On Tue, 2022-01-04 at 15:04 +0100, Christian Brauner wrote:
> From: Christian Brauner <christian.brauner@xxxxxxxxxx>
>
> When sending a mds request cephfs will send relevant data for the
> requested operation. For creation requests the caller's fs{g,u}id is
> used to set the ownership of the newly created filesystem object. For
> setattr requests the caller can pass in arbitrary {g,u}id values to
> which the relevant filesystem object is supposed to be changed.
>
> If the caller is performing the relevant operation via an idmapped mount
> cephfs simply needs to take the idmapping into account when it sends the
> relevant mds request.
>
> In order to support idmapped mounts for cephfs we stash the idmapping
> whenever they are relevant for the operation for the duration of the
> request. Since mds requests can be queued and performed asynchronously
> we make sure to keep the idmapping around and release it once the
> request has finished.
>
> In follow-up patches we will use this to send correct ownership
> information over the wire. This patch just adds the basic infrastructure
> to keep the idmapping around. The actual conversion patches are all
> fairly minimal.
>
> Cc: Jeff Layton <jlayton@xxxxxxxxxx>
> Cc: Ilya Dryomov <idryomov@xxxxxxxxx>
> Cc: ceph-devel@xxxxxxxxxxxxxxx
> Signed-off-by: Christian Brauner <christian.brauner@xxxxxxxxxx>
> ---
> fs/ceph/mds_client.c | 7 +++++++
> fs/ceph/mds_client.h | 1 +
> 2 files changed, 8 insertions(+)
>
> diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
> index c30eefc0ac19..ae2cc4ce1d48 100644
> --- a/fs/ceph/mds_client.c
> +++ b/fs/ceph/mds_client.c
> @@ -12,6 +12,7 @@
> #include <linux/bits.h>
> #include <linux/ktime.h>
> #include <linux/bitmap.h>
> +#include <linux/mnt_idmapping.h>
>
> #include "super.h"
> #include "mds_client.h"
> @@ -862,6 +863,8 @@ void ceph_mdsc_release_request(struct kref *kref)
> kfree(req->r_path1);
> kfree(req->r_path2);
> put_cred(req->r_cred);
> + if (!initial_idmapping(req->mnt_userns))
> + put_user_ns(req->mnt_userns);
I assume initial_idmapping returns true if it's init_user_ns ?
> if (req->r_pagelist)
> ceph_pagelist_release(req->r_pagelist);
> put_request_session(req);
> @@ -918,6 +921,10 @@ static void __register_request(struct ceph_mds_client *mdsc,
> insert_request(&mdsc->request_tree, req);
>
> req->r_cred = get_current_cred();
> + if (!req->mnt_userns)
> + req->mnt_userns = &init_user_ns;
> + else
> + get_user_ns(req->mnt_userns);
>
> if (mdsc->oldest_tid == 0 && req->r_op != CEPH_MDS_OP_SETFILELOCK)
> mdsc->oldest_tid = req->r_tid;
> diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
> index 97c7f7bfa55f..1b648645e340 100644
> --- a/fs/ceph/mds_client.h
> +++ b/fs/ceph/mds_client.h
> @@ -275,6 +275,7 @@ struct ceph_mds_request {
> union ceph_mds_request_args r_args;
> int r_fmode; /* file mode, if expecting cap */
> const struct cred *r_cred;
> + struct user_namespace *mnt_userns;
Can we call this r_mnt_userns to match the other fields ?
> int r_request_release_offset;
> struct timespec64 r_stamp;
>
--
Jeff Layton <jlayton@xxxxxxxxxx>
