linux-stable/fs/xattr.c

1186 lines
29 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
File: fs/xattr.c
Extended attribute handling.
Copyright (C) 2001 by Andreas Gruenbacher <a.gruenbacher@computer.org>
Copyright (C) 2001 SGI - Silicon Graphics, Inc <linux-xfs@oss.sgi.com>
Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com>
*/
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/xattr.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/security.h>
#include <linux/evm.h>
#include <linux/syscalls.h>
#include <linux/export.h>
#include <linux/fsnotify.h>
#include <linux/audit.h>
#include <linux/vmalloc.h>
2012-02-08 02:52:57 +00:00
#include <linux/posix_acl_xattr.h>
#include <linux/uaccess.h>
#include "internal.h"
static const char *
strcmp_prefix(const char *a, const char *a_prefix)
{
while (*a_prefix && *a == *a_prefix) {
a++;
a_prefix++;
}
return *a_prefix ? NULL : a;
}
/*
* In order to implement different sets of xattr operations for each xattr
* prefix, a filesystem should create a null-terminated array of struct
* xattr_handler (one for each prefix) and hang a pointer to it off of the
* s_xattr field of the superblock.
*/
#define for_each_xattr_handler(handlers, handler) \
if (handlers) \
for ((handler) = *(handlers)++; \
(handler) != NULL; \
(handler) = *(handlers)++)
/*
* Find the xattr_handler with the matching prefix.
*/
static const struct xattr_handler *
xattr_resolve_name(struct inode *inode, const char **name)
{
const struct xattr_handler **handlers = inode->i_sb->s_xattr;
const struct xattr_handler *handler;
if (!(inode->i_opflags & IOP_XATTR)) {
if (unlikely(is_bad_inode(inode)))
return ERR_PTR(-EIO);
return ERR_PTR(-EOPNOTSUPP);
}
for_each_xattr_handler(handlers, handler) {
const char *n;
n = strcmp_prefix(*name, xattr_prefix(handler));
if (n) {
if (!handler->prefix ^ !*n) {
if (*n)
continue;
return ERR_PTR(-EINVAL);
}
*name = n;
return handler;
}
}
return ERR_PTR(-EOPNOTSUPP);
}
/*
* Check permissions for extended attribute access. This is a bit complicated
* because different namespaces have very different rules.
*/
static int
xattr_permission(struct user_namespace *mnt_userns, struct inode *inode,
const char *name, int mask)
{
/*
* We can never set or remove an extended attribute on a read-only
* filesystem or on an immutable / append-only inode.
*/
if (mask & MAY_WRITE) {
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
return -EPERM;
vfs: Don't modify inodes with a uid or gid unknown to the vfs When a filesystem outside of init_user_ns is mounted it could have uids and gids stored in it that do not map to init_user_ns. The plan is to allow those filesystems to set i_uid to INVALID_UID and i_gid to INVALID_GID for unmapped uids and gids and then to handle that strange case in the vfs to ensure there is consistent robust handling of the weirdness. Upon a careful review of the vfs and filesystems about the only case where there is any possibility of confusion or trouble is when the inode is written back to disk. In that case filesystems typically read the inode->i_uid and inode->i_gid and write them to disk even when just an inode timestamp is being updated. Which leads to a rule that is very simple to implement and understand inodes whose i_uid or i_gid is not valid may not be written. In dealing with access times this means treat those inodes as if the inode flag S_NOATIME was set. Reads of the inodes appear safe and useful, but any write or modification is disallowed. The only inode write that is allowed is a chown that sets the uid and gid on the inode to valid values. After such a chown the inode is normal and may be treated as such. Denying all writes to inodes with uids or gids unknown to the vfs also prevents several oddball cases where corruption would have occurred because the vfs does not have complete information. One problem case that is prevented is attempting to use the gid of a directory for new inodes where the directories sgid bit is set but the directories gid is not mapped. Another problem case avoided is attempting to update the evm hash after setxattr, removexattr, and setattr. As the evm hash includeds the inode->i_uid or inode->i_gid not knowning the uid or gid prevents a correct evm hash from being computed. evm hash verification also fails when i_uid or i_gid is unknown but that is essentially harmless as it does not cause filesystem corruption. Acked-by: Seth Forshee <seth.forshee@canonical.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2016-06-29 19:54:46 +00:00
/*
* Updating an xattr will likely cause i_uid and i_gid
* to be writen back improperly if their true value is
* unknown to the vfs.
*/
if (HAS_UNMAPPED_ID(mnt_userns, inode))
vfs: Don't modify inodes with a uid or gid unknown to the vfs When a filesystem outside of init_user_ns is mounted it could have uids and gids stored in it that do not map to init_user_ns. The plan is to allow those filesystems to set i_uid to INVALID_UID and i_gid to INVALID_GID for unmapped uids and gids and then to handle that strange case in the vfs to ensure there is consistent robust handling of the weirdness. Upon a careful review of the vfs and filesystems about the only case where there is any possibility of confusion or trouble is when the inode is written back to disk. In that case filesystems typically read the inode->i_uid and inode->i_gid and write them to disk even when just an inode timestamp is being updated. Which leads to a rule that is very simple to implement and understand inodes whose i_uid or i_gid is not valid may not be written. In dealing with access times this means treat those inodes as if the inode flag S_NOATIME was set. Reads of the inodes appear safe and useful, but any write or modification is disallowed. The only inode write that is allowed is a chown that sets the uid and gid on the inode to valid values. After such a chown the inode is normal and may be treated as such. Denying all writes to inodes with uids or gids unknown to the vfs also prevents several oddball cases where corruption would have occurred because the vfs does not have complete information. One problem case that is prevented is attempting to use the gid of a directory for new inodes where the directories sgid bit is set but the directories gid is not mapped. Another problem case avoided is attempting to update the evm hash after setxattr, removexattr, and setattr. As the evm hash includeds the inode->i_uid or inode->i_gid not knowning the uid or gid prevents a correct evm hash from being computed. evm hash verification also fails when i_uid or i_gid is unknown but that is essentially harmless as it does not cause filesystem corruption. Acked-by: Seth Forshee <seth.forshee@canonical.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2016-06-29 19:54:46 +00:00
return -EPERM;
}
/*
* No restriction for security.* and system.* from the VFS. Decision
* on these is left to the underlying filesystem / security module.
*/
if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) ||
!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
return 0;
/*
* The trusted.* namespace can only be accessed by privileged users.
*/
if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) {
if (!capable(CAP_SYS_ADMIN))
return (mask & MAY_WRITE) ? -EPERM : -ENODATA;
return 0;
}
/*
* In the user.* namespace, only regular files and directories can have
* extended attributes. For sticky directories, only the owner and
* privileged users can write attributes.
*/
if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) {
if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
return (mask & MAY_WRITE) ? -EPERM : -ENODATA;
if (S_ISDIR(inode->i_mode) && (inode->i_mode & S_ISVTX) &&
(mask & MAY_WRITE) &&
!inode_owner_or_capable(mnt_userns, inode))
return -EPERM;
}
return inode_permission(mnt_userns, inode, mask);
}
/*
* Look for any handler that deals with the specified namespace.
*/
int
xattr_supported_namespace(struct inode *inode, const char *prefix)
{
const struct xattr_handler **handlers = inode->i_sb->s_xattr;
const struct xattr_handler *handler;
size_t preflen;
if (!(inode->i_opflags & IOP_XATTR)) {
if (unlikely(is_bad_inode(inode)))
return -EIO;
return -EOPNOTSUPP;
}
preflen = strlen(prefix);
for_each_xattr_handler(handlers, handler) {
if (!strncmp(xattr_prefix(handler), prefix, preflen))
return 0;
}
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(xattr_supported_namespace);
int
__vfs_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
struct inode *inode, const char *name, const void *value,
size_t size, int flags)
{
const struct xattr_handler *handler;
handler = xattr_resolve_name(inode, &name);
if (IS_ERR(handler))
return PTR_ERR(handler);
if (!handler->set)
return -EOPNOTSUPP;
if (size == 0)
value = ""; /* empty EA, do not remove */
return handler->set(handler, mnt_userns, dentry, inode, name, value,
acl: handle idmapped mounts The posix acl permission checking helpers determine whether a caller is privileged over an inode according to the acls associated with the inode. Add helpers that make it possible to handle acls on idmapped mounts. The vfs and the filesystems targeted by this first iteration make use of posix_acl_fix_xattr_from_user() and posix_acl_fix_xattr_to_user() to translate basic posix access and default permissions such as the ACL_USER and ACL_GROUP type according to the initial user namespace (or the superblock's user namespace) to and from the caller's current user namespace. Adapt these two helpers to handle idmapped mounts whereby we either map from or into the mount's user namespace depending on in which direction we're translating. Similarly, cap_convert_nscap() is used by the vfs to translate user namespace and non-user namespace aware filesystem capabilities from the superblock's user namespace to the caller's user namespace. Enable it to handle idmapped mounts by accounting for the mount's user namespace. In addition the fileystems targeted in the first iteration of this patch series make use of the posix_acl_chmod() and, posix_acl_update_mode() helpers. Both helpers perform permission checks on the target inode. Let them handle idmapped mounts. These two helpers are called when posix acls are set by the respective filesystems to handle this case we extend the ->set() method to take an additional user namespace argument to pass the mount's user namespace down. Link: https://lore.kernel.org/r/20210121131959.646623-9-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 13:19:27 +00:00
size, flags);
}
EXPORT_SYMBOL(__vfs_setxattr);
/**
* __vfs_setxattr_noperm - perform setxattr operation without performing
* permission checks.
*
* @mnt_userns: user namespace of the mount the inode was found from
* @dentry: object to perform setxattr on
* @name: xattr name to set
* @value: value to set @name to
* @size: size of @value
* @flags: flags to pass into filesystem operations
*
* returns the result of the internal setxattr or setsecurity operations.
*
* This function requires the caller to lock the inode's i_mutex before it
* is executed. It also assumes that the caller will make the appropriate
* permission checks.
*/
int __vfs_setxattr_noperm(struct user_namespace *mnt_userns,
struct dentry *dentry, const char *name,
const void *value, size_t size, int flags)
{
struct inode *inode = dentry->d_inode;
int error = -EAGAIN;
Cache xattr security drop check for write v2 Some recent benchmarking on btrfs showed that a major scaling bottleneck on large systems on btrfs is currently the xattr lookup on every write. Why xattr lookup on every write I hear you ask? write wants to drop suid and security related xattrs that could set o capabilities for executables. To do that it currently looks up security.capability on EVERY write (even for non executables) to decide whether to drop it or not. In btrfs this causes an additional tree walk, hitting some per file system locks and quite bad scalability. In a simple read workload on a 8S system I saw over 90% CPU time in spinlocks related to that. Chris Mason tells me this is also a problem in ext4, where it hits the global mbcache lock. This patch adds a simple per inode to avoid this problem. We only do the lookup once per file and then if there is no xattr cache the decision. All xattr changes clear the flag. I also used the same flag to avoid the suid check, although that one is pretty cheap. A file system can also set this flag when it creates the inode, if it has a cheap way to do so. This is done for some common file systems in followon patches. With this patch a major part of the lock contention disappears for btrfs. Some testing on smaller systems didn't show significant performance changes, but at least it helps the larger systems and is generally more efficient. v2: Rename is_sgid. add file system helper. Cc: chris.mason@oracle.com Cc: josef@redhat.com Cc: viro@zeniv.linux.org.uk Cc: agruen@linbit.com Cc: Serge E. Hallyn <serue@us.ibm.com> Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-05-28 15:25:51 +00:00
int issec = !strncmp(name, XATTR_SECURITY_PREFIX,
XATTR_SECURITY_PREFIX_LEN);
Cache xattr security drop check for write v2 Some recent benchmarking on btrfs showed that a major scaling bottleneck on large systems on btrfs is currently the xattr lookup on every write. Why xattr lookup on every write I hear you ask? write wants to drop suid and security related xattrs that could set o capabilities for executables. To do that it currently looks up security.capability on EVERY write (even for non executables) to decide whether to drop it or not. In btrfs this causes an additional tree walk, hitting some per file system locks and quite bad scalability. In a simple read workload on a 8S system I saw over 90% CPU time in spinlocks related to that. Chris Mason tells me this is also a problem in ext4, where it hits the global mbcache lock. This patch adds a simple per inode to avoid this problem. We only do the lookup once per file and then if there is no xattr cache the decision. All xattr changes clear the flag. I also used the same flag to avoid the suid check, although that one is pretty cheap. A file system can also set this flag when it creates the inode, if it has a cheap way to do so. This is done for some common file systems in followon patches. With this patch a major part of the lock contention disappears for btrfs. Some testing on smaller systems didn't show significant performance changes, but at least it helps the larger systems and is generally more efficient. v2: Rename is_sgid. add file system helper. Cc: chris.mason@oracle.com Cc: josef@redhat.com Cc: viro@zeniv.linux.org.uk Cc: agruen@linbit.com Cc: Serge E. Hallyn <serue@us.ibm.com> Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-05-28 15:25:51 +00:00
if (issec)
inode->i_flags &= ~S_NOSEC;
if (inode->i_opflags & IOP_XATTR) {
error = __vfs_setxattr(mnt_userns, dentry, inode, name, value,
size, flags);
if (!error) {
fsnotify_xattr(dentry);
security_inode_post_setxattr(dentry, name, value,
size, flags);
}
} else {
if (unlikely(is_bad_inode(inode)))
return -EIO;
}
if (error == -EAGAIN) {
error = -EOPNOTSUPP;
if (issec) {
const char *suffix = name + XATTR_SECURITY_PREFIX_LEN;
error = security_inode_setsecurity(inode, suffix, value,
size, flags);
if (!error)
fsnotify_xattr(dentry);
}
}
return error;
}
/**
fs/xattr.c: fix kernel-doc warnings for setxattr & removexattr Fix kernel-doc warnings in fs/xattr.c: ../fs/xattr.c:251: warning: Function parameter or member 'dentry' not described in '__vfs_setxattr_locked' ../fs/xattr.c:251: warning: Function parameter or member 'name' not described in '__vfs_setxattr_locked' ../fs/xattr.c:251: warning: Function parameter or member 'value' not described in '__vfs_setxattr_locked' ../fs/xattr.c:251: warning: Function parameter or member 'size' not described in '__vfs_setxattr_locked' ../fs/xattr.c:251: warning: Function parameter or member 'flags' not described in '__vfs_setxattr_locked' ../fs/xattr.c:251: warning: Function parameter or member 'delegated_inode' not described in '__vfs_setxattr_locked' ../fs/xattr.c:458: warning: Function parameter or member 'dentry' not described in '__vfs_removexattr_locked' ../fs/xattr.c:458: warning: Function parameter or member 'name' not described in '__vfs_removexattr_locked' ../fs/xattr.c:458: warning: Function parameter or member 'delegated_inode' not described in '__vfs_removexattr_locked' Fixes: 08b5d5014a27 ("xattr: break delegations in {set,remove}xattr") Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Frank van der Linden <fllinden@amazon.com> Cc: Chuck Lever <chuck.lever@oracle.com> Link: http://lkml.kernel.org/r/7a3dd5a2-5787-adf3-d525-c203f9910ec4@infradead.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-13 23:48:27 +00:00
* __vfs_setxattr_locked - set an extended attribute while holding the inode
* lock
*
* @mnt_userns: user namespace of the mount of the target inode
fs/xattr.c: fix kernel-doc warnings for setxattr & removexattr Fix kernel-doc warnings in fs/xattr.c: ../fs/xattr.c:251: warning: Function parameter or member 'dentry' not described in '__vfs_setxattr_locked' ../fs/xattr.c:251: warning: Function parameter or member 'name' not described in '__vfs_setxattr_locked' ../fs/xattr.c:251: warning: Function parameter or member 'value' not described in '__vfs_setxattr_locked' ../fs/xattr.c:251: warning: Function parameter or member 'size' not described in '__vfs_setxattr_locked' ../fs/xattr.c:251: warning: Function parameter or member 'flags' not described in '__vfs_setxattr_locked' ../fs/xattr.c:251: warning: Function parameter or member 'delegated_inode' not described in '__vfs_setxattr_locked' ../fs/xattr.c:458: warning: Function parameter or member 'dentry' not described in '__vfs_removexattr_locked' ../fs/xattr.c:458: warning: Function parameter or member 'name' not described in '__vfs_removexattr_locked' ../fs/xattr.c:458: warning: Function parameter or member 'delegated_inode' not described in '__vfs_removexattr_locked' Fixes: 08b5d5014a27 ("xattr: break delegations in {set,remove}xattr") Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Frank van der Linden <fllinden@amazon.com> Cc: Chuck Lever <chuck.lever@oracle.com> Link: http://lkml.kernel.org/r/7a3dd5a2-5787-adf3-d525-c203f9910ec4@infradead.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-13 23:48:27 +00:00
* @dentry: object to perform setxattr on
* @name: xattr name to set
* @value: value to set @name to
* @size: size of @value
* @flags: flags to pass into filesystem operations
* @delegated_inode: on return, will contain an inode pointer that
* a delegation was broken on, NULL if none.
*/
int
__vfs_setxattr_locked(struct user_namespace *mnt_userns, struct dentry *dentry,
const char *name, const void *value, size_t size,
int flags, struct inode **delegated_inode)
{
struct inode *inode = dentry->d_inode;
int error;
error = xattr_permission(mnt_userns, inode, name, MAY_WRITE);
if (error)
return error;
commoncap: handle idmapped mounts When interacting with user namespace and non-user namespace aware filesystem capabilities the vfs will perform various security checks to determine whether or not the filesystem capabilities can be used by the caller, whether they need to be removed and so on. The main infrastructure for this resides in the capability codepaths but they are called through the LSM security infrastructure even though they are not technically an LSM or optional. This extends the existing security hooks security_inode_removexattr(), security_inode_killpriv(), security_inode_getsecurity() to pass down the mount's user namespace and makes them aware of idmapped mounts. In order to actually get filesystem capabilities from disk the capability infrastructure exposes the get_vfs_caps_from_disk() helper. For user namespace aware filesystem capabilities a root uid is stored alongside the capabilities. In order to determine whether the caller can make use of the filesystem capability or whether it needs to be ignored it is translated according to the superblock's user namespace. If it can be translated to uid 0 according to that id mapping the caller can use the filesystem capabilities stored on disk. If we are accessing the inode that holds the filesystem capabilities through an idmapped mount we map the root uid according to the mount's user namespace. Afterwards the checks are identical to non-idmapped mounts: reading filesystem caps from disk enforces that the root uid associated with the filesystem capability must have a mapping in the superblock's user namespace and that the caller is either in the same user namespace or is a descendant of the superblock's user namespace. For filesystems that are mountable inside user namespace the caller can just mount the filesystem and won't usually need to idmap it. If they do want to idmap it they can create an idmapped mount and mark it with a user namespace they created and which is thus a descendant of s_user_ns. For filesystems that are not mountable inside user namespaces the descendant rule is trivially true because the s_user_ns will be the initial user namespace. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Link: https://lore.kernel.org/r/20210121131959.646623-11-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Acked-by: James Morris <jamorris@linux.microsoft.com> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 13:19:29 +00:00
error = security_inode_setxattr(mnt_userns, dentry, name, value, size,
flags);
if (error)
goto out;
error = try_break_deleg(inode, delegated_inode);
if (error)
goto out;
error = __vfs_setxattr_noperm(mnt_userns, dentry, name, value,
size, flags);
out:
return error;
}
EXPORT_SYMBOL_GPL(__vfs_setxattr_locked);
int
vfs_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
const char *name, const void *value, size_t size, int flags)
{
struct inode *inode = dentry->d_inode;
struct inode *delegated_inode = NULL;
const void *orig_value = value;
int error;
if (size && strcmp(name, XATTR_NAME_CAPS) == 0) {
error = cap_convert_nscap(mnt_userns, dentry, &value, size);
if (error < 0)
return error;
size = error;
}
retry_deleg:
inode_lock(inode);
error = __vfs_setxattr_locked(mnt_userns, dentry, name, value, size,
flags, &delegated_inode);
inode_unlock(inode);
if (delegated_inode) {
error = break_deleg_wait(&delegated_inode);
if (!error)
goto retry_deleg;
}
if (value != orig_value)
kfree(value);
return error;
}
EXPORT_SYMBOL_GPL(vfs_setxattr);
static ssize_t
commoncap: handle idmapped mounts When interacting with user namespace and non-user namespace aware filesystem capabilities the vfs will perform various security checks to determine whether or not the filesystem capabilities can be used by the caller, whether they need to be removed and so on. The main infrastructure for this resides in the capability codepaths but they are called through the LSM security infrastructure even though they are not technically an LSM or optional. This extends the existing security hooks security_inode_removexattr(), security_inode_killpriv(), security_inode_getsecurity() to pass down the mount's user namespace and makes them aware of idmapped mounts. In order to actually get filesystem capabilities from disk the capability infrastructure exposes the get_vfs_caps_from_disk() helper. For user namespace aware filesystem capabilities a root uid is stored alongside the capabilities. In order to determine whether the caller can make use of the filesystem capability or whether it needs to be ignored it is translated according to the superblock's user namespace. If it can be translated to uid 0 according to that id mapping the caller can use the filesystem capabilities stored on disk. If we are accessing the inode that holds the filesystem capabilities through an idmapped mount we map the root uid according to the mount's user namespace. Afterwards the checks are identical to non-idmapped mounts: reading filesystem caps from disk enforces that the root uid associated with the filesystem capability must have a mapping in the superblock's user namespace and that the caller is either in the same user namespace or is a descendant of the superblock's user namespace. For filesystems that are mountable inside user namespace the caller can just mount the filesystem and won't usually need to idmap it. If they do want to idmap it they can create an idmapped mount and mark it with a user namespace they created and which is thus a descendant of s_user_ns. For filesystems that are not mountable inside user namespaces the descendant rule is trivially true because the s_user_ns will be the initial user namespace. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Link: https://lore.kernel.org/r/20210121131959.646623-11-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Acked-by: James Morris <jamorris@linux.microsoft.com> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 13:19:29 +00:00
xattr_getsecurity(struct user_namespace *mnt_userns, struct inode *inode,
const char *name, void *value, size_t size)
{
void *buffer = NULL;
ssize_t len;
if (!value || !size) {
commoncap: handle idmapped mounts When interacting with user namespace and non-user namespace aware filesystem capabilities the vfs will perform various security checks to determine whether or not the filesystem capabilities can be used by the caller, whether they need to be removed and so on. The main infrastructure for this resides in the capability codepaths but they are called through the LSM security infrastructure even though they are not technically an LSM or optional. This extends the existing security hooks security_inode_removexattr(), security_inode_killpriv(), security_inode_getsecurity() to pass down the mount's user namespace and makes them aware of idmapped mounts. In order to actually get filesystem capabilities from disk the capability infrastructure exposes the get_vfs_caps_from_disk() helper. For user namespace aware filesystem capabilities a root uid is stored alongside the capabilities. In order to determine whether the caller can make use of the filesystem capability or whether it needs to be ignored it is translated according to the superblock's user namespace. If it can be translated to uid 0 according to that id mapping the caller can use the filesystem capabilities stored on disk. If we are accessing the inode that holds the filesystem capabilities through an idmapped mount we map the root uid according to the mount's user namespace. Afterwards the checks are identical to non-idmapped mounts: reading filesystem caps from disk enforces that the root uid associated with the filesystem capability must have a mapping in the superblock's user namespace and that the caller is either in the same user namespace or is a descendant of the superblock's user namespace. For filesystems that are mountable inside user namespace the caller can just mount the filesystem and won't usually need to idmap it. If they do want to idmap it they can create an idmapped mount and mark it with a user namespace they created and which is thus a descendant of s_user_ns. For filesystems that are not mountable inside user namespaces the descendant rule is trivially true because the s_user_ns will be the initial user namespace. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Link: https://lore.kernel.org/r/20210121131959.646623-11-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Acked-by: James Morris <jamorris@linux.microsoft.com> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 13:19:29 +00:00
len = security_inode_getsecurity(mnt_userns, inode, name,
&buffer, false);
goto out_noalloc;
}
commoncap: handle idmapped mounts When interacting with user namespace and non-user namespace aware filesystem capabilities the vfs will perform various security checks to determine whether or not the filesystem capabilities can be used by the caller, whether they need to be removed and so on. The main infrastructure for this resides in the capability codepaths but they are called through the LSM security infrastructure even though they are not technically an LSM or optional. This extends the existing security hooks security_inode_removexattr(), security_inode_killpriv(), security_inode_getsecurity() to pass down the mount's user namespace and makes them aware of idmapped mounts. In order to actually get filesystem capabilities from disk the capability infrastructure exposes the get_vfs_caps_from_disk() helper. For user namespace aware filesystem capabilities a root uid is stored alongside the capabilities. In order to determine whether the caller can make use of the filesystem capability or whether it needs to be ignored it is translated according to the superblock's user namespace. If it can be translated to uid 0 according to that id mapping the caller can use the filesystem capabilities stored on disk. If we are accessing the inode that holds the filesystem capabilities through an idmapped mount we map the root uid according to the mount's user namespace. Afterwards the checks are identical to non-idmapped mounts: reading filesystem caps from disk enforces that the root uid associated with the filesystem capability must have a mapping in the superblock's user namespace and that the caller is either in the same user namespace or is a descendant of the superblock's user namespace. For filesystems that are mountable inside user namespace the caller can just mount the filesystem and won't usually need to idmap it. If they do want to idmap it they can create an idmapped mount and mark it with a user namespace they created and which is thus a descendant of s_user_ns. For filesystems that are not mountable inside user namespaces the descendant rule is trivially true because the s_user_ns will be the initial user namespace. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Link: https://lore.kernel.org/r/20210121131959.646623-11-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Acked-by: James Morris <jamorris@linux.microsoft.com> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 13:19:29 +00:00
len = security_inode_getsecurity(mnt_userns, inode, name, &buffer,
true);
if (len < 0)
return len;
if (size < len) {
len = -ERANGE;
goto out;
}
memcpy(value, buffer, len);
out:
kfree(buffer);
out_noalloc:
return len;
}
/*
* vfs_getxattr_alloc - allocate memory, if necessary, before calling getxattr
*
* Allocate memory, if not already allocated, or re-allocate correct size,
* before retrieving the extended attribute.
*
* Returns the result of alloc, if failed, or the getxattr operation.
*/
ssize_t
vfs_getxattr_alloc(struct user_namespace *mnt_userns, struct dentry *dentry,
const char *name, char **xattr_value, size_t xattr_size,
gfp_t flags)
{
const struct xattr_handler *handler;
struct inode *inode = dentry->d_inode;
char *value = *xattr_value;
int error;
error = xattr_permission(mnt_userns, inode, name, MAY_READ);
if (error)
return error;
handler = xattr_resolve_name(inode, &name);
if (IS_ERR(handler))
return PTR_ERR(handler);
if (!handler->get)
return -EOPNOTSUPP;
error = handler->get(handler, dentry, inode, name, NULL, 0);
if (error < 0)
return error;
if (!value || (error > xattr_size)) {
value = krealloc(*xattr_value, error + 1, flags);
if (!value)
return -ENOMEM;
memset(value, 0, error + 1);
}
error = handler->get(handler, dentry, inode, name, value, error);
*xattr_value = value;
return error;
}
ssize_t
__vfs_getxattr(struct dentry *dentry, struct inode *inode, const char *name,
void *value, size_t size)
{
const struct xattr_handler *handler;
handler = xattr_resolve_name(inode, &name);
if (IS_ERR(handler))
return PTR_ERR(handler);
if (!handler->get)
return -EOPNOTSUPP;
return handler->get(handler, dentry, inode, name, value, size);
}
EXPORT_SYMBOL(__vfs_getxattr);
ssize_t
vfs_getxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
const char *name, void *value, size_t size)
{
struct inode *inode = dentry->d_inode;
int error;
error = xattr_permission(mnt_userns, inode, name, MAY_READ);
if (error)
return error;
error = security_inode_getxattr(dentry, name);
if (error)
return error;
if (!strncmp(name, XATTR_SECURITY_PREFIX,
XATTR_SECURITY_PREFIX_LEN)) {
const char *suffix = name + XATTR_SECURITY_PREFIX_LEN;
commoncap: handle idmapped mounts When interacting with user namespace and non-user namespace aware filesystem capabilities the vfs will perform various security checks to determine whether or not the filesystem capabilities can be used by the caller, whether they need to be removed and so on. The main infrastructure for this resides in the capability codepaths but they are called through the LSM security infrastructure even though they are not technically an LSM or optional. This extends the existing security hooks security_inode_removexattr(), security_inode_killpriv(), security_inode_getsecurity() to pass down the mount's user namespace and makes them aware of idmapped mounts. In order to actually get filesystem capabilities from disk the capability infrastructure exposes the get_vfs_caps_from_disk() helper. For user namespace aware filesystem capabilities a root uid is stored alongside the capabilities. In order to determine whether the caller can make use of the filesystem capability or whether it needs to be ignored it is translated according to the superblock's user namespace. If it can be translated to uid 0 according to that id mapping the caller can use the filesystem capabilities stored on disk. If we are accessing the inode that holds the filesystem capabilities through an idmapped mount we map the root uid according to the mount's user namespace. Afterwards the checks are identical to non-idmapped mounts: reading filesystem caps from disk enforces that the root uid associated with the filesystem capability must have a mapping in the superblock's user namespace and that the caller is either in the same user namespace or is a descendant of the superblock's user namespace. For filesystems that are mountable inside user namespace the caller can just mount the filesystem and won't usually need to idmap it. If they do want to idmap it they can create an idmapped mount and mark it with a user namespace they created and which is thus a descendant of s_user_ns. For filesystems that are not mountable inside user namespaces the descendant rule is trivially true because the s_user_ns will be the initial user namespace. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Link: https://lore.kernel.org/r/20210121131959.646623-11-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Acked-by: James Morris <jamorris@linux.microsoft.com> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 13:19:29 +00:00
int ret = xattr_getsecurity(mnt_userns, inode, suffix, value,
size);
/*
* Only overwrite the return value if a security module
* is actually active.
*/
if (ret == -EOPNOTSUPP)
goto nolsm;
return ret;
}
nolsm:
return __vfs_getxattr(dentry, inode, name, value, size);
}
EXPORT_SYMBOL_GPL(vfs_getxattr);
ssize_t
vfs_listxattr(struct dentry *dentry, char *list, size_t size)
{
struct inode *inode = d_inode(dentry);
ssize_t error;
error = security_inode_listxattr(dentry);
if (error)
return error;
if (inode->i_op->listxattr && (inode->i_opflags & IOP_XATTR)) {
error = inode->i_op->listxattr(dentry, list, size);
} else {
error = security_inode_listsecurity(inode, list, size);
if (size && error > size)
error = -ERANGE;
}
return error;
}
EXPORT_SYMBOL_GPL(vfs_listxattr);
int
__vfs_removexattr(struct user_namespace *mnt_userns, struct dentry *dentry,
const char *name)
{
struct inode *inode = d_inode(dentry);
const struct xattr_handler *handler;
handler = xattr_resolve_name(inode, &name);
if (IS_ERR(handler))
return PTR_ERR(handler);
if (!handler->set)
return -EOPNOTSUPP;
return handler->set(handler, mnt_userns, dentry, inode, name, NULL, 0,
XATTR_REPLACE);
}
EXPORT_SYMBOL(__vfs_removexattr);
/**
fs/xattr.c: fix kernel-doc warnings for setxattr & removexattr Fix kernel-doc warnings in fs/xattr.c: ../fs/xattr.c:251: warning: Function parameter or member 'dentry' not described in '__vfs_setxattr_locked' ../fs/xattr.c:251: warning: Function parameter or member 'name' not described in '__vfs_setxattr_locked' ../fs/xattr.c:251: warning: Function parameter or member 'value' not described in '__vfs_setxattr_locked' ../fs/xattr.c:251: warning: Function parameter or member 'size' not described in '__vfs_setxattr_locked' ../fs/xattr.c:251: warning: Function parameter or member 'flags' not described in '__vfs_setxattr_locked' ../fs/xattr.c:251: warning: Function parameter or member 'delegated_inode' not described in '__vfs_setxattr_locked' ../fs/xattr.c:458: warning: Function parameter or member 'dentry' not described in '__vfs_removexattr_locked' ../fs/xattr.c:458: warning: Function parameter or member 'name' not described in '__vfs_removexattr_locked' ../fs/xattr.c:458: warning: Function parameter or member 'delegated_inode' not described in '__vfs_removexattr_locked' Fixes: 08b5d5014a27 ("xattr: break delegations in {set,remove}xattr") Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Frank van der Linden <fllinden@amazon.com> Cc: Chuck Lever <chuck.lever@oracle.com> Link: http://lkml.kernel.org/r/7a3dd5a2-5787-adf3-d525-c203f9910ec4@infradead.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-13 23:48:27 +00:00
* __vfs_removexattr_locked - set an extended attribute while holding the inode
* lock
*
* @mnt_userns: user namespace of the mount of the target inode
fs/xattr.c: fix kernel-doc warnings for setxattr & removexattr Fix kernel-doc warnings in fs/xattr.c: ../fs/xattr.c:251: warning: Function parameter or member 'dentry' not described in '__vfs_setxattr_locked' ../fs/xattr.c:251: warning: Function parameter or member 'name' not described in '__vfs_setxattr_locked' ../fs/xattr.c:251: warning: Function parameter or member 'value' not described in '__vfs_setxattr_locked' ../fs/xattr.c:251: warning: Function parameter or member 'size' not described in '__vfs_setxattr_locked' ../fs/xattr.c:251: warning: Function parameter or member 'flags' not described in '__vfs_setxattr_locked' ../fs/xattr.c:251: warning: Function parameter or member 'delegated_inode' not described in '__vfs_setxattr_locked' ../fs/xattr.c:458: warning: Function parameter or member 'dentry' not described in '__vfs_removexattr_locked' ../fs/xattr.c:458: warning: Function parameter or member 'name' not described in '__vfs_removexattr_locked' ../fs/xattr.c:458: warning: Function parameter or member 'delegated_inode' not described in '__vfs_removexattr_locked' Fixes: 08b5d5014a27 ("xattr: break delegations in {set,remove}xattr") Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Frank van der Linden <fllinden@amazon.com> Cc: Chuck Lever <chuck.lever@oracle.com> Link: http://lkml.kernel.org/r/7a3dd5a2-5787-adf3-d525-c203f9910ec4@infradead.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-13 23:48:27 +00:00
* @dentry: object to perform setxattr on
* @name: name of xattr to remove
* @delegated_inode: on return, will contain an inode pointer that
* a delegation was broken on, NULL if none.
*/
int
__vfs_removexattr_locked(struct user_namespace *mnt_userns,
struct dentry *dentry, const char *name,
struct inode **delegated_inode)
{
struct inode *inode = dentry->d_inode;
int error;
error = xattr_permission(mnt_userns, inode, name, MAY_WRITE);
if (error)
return error;
commoncap: handle idmapped mounts When interacting with user namespace and non-user namespace aware filesystem capabilities the vfs will perform various security checks to determine whether or not the filesystem capabilities can be used by the caller, whether they need to be removed and so on. The main infrastructure for this resides in the capability codepaths but they are called through the LSM security infrastructure even though they are not technically an LSM or optional. This extends the existing security hooks security_inode_removexattr(), security_inode_killpriv(), security_inode_getsecurity() to pass down the mount's user namespace and makes them aware of idmapped mounts. In order to actually get filesystem capabilities from disk the capability infrastructure exposes the get_vfs_caps_from_disk() helper. For user namespace aware filesystem capabilities a root uid is stored alongside the capabilities. In order to determine whether the caller can make use of the filesystem capability or whether it needs to be ignored it is translated according to the superblock's user namespace. If it can be translated to uid 0 according to that id mapping the caller can use the filesystem capabilities stored on disk. If we are accessing the inode that holds the filesystem capabilities through an idmapped mount we map the root uid according to the mount's user namespace. Afterwards the checks are identical to non-idmapped mounts: reading filesystem caps from disk enforces that the root uid associated with the filesystem capability must have a mapping in the superblock's user namespace and that the caller is either in the same user namespace or is a descendant of the superblock's user namespace. For filesystems that are mountable inside user namespace the caller can just mount the filesystem and won't usually need to idmap it. If they do want to idmap it they can create an idmapped mount and mark it with a user namespace they created and which is thus a descendant of s_user_ns. For filesystems that are not mountable inside user namespaces the descendant rule is trivially true because the s_user_ns will be the initial user namespace. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Link: https://lore.kernel.org/r/20210121131959.646623-11-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Acked-by: James Morris <jamorris@linux.microsoft.com> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 13:19:29 +00:00
error = security_inode_removexattr(mnt_userns, dentry, name);
if (error)
goto out;
error = try_break_deleg(inode, delegated_inode);
if (error)
goto out;
error = __vfs_removexattr(mnt_userns, dentry, name);
if (!error) {
fsnotify_xattr(dentry);
evm_inode_post_removexattr(dentry, name);
}
out:
return error;
}
EXPORT_SYMBOL_GPL(__vfs_removexattr_locked);
int
vfs_removexattr(struct user_namespace *mnt_userns, struct dentry *dentry,
const char *name)
{
struct inode *inode = dentry->d_inode;
struct inode *delegated_inode = NULL;
int error;
retry_deleg:
inode_lock(inode);
error = __vfs_removexattr_locked(mnt_userns, dentry,
name, &delegated_inode);
inode_unlock(inode);
if (delegated_inode) {
error = break_deleg_wait(&delegated_inode);
if (!error)
goto retry_deleg;
}
return error;
}
EXPORT_SYMBOL_GPL(vfs_removexattr);
/*
* Extended attribute SET operations
*/
int setxattr_copy(const char __user *name, struct xattr_ctx *ctx)
{
int error;
if (ctx->flags & ~(XATTR_CREATE|XATTR_REPLACE))
return -EINVAL;
error = strncpy_from_user(ctx->kname->name, name,
sizeof(ctx->kname->name));
if (error == 0 || error == sizeof(ctx->kname->name))
return -ERANGE;
if (error < 0)
return error;
error = 0;
if (ctx->size) {
if (ctx->size > XATTR_SIZE_MAX)
return -E2BIG;
ctx->kvalue = vmemdup_user(ctx->cvalue, ctx->size);
if (IS_ERR(ctx->kvalue)) {
error = PTR_ERR(ctx->kvalue);
ctx->kvalue = NULL;
}
}
return error;
}
static void setxattr_convert(struct user_namespace *mnt_userns,
struct dentry *d, struct xattr_ctx *ctx)
{
if (ctx->size &&
((strcmp(ctx->kname->name, XATTR_NAME_POSIX_ACL_ACCESS) == 0) ||
(strcmp(ctx->kname->name, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)))
posix_acl_fix_xattr_from_user(mnt_userns, d_inode(d),
ctx->kvalue, ctx->size);
}
int do_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
struct xattr_ctx *ctx)
{
setxattr_convert(mnt_userns, dentry, ctx);
return vfs_setxattr(mnt_userns, dentry, ctx->kname->name,
ctx->kvalue, ctx->size, ctx->flags);
}
static long
setxattr(struct user_namespace *mnt_userns, struct dentry *d,
const char __user *name, const void __user *value, size_t size,
int flags)
{
struct xattr_name kname;
struct xattr_ctx ctx = {
.cvalue = value,
.kvalue = NULL,
.size = size,
.kname = &kname,
.flags = flags,
};
int error;
error = setxattr_copy(name, &ctx);
if (error)
return error;
error = do_setxattr(mnt_userns, d, &ctx);
kvfree(ctx.kvalue);
return error;
}
static int path_setxattr(const char __user *pathname,
const char __user *name, const void __user *value,
size_t size, int flags, unsigned int lookup_flags)
{
struct path path;
int error;
retry:
error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
if (error)
return error;
error = mnt_want_write(path.mnt);
if (!error) {
error = setxattr(mnt_user_ns(path.mnt), path.dentry, name,
value, size, flags);
mnt_drop_write(path.mnt);
}
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
return error;
}
SYSCALL_DEFINE5(setxattr, const char __user *, pathname,
const char __user *, name, const void __user *, value,
size_t, size, int, flags)
{
return path_setxattr(pathname, name, value, size, flags, LOOKUP_FOLLOW);
}
SYSCALL_DEFINE5(lsetxattr, const char __user *, pathname,
const char __user *, name, const void __user *, value,
size_t, size, int, flags)
{
return path_setxattr(pathname, name, value, size, flags, 0);
}
SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name,
const void __user *,value, size_t, size, int, flags)
{
struct fd f = fdget(fd);
int error = -EBADF;
if (!f.file)
return error;
audit_file(f.file);
error = mnt_want_write_file(f.file);
if (!error) {
error = setxattr(file_mnt_user_ns(f.file),
f.file->f_path.dentry, name,
value, size, flags);
mnt_drop_write_file(f.file);
}
fdput(f);
return error;
}
/*
* Extended attribute GET operations
*/
ssize_t
do_getxattr(struct user_namespace *mnt_userns, struct dentry *d,
struct xattr_ctx *ctx)
{
ssize_t error;
char *kname = ctx->kname->name;
if (ctx->size) {
if (ctx->size > XATTR_SIZE_MAX)
ctx->size = XATTR_SIZE_MAX;
ctx->kvalue = kvzalloc(ctx->size, GFP_KERNEL);
if (!ctx->kvalue)
treewide: use kv[mz]alloc* rather than opencoded variants There are many code paths opencoding kvmalloc. Let's use the helper instead. The main difference to kvmalloc is that those users are usually not considering all the aspects of the memory allocator. E.g. allocation requests <= 32kB (with 4kB pages) are basically never failing and invoke OOM killer to satisfy the allocation. This sounds too disruptive for something that has a reasonable fallback - the vmalloc. On the other hand those requests might fallback to vmalloc even when the memory allocator would succeed after several more reclaim/compaction attempts previously. There is no guarantee something like that happens though. This patch converts many of those places to kv[mz]alloc* helpers because they are more conservative. Link: http://lkml.kernel.org/r/20170306103327.2766-2-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> # Xen bits Acked-by: Kees Cook <keescook@chromium.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Andreas Dilger <andreas.dilger@intel.com> # Lustre Acked-by: Christian Borntraeger <borntraeger@de.ibm.com> # KVM/s390 Acked-by: Dan Williams <dan.j.williams@intel.com> # nvdim Acked-by: David Sterba <dsterba@suse.com> # btrfs Acked-by: Ilya Dryomov <idryomov@gmail.com> # Ceph Acked-by: Tariq Toukan <tariqt@mellanox.com> # mlx4 Acked-by: Leon Romanovsky <leonro@mellanox.com> # mlx5 Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: Anton Vorontsov <anton@enomsg.org> Cc: Colin Cross <ccross@android.com> Cc: Tony Luck <tony.luck@intel.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Kent Overstreet <kent.overstreet@gmail.com> Cc: Santosh Raspatur <santosh@chelsio.com> Cc: Hariprasad S <hariprasad@chelsio.com> Cc: Yishai Hadas <yishaih@mellanox.com> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: "Yan, Zheng" <zyan@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-08 22:57:27 +00:00
return -ENOMEM;
}
error = vfs_getxattr(mnt_userns, d, kname, ctx->kvalue, ctx->size);
if (error > 0) {
2012-02-08 02:52:57 +00:00
if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) ||
(strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0))
fs: fix acl translation Last cycle we extended the idmapped mounts infrastructure to support idmapped mounts of idmapped filesystems (No such filesystem yet exist.). Since then, the meaning of an idmapped mount is a mount whose idmapping is different from the filesystems idmapping. While doing that work we missed to adapt the acl translation helpers. They still assume that checking for the identity mapping is enough. But they need to use the no_idmapping() helper instead. Note, POSIX ACLs are always translated right at the userspace-kernel boundary using the caller's current idmapping and the initial idmapping. The order depends on whether we're coming from or going to userspace. The filesystem's idmapping doesn't matter at the border. Consequently, if a non-idmapped mount is passed we need to make sure to always pass the initial idmapping as the mount's idmapping and not the filesystem idmapping. Since it's irrelevant here it would yield invalid ids and prevent setting acls for filesystems that are mountable in a userns and support posix acls (tmpfs and fuse). I verified the regression reported in [1] and verified that this patch fixes it. A regression test will be added to xfstests in parallel. Link: https://bugzilla.kernel.org/show_bug.cgi?id=215849 [1] Fixes: bd303368b776 ("fs: support mapped mounts of mapped filesystems") Cc: Seth Forshee <sforshee@digitalocean.com> Cc: Christoph Hellwig <hch@lst.de> Cc: <stable@vger.kernel.org> # 5.17 Cc: <regressions@lists.linux.dev> Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-04-19 13:14:23 +00:00
posix_acl_fix_xattr_to_user(mnt_userns, d_inode(d),
ctx->kvalue, error);
if (ctx->size && copy_to_user(ctx->value, ctx->kvalue, error))
error = -EFAULT;
} else if (error == -ERANGE && ctx->size >= XATTR_SIZE_MAX) {
/* The file system tried to returned a value bigger
than XATTR_SIZE_MAX bytes. Not possible. */
error = -E2BIG;
}
return error;
}
static ssize_t
getxattr(struct user_namespace *mnt_userns, struct dentry *d,
const char __user *name, void __user *value, size_t size)
{
ssize_t error;
struct xattr_name kname;
struct xattr_ctx ctx = {
.value = value,
.kvalue = NULL,
.size = size,
.kname = &kname,
.flags = 0,
};
error = strncpy_from_user(kname.name, name, sizeof(kname.name));
if (error == 0 || error == sizeof(kname.name))
error = -ERANGE;
if (error < 0)
return error;
error = do_getxattr(mnt_userns, d, &ctx);
kvfree(ctx.kvalue);
return error;
}
static ssize_t path_getxattr(const char __user *pathname,
const char __user *name, void __user *value,
size_t size, unsigned int lookup_flags)
{
struct path path;
ssize_t error;
retry:
error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
if (error)
return error;
error = getxattr(mnt_user_ns(path.mnt), path.dentry, name, value, size);
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
return error;
}
SYSCALL_DEFINE4(getxattr, const char __user *, pathname,
const char __user *, name, void __user *, value, size_t, size)
{
return path_getxattr(pathname, name, value, size, LOOKUP_FOLLOW);
}
SYSCALL_DEFINE4(lgetxattr, const char __user *, pathname,
const char __user *, name, void __user *, value, size_t, size)
{
return path_getxattr(pathname, name, value, size, 0);
}
SYSCALL_DEFINE4(fgetxattr, int, fd, const char __user *, name,
void __user *, value, size_t, size)
{
struct fd f = fdget(fd);
ssize_t error = -EBADF;
if (!f.file)
return error;
audit_file(f.file);
error = getxattr(file_mnt_user_ns(f.file), f.file->f_path.dentry,
name, value, size);
fdput(f);
return error;
}
/*
* Extended attribute LIST operations
*/
static ssize_t
listxattr(struct dentry *d, char __user *list, size_t size)
{
ssize_t error;
char *klist = NULL;
if (size) {
if (size > XATTR_LIST_MAX)
size = XATTR_LIST_MAX;
treewide: use kv[mz]alloc* rather than opencoded variants There are many code paths opencoding kvmalloc. Let's use the helper instead. The main difference to kvmalloc is that those users are usually not considering all the aspects of the memory allocator. E.g. allocation requests <= 32kB (with 4kB pages) are basically never failing and invoke OOM killer to satisfy the allocation. This sounds too disruptive for something that has a reasonable fallback - the vmalloc. On the other hand those requests might fallback to vmalloc even when the memory allocator would succeed after several more reclaim/compaction attempts previously. There is no guarantee something like that happens though. This patch converts many of those places to kv[mz]alloc* helpers because they are more conservative. Link: http://lkml.kernel.org/r/20170306103327.2766-2-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> # Xen bits Acked-by: Kees Cook <keescook@chromium.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Andreas Dilger <andreas.dilger@intel.com> # Lustre Acked-by: Christian Borntraeger <borntraeger@de.ibm.com> # KVM/s390 Acked-by: Dan Williams <dan.j.williams@intel.com> # nvdim Acked-by: David Sterba <dsterba@suse.com> # btrfs Acked-by: Ilya Dryomov <idryomov@gmail.com> # Ceph Acked-by: Tariq Toukan <tariqt@mellanox.com> # mlx4 Acked-by: Leon Romanovsky <leonro@mellanox.com> # mlx5 Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: Anton Vorontsov <anton@enomsg.org> Cc: Colin Cross <ccross@android.com> Cc: Tony Luck <tony.luck@intel.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Kent Overstreet <kent.overstreet@gmail.com> Cc: Santosh Raspatur <santosh@chelsio.com> Cc: Hariprasad S <hariprasad@chelsio.com> Cc: Yishai Hadas <yishaih@mellanox.com> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: "Yan, Zheng" <zyan@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-08 22:57:27 +00:00
klist = kvmalloc(size, GFP_KERNEL);
if (!klist)
return -ENOMEM;
}
error = vfs_listxattr(d, klist, size);
if (error > 0) {
if (size && copy_to_user(list, klist, error))
error = -EFAULT;
} else if (error == -ERANGE && size >= XATTR_LIST_MAX) {
/* The file system tried to returned a list bigger
than XATTR_LIST_MAX bytes. Not possible. */
error = -E2BIG;
}
kvfree(klist);
return error;
}
static ssize_t path_listxattr(const char __user *pathname, char __user *list,
size_t size, unsigned int lookup_flags)
{
struct path path;
ssize_t error;
retry:
error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
if (error)
return error;
error = listxattr(path.dentry, list, size);
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
return error;
}
SYSCALL_DEFINE3(listxattr, const char __user *, pathname, char __user *, list,
size_t, size)
{
return path_listxattr(pathname, list, size, LOOKUP_FOLLOW);
}
SYSCALL_DEFINE3(llistxattr, const char __user *, pathname, char __user *, list,
size_t, size)
{
return path_listxattr(pathname, list, size, 0);
}
SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size)
{
struct fd f = fdget(fd);
ssize_t error = -EBADF;
if (!f.file)
return error;
audit_file(f.file);
error = listxattr(f.file->f_path.dentry, list, size);
fdput(f);
return error;
}
/*
* Extended attribute REMOVE operations
*/
static long
removexattr(struct user_namespace *mnt_userns, struct dentry *d,
const char __user *name)
{
int error;
char kname[XATTR_NAME_MAX + 1];
error = strncpy_from_user(kname, name, sizeof(kname));
if (error == 0 || error == sizeof(kname))
error = -ERANGE;
if (error < 0)
return error;
return vfs_removexattr(mnt_userns, d, kname);
}
static int path_removexattr(const char __user *pathname,
const char __user *name, unsigned int lookup_flags)
{
struct path path;
int error;
retry:
error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
if (error)
return error;
error = mnt_want_write(path.mnt);
if (!error) {
error = removexattr(mnt_user_ns(path.mnt), path.dentry, name);
mnt_drop_write(path.mnt);
}
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
return error;
}
SYSCALL_DEFINE2(removexattr, const char __user *, pathname,
const char __user *, name)
{
return path_removexattr(pathname, name, LOOKUP_FOLLOW);
}
SYSCALL_DEFINE2(lremovexattr, const char __user *, pathname,
const char __user *, name)
{
return path_removexattr(pathname, name, 0);
}
SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name)
{
struct fd f = fdget(fd);
int error = -EBADF;
if (!f.file)
return error;
audit_file(f.file);
error = mnt_want_write_file(f.file);
if (!error) {
error = removexattr(file_mnt_user_ns(f.file),
f.file->f_path.dentry, name);
mnt_drop_write_file(f.file);
}
fdput(f);
return error;
}
/*
* Combine the results of the list() operation from every xattr_handler in the
* list.
*/
ssize_t
generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
{
const struct xattr_handler *handler, **handlers = dentry->d_sb->s_xattr;
unsigned int size = 0;
if (!buffer) {
for_each_xattr_handler(handlers, handler) {
if (!handler->name ||
(handler->list && !handler->list(dentry)))
continue;
size += strlen(handler->name) + 1;
}
} else {
char *buf = buffer;
size_t len;
for_each_xattr_handler(handlers, handler) {
if (!handler->name ||
(handler->list && !handler->list(dentry)))
continue;
len = strlen(handler->name);
if (len + 1 > buffer_size)
return -ERANGE;
memcpy(buf, handler->name, len + 1);
buf += len + 1;
buffer_size -= len + 1;
}
size = buf - buffer;
}
return size;
}
EXPORT_SYMBOL(generic_listxattr);
/**
* xattr_full_name - Compute full attribute name from suffix
*
* @handler: handler of the xattr_handler operation
* @name: name passed to the xattr_handler operation
*
* The get and set xattr handler operations are called with the remainder of
* the attribute name after skipping the handler's prefix: for example, "foo"
* is passed to the get operation of a handler with prefix "user." to get
* attribute "user.foo". The full name is still "there" in the name though.
*
* Note: the list xattr handler operation when called from the vfs is passed a
* NULL name; some file systems use this operation internally, with varying
* semantics.
*/
const char *xattr_full_name(const struct xattr_handler *handler,
const char *name)
{
size_t prefix_len = strlen(xattr_prefix(handler));
return name - prefix_len;
}
EXPORT_SYMBOL(xattr_full_name);
/*
* Allocate new xattr and copy in the value; but leave the name to callers.
*/
struct simple_xattr *simple_xattr_alloc(const void *value, size_t size)
{
struct simple_xattr *new_xattr;
size_t len;
/* wrap around? */
len = sizeof(*new_xattr) + size;
if (len < sizeof(*new_xattr))
return NULL;
new_xattr = kvmalloc(len, GFP_KERNEL);
if (!new_xattr)
return NULL;
new_xattr->size = size;
memcpy(new_xattr->value, value, size);
return new_xattr;
}
/*
* xattr GET operation for in-memory/pseudo filesystems
*/
int simple_xattr_get(struct simple_xattrs *xattrs, const char *name,
void *buffer, size_t size)
{
struct simple_xattr *xattr;
int ret = -ENODATA;
spin_lock(&xattrs->lock);
list_for_each_entry(xattr, &xattrs->head, list) {
if (strcmp(name, xattr->name))
continue;
ret = xattr->size;
if (buffer) {
if (size < xattr->size)
ret = -ERANGE;
else
memcpy(buffer, xattr->value, xattr->size);
}
break;
}
spin_unlock(&xattrs->lock);
return ret;
}
/**
* simple_xattr_set - xattr SET operation for in-memory/pseudo filesystems
* @xattrs: target simple_xattr list
* @name: name of the extended attribute
* @value: value of the xattr. If %NULL, will remove the attribute.
* @size: size of the new xattr
* @flags: %XATTR_{CREATE|REPLACE}
* @removed_size: returns size of the removed xattr, -1 if none removed
*
* %XATTR_CREATE is set, the xattr shouldn't exist already; otherwise fails
* with -EEXIST. If %XATTR_REPLACE is set, the xattr should exist;
* otherwise, fails with -ENODATA.
*
* Returns 0 on success, -errno on failure.
*/
int simple_xattr_set(struct simple_xattrs *xattrs, const char *name,
const void *value, size_t size, int flags,
ssize_t *removed_size)
{
struct simple_xattr *xattr;
struct simple_xattr *new_xattr = NULL;
int err = 0;
if (removed_size)
*removed_size = -1;
/* value == NULL means remove */
if (value) {
new_xattr = simple_xattr_alloc(value, size);
if (!new_xattr)
return -ENOMEM;
new_xattr->name = kstrdup(name, GFP_KERNEL);
if (!new_xattr->name) {
kvfree(new_xattr);
return -ENOMEM;
}
}
spin_lock(&xattrs->lock);
list_for_each_entry(xattr, &xattrs->head, list) {
if (!strcmp(name, xattr->name)) {
if (flags & XATTR_CREATE) {
xattr = new_xattr;
err = -EEXIST;
} else if (new_xattr) {
list_replace(&xattr->list, &new_xattr->list);
if (removed_size)
*removed_size = xattr->size;
} else {
list_del(&xattr->list);
if (removed_size)
*removed_size = xattr->size;
}
goto out;
}
}
if (flags & XATTR_REPLACE) {
xattr = new_xattr;
err = -ENODATA;
} else {
list_add(&new_xattr->list, &xattrs->head);
xattr = NULL;
}
out:
spin_unlock(&xattrs->lock);
if (xattr) {
kfree(xattr->name);
kvfree(xattr);
}
return err;
}
static bool xattr_is_trusted(const char *name)
{
return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN);
}
static int xattr_list_one(char **buffer, ssize_t *remaining_size,
const char *name)
{
size_t len = strlen(name) + 1;
if (*buffer) {
if (*remaining_size < len)
return -ERANGE;
memcpy(*buffer, name, len);
*buffer += len;
}
*remaining_size -= len;
return 0;
}
/*
* xattr LIST operation for in-memory/pseudo filesystems
*/
ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
char *buffer, size_t size)
{
bool trusted = capable(CAP_SYS_ADMIN);
struct simple_xattr *xattr;
ssize_t remaining_size = size;
int err = 0;
#ifdef CONFIG_FS_POSIX_ACL
if (IS_POSIXACL(inode)) {
if (inode->i_acl) {
err = xattr_list_one(&buffer, &remaining_size,
XATTR_NAME_POSIX_ACL_ACCESS);
if (err)
return err;
}
if (inode->i_default_acl) {
err = xattr_list_one(&buffer, &remaining_size,
XATTR_NAME_POSIX_ACL_DEFAULT);
if (err)
return err;
}
}
#endif
spin_lock(&xattrs->lock);
list_for_each_entry(xattr, &xattrs->head, list) {
/* skip "trusted." attributes for unprivileged callers */
if (!trusted && xattr_is_trusted(xattr->name))
continue;
err = xattr_list_one(&buffer, &remaining_size, xattr->name);
if (err)
break;
}
spin_unlock(&xattrs->lock);
return err ? err : size - remaining_size;
}
/*
* Adds an extended attribute to the list
*/
void simple_xattr_list_add(struct simple_xattrs *xattrs,
struct simple_xattr *new_xattr)
{
spin_lock(&xattrs->lock);
list_add(&new_xattr->list, &xattrs->head);
spin_unlock(&xattrs->lock);
}