPP;
return 0;
}
#endif
/* FS_IOC_FSGETXATTR and FS_IOC_FSSETXATTR support */
/*
* To make a new on-disk f2fs i_flag gettable via FS_IOC_FSGETXATTR and settable
* via FS_IOC_FSSETXATTR, add an entry for it to f2fs_xflags_map[], and add its
* FS_XFLAG_* equivalent to F2FS_SUPPORTED_XFLAGS.
*/
static const struct {
u32 iflag;
u32 xflag;
} f2fs_xflags_map[] = {
{ F2FS_SYNC_FL, FS_XFLAG_SYNC },
{ F2FS_IMMUTABLE_FL, FS_XFLAG_IMMUTABLE },
{ F2FS_APPEND_FL, FS_XFLAG_APPEND },
{ F2FS_NODUMP_FL, FS_XFLAG_NODUMP },
{ F2FS_NOATIME_FL, FS_XFLAG_NOATIME },
{ F2FS_PROJINHERIT_FL, FS_XFLAG_PROJINHERIT },
};
#define F2FS_SUPPORTED_XFLAGS ( \
FS_XFLAG_SYNC | \
FS_XFLAG_IMMUTABLE | \
FS_XFLAG_APPEND | \
FS_XFLAG_NODUMP | \
FS_XFLAG_NOATIME | \
FS_XFLAG_PROJINHERIT)
/* Convert f2fs on-disk i_flags to FS_IOC_FS{GET,SET}XATTR flags */
static inline u32 f2fs_iflags_to_xflags(u32 iflags)
{
u32 xflags = 0;
int i;
for (i = 0; i < ARRAY_SIZE(f2fs_xflags_map); i++)
if (iflags & f2fs_xflags_map[i].iflag)
xflags |= f2fs_xflags_map[i].xflag;
return xflags;
}
/* Convert FS_IOC_FS{GET,SET}XATTR flags to f2fs on-disk i_flags */
static inline u32 f2fs_xflags_to_iflags(u32 xflags)
{
u32 iflags = 0;
int i;
for (i = 0; i < ARRAY_SIZE(f2fs_xflags_map); i++)
if (xflags & f2fs_xflags_map[i].xflag)
iflags |= f2fs_xflags_map[i].iflag;
return iflags;
}
static void f2fs_fill_fsxattr(struct inode *inode, struct fsxattr *fa)
{
struct f2fs_inode_info *fi = F2FS_I(inode);
simple_fill_fsxattr(fa, f2fs_iflags_to_xflags(fi->i_flags));
if (f2fs_sb_has_project_quota(F2FS_I_SB(inode)))
fa->fsx_projid = from_kprojid(&init_user_ns, fi->i_projid);
}
static int f2fs_ioc_fsgetxattr(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct fsxattr fa;
f2fs_fill_fsxattr(inode, &fa);
if (copy_to_user((struct fsxattr __user *)arg, &fa, sizeof(fa)))
return -EFAULT;
return 0;
}
static int f2fs_ioc_fssetxattr(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct fsxattr fa, old_fa;
u32 iflags;
int err;
if (copy_from_user(&fa, (struct fsxattr __user *)arg, sizeof(fa)))
return -EFAULT;
/* Make sure caller has proper permission */
if (!inode_owner_or_capable(&init_user_ns, inode))
return -EACCES;
if (fa.fsx_xflags & ~F2FS_SUPPORTED_XFLAGS)
return -EOPNOTSUPP;
iflags = f2fs_xflags_to_iflags(fa.fsx_xflags);
if (f2fs_mask_flags(inode->i_mode, iflags) != iflags)
return -EOPNOTSUPP;
err = mnt_want_write_file(filp);
if (err)
return err;
inode_lock(inode);
f2fs_fill_fsxattr(inode, &old_fa);
err = vfs_ioc_fssetxattr_check(inode, &old_fa, &fa);
if (err)
goto out;
err = f2fs_setflags_common(inode, iflags,
f2fs_xflags_to_iflags(F2FS_SUPPORTED_XFLAGS));
if (err)
goto out;
err = f2fs_ioc_setproject(filp, fa.fsx_projid);
out:
inode_unlock(inode);
mnt_drop_write_file(filp);
return err;
}
int f2fs_pin_file_control(struct inode *inode, bool inc)
{
struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
/* Use i_gc_failures for normal file as a risk signal. */
if (inc)
f2fs_i_gc_failures_write(inode,
fi->i_gc_failures[GC_FAILURE_PIN] + 1);
if (fi->i_gc_failures[GC_FAILURE_PIN] > sbi->gc_pin_file_threshold) {
f2fs_warn(sbi, "%s: Enable GC = ino %lx after %x GC trials",
__func__, inode->i_ino,
fi->i_gc_failures[GC_FAILURE_PIN]);
clear_inode_flag(inode, FI_PIN_FILE);
return -EAGAIN;
}
return 0;
}
static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
__u32 pin;
int ret = 0;
if (get_user(pin, (__u32 __user *)arg))
return -EFAULT;
if (!S_ISREG(inode->i_mode))
return -EINVAL;
if (f2fs_readonly(F2FS_I_SB(inode)->sb))
return -EROFS;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
inode_lock(inode);
if (f2fs_should_update_outplace(inode, NULL)) {
ret = -EINVAL;
goto out;
}
if (!pin) {
clear_inode_flag(inode, FI_PIN_FILE);
f2fs_i_gc_failures_write(inode, 0);
goto done;
}
if (f2fs_pin_file_control(inode, false)) {
ret = -EAGAIN;
goto out;
}
ret = f2fs_convert_inline_inode(inode);
if (ret)
goto out;
if (!f2fs_disable_compressed_file(inode)) {
ret = -EOPNOTSUPP;
goto out;
}
set_inode_flag(inode, FI_PIN_FILE);
ret = F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN];
done:
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
out:
inode_unlock(inode);
mnt_drop_write_file(filp);
return ret;
}
static int f2fs_ioc_get_pin_file(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
__u32 pin = 0;
if (is_inode_flag_set(inode, FI_PIN_FILE))
pin = F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN];
return put_user(pin, (u32 __user *)arg);
}
int f2fs_precache_extents(struct inode *inode)
{
struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_map_blocks map;
pgoff_t m_next_extent;
loff_t end;
int err;
if (is_inode_flag_set(inode, FI_NO_EXTENT))
return -EOPNOTSUPP;
map.m_lblk = 0;
map.m_next_pgofs = NULL;
map.m_next_extent = &m_next_extent;
map.m_seg_type = NO_CHECK_TYPE;
map.m_may_create = false;
end = max_file_blocks(inode);
while (map.m_lblk < end) {
map.m_len = end - map.m_lblk;
down_write(&fi->i_gc_rwsem[WRITE]);
err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_PRECACHE);
up_write(&fi->i_gc_rwsem[WRITE]);
if (err)
return err;
map.m_lblk = m_next_extent;
}
return err;
}
static int f2fs_ioc_precache_extents(struct file *filp, unsigned long arg)
{
return f2fs_precache_extents(file_inode(filp));
}
static int f2fs_ioc_resize_fs(struct file *filp, unsigned long arg)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(file_inode(filp));
__u64 block_count;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (f2fs_readonly(sbi->sb))
return -EROFS;
if (copy_from_user(&block_count, (void __user *)arg,
sizeof(block_count)))
return -EFAULT;
return f2fs_resize_fs(sbi, block_count);
}
static int f2fs_ioc_enable_verity(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
if (!f2fs_sb_has_verity(F2FS_I_SB(inode))) {
f2fs_warn(F2FS_I_SB(inode),
"Can't enable fs-verity on inode %lu: the verity feature is not enabled on this filesystem.\n",
inode->i_ino);
return -EOPNOTSUPP;
}
return fsverity_ioctl_enable(filp, (const void __user *)arg);
}
static int f2fs_ioc_measure_verity(struct file *filp, unsigned long arg)
{
if (!f2fs_sb_has_verity(F2FS_I_SB(file_inode(filp))))
return -EOPNOTSUPP;
return fsverity_ioctl_measure(filp, (void __user *)arg);
}
static int f2fs_ioc_read_verity_metadata(struct file *filp, unsigned long arg)
{
if (!f2fs_sb_has_verity(F2FS_I_SB(file_inode(filp))))
return -EOPNOTSUPP;
return fsverity_ioctl_read_metadata(filp, (const void __user *)arg);
}
static int f2fs_ioc_getfslabel(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
char *vbuf;
int count;
int err = 0;
vbuf = f2fs_kzalloc(sbi, MAX_VOLUME_NAME, GFP_KERNEL);
if (!vbuf)
return -ENOMEM;
down_read(&sbi->sb_lock);
count = utf16s_to_utf8s(sbi->raw_super->volume_name,
ARRAY_SIZE(sbi->raw_super->volume_name),
UTF16_LITTLE_ENDIAN, vbuf, MAX_VOLUME_NAME);
up_read(&sbi->sb_lock);
if (copy_to_user((char __user *)arg, vbuf,
min(FSLABEL_MAX, count)))
err = -EFAULT;
kfree(vbuf);
return err;
}
static int f2fs_ioc_setfslabel(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
char *vbuf;
int err = 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
vbuf = strndup_user((const char __user *)arg, FSLABEL_MAX);
if (IS_ERR(vbuf))
return PTR_ERR(vbuf);
err = mnt_want_write_file(filp);
if (err)
goto out;
down_write(&sbi->sb_lock);
memset(sbi->raw_super->volume_name, 0,
sizeof(sbi->raw_super->volume_name));
utf8s_to_utf16s(vbuf, strlen(vbuf), UTF16_LITTLE_ENDIAN,
sbi->raw_super->volume_name,
ARRAY_SIZE(sbi->raw_super->volume_name));
err = f2fs_commit_super(sbi, false);
up_write(&sbi->sb_lock);
mnt_drop_write_file(filp);
out:
kfree(vbuf);
return err;
}
static int f2fs_get_compress_blocks(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
__u64 blocks;
if (!f2fs_sb_has_compression(F2FS_I_SB(inode)))
return -EOPNOTSUPP;
if (!f2fs_compressed_file(inode))
return -EINVAL;
blocks = atomic_read(&F2FS_I(inode)->i_compr_blocks);
return put_user(blocks, (u64 __user *)arg);
}
static int release_compress_blocks(struct dnode_of_data *dn, pgoff_t count)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
unsigned int released_blocks = 0;
int cluster_size = F2FS_I(dn->inode)->i_cluster_size;
block_t blkaddr;
int i;
for (i = 0; i < count; i++) {
blkaddr = data_blkaddr(dn->inode, dn->node_page,
dn->ofs_in_node + i);
if (!__is_valid_data_blkaddr(blkaddr))
continue;
if (unlikely(!f2fs_is_valid_blkaddr(sbi, blkaddr,
DATA_GENERIC_ENHANCE)))
return -EFSCORRUPTED;
}
while (count) {
int compr_blocks = 0;
for (i = 0; i < cluster_size; i++, dn->ofs_in_node++) {
blkaddr = f2fs_data_blkaddr(dn);
if (i == 0) {
if (blkaddr == COMPRESS_ADDR)
continue;
dn->ofs_in_node += cluster_size;
goto next;
}
if (__is_valid_data_blkaddr(blkaddr))
compr_blocks++;
if (blkaddr != NEW_ADDR)
continue;
dn->data_blkaddr = NULL_ADDR;
f2fs_set_data_blkaddr(dn);
}
f2fs_i_compr_blocks_update(dn->inode, compr_blocks, false);
dec_valid_block_count(sbi, dn->inode,
cluster_size - compr_blocks);
released_blocks += cluster_size - compr_blocks;
next:
count -= cluster_size;
}
return released_blocks;
}
static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
pgoff_t page_idx = 0, last_idx;
unsigned int released_blocks = 0;
int ret;
int writecount;
if (!f2fs_sb_has_compression(F2FS_I_SB(inode)))
return -EOPNOTSUPP;
if (!f2fs_compressed_file(inode))
return -EINVAL;
if (f2fs_readonly(sbi->sb))
return -EROFS;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
f2fs_balance_fs(F2FS_I_SB(inode), true);
inode_lock(inode);
writecount = atomic_read(&inode->i_writecount);
if ((filp->f_mode & FMODE_WRITE && writecount != 1) ||
(!(filp->f_mode & FMODE_WRITE) && writecount)) {
ret = -EBUSY;
goto out;
}
if (IS_IMMUTABLE(inode)) {
ret = -EINVAL;
goto out;
}
ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX);
if (ret)
goto out;
F2FS_I(inode)->i_flags |= F2FS_IMMUTABLE_FL;
f2fs_set_inode_flags(inode);
inode->i_ctime = current_time(inode);
f2fs_mark_inode_dirty_sync(inode, true);
if (!atomic_read(&F2FS_I(inode)->i_compr_blocks))
goto out;
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
down_write(&F2FS_I(inode)->i_mmap_sem);
last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
while (page_idx < last_idx) {
struct dnode_of_data dn;
pgoff_t end_offset, count;
set_new_dnode(&dn, inode, NULL, NULL, 0);
ret = f2fs_get_dnode_of_data(&dn, page_idx, LOOKUP_NODE);
if (ret) {
if (ret == -ENOENT) {
page_idx = f2fs_get_next_page_offset(&dn,
page_idx);
ret = 0;
continue;
}
break;
}
end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
count = min(end_offset - dn.ofs_in_node, last_idx - page_idx);
count = round_up(count, F2FS_I(inode)->i_cluster_size);
ret = release_compress_blocks(&dn, count);
f2fs_put_dnode(&dn);
if (ret < 0)
break;
page_idx += count;
released_blocks += ret;
}
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
up_write(&F2FS_I(inode)->i_mmap_sem);
out:
inode_unlock(inode);
mnt_drop_write_file(filp);
if (ret >= 0) {
ret = put_user(released_blocks, (u64 __user *)arg);
} else if (released_blocks &&
atomic_read(&F2FS_I(inode)->i_compr_blocks)) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_warn(sbi, "%s: partial blocks were released i_ino=%lx "
"iblocks=%llu, released=%u, compr_blocks=%u, "
"run fsck to fix.",
__func__, inode->i_ino, inode->i_blocks,
released_blocks,
atomic_read(&F2FS_I(inode)->i_compr_blocks));
}
return ret;
}
static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
unsigned int reserved_blocks = 0;
int cluster_size = F2FS_I(dn->inode)->i_cluster_size;
block_t blkaddr;
int i;
for (i = 0; i < count; i++) {
blkaddr = data_blkaddr(dn->inode, dn->node_page,
dn->ofs_in_node + i);
if (!__is_valid_data_blkaddr(blkaddr))
continue;
if (unlikely(!f2fs_is_valid_blkaddr(sbi, blkaddr,
DATA_GENERIC_ENHANCE)))
return -EFSCORRUPTED;
}
while (count) {
int compr_blocks = 0;
blkcnt_t reserved;
int ret;
for (i = 0; i < cluster_size; i++, dn->ofs_in_node++) {
blkaddr = f2fs_data_blkaddr(dn);
if (i == 0) {
if (blkaddr == COMPRESS_ADDR)
continue;
dn->ofs_in_node += cluster_size;
goto next;
}
if (__is_valid_data_blkaddr(blkaddr)) {
compr_blocks++;
continue;
}
dn->data_blkaddr = NEW_ADDR;
f2fs_set_data_blkaddr(dn);
}
reserved = cluster_size - compr_blocks;
ret = inc_valid_block_count(sbi, dn->inode, &reserved);
if (ret)
return ret;
if (reserved != cluster_size - compr_blocks)
return -ENOSPC;
f2fs_i_compr_blocks_update(dn->inode, compr_blocks, true);
reserved_blocks += reserved;
next:
count -= cluster_size;
}
return reserved_blocks;
}
static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
pgoff_t page_idx = 0, last_idx;
unsigned int reserved_blocks = 0;
int ret;
if (!f2fs_sb_has_compression(F2FS_I_SB(inode)))
return -EOPNOTSUPP;
if (!f2fs_compressed_file(inode))
return -EINVAL;
if (f2fs_readonly(sbi->sb))
return -EROFS;
ret = mnt_want_write_file(filp);
if (ret)
return ret;
if (atomic_read(&F2FS_I(inode)->i_compr_blocks))
goto out;
f2fs_balance_fs(F2FS_I_SB(inode), true);
inode_lock(inode);
if (!IS_IMMUTABLE(inode)) {
ret = -EINVAL;
goto unlock_inode;
}
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
down_write(&F2FS_I(inode)->i_mmap_sem);
last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
while (page_idx < last_idx) {
struct dnode_of_data dn;
pgoff_t end_offset, count;
set_new_dnode(&dn, inode, NULL, NULL, 0);
ret = f2fs_get_dnode_of_data(&dn, page_idx, LOOKUP_NODE);
if (ret) {
if (ret == -ENOENT) {
page_idx = f2fs_get_next_page_offset(&dn,
page_idx);
ret = 0;
continue;
}
break;
}
end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
count = min(end_offset - dn.ofs_in_node, last_idx - page_idx);
count = round_up(count, F2FS_I(inode)->i_cluster_size);
ret = reserve_compress_blocks(&dn, count);
f2fs_put_dnode(&dn);
if (ret < 0)
break;
page_idx += count;
reserved_blocks += ret;
}
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
up_write(&F2FS_I(inode)->i_mmap_sem);
if (ret >= 0) {
F2FS_I(inode)->i_flags &= ~F2FS_IMMUTABLE_FL;
f2fs_set_inode_flags(inode);
inode->i_ctime = current_time(inode);
f2fs_mark_inode_dirty_sync(inode, true);
}
unlock_inode:
inode_unlock(inode);
out:
mnt_drop_write_file(filp);
if (ret >= 0) {
ret = put_user(reserved_blocks, (u64 __user *)arg);
} else if (reserved_blocks &&
atomic_read(&F2FS_I(inode)->i_compr_blocks)) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_warn(sbi, "%s: partial blocks were released i_ino=%lx "
"iblocks=%llu, reserved=%u, compr_blocks=%u, "
"run fsck to fix.",
__func__, inode->i_ino, inode->i_blocks,
reserved_blocks,
atomic_read(&F2FS_I(inode)->i_compr_blocks));
}
return ret;
}
static int f2fs_secure_erase(struct block_device *bdev, struct inode *inode,
pgoff_t off, block_t block, block_t len, u32 flags)
{
struct request_queue *q = bdev_get_queue(bdev);
sector_t sector = SECTOR_FROM_BLOCK(block);
sector_t nr_sects = SECTOR_FROM_BLOCK(len);
int ret = 0;
if (!q)
return -ENXIO;
if (flags & F2FS_TRIM_FILE_DISCARD)
ret = blkdev_issue_discard(bdev, sector, nr_sects, GFP_NOFS,
blk_queue_secure_erase(q) ?
BLKDEV_DISCARD_SECURE : 0);
if (!ret && (flags & F2FS_TRIM_FILE_ZEROOUT)) {
if (IS_ENCRYPTED(inode))
ret = fscrypt_zeroout_range(inode, off, block, len);
else
ret = blkdev_issue_zeroout(bdev, sector, nr_sects,
GFP_NOFS, 0);
}
return ret;
}
static int f2fs_sec_trim_file(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct address_space *mapping = inode->i_mapping;
struct block_device *prev_bdev = NULL;
struct f2fs_sectrim_range range;
pgoff_t index, pg_end, prev_index = 0;
block_t prev_block = 0, len = 0;
loff_t end_addr;
bool to_end = false;
int ret = 0;
if (!(filp->f_mode & FMODE_WRITE))
return -EBADF;
if (copy_from_user(&range, (struct f2fs_sectrim_range __user *)arg,
sizeof(range)))
return -EFAULT;
if (range.flags == 0 || (range.flags & ~F2FS_TRIM_FILE_MASK) ||
!S_ISREG(inode->i_mode))
return -EINVAL;
if (((range.flags & F2FS_TRIM_FILE_DISCARD) &&
!f2fs_hw_support_discard(sbi)) ||
((range.flags & F2FS_TRIM_FILE_ZEROOUT) &&
IS_ENCRYPTED(inode) && f2fs_is_multi_device(sbi)))
return -EOPNOTSUPP;
file_start_write(filp);
inode_lock(inode);
if (f2fs_is_atomic_file(inode) || f2fs_compressed_file(inode) ||
range.start >= inode->i_size) {
ret = -EINVAL;
goto err;
}
if (range.len == 0)
goto err;
if (inode->i_size - range.start > range.len) {
end_addr = range.start + range.len;
} else {
end_addr = range.len == (u64)-1 ?
sbi->sb->s_maxbytes : inode->i_size;
to_end = true;
}
if (!IS_ALIGNED(range.start, F2FS_BLKSIZE) ||
(!to_end && !IS_ALIGNED(end_addr, F2FS_BLKSIZE))) {
ret = -EINVAL;
goto err;
}
index = F2FS_BYTES_TO_BLK(range.start);
pg_end = DIV_ROUND_UP(end_addr, F2FS_BLKSIZE);
ret = f2fs_convert_inline_inode(inode);
if (ret)
goto err;
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
down_write(&F2FS_I(inode)->i_mmap_sem);
ret = filemap_write_and_wait_range(mapping, range.start,
to_end ? LLONG_MAX : end_addr - 1);
if (ret)
goto out;
truncate_inode_pages_range(mapping, range.start,
to_end ? -1 : end_addr - 1);
while (index < pg_end) {
struct dnode_of_data dn;
pgoff_t end_offset, count;
int i;
set_new_dnode(&dn, inode, NULL, NULL, 0);
ret = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE);
if (ret) {
if (ret == -ENOENT) {
index = f2fs_get_next_page_offset(&dn, index);
continue;
}
goto out;
}
end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
count = min(end_offset - dn.ofs_in_node, pg_end - index);
for (i = 0; i < count; i++, index++, dn.ofs_in_node++) {
struct block_device *cur_bdev;
block_t blkaddr = f2fs_data_blkaddr(&dn);
if (!__is_valid_data_blkaddr(blkaddr))
continue;
if (!f2fs_is_valid_blkaddr(sbi, blkaddr,
DATA_GENERIC_ENHANCE)) {
ret = -EFSCORRUPTED;
f2fs_put_dnode(&dn);
goto out;
}
cur_bdev = f2fs_target_device(sbi, blkaddr, NULL);
if (f2fs_is_multi_device(sbi)) {
int di = f2fs_target_device_index(sbi, blkaddr);
blkaddr -= FDEV(di).start_blk;
}
if (len) {
if (prev_bdev == cur_bdev &&
index == prev_index + len &&
blkaddr == prev_block + len) {
len++;
} else {
ret = f2fs_secure_erase(prev_bdev,
inode, prev_index, prev_block,
len, range.flags);
if (ret) {
f2fs_put_dnode(&dn);
goto out;
}
len = 0;
}
}
if (!len) {
prev_bdev = cur_bdev;
prev_index = index;
prev_block = blkaddr;
len = 1;
}
}
f2fs_put_dnode(&dn);
if (fatal_signal_pending(current)) {
ret = -EINTR;
goto out;
}
cond_resched();
}
if (len)
ret = f2fs_secure_erase(prev_bdev, inode, prev_index,
prev_block, len, range.flags);
out:
up_write(&F2FS_I(inode)->i_mmap_sem);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
err:
inode_unlock(inode);
file_end_write(filp);
return ret;
}
static int f2fs_ioc_get_compress_option(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_comp_option option;
if (!f2fs_sb_has_compression(F2FS_I_SB(inode)))
return -EOPNOTSUPP;
inode_lock_shared(inode);
if (!f2fs_compressed_file(inode)) {
inode_unlock_shared(inode);
return -ENODATA;
}
option.algorithm = F2FS_I(inode)->i_compress_algorithm;
option.log_cluster_size = F2FS_I(inode)->i_log_cluster_size;
inode_unlock_shared(inode);
if (copy_to_user((struct f2fs_comp_option __user *)arg, &option,
sizeof(option)))
return -EFAULT;
return 0;
}
static int f2fs_ioc_set_compress_option(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_comp_option option;
int ret = 0;
if (!f2fs_sb_has_compression(sbi))
return -EOPNOTSUPP;
if (!(filp->f_mode & FMODE_WRITE))
return -EBADF;
if (copy_from_user(&option, (struct f2fs_comp_option __user *)arg,
sizeof(option)))
return -EFAULT;
if (!f2fs_compressed_file(inode) ||
option.log_cluster_size < MIN_COMPRESS_LOG_SIZE ||
option.log_cluster_size > MAX_COMPRESS_LOG_SIZE ||
option.algorithm >= COMPRESS_MAX)
return -EINVAL;
file_start_write(filp);
inode_lock(inode);
if (f2fs_is_mmap_file(inode) || get_dirty_pages(inode)) {
ret = -EBUSY;
goto out;
}
if (inode->i_size != 0) {
ret = -EFBIG;
goto out;
}
F2FS_I(inode)->i_compress_algorithm = option.algorithm;
F2FS_I(inode)->i_log_cluster_size = option.log_cluster_size;
F2FS_I(inode)->i_cluster_size = 1 << option.log_cluster_size;
f2fs_mark_inode_dirty_sync(inode, true);
if (!f2fs_is_compress_backend_ready(inode))
f2fs_warn(sbi, "compression algorithm is successfully set, "
"but current kernel doesn't support this algorithm.");
out:
inode_unlock(inode);
file_end_write(filp);
return ret;
}
static int redirty_blocks(struct inode *inode, pgoff_t page_idx, int len)
{
DEFINE_READAHEAD(ractl, NULL, inode->i_mapping, page_idx);
struct address_space *mapping = inode->i_mapping;
struct page *page;
pgoff_t redirty_idx = page_idx;
int i, page_len = 0, ret = 0;
page_cache_ra_unbounded(&ractl, len, 0);
for (i = 0; i < len; i++, page_idx++) {
page = read_cache_page(mapping, page_idx, NULL, NULL);
if (IS_ERR(page)) {
ret = PTR_ERR(page);
break;
}
page_len++;
}
for (i = 0; i < page_len; i++, redirty_idx++) {
page = find_lock_page(mapping, redirty_idx);
if (!page) {
ret = -ENOMEM;
break;
}
set_page_dirty(page);
f2fs_put_page(page, 1);
f2fs_put_page(page, 0);
}
return ret;
}
static int f2fs_ioc_decompress_file(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
pgoff_t page_idx = 0, last_idx;
unsigned int blk_per_seg = sbi->blocks_per_seg;
int cluster_size = F2FS_I(inode)->i_cluster_size;
int count, ret;
if (!f2fs_sb_has_compression(sbi) ||
F2FS_OPTION(sbi).compress_mode != COMPR_MODE_USER)
return -EOPNOTSUPP;
if (!(filp->f_mode & FMODE_WRITE))
return -EBADF;
if (!f2fs_compressed_file(inode))
return -EINVAL;
f2fs_balance_fs(F2FS_I_SB(inode), true);
file_start_write(filp);
inode_lock(inode);
if (!f2fs_is_compress_backend_ready(inode)) {
ret = -EOPNOTSUPP;
goto out;
}
if (f2fs_is_mmap_file(inode)) {
ret = -EBUSY;
goto out;
}
ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX);
if (ret)
goto out;
if (!atomic_read(&fi->i_compr_blocks))
goto out;
last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
count = last_idx - page_idx;
while (count) {
int len = min(cluster_size, count);
ret = redirty_blocks(inode, page_idx, len);
if (ret < 0)
break;
if (get_dirty_pages(inode) >= blk_per_seg)
filemap_fdatawrite(inode->i_mapping);
count -= len;
page_idx += len;
}
if (!ret)
ret = filemap_write_and_wait_range(inode->i_mapping, 0,
LLONG_MAX);
if (ret)
f2fs_warn(sbi, "%s: The file might be partially decompressed "
"(errno=%d). Please delete the file.\n",
__func__, ret);
out:
inode_unlock(inode);
file_end_write(filp);
return ret;
}
static int f2fs_ioc_compress_file(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
pgoff_t page_idx = 0, last_idx;
unsigned int blk_per_seg = sbi->blocks_per_seg;
int cluster_size = F2FS_I(inode)->i_cluster_size;
int count, ret;
if (!f2fs_sb_has_compression(sbi) ||
F2FS_OPTION(sbi).compress_mode != COMPR_MODE_USER)
return -EOPNOTSUPP;
if (!(filp->f_mode & FMODE_WRITE))
return -EBADF;
if (!f2fs_compressed_file(inode))
return -EINVAL;
f2fs_balance_fs(F2FS_I_SB(inode), true);
file_start_write(filp);
inode_lock(inode);
if (!f2fs_is_compress_backend_ready(inode)) {
ret = -EOPNOTSUPP;
goto out;
}
if (f2fs_is_mmap_file(inode)) {
ret = -EBUSY;
goto out;
}
ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX);
if (ret)
goto out;
set_inode_flag(inode, FI_ENABLE_COMPRESS);
last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
count = last_idx - page_idx;
while (count) {
int len = min(cluster_size, count);
ret = redirty_blocks(inode, page_idx, len);
if (ret < 0)
break;
if (get_dirty_pages(inode) >= blk_per_seg)
filemap_fdatawrite(inode->i_mapping);
count -= len;
page_idx += len;
}
if (!ret)
ret = filemap_write_and_wait_range(inode->i_mapping, 0,
LLONG_MAX);
clear_inode_flag(inode, FI_ENABLE_COMPRESS);
if (ret)
f2fs_warn(sbi, "%s: The file might be partially compressed "
"(errno=%d). Please delete the file.\n",
__func__, ret);
out:
inode_unlock(inode);
file_end_write(filp);
return ret;
}
static long __f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
switch (cmd) {
case FS_IOC_GETFLAGS:
return f2fs_ioc_getflags(filp, arg);
case FS_IOC_SETFLAGS:
return f2fs_ioc_setflags(filp, arg);
case FS_IOC_GETVERSION:
return f2fs_ioc_getversion(filp, arg);
case F2FS_IOC_START_ATOMIC_WRITE:
return f2fs_ioc_start_atomic_write(filp);
case F2FS_IOC_COMMIT_ATOMIC_WRITE:
return f2fs_ioc_commit_atomic_write(filp);
case F2FS_IOC_START_VOLATILE_WRITE:
return f2fs_ioc_start_volatile_write(filp);
case F2FS_IOC_RELEASE_VOLATILE_WRITE:
return f2fs_ioc_release_volatile_write(filp);
case F2FS_IOC_ABORT_VOLATILE_WRITE:
return f2fs_ioc_abort_volatile_write(filp);
case F2FS_IOC_SHUTDOWN:
return f2fs_ioc_shutdown(filp, arg);
case FITRIM:
return f2fs_ioc_fitrim(filp, arg);
case FS_IOC_SET_ENCRYPTION_POLICY:
return f2fs_ioc_set_encryption_policy(filp, arg);
case FS_IOC_GET_ENCRYPTION_POLICY:
return f2fs_ioc_get_encryption_policy(filp, arg);
case FS_IOC_GET_ENCRYPTION_PWSALT:
return f2fs_ioc_get_encryption_pwsalt(filp, arg);
case FS_IOC_GET_ENCRYPTION_POLICY_EX:
return f2fs_ioc_get_encryption_policy_ex(filp, arg);
case FS_IOC_ADD_ENCRYPTION_KEY:
return f2fs_ioc_add_encryption_key(filp, arg);
case FS_IOC_REMOVE_ENCRYPTION_KEY:
return f2fs_ioc_remove_encryption_key(filp, arg);
case FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS:
return f2fs_ioc_remove_encryption_key_all_users(filp, arg);
case FS_IOC_GET_ENCRYPTION_KEY_STATUS:
return f2fs_ioc_get_encryption_key_status(filp, arg);
case FS_IOC_GET_ENCRYPTION_NONCE:
return f2fs_ioc_get_encryption_nonce(filp, arg);
case F2FS_IOC_GARBAGE_COLLECT:
return f2fs_ioc_gc(filp, arg);
case F2FS_IOC_GARBAGE_COLLECT_RANGE:
return f2fs_ioc_gc_range(filp, arg);
case F2FS_IOC_WRITE_CHECKPOINT:
return f2fs_ioc_write_checkpoint(filp, arg);
case F2FS_IOC_DEFRAGMENT:
return f2fs_ioc_defragment(filp, arg);
case F2FS_IOC_MOVE_RANGE:
return f2fs_ioc_move_range(filp, arg);
case F2FS_IOC_FLUSH_DEVICE:
return f2fs_ioc_flush_device(filp, arg);
case F2FS_IOC_GET_FEATURES:
return f2fs_ioc_get_features(filp, arg);
case FS_IOC_FSGETXATTR:
return f2fs_ioc_fsgetxattr(filp, arg);
case FS_IOC_FSSETXATTR:
return f2fs_ioc_fssetxattr(filp, arg);
case F2FS_IOC_GET_PIN_FILE:
return f2fs_ioc_get_pin_file(filp, arg);
case F2FS_IOC_SET_PIN_FILE:
return f2fs_ioc_set_pin_file(filp, arg);
case F2FS_IOC_PRECACHE_EXTENTS:
return f2fs_ioc_precache_extents(filp, arg);
case F2FS_IOC_RESIZE_FS:
return f2fs_ioc_resize_fs(filp, arg);
case FS_IOC_ENABLE_VERITY:
return f2fs_ioc_enable_verity(filp, arg);
case FS_IOC_MEASURE_VERITY:
return f2fs_ioc_measure_verity(filp, arg);
case FS_IOC_READ_VERITY_METADATA:
return f2fs_ioc_read_verity_metadata(filp, arg);
case FS_IOC_GETFSLABEL:
return f2fs_ioc_getfslabel(filp, arg);
case FS_IOC_SETFSLABEL:
return f2fs_ioc_setfslabel(filp, arg);
case F2FS_IOC_GET_COMPRESS_BLOCKS:
return f2fs_get_compress_blocks(filp, arg);
case F2FS_IOC_RELEASE_COMPRESS_BLOCKS:
return f2fs_release_compress_blocks(filp, arg);
case F2FS_IOC_RESERVE_COMPRESS_BLOCKS:
return f2fs_reserve_compress_blocks(filp, arg);
case F2FS_IOC_SEC_TRIM_FILE:
return f2fs_sec_trim_file(filp, arg);
case F2FS_IOC_GET_COMPRESS_OPTION:
return f2fs_ioc_get_compress_option(filp, arg);
case F2FS_IOC_SET_COMPRESS_OPTION:
return f2fs_ioc_set_compress_option(filp, arg);
case F2FS_IOC_DECOMPRESS_FILE:
return f2fs_ioc_decompress_file(filp, arg);
case F2FS_IOC_COMPRESS_FILE:
return f2fs_ioc_compress_file(filp, arg);
default:
return -ENOTTY;
}
}
long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(filp)))))
return -EIO;
if (!f2fs_is_checkpoint_ready(F2FS_I_SB(file_inode(filp))))
return -ENOSPC;
return __f2fs_ioctl(filp, cmd, arg);
}
static ssize_t f2fs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
int ret;
if (!f2fs_is_compress_backend_ready(inode))
return -EOPNOTSUPP;
ret = generic_file_read_iter(iocb, iter);
if (ret > 0)
f2fs_update_iostat(F2FS_I_SB(inode), APP_READ_IO, ret);
return ret;
}
static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
ssize_t ret;
if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) {
ret = -EIO;
goto out;
}
if (!f2fs_is_compress_backend_ready(inode)) {
ret = -EOPNOTSUPP;
goto out;
}
if (iocb->ki_flags & IOCB_NOWAIT) {
if (!inode_trylock(inode)) {
ret = -EAGAIN;
goto out;
}
} else {
inode_lock(inode);
}
if (unlikely(IS_IMMUTABLE(inode))) {
ret = -EPERM;
goto unlock;
}
ret = generic_write_checks(iocb, from);
if (ret > 0) {
bool preallocated = false;
size_t target_size = 0;
int err;
if (iov_iter_fault_in_readable(from, iov_iter_count(from)))
set_inode_flag(inode, FI_NO_PREALLOC);
if ((iocb->ki_flags & IOCB_NOWAIT)) {
if (!f2fs_overwrite_io(inode, iocb->ki_pos,
iov_iter_count(from)) ||
f2fs_has_inline_data(inode) ||
f2fs_force_buffered_io(inode, iocb, from)) {
clear_inode_flag(inode, FI_NO_PREALLOC);
inode_unlock(inode);
ret = -EAGAIN;
goto out;
}
goto write;
}
if (is_inode_flag_set(inode, FI_NO_PREALLOC))
goto write;
if (iocb->ki_flags & IOCB_DIRECT) {
/*
* Convert inline data for Direct I/O before entering
* f2fs_direct_IO().
*/
err = f2fs_convert_inline_inode(inode);
if (err)
goto out_err;
/*
* If force_buffere_io() is true, we have to allocate
* blocks all the time, since f2fs_direct_IO will fall
* back to buffered IO.
*/
if (!f2fs_force_buffered_io(inode, iocb, from) &&
allow_outplace_dio(inode, iocb, from))
goto write;
}
preallocated = true;
target_size = iocb->ki_pos + iov_iter_count(from);
err = f2fs_preallocate_blocks(iocb, from);
if (err) {
out_err:
clear_inode_flag(inode, FI_NO_PREALLOC);
inode_unlock(inode);
ret = err;
goto out;
}
write:
ret = __generic_file_write_iter(iocb, from);
clear_inode_flag(inode, FI_NO_PREALLOC);
/* if we couldn't write data, we should deallocate blocks. */
if (preallocated && i_size_read(inode) < target_size)
f2fs_truncate(inode);
if (ret > 0)
f2fs_update_iostat(F2FS_I_SB(inode), APP_WRITE_IO, ret);
}
unlock:
inode_unlock(inode);
out:
trace_f2fs_file_write_iter(inode, iocb->ki_pos,
iov_iter_count(from), ret);
if (ret > 0)
ret = generic_write_sync(iocb, ret);
return ret;
}
#ifdef CONFIG_COMPAT
struct compat_f2fs_gc_range {
u32 sync;
compat_u64 start;
compat_u64 len;
};
#define F2FS_IOC32_GARBAGE_COLLECT_RANGE _IOW(F2FS_IOCTL_MAGIC, 11,\
struct compat_f2fs_gc_range)
static int f2fs_compat_ioc_gc_range(struct file *file, unsigned long arg)
{
struct compat_f2fs_gc_range __user *urange;
struct f2fs_gc_range range;
int err;
urange = compat_ptr(arg);
err = get_user(range.sync, &urange->sync);
err |= get_user(range.start, &urange->start);
err |= get_user(range.len, &urange->len);
if (err)
return -EFAULT;
return __f2fs_ioc_gc_range(file, &range);
}
struct compat_f2fs_move_range {
u32 dst_fd;
compat_u64 pos_in;
compat_u64 pos_out;
compat_u64 len;
};
#define F2FS_IOC32_MOVE_RANGE _IOWR(F2FS_IOCTL_MAGIC, 9, \
struct compat_f2fs_move_range)
static int f2fs_compat_ioc_move_range(struct file *file, unsigned long arg)
{
struct compat_f2fs_move_range __user *urange;
struct f2fs_move_range range;
int err;
urange = compat_ptr(arg);
err = get_user(range.dst_fd, &urange->dst_fd);
err |= get_user(range.pos_in, &urange->pos_in);
err |= get_user(range.pos_out, &urange->pos_out);
err |= get_user(range.len, &urange->len);
if (err)
return -EFAULT;
return __f2fs_ioc_move_range(file, &range);
}
long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(file)))))
return -EIO;
if (!f2fs_is_checkpoint_ready(F2FS_I_SB(file_inode(file))))
return -ENOSPC;
switch (cmd) {
case FS_IOC32_GETFLAGS:
cmd = FS_IOC_GETFLAGS;
break;
case FS_IOC32_SETFLAGS:
cmd = FS_IOC_SETFLAGS;
break;
case FS_IOC32_GETVERSION:
cmd = FS_IOC_GETVERSION;
break;
case F2FS_IOC32_GARBAGE_COLLECT_RANGE:
return f2fs_compat_ioc_gc_range(file, arg);
case F2FS_IOC32_MOVE_RANGE:
return f2fs_compat_ioc_move_range(file, arg);
case F2FS_IOC_START_ATOMIC_WRITE:
case F2FS_IOC_COMMIT_ATOMIC_WRITE:
case F2FS_IOC_START_VOLATILE_WRITE:
case F2FS_IOC_RELEASE_VOLATILE_WRITE:
case F2FS_IOC_ABORT_VOLATILE_WRITE:
case F2FS_IOC_SHUTDOWN:
case FITRIM:
case FS_IOC_SET_ENCRYPTION_POLICY:
case FS_IOC_GET_ENCRYPTION_PWSALT:
case FS_IOC_GET_ENCRYPTION_POLICY:
case FS_IOC_GET_ENCRYPTION_POLICY_EX:
case FS_IOC_ADD_ENCRYPTION_KEY:
case FS_IOC_REMOVE_ENCRYPTION_KEY:
case FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS:
case FS_IOC_GET_ENCRYPTION_KEY_STATUS:
case FS_IOC_GET_ENCRYPTION_NONCE:
case F2FS_IOC_GARBAGE_COLLECT:
case F2FS_IOC_WRITE_CHECKPOINT:
case F2FS_IOC_DEFRAGMENT:
case F2FS_IOC_FLUSH_DEVICE:
case F2FS_IOC_GET_FEATURES:
case FS_IOC_FSGETXATTR:
case FS_IOC_FSSETXATTR:
case F2FS_IOC_GET_PIN_FILE:
case F2FS_IOC_SET_PIN_FILE:
case F2FS_IOC_PRECACHE_EXTENTS:
case F2FS_IOC_RESIZE_FS:
case FS_IOC_ENABLE_VERITY:
case FS_IOC_MEASURE_VERITY:
case FS_IOC_READ_VERITY_METADATA:
case FS_IOC_GETFSLABEL:
case FS_IOC_SETFSLABEL:
case F2FS_IOC_GET_COMPRESS_BLOCKS:
case F2FS_IOC_RELEASE_COMPRESS_BLOCKS:
case F2FS_IOC_RESERVE_COMPRESS_BLOCKS:
case F2FS_IOC_SEC_TRIM_FILE:
case F2FS_IOC_GET_COMPRESS_OPTION:
case F2FS_IOC_SET_COMPRESS_OPTION:
case F2FS_IOC_DECOMPRESS_FILE:
case F2FS_IOC_COMPRESS_FILE:
break;
default:
return -ENOIOCTLCMD;
}
return __f2fs_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
}
#endif
const struct file_operations f2fs_file_operations = {
.llseek = f2fs_llseek,
.read_iter = f2fs_file_read_iter,
.write_iter = f2fs_file_write_iter,
.open = f2fs_file_open,
.release = f2fs_release_file,
.mmap = f2fs_file_mmap,
.flush = f2fs_file_flush,
.fsync = f2fs_sync_file,
.fallocate = f2fs_fallocate,
.unlocked_ioctl = f2fs_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = f2fs_compat_ioctl,
#endif
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
};
Reference in New Issue View Git Blame Copy Permalink