summaryrefslogtreecommitdiffstats
path: root/fs/inode.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-02-20 20:53:11 +0100
committerLinus Torvalds <torvalds@linux-foundation.org>2023-02-20 20:53:11 +0100
commit05e6295f7b5e05f09e369a3eb2882ec5b40fff20 (patch)
tree60ea7c6806f58371bfafe6317089c7ae1a65fca4 /fs/inode.c
parentMerge tag 'iversion-v6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/jl... (diff)
parentshmem: support idmapped mounts for tmpfs (diff)
downloadlinux-05e6295f7b5e05f09e369a3eb2882ec5b40fff20.tar.xz
linux-05e6295f7b5e05f09e369a3eb2882ec5b40fff20.zip
Merge tag 'fs.idmapped.v6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping
Pull vfs idmapping updates from Christian Brauner: - Last cycle we introduced the dedicated struct mnt_idmap type for mount idmapping and the required infrastucture in 256c8aed2b42 ("fs: introduce dedicated idmap type for mounts"). As promised in last cycle's pull request message this converts everything to rely on struct mnt_idmap. Currently we still pass around the plain namespace that was attached to a mount. This is in general pretty convenient but it makes it easy to conflate namespaces that are relevant on the filesystem with namespaces that are relevant on the mount level. Especially for non-vfs developers without detailed knowledge in this area this was a potential source for bugs. This finishes the conversion. Instead of passing the plain namespace around this updates all places that currently take a pointer to a mnt_userns with a pointer to struct mnt_idmap. Now that the conversion is done all helpers down to the really low-level helpers only accept a struct mnt_idmap argument instead of two namespace arguments. Conflating mount and other idmappings will now cause the compiler to complain loudly thus eliminating the possibility of any bugs. This makes it impossible for filesystem developers to mix up mount and filesystem idmappings as they are two distinct types and require distinct helpers that cannot be used interchangeably. Everything associated with struct mnt_idmap is moved into a single separate file. With that change no code can poke around in struct mnt_idmap. It can only be interacted with through dedicated helpers. That means all filesystems are and all of the vfs is completely oblivious to the actual implementation of idmappings. We are now also able to extend struct mnt_idmap as we see fit. For example, we can decouple it completely from namespaces for users that don't require or don't want to use them at all. We can also extend the concept of idmappings so we can cover filesystem specific requirements. In combination with the vfs{g,u}id_t work we finished in v6.2 this makes this feature substantially more robust and thus difficult to implement wrong by a given filesystem and also protects the vfs. - Enable idmapped mounts for tmpfs and fulfill a longstanding request. A long-standing request from users had been to make it possible to create idmapped mounts for tmpfs. For example, to share the host's tmpfs mount between multiple sandboxes. This is a prerequisite for some advanced Kubernetes cases. Systemd also has a range of use-cases to increase service isolation. And there are more users of this. However, with all of the other work going on this was way down on the priority list but luckily someone other than ourselves picked this up. As usual the patch is tiny as all the infrastructure work had been done multiple kernel releases ago. In addition to all the tests that we already have I requested that Rodrigo add a dedicated tmpfs testsuite for idmapped mounts to xfstests. It is to be included into xfstests during the v6.3 development cycle. This should add a slew of additional tests. * tag 'fs.idmapped.v6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping: (26 commits) shmem: support idmapped mounts for tmpfs fs: move mnt_idmap fs: port vfs{g,u}id helpers to mnt_idmap fs: port fs{g,u}id helpers to mnt_idmap fs: port i_{g,u}id_into_vfs{g,u}id() to mnt_idmap fs: port i_{g,u}id_{needs_}update() to mnt_idmap quota: port to mnt_idmap fs: port privilege checking helpers to mnt_idmap fs: port inode_owner_or_capable() to mnt_idmap fs: port inode_init_owner() to mnt_idmap fs: port acl to mnt_idmap fs: port xattr to mnt_idmap fs: port ->permission() to pass mnt_idmap fs: port ->fileattr_set() to pass mnt_idmap fs: port ->set_acl() to pass mnt_idmap fs: port ->get_acl() to pass mnt_idmap fs: port ->tmpfile() to pass mnt_idmap fs: port ->rename() to pass mnt_idmap fs: port ->mknod() to pass mnt_idmap fs: port ->mkdir() to pass mnt_idmap ...
Diffstat (limited to 'fs/inode.c')
-rw-r--r--fs/inode.c57
1 files changed, 28 insertions, 29 deletions
diff --git a/fs/inode.c b/fs/inode.c
index d02dd8f1e967..4558dc2f1355 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1894,7 +1894,7 @@ bool atime_needs_update(const struct path *path, struct inode *inode)
/* Atime updates will likely cause i_uid and i_gid to be written
* back improprely if their true value is unknown to the vfs.
*/
- if (HAS_UNMAPPED_ID(mnt_user_ns(mnt), inode))
+ if (HAS_UNMAPPED_ID(mnt_idmap(mnt), inode))
return false;
if (IS_NOATIME(inode))
@@ -1954,7 +1954,7 @@ EXPORT_SYMBOL(touch_atime);
* response to write or truncate. Return 0 if nothing has to be changed.
* Negative value on error (change should be denied).
*/
-int dentry_needs_remove_privs(struct user_namespace *mnt_userns,
+int dentry_needs_remove_privs(struct mnt_idmap *idmap,
struct dentry *dentry)
{
struct inode *inode = d_inode(dentry);
@@ -1964,7 +1964,7 @@ int dentry_needs_remove_privs(struct user_namespace *mnt_userns,
if (IS_NOSEC(inode))
return 0;
- mask = setattr_should_drop_suidgid(mnt_userns, inode);
+ mask = setattr_should_drop_suidgid(idmap, inode);
ret = security_inode_need_killpriv(dentry);
if (ret < 0)
return ret;
@@ -1973,7 +1973,7 @@ int dentry_needs_remove_privs(struct user_namespace *mnt_userns,
return mask;
}
-static int __remove_privs(struct user_namespace *mnt_userns,
+static int __remove_privs(struct mnt_idmap *idmap,
struct dentry *dentry, int kill)
{
struct iattr newattrs;
@@ -1983,7 +1983,7 @@ static int __remove_privs(struct user_namespace *mnt_userns,
* Note we call this on write, so notify_change will not
* encounter any conflicting delegations:
*/
- return notify_change(mnt_userns, dentry, &newattrs, NULL);
+ return notify_change(idmap, dentry, &newattrs, NULL);
}
static int __file_remove_privs(struct file *file, unsigned int flags)
@@ -1996,7 +1996,7 @@ static int __file_remove_privs(struct file *file, unsigned int flags)
if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode))
return 0;
- kill = dentry_needs_remove_privs(file_mnt_user_ns(file), dentry);
+ kill = dentry_needs_remove_privs(file_mnt_idmap(file), dentry);
if (kill < 0)
return kill;
@@ -2004,7 +2004,7 @@ static int __file_remove_privs(struct file *file, unsigned int flags)
if (flags & IOCB_NOWAIT)
return -EAGAIN;
- error = __remove_privs(file_mnt_user_ns(file), dentry, kill);
+ error = __remove_privs(file_mnt_idmap(file), dentry, kill);
}
if (!error)
@@ -2280,21 +2280,21 @@ EXPORT_SYMBOL(init_special_inode);
/**
* inode_init_owner - Init uid,gid,mode for new inode according to posix standards
- * @mnt_userns: User namespace of the mount the inode was created from
+ * @idmap: idmap of the mount the inode was created from
* @inode: New inode
* @dir: Directory inode
* @mode: mode of the new inode
*
- * If the inode has been created through an idmapped mount the user namespace of
- * the vfsmount must be passed through @mnt_userns. This function will then take
- * care to map the inode according to @mnt_userns before checking permissions
+ * If the inode has been created through an idmapped mount the idmap of
+ * the vfsmount must be passed through @idmap. This function will then take
+ * care to map the inode according to @idmap before checking permissions
* and initializing i_uid and i_gid. On non-idmapped mounts or if permission
- * checking is to be performed on the raw inode simply passs init_user_ns.
+ * checking is to be performed on the raw inode simply pass @nop_mnt_idmap.
*/
-void inode_init_owner(struct user_namespace *mnt_userns, struct inode *inode,
+void inode_init_owner(struct mnt_idmap *idmap, struct inode *inode,
const struct inode *dir, umode_t mode)
{
- inode_fsuid_set(inode, mnt_userns);
+ inode_fsuid_set(inode, idmap);
if (dir && dir->i_mode & S_ISGID) {
inode->i_gid = dir->i_gid;
@@ -2302,32 +2302,32 @@ void inode_init_owner(struct user_namespace *mnt_userns, struct inode *inode,
if (S_ISDIR(mode))
mode |= S_ISGID;
} else
- inode_fsgid_set(inode, mnt_userns);
+ inode_fsgid_set(inode, idmap);
inode->i_mode = mode;
}
EXPORT_SYMBOL(inode_init_owner);
/**
* inode_owner_or_capable - check current task permissions to inode
- * @mnt_userns: user namespace of the mount the inode was found from
+ * @idmap: idmap of the mount the inode was found from
* @inode: inode being checked
*
* Return true if current either has CAP_FOWNER in a namespace with the
* inode owner uid mapped, or owns the file.
*
- * If the inode has been found through an idmapped mount the user namespace of
- * the vfsmount must be passed through @mnt_userns. This function will then take
- * care to map the inode according to @mnt_userns before checking permissions.
+ * If the inode has been found through an idmapped mount the idmap of
+ * the vfsmount must be passed through @idmap. This function will then take
+ * care to map the inode according to @idmap before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply passs init_user_ns.
+ * raw inode simply passs @nop_mnt_idmap.
*/
-bool inode_owner_or_capable(struct user_namespace *mnt_userns,
+bool inode_owner_or_capable(struct mnt_idmap *idmap,
const struct inode *inode)
{
vfsuid_t vfsuid;
struct user_namespace *ns;
- vfsuid = i_uid_into_vfsuid(mnt_userns, inode);
+ vfsuid = i_uid_into_vfsuid(idmap, inode);
if (vfsuid_eq_kuid(vfsuid, current_fsuid()))
return true;
@@ -2459,7 +2459,7 @@ EXPORT_SYMBOL(current_time);
/**
* in_group_or_capable - check whether caller is CAP_FSETID privileged
- * @mnt_userns: user namespace of the mount @inode was found from
+ * @idmap: idmap of the mount @inode was found from
* @inode: inode to check
* @vfsgid: the new/current vfsgid of @inode
*
@@ -2469,19 +2469,19 @@ EXPORT_SYMBOL(current_time);
*
* Return: true if the caller is sufficiently privileged, false if not.
*/
-bool in_group_or_capable(struct user_namespace *mnt_userns,
+bool in_group_or_capable(struct mnt_idmap *idmap,
const struct inode *inode, vfsgid_t vfsgid)
{
if (vfsgid_in_group_p(vfsgid))
return true;
- if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID))
+ if (capable_wrt_inode_uidgid(idmap, inode, CAP_FSETID))
return true;
return false;
}
/**
* mode_strip_sgid - handle the sgid bit for non-directories
- * @mnt_userns: User namespace of the mount the inode was created from
+ * @idmap: idmap of the mount the inode was created from
* @dir: parent directory inode
* @mode: mode of the file to be created in @dir
*
@@ -2493,15 +2493,14 @@ bool in_group_or_capable(struct user_namespace *mnt_userns,
*
* Return: the new mode to use for the file
*/
-umode_t mode_strip_sgid(struct user_namespace *mnt_userns,
+umode_t mode_strip_sgid(struct mnt_idmap *idmap,
const struct inode *dir, umode_t mode)
{
if ((mode & (S_ISGID | S_IXGRP)) != (S_ISGID | S_IXGRP))
return mode;
if (S_ISDIR(mode) || !dir || !(dir->i_mode & S_ISGID))
return mode;
- if (in_group_or_capable(mnt_userns, dir,
- i_gid_into_vfsgid(mnt_userns, dir)))
+ if (in_group_or_capable(idmap, dir, i_gid_into_vfsgid(idmap, dir)))
return mode;
return mode & ~S_ISGID;
}