WSL2-Linux-Kernel/fs/jfs/file.c

154 строки
3.8 KiB
C
Исходник Обычный вид История

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright (C) International Business Machines Corp., 2000-2002
* Portions Copyright (C) Christoph Hellwig, 2001-2002
*/
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/posix_acl.h>
#include <linux/quotaops.h>
#include "jfs_incore.h"
#include "jfs_inode.h"
#include "jfs_dmap.h"
#include "jfs_txnmgr.h"
#include "jfs_xattr.h"
#include "jfs_acl.h"
#include "jfs_debug.h"
int jfs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
struct inode *inode = file->f_mapping->host;
int rc = 0;
rc = file_write_and_wait_range(file, start, end);
if (rc)
return rc;
inode_lock(inode);
if (!(inode->i_state & I_DIRTY_ALL) ||
(datasync && !(inode->i_state & I_DIRTY_DATASYNC))) {
/* Make sure committed changes hit the disk */
jfs_flush_journal(JFS_SBI(inode->i_sb)->log, 1);
inode_unlock(inode);
return rc;
}
rc |= jfs_commit_inode(inode, 1);
inode_unlock(inode);
return rc ? -EIO : 0;
}
static int jfs_open(struct inode *inode, struct file *file)
{
int rc;
if ((rc = dquot_file_open(inode, file)))
return rc;
/*
* We attempt to allow only one "active" file open per aggregate
* group. Otherwise, appending to files in parallel can cause
* fragmentation within the files.
*
* If the file is empty, it was probably just created and going
* to be written to. If it has a size, we'll hold off until the
* file is actually grown.
*/
if (S_ISREG(inode->i_mode) && file->f_mode & FMODE_WRITE &&
(inode->i_size == 0)) {
struct jfs_inode_info *ji = JFS_IP(inode);
spin_lock_irq(&ji->ag_lock);
if (ji->active_ag == -1) {
struct jfs_sb_info *jfs_sb = JFS_SBI(inode->i_sb);
ji->active_ag = BLKTOAG(addressPXD(&ji->ixpxd), jfs_sb);
atomic_inc(&jfs_sb->bmap->db_active[ji->active_ag]);
}
spin_unlock_irq(&ji->ag_lock);
}
return 0;
}
static int jfs_release(struct inode *inode, struct file *file)
{
struct jfs_inode_info *ji = JFS_IP(inode);
spin_lock_irq(&ji->ag_lock);
if (ji->active_ag != -1) {
struct bmap *bmap = JFS_SBI(inode->i_sb)->bmap;
atomic_dec(&bmap->db_active[ji->active_ag]);
ji->active_ag = -1;
}
spin_unlock_irq(&ji->ag_lock);
return 0;
}
int jfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
struct iattr *iattr)
{
struct inode *inode = d_inode(dentry);
int rc;
rc = setattr_prepare(&init_user_ns, dentry, iattr);
if (rc)
return rc;
attr: port attribute changes to new types Now that we introduced new infrastructure to increase the type safety for filesystems supporting idmapped mounts port the first part of the vfs over to them. This ports the attribute changes codepaths to rely on the new better helpers using a dedicated type. Before this change we used to take a shortcut and place the actual values that would be written to inode->i_{g,u}id into struct iattr. This had the advantage that we moved idmappings mostly out of the picture early on but it made reasoning about changes more difficult than it should be. The filesystem was never explicitly told that it dealt with an idmapped mount. The transition to the value that needed to be stored in inode->i_{g,u}id appeared way too early and increased the probability of bugs in various codepaths. We know place the same value in struct iattr no matter if this is an idmapped mount or not. The vfs will only deal with type safe vfs{g,u}id_t. This makes it massively safer to perform permission checks as the type will tell us what checks we need to perform and what helpers we need to use. Fileystems raising FS_ALLOW_IDMAP can't simply write ia_vfs{g,u}id to inode->i_{g,u}id since they are different types. Instead they need to use the dedicated vfs{g,u}id_to_k{g,u}id() helpers that map the vfs{g,u}id into the filesystem. The other nice effect is that filesystems like overlayfs don't need to care about idmappings explicitly anymore and can simply set up struct iattr accordingly directly. Link: https://lore.kernel.org/lkml/CAHk-=win6+ahs1EwLkcq8apqLi_1wXFWbrPf340zYEhObpz4jA@mail.gmail.com [1] Link: https://lore.kernel.org/r/20220621141454.2914719-9-brauner@kernel.org Cc: Seth Forshee <sforshee@digitalocean.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Aleksa Sarai <cyphar@cyphar.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Al Viro <viro@zeniv.linux.org.uk> CC: linux-fsdevel@vger.kernel.org Reviewed-by: Seth Forshee <sforshee@digitalocean.com> Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
2022-06-21 17:14:54 +03:00
if (is_quota_modification(mnt_userns, inode, iattr)) {
rc = dquot_initialize(inode);
if (rc)
return rc;
}
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))) {
attr: port attribute changes to new types Now that we introduced new infrastructure to increase the type safety for filesystems supporting idmapped mounts port the first part of the vfs over to them. This ports the attribute changes codepaths to rely on the new better helpers using a dedicated type. Before this change we used to take a shortcut and place the actual values that would be written to inode->i_{g,u}id into struct iattr. This had the advantage that we moved idmappings mostly out of the picture early on but it made reasoning about changes more difficult than it should be. The filesystem was never explicitly told that it dealt with an idmapped mount. The transition to the value that needed to be stored in inode->i_{g,u}id appeared way too early and increased the probability of bugs in various codepaths. We know place the same value in struct iattr no matter if this is an idmapped mount or not. The vfs will only deal with type safe vfs{g,u}id_t. This makes it massively safer to perform permission checks as the type will tell us what checks we need to perform and what helpers we need to use. Fileystems raising FS_ALLOW_IDMAP can't simply write ia_vfs{g,u}id to inode->i_{g,u}id since they are different types. Instead they need to use the dedicated vfs{g,u}id_to_k{g,u}id() helpers that map the vfs{g,u}id into the filesystem. The other nice effect is that filesystems like overlayfs don't need to care about idmappings explicitly anymore and can simply set up struct iattr accordingly directly. Link: https://lore.kernel.org/lkml/CAHk-=win6+ahs1EwLkcq8apqLi_1wXFWbrPf340zYEhObpz4jA@mail.gmail.com [1] Link: https://lore.kernel.org/r/20220621141454.2914719-9-brauner@kernel.org Cc: Seth Forshee <sforshee@digitalocean.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Aleksa Sarai <cyphar@cyphar.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Al Viro <viro@zeniv.linux.org.uk> CC: linux-fsdevel@vger.kernel.org Reviewed-by: Seth Forshee <sforshee@digitalocean.com> Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
2022-06-21 17:14:54 +03:00
rc = dquot_transfer(mnt_userns, inode, iattr);
if (rc)
return rc;
}
if ((iattr->ia_valid & ATTR_SIZE) &&
iattr->ia_size != i_size_read(inode)) {
inode_dio_wait(inode);
rc = inode_newsize_ok(inode, iattr->ia_size);
if (rc)
return rc;
truncate_setsize(inode, iattr->ia_size);
jfs_truncate(inode);
}
setattr_copy(&init_user_ns, inode, iattr);
mark_inode_dirty(inode);
if (iattr->ia_valid & ATTR_MODE)
fs: pass dentry to set acl method The current way of setting and getting posix acls through the generic xattr interface is error prone and type unsafe. The vfs needs to interpret and fixup posix acls before storing or reporting it to userspace. Various hacks exist to make this work. The code is hard to understand and difficult to maintain in it's current form. Instead of making this work by hacking posix acls through xattr handlers we are building a dedicated posix acl api around the get and set inode operations. This removes a lot of hackiness and makes the codepaths easier to maintain. A lot of background can be found in [1]. Since some filesystem rely on the dentry being available to them when setting posix acls (e.g., 9p and cifs) they cannot rely on set acl inode operation. But since ->set_acl() is required in order to use the generic posix acl xattr handlers filesystems that do not implement this inode operation cannot use the handler and need to implement their own dedicated posix acl handlers. Update the ->set_acl() inode method to take a dentry argument. This allows all filesystems to rely on ->set_acl(). As far as I can tell all codepaths can be switched to rely on the dentry instead of just the inode. Note that the original motivation for passing the dentry separate from the inode instead of just the dentry in the xattr handlers was because of security modules that call security_d_instantiate(). This hook is called during d_instantiate_new(), d_add(), __d_instantiate_anon(), and d_splice_alias() to initialize the inode's security context and possibly to set security.* xattrs. Since this only affects security.* xattrs this is completely irrelevant for posix acls. Link: https://lore.kernel.org/all/20220801145520.1532837-1-brauner@kernel.org [1] Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
2022-09-23 11:29:39 +03:00
rc = posix_acl_chmod(&init_user_ns, dentry, inode->i_mode);
return rc;
}
const struct inode_operations jfs_file_inode_operations = {
.listxattr = jfs_listxattr,
.setattr = jfs_setattr,
.fileattr_get = jfs_fileattr_get,
.fileattr_set = jfs_fileattr_set,
#ifdef CONFIG_JFS_POSIX_ACL
fs: rename current get acl method The current way of setting and getting posix acls through the generic xattr interface is error prone and type unsafe. The vfs needs to interpret and fixup posix acls before storing or reporting it to userspace. Various hacks exist to make this work. The code is hard to understand and difficult to maintain in it's current form. Instead of making this work by hacking posix acls through xattr handlers we are building a dedicated posix acl api around the get and set inode operations. This removes a lot of hackiness and makes the codepaths easier to maintain. A lot of background can be found in [1]. The current inode operation for getting posix acls takes an inode argument but various filesystems (e.g., 9p, cifs, overlayfs) need access to the dentry. In contrast to the ->set_acl() inode operation we cannot simply extend ->get_acl() to take a dentry argument. The ->get_acl() inode operation is called from: acl_permission_check() -> check_acl() -> get_acl() which is part of generic_permission() which in turn is part of inode_permission(). Both generic_permission() and inode_permission() are called in the ->permission() handler of various filesystems (e.g., overlayfs). So simply passing a dentry argument to ->get_acl() would amount to also having to pass a dentry argument to ->permission(). We should avoid this unnecessary change. So instead of extending the existing inode operation rename it from ->get_acl() to ->get_inode_acl() and add a ->get_acl() method later that passes a dentry argument and which filesystems that need access to the dentry can implement instead of ->get_inode_acl(). Filesystems like cifs which allow setting and getting posix acls but not using them for permission checking during lookup can simply not implement ->get_inode_acl(). This is intended to be a non-functional change. Link: https://lore.kernel.org/all/20220801145520.1532837-1-brauner@kernel.org [1] Suggested-by/Inspired-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
2022-09-22 18:17:00 +03:00
.get_inode_acl = jfs_get_acl,
.set_acl = jfs_set_acl,
#endif
};
const struct file_operations jfs_file_operations = {
.open = jfs_open,
.llseek = generic_file_llseek,
.read_iter = generic_file_read_iter,
.write_iter = generic_file_write_iter,
.mmap = generic_file_mmap,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.fsync = jfs_fsync,
.release = jfs_release,
.unlocked_ioctl = jfs_ioctl,
.compat_ioctl = compat_ptr_ioctl,
};