7d6beb71da
-----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
...
1738 lines
45 KiB
C
1738 lines
45 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Simple file system for zoned block devices exposing zones as files.
|
|
*
|
|
* Copyright (C) 2019 Western Digital Corporation or its affiliates.
|
|
*/
|
|
#include <linux/module.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/magic.h>
|
|
#include <linux/iomap.h>
|
|
#include <linux/init.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/blkdev.h>
|
|
#include <linux/statfs.h>
|
|
#include <linux/writeback.h>
|
|
#include <linux/quotaops.h>
|
|
#include <linux/seq_file.h>
|
|
#include <linux/parser.h>
|
|
#include <linux/uio.h>
|
|
#include <linux/mman.h>
|
|
#include <linux/sched/mm.h>
|
|
#include <linux/crc32.h>
|
|
#include <linux/task_io_accounting_ops.h>
|
|
|
|
#include "zonefs.h"
|
|
|
|
#define CREATE_TRACE_POINTS
|
|
#include "trace.h"
|
|
|
|
static inline int zonefs_zone_mgmt(struct inode *inode,
|
|
enum req_opf op)
|
|
{
|
|
struct zonefs_inode_info *zi = ZONEFS_I(inode);
|
|
int ret;
|
|
|
|
lockdep_assert_held(&zi->i_truncate_mutex);
|
|
|
|
trace_zonefs_zone_mgmt(inode, op);
|
|
ret = blkdev_zone_mgmt(inode->i_sb->s_bdev, op, zi->i_zsector,
|
|
zi->i_zone_size >> SECTOR_SHIFT, GFP_NOFS);
|
|
if (ret) {
|
|
zonefs_err(inode->i_sb,
|
|
"Zone management operation %s at %llu failed %d\n",
|
|
blk_op_str(op), zi->i_zsector, ret);
|
|
return ret;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static inline void zonefs_i_size_write(struct inode *inode, loff_t isize)
|
|
{
|
|
struct zonefs_inode_info *zi = ZONEFS_I(inode);
|
|
|
|
i_size_write(inode, isize);
|
|
/*
|
|
* A full zone is no longer open/active and does not need
|
|
* explicit closing.
|
|
*/
|
|
if (isize >= zi->i_max_size)
|
|
zi->i_flags &= ~ZONEFS_ZONE_OPEN;
|
|
}
|
|
|
|
static int zonefs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
|
|
unsigned int flags, struct iomap *iomap,
|
|
struct iomap *srcmap)
|
|
{
|
|
struct zonefs_inode_info *zi = ZONEFS_I(inode);
|
|
struct super_block *sb = inode->i_sb;
|
|
loff_t isize;
|
|
|
|
/* All I/Os should always be within the file maximum size */
|
|
if (WARN_ON_ONCE(offset + length > zi->i_max_size))
|
|
return -EIO;
|
|
|
|
/*
|
|
* Sequential zones can only accept direct writes. This is already
|
|
* checked when writes are issued, so warn if we see a page writeback
|
|
* operation.
|
|
*/
|
|
if (WARN_ON_ONCE(zi->i_ztype == ZONEFS_ZTYPE_SEQ &&
|
|
(flags & IOMAP_WRITE) && !(flags & IOMAP_DIRECT)))
|
|
return -EIO;
|
|
|
|
/*
|
|
* For conventional zones, all blocks are always mapped. For sequential
|
|
* zones, all blocks after always mapped below the inode size (zone
|
|
* write pointer) and unwriten beyond.
|
|
*/
|
|
mutex_lock(&zi->i_truncate_mutex);
|
|
isize = i_size_read(inode);
|
|
if (offset >= isize)
|
|
iomap->type = IOMAP_UNWRITTEN;
|
|
else
|
|
iomap->type = IOMAP_MAPPED;
|
|
if (flags & IOMAP_WRITE)
|
|
length = zi->i_max_size - offset;
|
|
else
|
|
length = min(length, isize - offset);
|
|
mutex_unlock(&zi->i_truncate_mutex);
|
|
|
|
iomap->offset = ALIGN_DOWN(offset, sb->s_blocksize);
|
|
iomap->length = ALIGN(offset + length, sb->s_blocksize) - iomap->offset;
|
|
iomap->bdev = inode->i_sb->s_bdev;
|
|
iomap->addr = (zi->i_zsector << SECTOR_SHIFT) + iomap->offset;
|
|
|
|
trace_zonefs_iomap_begin(inode, iomap);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static const struct iomap_ops zonefs_iomap_ops = {
|
|
.iomap_begin = zonefs_iomap_begin,
|
|
};
|
|
|
|
static int zonefs_readpage(struct file *unused, struct page *page)
|
|
{
|
|
return iomap_readpage(page, &zonefs_iomap_ops);
|
|
}
|
|
|
|
static void zonefs_readahead(struct readahead_control *rac)
|
|
{
|
|
iomap_readahead(rac, &zonefs_iomap_ops);
|
|
}
|
|
|
|
/*
|
|
* Map blocks for page writeback. This is used only on conventional zone files,
|
|
* which implies that the page range can only be within the fixed inode size.
|
|
*/
|
|
static int zonefs_map_blocks(struct iomap_writepage_ctx *wpc,
|
|
struct inode *inode, loff_t offset)
|
|
{
|
|
struct zonefs_inode_info *zi = ZONEFS_I(inode);
|
|
|
|
if (WARN_ON_ONCE(zi->i_ztype != ZONEFS_ZTYPE_CNV))
|
|
return -EIO;
|
|
if (WARN_ON_ONCE(offset >= i_size_read(inode)))
|
|
return -EIO;
|
|
|
|
/* If the mapping is already OK, nothing needs to be done */
|
|
if (offset >= wpc->iomap.offset &&
|
|
offset < wpc->iomap.offset + wpc->iomap.length)
|
|
return 0;
|
|
|
|
return zonefs_iomap_begin(inode, offset, zi->i_max_size - offset,
|
|
IOMAP_WRITE, &wpc->iomap, NULL);
|
|
}
|
|
|
|
static const struct iomap_writeback_ops zonefs_writeback_ops = {
|
|
.map_blocks = zonefs_map_blocks,
|
|
};
|
|
|
|
static int zonefs_writepage(struct page *page, struct writeback_control *wbc)
|
|
{
|
|
struct iomap_writepage_ctx wpc = { };
|
|
|
|
return iomap_writepage(page, wbc, &wpc, &zonefs_writeback_ops);
|
|
}
|
|
|
|
static int zonefs_writepages(struct address_space *mapping,
|
|
struct writeback_control *wbc)
|
|
{
|
|
struct iomap_writepage_ctx wpc = { };
|
|
|
|
return iomap_writepages(mapping, wbc, &wpc, &zonefs_writeback_ops);
|
|
}
|
|
|
|
static const struct address_space_operations zonefs_file_aops = {
|
|
.readpage = zonefs_readpage,
|
|
.readahead = zonefs_readahead,
|
|
.writepage = zonefs_writepage,
|
|
.writepages = zonefs_writepages,
|
|
.set_page_dirty = iomap_set_page_dirty,
|
|
.releasepage = iomap_releasepage,
|
|
.invalidatepage = iomap_invalidatepage,
|
|
.migratepage = iomap_migrate_page,
|
|
.is_partially_uptodate = iomap_is_partially_uptodate,
|
|
.error_remove_page = generic_error_remove_page,
|
|
.direct_IO = noop_direct_IO,
|
|
};
|
|
|
|
static void zonefs_update_stats(struct inode *inode, loff_t new_isize)
|
|
{
|
|
struct super_block *sb = inode->i_sb;
|
|
struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
|
|
loff_t old_isize = i_size_read(inode);
|
|
loff_t nr_blocks;
|
|
|
|
if (new_isize == old_isize)
|
|
return;
|
|
|
|
spin_lock(&sbi->s_lock);
|
|
|
|
/*
|
|
* This may be called for an update after an IO error.
|
|
* So beware of the values seen.
|
|
*/
|
|
if (new_isize < old_isize) {
|
|
nr_blocks = (old_isize - new_isize) >> sb->s_blocksize_bits;
|
|
if (sbi->s_used_blocks > nr_blocks)
|
|
sbi->s_used_blocks -= nr_blocks;
|
|
else
|
|
sbi->s_used_blocks = 0;
|
|
} else {
|
|
sbi->s_used_blocks +=
|
|
(new_isize - old_isize) >> sb->s_blocksize_bits;
|
|
if (sbi->s_used_blocks > sbi->s_blocks)
|
|
sbi->s_used_blocks = sbi->s_blocks;
|
|
}
|
|
|
|
spin_unlock(&sbi->s_lock);
|
|
}
|
|
|
|
/*
|
|
* Check a zone condition and adjust its file inode access permissions for
|
|
* offline and readonly zones. Return the inode size corresponding to the
|
|
* amount of readable data in the zone.
|
|
*/
|
|
static loff_t zonefs_check_zone_condition(struct inode *inode,
|
|
struct blk_zone *zone, bool warn,
|
|
bool mount)
|
|
{
|
|
struct zonefs_inode_info *zi = ZONEFS_I(inode);
|
|
|
|
switch (zone->cond) {
|
|
case BLK_ZONE_COND_OFFLINE:
|
|
/*
|
|
* Dead zone: make the inode immutable, disable all accesses
|
|
* and set the file size to 0 (zone wp set to zone start).
|
|
*/
|
|
if (warn)
|
|
zonefs_warn(inode->i_sb, "inode %lu: offline zone\n",
|
|
inode->i_ino);
|
|
inode->i_flags |= S_IMMUTABLE;
|
|
inode->i_mode &= ~0777;
|
|
zone->wp = zone->start;
|
|
return 0;
|
|
case BLK_ZONE_COND_READONLY:
|
|
/*
|
|
* The write pointer of read-only zones is invalid. If such a
|
|
* zone is found during mount, the file size cannot be retrieved
|
|
* so we treat the zone as offline (mount == true case).
|
|
* Otherwise, keep the file size as it was when last updated
|
|
* so that the user can recover data. In both cases, writes are
|
|
* always disabled for the zone.
|
|
*/
|
|
if (warn)
|
|
zonefs_warn(inode->i_sb, "inode %lu: read-only zone\n",
|
|
inode->i_ino);
|
|
inode->i_flags |= S_IMMUTABLE;
|
|
if (mount) {
|
|
zone->cond = BLK_ZONE_COND_OFFLINE;
|
|
inode->i_mode &= ~0777;
|
|
zone->wp = zone->start;
|
|
return 0;
|
|
}
|
|
inode->i_mode &= ~0222;
|
|
return i_size_read(inode);
|
|
case BLK_ZONE_COND_FULL:
|
|
/* The write pointer of full zones is invalid. */
|
|
return zi->i_max_size;
|
|
default:
|
|
if (zi->i_ztype == ZONEFS_ZTYPE_CNV)
|
|
return zi->i_max_size;
|
|
return (zone->wp - zone->start) << SECTOR_SHIFT;
|
|
}
|
|
}
|
|
|
|
struct zonefs_ioerr_data {
|
|
struct inode *inode;
|
|
bool write;
|
|
};
|
|
|
|
static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
|
|
void *data)
|
|
{
|
|
struct zonefs_ioerr_data *err = data;
|
|
struct inode *inode = err->inode;
|
|
struct zonefs_inode_info *zi = ZONEFS_I(inode);
|
|
struct super_block *sb = inode->i_sb;
|
|
struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
|
|
loff_t isize, data_size;
|
|
|
|
/*
|
|
* Check the zone condition: if the zone is not "bad" (offline or
|
|
* read-only), read errors are simply signaled to the IO issuer as long
|
|
* as there is no inconsistency between the inode size and the amount of
|
|
* data writen in the zone (data_size).
|
|
*/
|
|
data_size = zonefs_check_zone_condition(inode, zone, true, false);
|
|
isize = i_size_read(inode);
|
|
if (zone->cond != BLK_ZONE_COND_OFFLINE &&
|
|
zone->cond != BLK_ZONE_COND_READONLY &&
|
|
!err->write && isize == data_size)
|
|
return 0;
|
|
|
|
/*
|
|
* At this point, we detected either a bad zone or an inconsistency
|
|
* between the inode size and the amount of data written in the zone.
|
|
* For the latter case, the cause may be a write IO error or an external
|
|
* action on the device. Two error patterns exist:
|
|
* 1) The inode size is lower than the amount of data in the zone:
|
|
* a write operation partially failed and data was writen at the end
|
|
* of the file. This can happen in the case of a large direct IO
|
|
* needing several BIOs and/or write requests to be processed.
|
|
* 2) The inode size is larger than the amount of data in the zone:
|
|
* this can happen with a deferred write error with the use of the
|
|
* device side write cache after getting successful write IO
|
|
* completions. Other possibilities are (a) an external corruption,
|
|
* e.g. an application reset the zone directly, or (b) the device
|
|
* has a serious problem (e.g. firmware bug).
|
|
*
|
|
* In all cases, warn about inode size inconsistency and handle the
|
|
* IO error according to the zone condition and to the mount options.
|
|
*/
|
|
if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && isize != data_size)
|
|
zonefs_warn(sb, "inode %lu: invalid size %lld (should be %lld)\n",
|
|
inode->i_ino, isize, data_size);
|
|
|
|
/*
|
|
* First handle bad zones signaled by hardware. The mount options
|
|
* errors=zone-ro and errors=zone-offline result in changing the
|
|
* zone condition to read-only and offline respectively, as if the
|
|
* condition was signaled by the hardware.
|
|
*/
|
|
if (zone->cond == BLK_ZONE_COND_OFFLINE ||
|
|
sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZOL) {
|
|
zonefs_warn(sb, "inode %lu: read/write access disabled\n",
|
|
inode->i_ino);
|
|
if (zone->cond != BLK_ZONE_COND_OFFLINE) {
|
|
zone->cond = BLK_ZONE_COND_OFFLINE;
|
|
data_size = zonefs_check_zone_condition(inode, zone,
|
|
false, false);
|
|
}
|
|
} else if (zone->cond == BLK_ZONE_COND_READONLY ||
|
|
sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZRO) {
|
|
zonefs_warn(sb, "inode %lu: write access disabled\n",
|
|
inode->i_ino);
|
|
if (zone->cond != BLK_ZONE_COND_READONLY) {
|
|
zone->cond = BLK_ZONE_COND_READONLY;
|
|
data_size = zonefs_check_zone_condition(inode, zone,
|
|
false, false);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* If the filesystem is mounted with the explicit-open mount option, we
|
|
* need to clear the ZONEFS_ZONE_OPEN flag if the zone transitioned to
|
|
* the read-only or offline condition, to avoid attempting an explicit
|
|
* close of the zone when the inode file is closed.
|
|
*/
|
|
if ((sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) &&
|
|
(zone->cond == BLK_ZONE_COND_OFFLINE ||
|
|
zone->cond == BLK_ZONE_COND_READONLY))
|
|
zi->i_flags &= ~ZONEFS_ZONE_OPEN;
|
|
|
|
/*
|
|
* If error=remount-ro was specified, any error result in remounting
|
|
* the volume as read-only.
|
|
*/
|
|
if ((sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_RO) && !sb_rdonly(sb)) {
|
|
zonefs_warn(sb, "remounting filesystem read-only\n");
|
|
sb->s_flags |= SB_RDONLY;
|
|
}
|
|
|
|
/*
|
|
* Update block usage stats and the inode size to prevent access to
|
|
* invalid data.
|
|
*/
|
|
zonefs_update_stats(inode, data_size);
|
|
zonefs_i_size_write(inode, data_size);
|
|
zi->i_wpoffset = data_size;
|
|
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* When an file IO error occurs, check the file zone to see if there is a change
|
|
* in the zone condition (e.g. offline or read-only). For a failed write to a
|
|
* sequential zone, the zone write pointer position must also be checked to
|
|
* eventually correct the file size and zonefs inode write pointer offset
|
|
* (which can be out of sync with the drive due to partial write failures).
|
|
*/
|
|
static void __zonefs_io_error(struct inode *inode, bool write)
|
|
{
|
|
struct zonefs_inode_info *zi = ZONEFS_I(inode);
|
|
struct super_block *sb = inode->i_sb;
|
|
struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
|
|
unsigned int noio_flag;
|
|
unsigned int nr_zones =
|
|
zi->i_zone_size >> (sbi->s_zone_sectors_shift + SECTOR_SHIFT);
|
|
struct zonefs_ioerr_data err = {
|
|
.inode = inode,
|
|
.write = write,
|
|
};
|
|
int ret;
|
|
|
|
/*
|
|
* Memory allocations in blkdev_report_zones() can trigger a memory
|
|
* reclaim which may in turn cause a recursion into zonefs as well as
|
|
* struct request allocations for the same device. The former case may
|
|
* end up in a deadlock on the inode truncate mutex, while the latter
|
|
* may prevent IO forward progress. Executing the report zones under
|
|
* the GFP_NOIO context avoids both problems.
|
|
*/
|
|
noio_flag = memalloc_noio_save();
|
|
ret = blkdev_report_zones(sb->s_bdev, zi->i_zsector, nr_zones,
|
|
zonefs_io_error_cb, &err);
|
|
if (ret != nr_zones)
|
|
zonefs_err(sb, "Get inode %lu zone information failed %d\n",
|
|
inode->i_ino, ret);
|
|
memalloc_noio_restore(noio_flag);
|
|
}
|
|
|
|
static void zonefs_io_error(struct inode *inode, bool write)
|
|
{
|
|
struct zonefs_inode_info *zi = ZONEFS_I(inode);
|
|
|
|
mutex_lock(&zi->i_truncate_mutex);
|
|
__zonefs_io_error(inode, write);
|
|
mutex_unlock(&zi->i_truncate_mutex);
|
|
}
|
|
|
|
static int zonefs_file_truncate(struct inode *inode, loff_t isize)
|
|
{
|
|
struct zonefs_inode_info *zi = ZONEFS_I(inode);
|
|
loff_t old_isize;
|
|
enum req_opf op;
|
|
int ret = 0;
|
|
|
|
/*
|
|
* Only sequential zone files can be truncated and truncation is allowed
|
|
* only down to a 0 size, which is equivalent to a zone reset, and to
|
|
* the maximum file size, which is equivalent to a zone finish.
|
|
*/
|
|
if (zi->i_ztype != ZONEFS_ZTYPE_SEQ)
|
|
return -EPERM;
|
|
|
|
if (!isize)
|
|
op = REQ_OP_ZONE_RESET;
|
|
else if (isize == zi->i_max_size)
|
|
op = REQ_OP_ZONE_FINISH;
|
|
else
|
|
return -EPERM;
|
|
|
|
inode_dio_wait(inode);
|
|
|
|
/* Serialize against page faults */
|
|
down_write(&zi->i_mmap_sem);
|
|
|
|
/* Serialize against zonefs_iomap_begin() */
|
|
mutex_lock(&zi->i_truncate_mutex);
|
|
|
|
old_isize = i_size_read(inode);
|
|
if (isize == old_isize)
|
|
goto unlock;
|
|
|
|
ret = zonefs_zone_mgmt(inode, op);
|
|
if (ret)
|
|
goto unlock;
|
|
|
|
/*
|
|
* If the mount option ZONEFS_MNTOPT_EXPLICIT_OPEN is set,
|
|
* take care of open zones.
|
|
*/
|
|
if (zi->i_flags & ZONEFS_ZONE_OPEN) {
|
|
/*
|
|
* Truncating a zone to EMPTY or FULL is the equivalent of
|
|
* closing the zone. For a truncation to 0, we need to
|
|
* re-open the zone to ensure new writes can be processed.
|
|
* For a truncation to the maximum file size, the zone is
|
|
* closed and writes cannot be accepted anymore, so clear
|
|
* the open flag.
|
|
*/
|
|
if (!isize)
|
|
ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_OPEN);
|
|
else
|
|
zi->i_flags &= ~ZONEFS_ZONE_OPEN;
|
|
}
|
|
|
|
zonefs_update_stats(inode, isize);
|
|
truncate_setsize(inode, isize);
|
|
zi->i_wpoffset = isize;
|
|
|
|
unlock:
|
|
mutex_unlock(&zi->i_truncate_mutex);
|
|
up_write(&zi->i_mmap_sem);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int zonefs_inode_setattr(struct user_namespace *mnt_userns,
|
|
struct dentry *dentry, struct iattr *iattr)
|
|
{
|
|
struct inode *inode = d_inode(dentry);
|
|
int ret;
|
|
|
|
if (unlikely(IS_IMMUTABLE(inode)))
|
|
return -EPERM;
|
|
|
|
ret = setattr_prepare(&init_user_ns, dentry, iattr);
|
|
if (ret)
|
|
return ret;
|
|
|
|
/*
|
|
* Since files and directories cannot be created nor deleted, do not
|
|
* allow setting any write attributes on the sub-directories grouping
|
|
* files by zone type.
|
|
*/
|
|
if ((iattr->ia_valid & ATTR_MODE) && S_ISDIR(inode->i_mode) &&
|
|
(iattr->ia_mode & 0222))
|
|
return -EPERM;
|
|
|
|
if (((iattr->ia_valid & ATTR_UID) &&
|
|
!uid_eq(iattr->ia_uid, inode->i_uid)) ||
|
|
((iattr->ia_valid & ATTR_GID) &&
|
|
!gid_eq(iattr->ia_gid, inode->i_gid))) {
|
|
ret = dquot_transfer(inode, iattr);
|
|
if (ret)
|
|
return ret;
|
|
}
|
|
|
|
if (iattr->ia_valid & ATTR_SIZE) {
|
|
ret = zonefs_file_truncate(inode, iattr->ia_size);
|
|
if (ret)
|
|
return ret;
|
|
}
|
|
|
|
setattr_copy(&init_user_ns, inode, iattr);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static const struct inode_operations zonefs_file_inode_operations = {
|
|
.setattr = zonefs_inode_setattr,
|
|
};
|
|
|
|
static int zonefs_file_fsync(struct file *file, loff_t start, loff_t end,
|
|
int datasync)
|
|
{
|
|
struct inode *inode = file_inode(file);
|
|
int ret = 0;
|
|
|
|
if (unlikely(IS_IMMUTABLE(inode)))
|
|
return -EPERM;
|
|
|
|
/*
|
|
* Since only direct writes are allowed in sequential files, page cache
|
|
* flush is needed only for conventional zone files.
|
|
*/
|
|
if (ZONEFS_I(inode)->i_ztype == ZONEFS_ZTYPE_CNV)
|
|
ret = file_write_and_wait_range(file, start, end);
|
|
if (!ret)
|
|
ret = blkdev_issue_flush(inode->i_sb->s_bdev);
|
|
|
|
if (ret)
|
|
zonefs_io_error(inode, true);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static vm_fault_t zonefs_filemap_fault(struct vm_fault *vmf)
|
|
{
|
|
struct zonefs_inode_info *zi = ZONEFS_I(file_inode(vmf->vma->vm_file));
|
|
vm_fault_t ret;
|
|
|
|
down_read(&zi->i_mmap_sem);
|
|
ret = filemap_fault(vmf);
|
|
up_read(&zi->i_mmap_sem);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static vm_fault_t zonefs_filemap_page_mkwrite(struct vm_fault *vmf)
|
|
{
|
|
struct inode *inode = file_inode(vmf->vma->vm_file);
|
|
struct zonefs_inode_info *zi = ZONEFS_I(inode);
|
|
vm_fault_t ret;
|
|
|
|
if (unlikely(IS_IMMUTABLE(inode)))
|
|
return VM_FAULT_SIGBUS;
|
|
|
|
/*
|
|
* Sanity check: only conventional zone files can have shared
|
|
* writeable mappings.
|
|
*/
|
|
if (WARN_ON_ONCE(zi->i_ztype != ZONEFS_ZTYPE_CNV))
|
|
return VM_FAULT_NOPAGE;
|
|
|
|
sb_start_pagefault(inode->i_sb);
|
|
file_update_time(vmf->vma->vm_file);
|
|
|
|
/* Serialize against truncates */
|
|
down_read(&zi->i_mmap_sem);
|
|
ret = iomap_page_mkwrite(vmf, &zonefs_iomap_ops);
|
|
up_read(&zi->i_mmap_sem);
|
|
|
|
sb_end_pagefault(inode->i_sb);
|
|
return ret;
|
|
}
|
|
|
|
static const struct vm_operations_struct zonefs_file_vm_ops = {
|
|
.fault = zonefs_filemap_fault,
|
|
.map_pages = filemap_map_pages,
|
|
.page_mkwrite = zonefs_filemap_page_mkwrite,
|
|
};
|
|
|
|
static int zonefs_file_mmap(struct file *file, struct vm_area_struct *vma)
|
|
{
|
|
/*
|
|
* Conventional zones accept random writes, so their files can support
|
|
* shared writable mappings. For sequential zone files, only read
|
|
* mappings are possible since there are no guarantees for write
|
|
* ordering between msync() and page cache writeback.
|
|
*/
|
|
if (ZONEFS_I(file_inode(file))->i_ztype == ZONEFS_ZTYPE_SEQ &&
|
|
(vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE))
|
|
return -EINVAL;
|
|
|
|
file_accessed(file);
|
|
vma->vm_ops = &zonefs_file_vm_ops;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static loff_t zonefs_file_llseek(struct file *file, loff_t offset, int whence)
|
|
{
|
|
loff_t isize = i_size_read(file_inode(file));
|
|
|
|
/*
|
|
* Seeks are limited to below the zone size for conventional zones
|
|
* and below the zone write pointer for sequential zones. In both
|
|
* cases, this limit is the inode size.
|
|
*/
|
|
return generic_file_llseek_size(file, offset, whence, isize, isize);
|
|
}
|
|
|
|
static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size,
|
|
int error, unsigned int flags)
|
|
{
|
|
struct inode *inode = file_inode(iocb->ki_filp);
|
|
struct zonefs_inode_info *zi = ZONEFS_I(inode);
|
|
|
|
if (error) {
|
|
zonefs_io_error(inode, true);
|
|
return error;
|
|
}
|
|
|
|
if (size && zi->i_ztype != ZONEFS_ZTYPE_CNV) {
|
|
/*
|
|
* Note that we may be seeing completions out of order,
|
|
* but that is not a problem since a write completed
|
|
* successfully necessarily means that all preceding writes
|
|
* were also successful. So we can safely increase the inode
|
|
* size to the write end location.
|
|
*/
|
|
mutex_lock(&zi->i_truncate_mutex);
|
|
if (i_size_read(inode) < iocb->ki_pos + size) {
|
|
zonefs_update_stats(inode, iocb->ki_pos + size);
|
|
zonefs_i_size_write(inode, iocb->ki_pos + size);
|
|
}
|
|
mutex_unlock(&zi->i_truncate_mutex);
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static const struct iomap_dio_ops zonefs_write_dio_ops = {
|
|
.end_io = zonefs_file_write_dio_end_io,
|
|
};
|
|
|
|
static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from)
|
|
{
|
|
struct inode *inode = file_inode(iocb->ki_filp);
|
|
struct zonefs_inode_info *zi = ZONEFS_I(inode);
|
|
struct block_device *bdev = inode->i_sb->s_bdev;
|
|
unsigned int max;
|
|
struct bio *bio;
|
|
ssize_t size;
|
|
int nr_pages;
|
|
ssize_t ret;
|
|
|
|
max = queue_max_zone_append_sectors(bdev_get_queue(bdev));
|
|
max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize);
|
|
iov_iter_truncate(from, max);
|
|
|
|
nr_pages = iov_iter_npages(from, BIO_MAX_PAGES);
|
|
if (!nr_pages)
|
|
return 0;
|
|
|
|
bio = bio_alloc(GFP_NOFS, nr_pages);
|
|
if (!bio)
|
|
return -ENOMEM;
|
|
|
|
bio_set_dev(bio, bdev);
|
|
bio->bi_iter.bi_sector = zi->i_zsector;
|
|
bio->bi_write_hint = iocb->ki_hint;
|
|
bio->bi_ioprio = iocb->ki_ioprio;
|
|
bio->bi_opf = REQ_OP_ZONE_APPEND | REQ_SYNC | REQ_IDLE;
|
|
if (iocb->ki_flags & IOCB_DSYNC)
|
|
bio->bi_opf |= REQ_FUA;
|
|
|
|
ret = bio_iov_iter_get_pages(bio, from);
|
|
if (unlikely(ret))
|
|
goto out_release;
|
|
|
|
size = bio->bi_iter.bi_size;
|
|
task_io_account_write(size);
|
|
|
|
if (iocb->ki_flags & IOCB_HIPRI)
|
|
bio_set_polled(bio, iocb);
|
|
|
|
ret = submit_bio_wait(bio);
|
|
|
|
zonefs_file_write_dio_end_io(iocb, size, ret, 0);
|
|
trace_zonefs_file_dio_append(inode, size, ret);
|
|
|
|
out_release:
|
|
bio_release_pages(bio, false);
|
|
bio_put(bio);
|
|
|
|
if (ret >= 0) {
|
|
iocb->ki_pos += size;
|
|
return size;
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Handle direct writes. For sequential zone files, this is the only possible
|
|
* write path. For these files, check that the user is issuing writes
|
|
* sequentially from the end of the file. This code assumes that the block layer
|
|
* delivers write requests to the device in sequential order. This is always the
|
|
* case if a block IO scheduler implementing the ELEVATOR_F_ZBD_SEQ_WRITE
|
|
* elevator feature is being used (e.g. mq-deadline). The block layer always
|
|
* automatically select such an elevator for zoned block devices during the
|
|
* device initialization.
|
|
*/
|
|
static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
|
|
{
|
|
struct inode *inode = file_inode(iocb->ki_filp);
|
|
struct zonefs_inode_info *zi = ZONEFS_I(inode);
|
|
struct super_block *sb = inode->i_sb;
|
|
bool sync = is_sync_kiocb(iocb);
|
|
bool append = false;
|
|
size_t count;
|
|
ssize_t ret;
|
|
|
|
/*
|
|
* For async direct IOs to sequential zone files, refuse IOCB_NOWAIT
|
|
* as this can cause write reordering (e.g. the first aio gets EAGAIN
|
|
* on the inode lock but the second goes through but is now unaligned).
|
|
*/
|
|
if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && !sync &&
|
|
(iocb->ki_flags & IOCB_NOWAIT))
|
|
return -EOPNOTSUPP;
|
|
|
|
if (iocb->ki_flags & IOCB_NOWAIT) {
|
|
if (!inode_trylock(inode))
|
|
return -EAGAIN;
|
|
} else {
|
|
inode_lock(inode);
|
|
}
|
|
|
|
ret = generic_write_checks(iocb, from);
|
|
if (ret <= 0)
|
|
goto inode_unlock;
|
|
|
|
iov_iter_truncate(from, zi->i_max_size - iocb->ki_pos);
|
|
count = iov_iter_count(from);
|
|
|
|
if ((iocb->ki_pos | count) & (sb->s_blocksize - 1)) {
|
|
ret = -EINVAL;
|
|
goto inode_unlock;
|
|
}
|
|
|
|
/* Enforce sequential writes (append only) in sequential zones */
|
|
if (zi->i_ztype == ZONEFS_ZTYPE_SEQ) {
|
|
mutex_lock(&zi->i_truncate_mutex);
|
|
if (iocb->ki_pos != zi->i_wpoffset) {
|
|
mutex_unlock(&zi->i_truncate_mutex);
|
|
ret = -EINVAL;
|
|
goto inode_unlock;
|
|
}
|
|
mutex_unlock(&zi->i_truncate_mutex);
|
|
append = sync;
|
|
}
|
|
|
|
if (append)
|
|
ret = zonefs_file_dio_append(iocb, from);
|
|
else
|
|
ret = iomap_dio_rw(iocb, from, &zonefs_iomap_ops,
|
|
&zonefs_write_dio_ops, 0);
|
|
if (zi->i_ztype == ZONEFS_ZTYPE_SEQ &&
|
|
(ret > 0 || ret == -EIOCBQUEUED)) {
|
|
if (ret > 0)
|
|
count = ret;
|
|
mutex_lock(&zi->i_truncate_mutex);
|
|
zi->i_wpoffset += count;
|
|
mutex_unlock(&zi->i_truncate_mutex);
|
|
}
|
|
|
|
inode_unlock:
|
|
inode_unlock(inode);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static ssize_t zonefs_file_buffered_write(struct kiocb *iocb,
|
|
struct iov_iter *from)
|
|
{
|
|
struct inode *inode = file_inode(iocb->ki_filp);
|
|
struct zonefs_inode_info *zi = ZONEFS_I(inode);
|
|
ssize_t ret;
|
|
|
|
/*
|
|
* Direct IO writes are mandatory for sequential zone files so that the
|
|
* write IO issuing order is preserved.
|
|
*/
|
|
if (zi->i_ztype != ZONEFS_ZTYPE_CNV)
|
|
return -EIO;
|
|
|
|
if (iocb->ki_flags & IOCB_NOWAIT) {
|
|
if (!inode_trylock(inode))
|
|
return -EAGAIN;
|
|
} else {
|
|
inode_lock(inode);
|
|
}
|
|
|
|
ret = generic_write_checks(iocb, from);
|
|
if (ret <= 0)
|
|
goto inode_unlock;
|
|
|
|
iov_iter_truncate(from, zi->i_max_size - iocb->ki_pos);
|
|
|
|
ret = iomap_file_buffered_write(iocb, from, &zonefs_iomap_ops);
|
|
if (ret > 0)
|
|
iocb->ki_pos += ret;
|
|
else if (ret == -EIO)
|
|
zonefs_io_error(inode, true);
|
|
|
|
inode_unlock:
|
|
inode_unlock(inode);
|
|
if (ret > 0)
|
|
ret = generic_write_sync(iocb, ret);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static ssize_t zonefs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
|
|
{
|
|
struct inode *inode = file_inode(iocb->ki_filp);
|
|
|
|
if (unlikely(IS_IMMUTABLE(inode)))
|
|
return -EPERM;
|
|
|
|
if (sb_rdonly(inode->i_sb))
|
|
return -EROFS;
|
|
|
|
/* Write operations beyond the zone size are not allowed */
|
|
if (iocb->ki_pos >= ZONEFS_I(inode)->i_max_size)
|
|
return -EFBIG;
|
|
|
|
if (iocb->ki_flags & IOCB_DIRECT) {
|
|
ssize_t ret = zonefs_file_dio_write(iocb, from);
|
|
if (ret != -ENOTBLK)
|
|
return ret;
|
|
}
|
|
|
|
return zonefs_file_buffered_write(iocb, from);
|
|
}
|
|
|
|
static int zonefs_file_read_dio_end_io(struct kiocb *iocb, ssize_t size,
|
|
int error, unsigned int flags)
|
|
{
|
|
if (error) {
|
|
zonefs_io_error(file_inode(iocb->ki_filp), false);
|
|
return error;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static const struct iomap_dio_ops zonefs_read_dio_ops = {
|
|
.end_io = zonefs_file_read_dio_end_io,
|
|
};
|
|
|
|
static ssize_t zonefs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
|
|
{
|
|
struct inode *inode = file_inode(iocb->ki_filp);
|
|
struct zonefs_inode_info *zi = ZONEFS_I(inode);
|
|
struct super_block *sb = inode->i_sb;
|
|
loff_t isize;
|
|
ssize_t ret;
|
|
|
|
/* Offline zones cannot be read */
|
|
if (unlikely(IS_IMMUTABLE(inode) && !(inode->i_mode & 0777)))
|
|
return -EPERM;
|
|
|
|
if (iocb->ki_pos >= zi->i_max_size)
|
|
return 0;
|
|
|
|
if (iocb->ki_flags & IOCB_NOWAIT) {
|
|
if (!inode_trylock_shared(inode))
|
|
return -EAGAIN;
|
|
} else {
|
|
inode_lock_shared(inode);
|
|
}
|
|
|
|
/* Limit read operations to written data */
|
|
mutex_lock(&zi->i_truncate_mutex);
|
|
isize = i_size_read(inode);
|
|
if (iocb->ki_pos >= isize) {
|
|
mutex_unlock(&zi->i_truncate_mutex);
|
|
ret = 0;
|
|
goto inode_unlock;
|
|
}
|
|
iov_iter_truncate(to, isize - iocb->ki_pos);
|
|
mutex_unlock(&zi->i_truncate_mutex);
|
|
|
|
if (iocb->ki_flags & IOCB_DIRECT) {
|
|
size_t count = iov_iter_count(to);
|
|
|
|
if ((iocb->ki_pos | count) & (sb->s_blocksize - 1)) {
|
|
ret = -EINVAL;
|
|
goto inode_unlock;
|
|
}
|
|
file_accessed(iocb->ki_filp);
|
|
ret = iomap_dio_rw(iocb, to, &zonefs_iomap_ops,
|
|
&zonefs_read_dio_ops, 0);
|
|
} else {
|
|
ret = generic_file_read_iter(iocb, to);
|
|
if (ret == -EIO)
|
|
zonefs_io_error(inode, false);
|
|
}
|
|
|
|
inode_unlock:
|
|
inode_unlock_shared(inode);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static inline bool zonefs_file_use_exp_open(struct inode *inode, struct file *file)
|
|
{
|
|
struct zonefs_inode_info *zi = ZONEFS_I(inode);
|
|
struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb);
|
|
|
|
if (!(sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN))
|
|
return false;
|
|
|
|
if (zi->i_ztype != ZONEFS_ZTYPE_SEQ)
|
|
return false;
|
|
|
|
if (!(file->f_mode & FMODE_WRITE))
|
|
return false;
|
|
|
|
return true;
|
|
}
|
|
|
|
static int zonefs_open_zone(struct inode *inode)
|
|
{
|
|
struct zonefs_inode_info *zi = ZONEFS_I(inode);
|
|
struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb);
|
|
int ret = 0;
|
|
|
|
mutex_lock(&zi->i_truncate_mutex);
|
|
|
|
zi->i_wr_refcnt++;
|
|
if (zi->i_wr_refcnt == 1) {
|
|
|
|
if (atomic_inc_return(&sbi->s_open_zones) > sbi->s_max_open_zones) {
|
|
atomic_dec(&sbi->s_open_zones);
|
|
ret = -EBUSY;
|
|
goto unlock;
|
|
}
|
|
|
|
if (i_size_read(inode) < zi->i_max_size) {
|
|
ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_OPEN);
|
|
if (ret) {
|
|
zi->i_wr_refcnt--;
|
|
atomic_dec(&sbi->s_open_zones);
|
|
goto unlock;
|
|
}
|
|
zi->i_flags |= ZONEFS_ZONE_OPEN;
|
|
}
|
|
}
|
|
|
|
unlock:
|
|
mutex_unlock(&zi->i_truncate_mutex);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int zonefs_file_open(struct inode *inode, struct file *file)
|
|
{
|
|
int ret;
|
|
|
|
ret = generic_file_open(inode, file);
|
|
if (ret)
|
|
return ret;
|
|
|
|
if (zonefs_file_use_exp_open(inode, file))
|
|
return zonefs_open_zone(inode);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void zonefs_close_zone(struct inode *inode)
|
|
{
|
|
struct zonefs_inode_info *zi = ZONEFS_I(inode);
|
|
int ret = 0;
|
|
|
|
mutex_lock(&zi->i_truncate_mutex);
|
|
zi->i_wr_refcnt--;
|
|
if (!zi->i_wr_refcnt) {
|
|
struct zonefs_sb_info *sbi = ZONEFS_SB(inode->i_sb);
|
|
struct super_block *sb = inode->i_sb;
|
|
|
|
/*
|
|
* If the file zone is full, it is not open anymore and we only
|
|
* need to decrement the open count.
|
|
*/
|
|
if (!(zi->i_flags & ZONEFS_ZONE_OPEN))
|
|
goto dec;
|
|
|
|
ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_CLOSE);
|
|
if (ret) {
|
|
__zonefs_io_error(inode, false);
|
|
/*
|
|
* Leaving zones explicitly open may lead to a state
|
|
* where most zones cannot be written (zone resources
|
|
* exhausted). So take preventive action by remounting
|
|
* read-only.
|
|
*/
|
|
if (zi->i_flags & ZONEFS_ZONE_OPEN &&
|
|
!(sb->s_flags & SB_RDONLY)) {
|
|
zonefs_warn(sb, "closing zone failed, remounting filesystem read-only\n");
|
|
sb->s_flags |= SB_RDONLY;
|
|
}
|
|
}
|
|
zi->i_flags &= ~ZONEFS_ZONE_OPEN;
|
|
dec:
|
|
atomic_dec(&sbi->s_open_zones);
|
|
}
|
|
mutex_unlock(&zi->i_truncate_mutex);
|
|
}
|
|
|
|
static int zonefs_file_release(struct inode *inode, struct file *file)
|
|
{
|
|
/*
|
|
* If we explicitly open a zone we must close it again as well, but the
|
|
* zone management operation can fail (either due to an IO error or as
|
|
* the zone has gone offline or read-only). Make sure we don't fail the
|
|
* close(2) for user-space.
|
|
*/
|
|
if (zonefs_file_use_exp_open(inode, file))
|
|
zonefs_close_zone(inode);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static const struct file_operations zonefs_file_operations = {
|
|
.open = zonefs_file_open,
|
|
.release = zonefs_file_release,
|
|
.fsync = zonefs_file_fsync,
|
|
.mmap = zonefs_file_mmap,
|
|
.llseek = zonefs_file_llseek,
|
|
.read_iter = zonefs_file_read_iter,
|
|
.write_iter = zonefs_file_write_iter,
|
|
.splice_read = generic_file_splice_read,
|
|
.splice_write = iter_file_splice_write,
|
|
.iopoll = iomap_dio_iopoll,
|
|
};
|
|
|
|
static struct kmem_cache *zonefs_inode_cachep;
|
|
|
|
static struct inode *zonefs_alloc_inode(struct super_block *sb)
|
|
{
|
|
struct zonefs_inode_info *zi;
|
|
|
|
zi = kmem_cache_alloc(zonefs_inode_cachep, GFP_KERNEL);
|
|
if (!zi)
|
|
return NULL;
|
|
|
|
inode_init_once(&zi->i_vnode);
|
|
mutex_init(&zi->i_truncate_mutex);
|
|
init_rwsem(&zi->i_mmap_sem);
|
|
zi->i_wr_refcnt = 0;
|
|
|
|
return &zi->i_vnode;
|
|
}
|
|
|
|
static void zonefs_free_inode(struct inode *inode)
|
|
{
|
|
kmem_cache_free(zonefs_inode_cachep, ZONEFS_I(inode));
|
|
}
|
|
|
|
/*
|
|
* File system stat.
|
|
*/
|
|
static int zonefs_statfs(struct dentry *dentry, struct kstatfs *buf)
|
|
{
|
|
struct super_block *sb = dentry->d_sb;
|
|
struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
|
|
enum zonefs_ztype t;
|
|
u64 fsid;
|
|
|
|
buf->f_type = ZONEFS_MAGIC;
|
|
buf->f_bsize = sb->s_blocksize;
|
|
buf->f_namelen = ZONEFS_NAME_MAX;
|
|
|
|
spin_lock(&sbi->s_lock);
|
|
|
|
buf->f_blocks = sbi->s_blocks;
|
|
if (WARN_ON(sbi->s_used_blocks > sbi->s_blocks))
|
|
buf->f_bfree = 0;
|
|
else
|
|
buf->f_bfree = buf->f_blocks - sbi->s_used_blocks;
|
|
buf->f_bavail = buf->f_bfree;
|
|
|
|
for (t = 0; t < ZONEFS_ZTYPE_MAX; t++) {
|
|
if (sbi->s_nr_files[t])
|
|
buf->f_files += sbi->s_nr_files[t] + 1;
|
|
}
|
|
buf->f_ffree = 0;
|
|
|
|
spin_unlock(&sbi->s_lock);
|
|
|
|
fsid = le64_to_cpup((void *)sbi->s_uuid.b) ^
|
|
le64_to_cpup((void *)sbi->s_uuid.b + sizeof(u64));
|
|
buf->f_fsid = u64_to_fsid(fsid);
|
|
|
|
return 0;
|
|
}
|
|
|
|
enum {
|
|
Opt_errors_ro, Opt_errors_zro, Opt_errors_zol, Opt_errors_repair,
|
|
Opt_explicit_open, Opt_err,
|
|
};
|
|
|
|
static const match_table_t tokens = {
|
|
{ Opt_errors_ro, "errors=remount-ro"},
|
|
{ Opt_errors_zro, "errors=zone-ro"},
|
|
{ Opt_errors_zol, "errors=zone-offline"},
|
|
{ Opt_errors_repair, "errors=repair"},
|
|
{ Opt_explicit_open, "explicit-open" },
|
|
{ Opt_err, NULL}
|
|
};
|
|
|
|
static int zonefs_parse_options(struct super_block *sb, char *options)
|
|
{
|
|
struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
|
|
substring_t args[MAX_OPT_ARGS];
|
|
char *p;
|
|
|
|
if (!options)
|
|
return 0;
|
|
|
|
while ((p = strsep(&options, ",")) != NULL) {
|
|
int token;
|
|
|
|
if (!*p)
|
|
continue;
|
|
|
|
token = match_token(p, tokens, args);
|
|
switch (token) {
|
|
case Opt_errors_ro:
|
|
sbi->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK;
|
|
sbi->s_mount_opts |= ZONEFS_MNTOPT_ERRORS_RO;
|
|
break;
|
|
case Opt_errors_zro:
|
|
sbi->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK;
|
|
sbi->s_mount_opts |= ZONEFS_MNTOPT_ERRORS_ZRO;
|
|
break;
|
|
case Opt_errors_zol:
|
|
sbi->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK;
|
|
sbi->s_mount_opts |= ZONEFS_MNTOPT_ERRORS_ZOL;
|
|
break;
|
|
case Opt_errors_repair:
|
|
sbi->s_mount_opts &= ~ZONEFS_MNTOPT_ERRORS_MASK;
|
|
sbi->s_mount_opts |= ZONEFS_MNTOPT_ERRORS_REPAIR;
|
|
break;
|
|
case Opt_explicit_open:
|
|
sbi->s_mount_opts |= ZONEFS_MNTOPT_EXPLICIT_OPEN;
|
|
break;
|
|
default:
|
|
return -EINVAL;
|
|
}
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int zonefs_show_options(struct seq_file *seq, struct dentry *root)
|
|
{
|
|
struct zonefs_sb_info *sbi = ZONEFS_SB(root->d_sb);
|
|
|
|
if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_RO)
|
|
seq_puts(seq, ",errors=remount-ro");
|
|
if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZRO)
|
|
seq_puts(seq, ",errors=zone-ro");
|
|
if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_ZOL)
|
|
seq_puts(seq, ",errors=zone-offline");
|
|
if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_REPAIR)
|
|
seq_puts(seq, ",errors=repair");
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int zonefs_remount(struct super_block *sb, int *flags, char *data)
|
|
{
|
|
sync_filesystem(sb);
|
|
|
|
return zonefs_parse_options(sb, data);
|
|
}
|
|
|
|
static const struct super_operations zonefs_sops = {
|
|
.alloc_inode = zonefs_alloc_inode,
|
|
.free_inode = zonefs_free_inode,
|
|
.statfs = zonefs_statfs,
|
|
.remount_fs = zonefs_remount,
|
|
.show_options = zonefs_show_options,
|
|
};
|
|
|
|
static const struct inode_operations zonefs_dir_inode_operations = {
|
|
.lookup = simple_lookup,
|
|
.setattr = zonefs_inode_setattr,
|
|
};
|
|
|
|
static void zonefs_init_dir_inode(struct inode *parent, struct inode *inode,
|
|
enum zonefs_ztype type)
|
|
{
|
|
struct super_block *sb = parent->i_sb;
|
|
|
|
inode->i_ino = blkdev_nr_zones(sb->s_bdev->bd_disk) + type + 1;
|
|
inode_init_owner(&init_user_ns, inode, parent, S_IFDIR | 0555);
|
|
inode->i_op = &zonefs_dir_inode_operations;
|
|
inode->i_fop = &simple_dir_operations;
|
|
set_nlink(inode, 2);
|
|
inc_nlink(parent);
|
|
}
|
|
|
|
static void zonefs_init_file_inode(struct inode *inode, struct blk_zone *zone,
|
|
enum zonefs_ztype type)
|
|
{
|
|
struct super_block *sb = inode->i_sb;
|
|
struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
|
|
struct zonefs_inode_info *zi = ZONEFS_I(inode);
|
|
|
|
inode->i_ino = zone->start >> sbi->s_zone_sectors_shift;
|
|
inode->i_mode = S_IFREG | sbi->s_perm;
|
|
|
|
zi->i_ztype = type;
|
|
zi->i_zsector = zone->start;
|
|
zi->i_zone_size = zone->len << SECTOR_SHIFT;
|
|
|
|
zi->i_max_size = min_t(loff_t, MAX_LFS_FILESIZE,
|
|
zone->capacity << SECTOR_SHIFT);
|
|
zi->i_wpoffset = zonefs_check_zone_condition(inode, zone, true, true);
|
|
|
|
inode->i_uid = sbi->s_uid;
|
|
inode->i_gid = sbi->s_gid;
|
|
inode->i_size = zi->i_wpoffset;
|
|
inode->i_blocks = zi->i_max_size >> SECTOR_SHIFT;
|
|
|
|
inode->i_op = &zonefs_file_inode_operations;
|
|
inode->i_fop = &zonefs_file_operations;
|
|
inode->i_mapping->a_ops = &zonefs_file_aops;
|
|
|
|
sb->s_maxbytes = max(zi->i_max_size, sb->s_maxbytes);
|
|
sbi->s_blocks += zi->i_max_size >> sb->s_blocksize_bits;
|
|
sbi->s_used_blocks += zi->i_wpoffset >> sb->s_blocksize_bits;
|
|
}
|
|
|
|
static struct dentry *zonefs_create_inode(struct dentry *parent,
|
|
const char *name, struct blk_zone *zone,
|
|
enum zonefs_ztype type)
|
|
{
|
|
struct inode *dir = d_inode(parent);
|
|
struct dentry *dentry;
|
|
struct inode *inode;
|
|
|
|
dentry = d_alloc_name(parent, name);
|
|
if (!dentry)
|
|
return NULL;
|
|
|
|
inode = new_inode(parent->d_sb);
|
|
if (!inode)
|
|
goto dput;
|
|
|
|
inode->i_ctime = inode->i_mtime = inode->i_atime = dir->i_ctime;
|
|
if (zone)
|
|
zonefs_init_file_inode(inode, zone, type);
|
|
else
|
|
zonefs_init_dir_inode(dir, inode, type);
|
|
d_add(dentry, inode);
|
|
dir->i_size++;
|
|
|
|
return dentry;
|
|
|
|
dput:
|
|
dput(dentry);
|
|
|
|
return NULL;
|
|
}
|
|
|
|
struct zonefs_zone_data {
|
|
struct super_block *sb;
|
|
unsigned int nr_zones[ZONEFS_ZTYPE_MAX];
|
|
struct blk_zone *zones;
|
|
};
|
|
|
|
/*
|
|
* Create a zone group and populate it with zone files.
|
|
*/
|
|
static int zonefs_create_zgroup(struct zonefs_zone_data *zd,
|
|
enum zonefs_ztype type)
|
|
{
|
|
struct super_block *sb = zd->sb;
|
|
struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
|
|
struct blk_zone *zone, *next, *end;
|
|
const char *zgroup_name;
|
|
char *file_name;
|
|
struct dentry *dir;
|
|
unsigned int n = 0;
|
|
int ret;
|
|
|
|
/* If the group is empty, there is nothing to do */
|
|
if (!zd->nr_zones[type])
|
|
return 0;
|
|
|
|
file_name = kmalloc(ZONEFS_NAME_MAX, GFP_KERNEL);
|
|
if (!file_name)
|
|
return -ENOMEM;
|
|
|
|
if (type == ZONEFS_ZTYPE_CNV)
|
|
zgroup_name = "cnv";
|
|
else
|
|
zgroup_name = "seq";
|
|
|
|
dir = zonefs_create_inode(sb->s_root, zgroup_name, NULL, type);
|
|
if (!dir) {
|
|
ret = -ENOMEM;
|
|
goto free;
|
|
}
|
|
|
|
/*
|
|
* The first zone contains the super block: skip it.
|
|
*/
|
|
end = zd->zones + blkdev_nr_zones(sb->s_bdev->bd_disk);
|
|
for (zone = &zd->zones[1]; zone < end; zone = next) {
|
|
|
|
next = zone + 1;
|
|
if (zonefs_zone_type(zone) != type)
|
|
continue;
|
|
|
|
/*
|
|
* For conventional zones, contiguous zones can be aggregated
|
|
* together to form larger files. Note that this overwrites the
|
|
* length of the first zone of the set of contiguous zones
|
|
* aggregated together. If one offline or read-only zone is
|
|
* found, assume that all zones aggregated have the same
|
|
* condition.
|
|
*/
|
|
if (type == ZONEFS_ZTYPE_CNV &&
|
|
(sbi->s_features & ZONEFS_F_AGGRCNV)) {
|
|
for (; next < end; next++) {
|
|
if (zonefs_zone_type(next) != type)
|
|
break;
|
|
zone->len += next->len;
|
|
zone->capacity += next->capacity;
|
|
if (next->cond == BLK_ZONE_COND_READONLY &&
|
|
zone->cond != BLK_ZONE_COND_OFFLINE)
|
|
zone->cond = BLK_ZONE_COND_READONLY;
|
|
else if (next->cond == BLK_ZONE_COND_OFFLINE)
|
|
zone->cond = BLK_ZONE_COND_OFFLINE;
|
|
}
|
|
if (zone->capacity != zone->len) {
|
|
zonefs_err(sb, "Invalid conventional zone capacity\n");
|
|
ret = -EINVAL;
|
|
goto free;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Use the file number within its group as file name.
|
|
*/
|
|
snprintf(file_name, ZONEFS_NAME_MAX - 1, "%u", n);
|
|
if (!zonefs_create_inode(dir, file_name, zone, type)) {
|
|
ret = -ENOMEM;
|
|
goto free;
|
|
}
|
|
|
|
n++;
|
|
}
|
|
|
|
zonefs_info(sb, "Zone group \"%s\" has %u file%s\n",
|
|
zgroup_name, n, n > 1 ? "s" : "");
|
|
|
|
sbi->s_nr_files[type] = n;
|
|
ret = 0;
|
|
|
|
free:
|
|
kfree(file_name);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int zonefs_get_zone_info_cb(struct blk_zone *zone, unsigned int idx,
|
|
void *data)
|
|
{
|
|
struct zonefs_zone_data *zd = data;
|
|
|
|
/*
|
|
* Count the number of usable zones: the first zone at index 0 contains
|
|
* the super block and is ignored.
|
|
*/
|
|
switch (zone->type) {
|
|
case BLK_ZONE_TYPE_CONVENTIONAL:
|
|
zone->wp = zone->start + zone->len;
|
|
if (idx)
|
|
zd->nr_zones[ZONEFS_ZTYPE_CNV]++;
|
|
break;
|
|
case BLK_ZONE_TYPE_SEQWRITE_REQ:
|
|
case BLK_ZONE_TYPE_SEQWRITE_PREF:
|
|
if (idx)
|
|
zd->nr_zones[ZONEFS_ZTYPE_SEQ]++;
|
|
break;
|
|
default:
|
|
zonefs_err(zd->sb, "Unsupported zone type 0x%x\n",
|
|
zone->type);
|
|
return -EIO;
|
|
}
|
|
|
|
memcpy(&zd->zones[idx], zone, sizeof(struct blk_zone));
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int zonefs_get_zone_info(struct zonefs_zone_data *zd)
|
|
{
|
|
struct block_device *bdev = zd->sb->s_bdev;
|
|
int ret;
|
|
|
|
zd->zones = kvcalloc(blkdev_nr_zones(bdev->bd_disk),
|
|
sizeof(struct blk_zone), GFP_KERNEL);
|
|
if (!zd->zones)
|
|
return -ENOMEM;
|
|
|
|
/* Get zones information from the device */
|
|
ret = blkdev_report_zones(bdev, 0, BLK_ALL_ZONES,
|
|
zonefs_get_zone_info_cb, zd);
|
|
if (ret < 0) {
|
|
zonefs_err(zd->sb, "Zone report failed %d\n", ret);
|
|
return ret;
|
|
}
|
|
|
|
if (ret != blkdev_nr_zones(bdev->bd_disk)) {
|
|
zonefs_err(zd->sb, "Invalid zone report (%d/%u zones)\n",
|
|
ret, blkdev_nr_zones(bdev->bd_disk));
|
|
return -EIO;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static inline void zonefs_cleanup_zone_info(struct zonefs_zone_data *zd)
|
|
{
|
|
kvfree(zd->zones);
|
|
}
|
|
|
|
/*
|
|
* Read super block information from the device.
|
|
*/
|
|
static int zonefs_read_super(struct super_block *sb)
|
|
{
|
|
struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
|
|
struct zonefs_super *super;
|
|
u32 crc, stored_crc;
|
|
struct page *page;
|
|
struct bio_vec bio_vec;
|
|
struct bio bio;
|
|
int ret;
|
|
|
|
page = alloc_page(GFP_KERNEL);
|
|
if (!page)
|
|
return -ENOMEM;
|
|
|
|
bio_init(&bio, &bio_vec, 1);
|
|
bio.bi_iter.bi_sector = 0;
|
|
bio.bi_opf = REQ_OP_READ;
|
|
bio_set_dev(&bio, sb->s_bdev);
|
|
bio_add_page(&bio, page, PAGE_SIZE, 0);
|
|
|
|
ret = submit_bio_wait(&bio);
|
|
if (ret)
|
|
goto free_page;
|
|
|
|
super = kmap(page);
|
|
|
|
ret = -EINVAL;
|
|
if (le32_to_cpu(super->s_magic) != ZONEFS_MAGIC)
|
|
goto unmap;
|
|
|
|
stored_crc = le32_to_cpu(super->s_crc);
|
|
super->s_crc = 0;
|
|
crc = crc32(~0U, (unsigned char *)super, sizeof(struct zonefs_super));
|
|
if (crc != stored_crc) {
|
|
zonefs_err(sb, "Invalid checksum (Expected 0x%08x, got 0x%08x)",
|
|
crc, stored_crc);
|
|
goto unmap;
|
|
}
|
|
|
|
sbi->s_features = le64_to_cpu(super->s_features);
|
|
if (sbi->s_features & ~ZONEFS_F_DEFINED_FEATURES) {
|
|
zonefs_err(sb, "Unknown features set 0x%llx\n",
|
|
sbi->s_features);
|
|
goto unmap;
|
|
}
|
|
|
|
if (sbi->s_features & ZONEFS_F_UID) {
|
|
sbi->s_uid = make_kuid(current_user_ns(),
|
|
le32_to_cpu(super->s_uid));
|
|
if (!uid_valid(sbi->s_uid)) {
|
|
zonefs_err(sb, "Invalid UID feature\n");
|
|
goto unmap;
|
|
}
|
|
}
|
|
|
|
if (sbi->s_features & ZONEFS_F_GID) {
|
|
sbi->s_gid = make_kgid(current_user_ns(),
|
|
le32_to_cpu(super->s_gid));
|
|
if (!gid_valid(sbi->s_gid)) {
|
|
zonefs_err(sb, "Invalid GID feature\n");
|
|
goto unmap;
|
|
}
|
|
}
|
|
|
|
if (sbi->s_features & ZONEFS_F_PERM)
|
|
sbi->s_perm = le32_to_cpu(super->s_perm);
|
|
|
|
if (memchr_inv(super->s_reserved, 0, sizeof(super->s_reserved))) {
|
|
zonefs_err(sb, "Reserved area is being used\n");
|
|
goto unmap;
|
|
}
|
|
|
|
import_uuid(&sbi->s_uuid, super->s_uuid);
|
|
ret = 0;
|
|
|
|
unmap:
|
|
kunmap(page);
|
|
free_page:
|
|
__free_page(page);
|
|
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Check that the device is zoned. If it is, get the list of zones and create
|
|
* sub-directories and files according to the device zone configuration and
|
|
* format options.
|
|
*/
|
|
static int zonefs_fill_super(struct super_block *sb, void *data, int silent)
|
|
{
|
|
struct zonefs_zone_data zd;
|
|
struct zonefs_sb_info *sbi;
|
|
struct inode *inode;
|
|
enum zonefs_ztype t;
|
|
int ret;
|
|
|
|
if (!bdev_is_zoned(sb->s_bdev)) {
|
|
zonefs_err(sb, "Not a zoned block device\n");
|
|
return -EINVAL;
|
|
}
|
|
|
|
/*
|
|
* Initialize super block information: the maximum file size is updated
|
|
* when the zone files are created so that the format option
|
|
* ZONEFS_F_AGGRCNV which increases the maximum file size of a file
|
|
* beyond the zone size is taken into account.
|
|
*/
|
|
sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
|
|
if (!sbi)
|
|
return -ENOMEM;
|
|
|
|
spin_lock_init(&sbi->s_lock);
|
|
sb->s_fs_info = sbi;
|
|
sb->s_magic = ZONEFS_MAGIC;
|
|
sb->s_maxbytes = 0;
|
|
sb->s_op = &zonefs_sops;
|
|
sb->s_time_gran = 1;
|
|
|
|
/*
|
|
* The block size is set to the device zone write granularity to ensure
|
|
* that write operations are always aligned according to the device
|
|
* interface constraints.
|
|
*/
|
|
sb_set_blocksize(sb, bdev_zone_write_granularity(sb->s_bdev));
|
|
sbi->s_zone_sectors_shift = ilog2(bdev_zone_sectors(sb->s_bdev));
|
|
sbi->s_uid = GLOBAL_ROOT_UID;
|
|
sbi->s_gid = GLOBAL_ROOT_GID;
|
|
sbi->s_perm = 0640;
|
|
sbi->s_mount_opts = ZONEFS_MNTOPT_ERRORS_RO;
|
|
sbi->s_max_open_zones = bdev_max_open_zones(sb->s_bdev);
|
|
atomic_set(&sbi->s_open_zones, 0);
|
|
if (!sbi->s_max_open_zones &&
|
|
sbi->s_mount_opts & ZONEFS_MNTOPT_EXPLICIT_OPEN) {
|
|
zonefs_info(sb, "No open zones limit. Ignoring explicit_open mount option\n");
|
|
sbi->s_mount_opts &= ~ZONEFS_MNTOPT_EXPLICIT_OPEN;
|
|
}
|
|
|
|
ret = zonefs_read_super(sb);
|
|
if (ret)
|
|
return ret;
|
|
|
|
ret = zonefs_parse_options(sb, data);
|
|
if (ret)
|
|
return ret;
|
|
|
|
memset(&zd, 0, sizeof(struct zonefs_zone_data));
|
|
zd.sb = sb;
|
|
ret = zonefs_get_zone_info(&zd);
|
|
if (ret)
|
|
goto cleanup;
|
|
|
|
zonefs_info(sb, "Mounting %u zones",
|
|
blkdev_nr_zones(sb->s_bdev->bd_disk));
|
|
|
|
/* Create root directory inode */
|
|
ret = -ENOMEM;
|
|
inode = new_inode(sb);
|
|
if (!inode)
|
|
goto cleanup;
|
|
|
|
inode->i_ino = blkdev_nr_zones(sb->s_bdev->bd_disk);
|
|
inode->i_mode = S_IFDIR | 0555;
|
|
inode->i_ctime = inode->i_mtime = inode->i_atime = current_time(inode);
|
|
inode->i_op = &zonefs_dir_inode_operations;
|
|
inode->i_fop = &simple_dir_operations;
|
|
set_nlink(inode, 2);
|
|
|
|
sb->s_root = d_make_root(inode);
|
|
if (!sb->s_root)
|
|
goto cleanup;
|
|
|
|
/* Create and populate files in zone groups directories */
|
|
for (t = 0; t < ZONEFS_ZTYPE_MAX; t++) {
|
|
ret = zonefs_create_zgroup(&zd, t);
|
|
if (ret)
|
|
break;
|
|
}
|
|
|
|
cleanup:
|
|
zonefs_cleanup_zone_info(&zd);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static struct dentry *zonefs_mount(struct file_system_type *fs_type,
|
|
int flags, const char *dev_name, void *data)
|
|
{
|
|
return mount_bdev(fs_type, flags, dev_name, data, zonefs_fill_super);
|
|
}
|
|
|
|
static void zonefs_kill_super(struct super_block *sb)
|
|
{
|
|
struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
|
|
|
|
if (sb->s_root)
|
|
d_genocide(sb->s_root);
|
|
kill_block_super(sb);
|
|
kfree(sbi);
|
|
}
|
|
|
|
/*
|
|
* File system definition and registration.
|
|
*/
|
|
static struct file_system_type zonefs_type = {
|
|
.owner = THIS_MODULE,
|
|
.name = "zonefs",
|
|
.mount = zonefs_mount,
|
|
.kill_sb = zonefs_kill_super,
|
|
.fs_flags = FS_REQUIRES_DEV,
|
|
};
|
|
|
|
static int __init zonefs_init_inodecache(void)
|
|
{
|
|
zonefs_inode_cachep = kmem_cache_create("zonefs_inode_cache",
|
|
sizeof(struct zonefs_inode_info), 0,
|
|
(SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD | SLAB_ACCOUNT),
|
|
NULL);
|
|
if (zonefs_inode_cachep == NULL)
|
|
return -ENOMEM;
|
|
return 0;
|
|
}
|
|
|
|
static void zonefs_destroy_inodecache(void)
|
|
{
|
|
/*
|
|
* Make sure all delayed rcu free inodes are flushed before we
|
|
* destroy the inode cache.
|
|
*/
|
|
rcu_barrier();
|
|
kmem_cache_destroy(zonefs_inode_cachep);
|
|
}
|
|
|
|
static int __init zonefs_init(void)
|
|
{
|
|
int ret;
|
|
|
|
BUILD_BUG_ON(sizeof(struct zonefs_super) != ZONEFS_SUPER_SIZE);
|
|
|
|
ret = zonefs_init_inodecache();
|
|
if (ret)
|
|
return ret;
|
|
|
|
ret = register_filesystem(&zonefs_type);
|
|
if (ret) {
|
|
zonefs_destroy_inodecache();
|
|
return ret;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void __exit zonefs_exit(void)
|
|
{
|
|
zonefs_destroy_inodecache();
|
|
unregister_filesystem(&zonefs_type);
|
|
}
|
|
|
|
MODULE_AUTHOR("Damien Le Moal");
|
|
MODULE_DESCRIPTION("Zone file system for zoned block devices");
|
|
MODULE_LICENSE("GPL");
|
|
module_init(zonefs_init);
|
|
module_exit(zonefs_exit);
|