diff mbox series

[v2,10/13] ceph: allow idmapped setattr inode op

Message ID 20230524153316.476973-11-aleksandr.mikhalitsyn@canonical.com
State New
Headers show
Series ceph: support idmapped mounts | expand

Commit Message

Aleksandr Mikhalitsyn May 24, 2023, 3:33 p.m. UTC 
From: Christian Brauner <christian.brauner@ubuntu.com>

Enable __ceph_setattr() to handle idmapped mounts. This is just a matter
of passing down the mount's idmapping.

Cc: Jeff Layton <jlayton@kernel.org>
Cc: Ilya Dryomov <idryomov@gmail.com>
Cc: ceph-devel@vger.kernel.org
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com>
---
 fs/ceph/inode.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

Comments

Aleksandr Mikhalitsyn June 2, 2023, 12:45 p.m. UTC | #1 
On Fri, Jun 2, 2023 at 3:30 AM Xiubo Li <xiubli@redhat.com> wrote:
>
>
> On 5/24/23 23:33, Alexander Mikhalitsyn wrote:
> > From: Christian Brauner <christian.brauner@ubuntu.com>
> >
> > Enable __ceph_setattr() to handle idmapped mounts. This is just a matter
> > of passing down the mount's idmapping.
> >
> > Cc: Jeff Layton <jlayton@kernel.org>
> > Cc: Ilya Dryomov <idryomov@gmail.com>
> > Cc: ceph-devel@vger.kernel.org
> > Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
> > Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com>
> > ---
> >   fs/ceph/inode.c | 11 +++++++++--
> >   1 file changed, 9 insertions(+), 2 deletions(-)
> >
> > diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
> > index 37e1cbfc7c89..f1f934439be0 100644
> > --- a/fs/ceph/inode.c
> > +++ b/fs/ceph/inode.c
> > @@ -2050,6 +2050,13 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr)
> >
> >       dout("setattr %p issued %s\n", inode, ceph_cap_string(issued));
> >
> > +     /*
> > +      * The attr->ia_{g,u}id members contain the target {g,u}id we're
> > +      * sending over the wire. The mount idmapping only matters when we
> > +      * create new filesystem objects based on the caller's mapped
> > +      * fs{g,u}id.
> > +      */
> > +     req->r_mnt_idmap = &nop_mnt_idmap;
>
> For example with an idmapping 1000:0 and in the /mnt/idmapped_ceph/.
>
> This means the "__ceph_setattr()" will always use UID 0 to set the
> caller_uid, right ? If it is then the client auth checking for the

Yes, if you have a mapping like b:1000:0:1 (the last number is a
length of a mapping). It means even more,
the only user from which you can create something on the filesystem
will be UID = 0,
because all other UIDs/GIDs are not mapped and you'll instantly get
-EOVERFLOW from the kernel.

> setattr requests in cephfs MDS will succeed, since the UID 0 is root.
> But if you use a different idmapping, such as 1000:2000, it will fail.

If you have a mapping b:1000:2000:1 then the only valid UID/GID from
which you can create something
on an idmapped mount will be UID/GID = 2000:2000 (and this will be
mapped to 1000:1000 and sent over the wire,
because we performing an idmapping procedure for requests those are
creating inodes).
So, even root with UID = 0 will not be able to create a file on such a
mount and get -EOVERFLOW.

>
> So here IMO we should set it to 'idmap' too ?

Good question. I can't see any obvious issue with setting an actual
idmapping here.
It will be interesting to know Christian's opinion about this.

Kind regards,
Alex

>
> Thanks
>
> - Xiubo
>
> >       if (ia_valid & ATTR_UID) {
> >               dout("setattr %p uid %d -> %d\n", inode,
> >                    from_kuid(&init_user_ns, inode->i_uid),
> > @@ -2240,7 +2247,7 @@ int ceph_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
> >       if (ceph_inode_is_shutdown(inode))
> >               return -ESTALE;
> >
> > -     err = setattr_prepare(&nop_mnt_idmap, dentry, attr);
> > +     err = setattr_prepare(idmap, dentry, attr);
> >       if (err != 0)
> >               return err;
> >
> > @@ -2255,7 +2262,7 @@ int ceph_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
> >       err = __ceph_setattr(inode, attr);
> >
> >       if (err >= 0 && (attr->ia_valid & ATTR_MODE))
> > -             err = posix_acl_chmod(&nop_mnt_idmap, dentry, attr->ia_mode);
> > +             err = posix_acl_chmod(idmap, dentry, attr->ia_mode);
> >
> >       return err;
> >   }
>
Aleksandr Mikhalitsyn June 2, 2023, 1:05 p.m. UTC | #2 
On Fri, Jun 2, 2023 at 2:54 PM Christian Brauner <brauner@kernel.org> wrote:
>
> On Fri, Jun 02, 2023 at 02:45:30PM +0200, Aleksandr Mikhalitsyn wrote:
> > On Fri, Jun 2, 2023 at 3:30 AM Xiubo Li <xiubli@redhat.com> wrote:
> > >
> > >
> > > On 5/24/23 23:33, Alexander Mikhalitsyn wrote:
> > > > From: Christian Brauner <christian.brauner@ubuntu.com>
> > > >
> > > > Enable __ceph_setattr() to handle idmapped mounts. This is just a matter
> > > > of passing down the mount's idmapping.
> > > >
> > > > Cc: Jeff Layton <jlayton@kernel.org>
> > > > Cc: Ilya Dryomov <idryomov@gmail.com>
> > > > Cc: ceph-devel@vger.kernel.org
> > > > Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
> > > > Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com>
> > > > ---
> > > >   fs/ceph/inode.c | 11 +++++++++--
> > > >   1 file changed, 9 insertions(+), 2 deletions(-)
> > > >
> > > > diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
> > > > index 37e1cbfc7c89..f1f934439be0 100644
> > > > --- a/fs/ceph/inode.c
> > > > +++ b/fs/ceph/inode.c
> > > > @@ -2050,6 +2050,13 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr)
> > > >
> > > >       dout("setattr %p issued %s\n", inode, ceph_cap_string(issued));
> > > >
> > > > +     /*
> > > > +      * The attr->ia_{g,u}id members contain the target {g,u}id we're
>
> This is now obsolete... In earlier imlementations attr->ia_{g,u}id was
> used and contained the filesystem wide value, not the idmapped mount
> value.
>
> However, this was misleading and we changed that in commit b27c82e12965
> ("attr: port attribute changes to new types") and introduced dedicated
> new types into struct iattr->ia_vfs{g,u}id. So the you need to use
> attr->ia_vfs{g,u}id as documented in include/linux/fs.h and you need to
> transform them into filesystem wide values and then to raw values you
> send over the wire.
>
> Alex should be able to figure this out though.

Hi Christian,

Thanks for pointing this out. Unfortunately I wasn't able to notice
that. I'll take a look closer and fix that.

>
> > > > +      * sending over the wire. The mount idmapping only matters when we
> > > > +      * create new filesystem objects based on the caller's mapped
> > > > +      * fs{g,u}id.
> > > > +      */
> > > > +     req->r_mnt_idmap = &nop_mnt_idmap;
> > >
> > > For example with an idmapping 1000:0 and in the /mnt/idmapped_ceph/.
> > >
> > > This means the "__ceph_setattr()" will always use UID 0 to set the
> > > caller_uid, right ? If it is then the client auth checking for the
> >
> > Yes, if you have a mapping like b:1000:0:1 (the last number is a
> > length of a mapping). It means even more,
> > the only user from which you can create something on the filesystem
> > will be UID = 0,
> > because all other UIDs/GIDs are not mapped and you'll instantly get
> > -EOVERFLOW from the kernel.
> >
> > > setattr requests in cephfs MDS will succeed, since the UID 0 is root.
> > > But if you use a different idmapping, such as 1000:2000, it will fail.
> >
> > If you have a mapping b:1000:2000:1 then the only valid UID/GID from
> > which you can create something
> > on an idmapped mount will be UID/GID = 2000:2000 (and this will be
> > mapped to 1000:1000 and sent over the wire,
> > because we performing an idmapping procedure for requests those are
> > creating inodes).
> > So, even root with UID = 0 will not be able to create a file on such a
> > mount and get -EOVERFLOW.
> >
> > >
> > > So here IMO we should set it to 'idmap' too ?
> >
> > Good question. I can't see any obvious issue with setting an actual
> > idmapping here.
> > It will be interesting to know Christian's opinion about this.

^

Kind regards,
Alex

> >
> > Kind regards,
> > Alex
> >
> > >
> > > Thanks
> > >
> > > - Xiubo
> > >
> > > >       if (ia_valid & ATTR_UID) {
> > > >               dout("setattr %p uid %d -> %d\n", inode,
> > > >                    from_kuid(&init_user_ns, inode->i_uid),
> > > > @@ -2240,7 +2247,7 @@ int ceph_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
> > > >       if (ceph_inode_is_shutdown(inode))
> > > >               return -ESTALE;
> > > >
> > > > -     err = setattr_prepare(&nop_mnt_idmap, dentry, attr);
> > > > +     err = setattr_prepare(idmap, dentry, attr);
> > > >       if (err != 0)
> > > >               return err;
> > > >
> > > > @@ -2255,7 +2262,7 @@ int ceph_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
> > > >       err = __ceph_setattr(inode, attr);
> > > >
> > > >       if (err >= 0 && (attr->ia_valid & ATTR_MODE))
> > > > -             err = posix_acl_chmod(&nop_mnt_idmap, dentry, attr->ia_mode);
> > > > +             err = posix_acl_chmod(idmap, dentry, attr->ia_mode);
> > > >
> > > >       return err;
> > > >   }
> > >
Aleksandr Mikhalitsyn June 2, 2023, 1:15 p.m. UTC | #3 
On Fri, Jun 2, 2023 at 3:08 PM Christian Brauner <brauner@kernel.org> wrote:
>
> On Fri, Jun 02, 2023 at 03:05:50PM +0200, Aleksandr Mikhalitsyn wrote:
> > On Fri, Jun 2, 2023 at 2:54 PM Christian Brauner <brauner@kernel.org> wrote:
> > >
> > > On Fri, Jun 02, 2023 at 02:45:30PM +0200, Aleksandr Mikhalitsyn wrote:
> > > > On Fri, Jun 2, 2023 at 3:30 AM Xiubo Li <xiubli@redhat.com> wrote:
> > > > >
> > > > >
> > > > > On 5/24/23 23:33, Alexander Mikhalitsyn wrote:
> > > > > > From: Christian Brauner <christian.brauner@ubuntu.com>
> > > > > >
> > > > > > Enable __ceph_setattr() to handle idmapped mounts. This is just a matter
> > > > > > of passing down the mount's idmapping.
> > > > > >
> > > > > > Cc: Jeff Layton <jlayton@kernel.org>
> > > > > > Cc: Ilya Dryomov <idryomov@gmail.com>
> > > > > > Cc: ceph-devel@vger.kernel.org
> > > > > > Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
> > > > > > Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com>
> > > > > > ---
> > > > > >   fs/ceph/inode.c | 11 +++++++++--
> > > > > >   1 file changed, 9 insertions(+), 2 deletions(-)
> > > > > >
> > > > > > diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
> > > > > > index 37e1cbfc7c89..f1f934439be0 100644
> > > > > > --- a/fs/ceph/inode.c
> > > > > > +++ b/fs/ceph/inode.c
> > > > > > @@ -2050,6 +2050,13 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr)
> > > > > >
> > > > > >       dout("setattr %p issued %s\n", inode, ceph_cap_string(issued));
> > > > > >
> > > > > > +     /*
> > > > > > +      * The attr->ia_{g,u}id members contain the target {g,u}id we're
> > >
> > > This is now obsolete... In earlier imlementations attr->ia_{g,u}id was
> > > used and contained the filesystem wide value, not the idmapped mount
> > > value.
> > >
> > > However, this was misleading and we changed that in commit b27c82e12965
> > > ("attr: port attribute changes to new types") and introduced dedicated
> > > new types into struct iattr->ia_vfs{g,u}id. So the you need to use
> > > attr->ia_vfs{g,u}id as documented in include/linux/fs.h and you need to
> > > transform them into filesystem wide values and then to raw values you
> > > send over the wire.
> > >
> > > Alex should be able to figure this out though.
> >
> > Hi Christian,
> >
> > Thanks for pointing this out. Unfortunately I wasn't able to notice
> > that. I'll take a look closer and fix that.
>
> Just to clarify: I wasn't trying to imply that you should've figured
> this out on your own. I was just trying to say that you should be able
> figure out the exact details how to implement this in ceph after I told
> you about the attr->ia_vfs{g,u}id change.

No problem, I've got your idea the same as you explained it ;-)
I'll rework that place and I will recheck that we pass xfstests after that.
Aleksandr Mikhalitsyn June 7, 2023, 3:28 p.m. UTC | #4 
On Fri, Jun 2, 2023 at 2:54 PM Christian Brauner <brauner@kernel.org> wrote:
>
> On Fri, Jun 02, 2023 at 02:45:30PM +0200, Aleksandr Mikhalitsyn wrote:
> > On Fri, Jun 2, 2023 at 3:30 AM Xiubo Li <xiubli@redhat.com> wrote:
> > >
> > >
> > > On 5/24/23 23:33, Alexander Mikhalitsyn wrote:
> > > > From: Christian Brauner <christian.brauner@ubuntu.com>
> > > >
> > > > Enable __ceph_setattr() to handle idmapped mounts. This is just a matter
> > > > of passing down the mount's idmapping.
> > > >
> > > > Cc: Jeff Layton <jlayton@kernel.org>
> > > > Cc: Ilya Dryomov <idryomov@gmail.com>
> > > > Cc: ceph-devel@vger.kernel.org
> > > > Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
> > > > Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com>
> > > > ---
> > > >   fs/ceph/inode.c | 11 +++++++++--
> > > >   1 file changed, 9 insertions(+), 2 deletions(-)
> > > >
> > > > diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
> > > > index 37e1cbfc7c89..f1f934439be0 100644
> > > > --- a/fs/ceph/inode.c
> > > > +++ b/fs/ceph/inode.c
> > > > @@ -2050,6 +2050,13 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr)
> > > >
> > > >       dout("setattr %p issued %s\n", inode, ceph_cap_string(issued));
> > > >
> > > > +     /*
> > > > +      * The attr->ia_{g,u}id members contain the target {g,u}id we're
>
> This is now obsolete... In earlier imlementations attr->ia_{g,u}id was
> used and contained the filesystem wide value, not the idmapped mount
> value.
>
> However, this was misleading and we changed that in commit b27c82e12965
> ("attr: port attribute changes to new types") and introduced dedicated
> new types into struct iattr->ia_vfs{g,u}id. So the you need to use
> attr->ia_vfs{g,u}id as documented in include/linux/fs.h and you need to
> transform them into filesystem wide values and then to raw values you
> send over the wire.
>
> Alex should be able to figure this out though.

Hi Christian,

Reworked in v3:
https://lore.kernel.org/lkml/20230607152038.469739-12-aleksandr.mikhalitsyn@canonical.com/#t

The only thing is that I've forgotten to remove the comment, but I'll
do that in v4.

Kind regards,
Alex

>
> > > > +      * sending over the wire. The mount idmapping only matters when we
> > > > +      * create new filesystem objects based on the caller's mapped
> > > > +      * fs{g,u}id.
> > > > +      */
> > > > +     req->r_mnt_idmap = &nop_mnt_idmap;
> > >
> > > For example with an idmapping 1000:0 and in the /mnt/idmapped_ceph/.
> > >
> > > This means the "__ceph_setattr()" will always use UID 0 to set the
> > > caller_uid, right ? If it is then the client auth checking for the
> >
> > Yes, if you have a mapping like b:1000:0:1 (the last number is a
> > length of a mapping). It means even more,
> > the only user from which you can create something on the filesystem
> > will be UID = 0,
> > because all other UIDs/GIDs are not mapped and you'll instantly get
> > -EOVERFLOW from the kernel.
> >
> > > setattr requests in cephfs MDS will succeed, since the UID 0 is root.
> > > But if you use a different idmapping, such as 1000:2000, it will fail.
> >
> > If you have a mapping b:1000:2000:1 then the only valid UID/GID from
> > which you can create something
> > on an idmapped mount will be UID/GID = 2000:2000 (and this will be
> > mapped to 1000:1000 and sent over the wire,
> > because we performing an idmapping procedure for requests those are
> > creating inodes).
> > So, even root with UID = 0 will not be able to create a file on such a
> > mount and get -EOVERFLOW.
> >
> > >
> > > So here IMO we should set it to 'idmap' too ?
> >
> > Good question. I can't see any obvious issue with setting an actual
> > idmapping here.
> > It will be interesting to know Christian's opinion about this.
> >
> > Kind regards,
> > Alex
> >
> > >
> > > Thanks
> > >
> > > - Xiubo
> > >
> > > >       if (ia_valid & ATTR_UID) {
> > > >               dout("setattr %p uid %d -> %d\n", inode,
> > > >                    from_kuid(&init_user_ns, inode->i_uid),
> > > > @@ -2240,7 +2247,7 @@ int ceph_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
> > > >       if (ceph_inode_is_shutdown(inode))
> > > >               return -ESTALE;
> > > >
> > > > -     err = setattr_prepare(&nop_mnt_idmap, dentry, attr);
> > > > +     err = setattr_prepare(idmap, dentry, attr);
> > > >       if (err != 0)
> > > >               return err;
> > > >
> > > > @@ -2255,7 +2262,7 @@ int ceph_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
> > > >       err = __ceph_setattr(inode, attr);
> > > >
> > > >       if (err >= 0 && (attr->ia_valid & ATTR_MODE))
> > > > -             err = posix_acl_chmod(&nop_mnt_idmap, dentry, attr->ia_mode);
> > > > +             err = posix_acl_chmod(idmap, dentry, attr->ia_mode);
> > > >
> > > >       return err;
> > > >   }
> > >
diff mbox series

Patch

diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 37e1cbfc7c89..f1f934439be0 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -2050,6 +2050,13 @@  int __ceph_setattr(struct inode *inode, struct iattr *attr)
 
 	dout("setattr %p issued %s\n", inode, ceph_cap_string(issued));
 
+	/*
+	 * The attr->ia_{g,u}id members contain the target {g,u}id we're
+	 * sending over the wire. The mount idmapping only matters when we
+	 * create new filesystem objects based on the caller's mapped
+	 * fs{g,u}id.
+	 */
+	req->r_mnt_idmap = &nop_mnt_idmap;
 	if (ia_valid & ATTR_UID) {
 		dout("setattr %p uid %d -> %d\n", inode,
 		     from_kuid(&init_user_ns, inode->i_uid),
@@ -2240,7 +2247,7 @@  int ceph_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	if (ceph_inode_is_shutdown(inode))
 		return -ESTALE;
 
-	err = setattr_prepare(&nop_mnt_idmap, dentry, attr);
+	err = setattr_prepare(idmap, dentry, attr);
 	if (err != 0)
 		return err;
 
@@ -2255,7 +2262,7 @@  int ceph_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	err = __ceph_setattr(inode, attr);
 
 	if (err >= 0 && (attr->ia_valid & ATTR_MODE))
-		err = posix_acl_chmod(&nop_mnt_idmap, dentry, attr->ia_mode);
+		err = posix_acl_chmod(idmap, dentry, attr->ia_mode);
 
 	return err;
 }