On Fri, 2016-11-04 at 07:34 -0400, Jeff Layton wrote:
> The userland ceph has MClientCaps at struct version 9. This brings the
> kernel up the same version.
>
> With this change, we have to start tracking the btime and change_attr,
> so that the client can pass back sane values in cap messages. The
> client doesn't care about the btime at all, so this is just passed
> around, but the change_attr is used when ceph is exported via NFS.
>
> For now, the new "sync" parm is left at 0, to preserve the existing
> behavior of the client.
>
> Signed-off-by: Jeff Layton <jlayton@xxxxxxxxxx>
> ---
> fs/ceph/caps.c | 33 +++++++++++++++++++++++++--------
> 1 file changed, 25 insertions(+), 8 deletions(-)
>
> diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
> index 6e99866b1946..452f5024589f 100644
> --- a/fs/ceph/caps.c
> +++ b/fs/ceph/caps.c
> @@ -991,9 +991,9 @@ struct cap_msg_args {
> struct ceph_mds_session *session;
> u64 ino, cid, follows;
> u64 flush_tid, oldest_flush_tid, size, max_size;
> - u64 xattr_version;
> + u64 xattr_version, change_attr;
> struct ceph_buffer *xattr_buf;
> - struct timespec atime, mtime, ctime;
> + struct timespec atime, mtime, ctime, btime;
> int op, caps, wanted, dirty;
> u32 seq, issue_seq, mseq, time_warp_seq;
> kuid_t uid;
> @@ -1026,13 +1026,13 @@ static int send_cap_msg(struct cap_msg_args *arg)
>
> /* flock buffer size + inline version + inline data size +
> * osd_epoch_barrier + oldest_flush_tid */
> - extra_len = 4 + 8 + 4 + 4 + 8;
> + extra_len = 4 + 8 + 4 + 4 + 8 + 4 + 4 + 4 + 8 + 8 + 1;
> msg = ceph_msg_new(CEPH_MSG_CLIENT_CAPS, sizeof(*fc) + extra_len,
> GFP_NOFS, false);
> if (!msg)
> return -ENOMEM;
>
> - msg->hdr.version = cpu_to_le16(6);
> + msg->hdr.version = cpu_to_le16(9);
> msg->hdr.tid = cpu_to_le64(arg->flush_tid);
>
> fc = msg->front.iov_base;
> @@ -1068,17 +1068,30 @@ static int send_cap_msg(struct cap_msg_args *arg)
> }
>
> p = fc + 1;
> - /* flock buffer size */
> + /* flock buffer size (version 2) */
> ceph_encode_32(&p, 0);
> - /* inline version */
> + /* inline version (version 4) */
> ceph_encode_64(&p, arg->inline_data ? 0 : CEPH_INLINE_NONE);
> /* inline data size */
> ceph_encode_32(&p, 0);
> - /* osd_epoch_barrier */
> + /* osd_epoch_barrier (version 5) */
> ceph_encode_32(&p, 0);
> - /* oldest_flush_tid */
> + /* oldest_flush_tid (version 6) */
> ceph_encode_64(&p, arg->oldest_flush_tid);
>
> + /* caller_uid/caller_gid (version 7) */
> + ceph_encode_32(&p, (u32)-1);
> + ceph_encode_32(&p, (u32)-1);
A bit of self-review...
Not sure if we want to set the above to something else -- maybe 0 or to
current's creds? That may not always make sense though (during e.g.
writeback).
> +
> + /* pool namespace (version 8) */
> + ceph_encode_32(&p, 0);
> +
I'm a little unclear on how the above should be set, but I'll look over
the userland code and ape what it does.
> + /* btime, change_attr, sync (version 9) */
> + ceph_encode_timespec(p, &arg->btime);
> + p += sizeof(struct ceph_timespec);
> + ceph_encode_64(&p, arg->change_attr);
> + ceph_encode_8(&p, 0);
> +
> ceph_con_send(&arg->session->s_con, msg);
> return 0;
> }
> @@ -1189,9 +1202,11 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
> arg.xattr_buf = NULL;
> }
>
> + arg.change_attr = inode->i_version;
> arg.mtime = inode->i_mtime;
> arg.atime = inode->i_atime;
> arg.ctime = inode->i_ctime;
> + arg.btime = ci->i_btime;
>
> arg.op = op;
> arg.caps = cap->implemented;
> @@ -1241,10 +1256,12 @@ static inline int __send_flush_snap(struct inode *inode,
> arg.max_size = 0;
> arg.xattr_version = capsnap->xattr_version;
> arg.xattr_buf = capsnap->xattr_blob;
> + arg.change_attr = capsnap->change_attr;
>
> arg.atime = capsnap->atime;
> arg.mtime = capsnap->mtime;
> arg.ctime = capsnap->ctime;
> + arg.btime = capsnap->btime;
>
> arg.op = CEPH_CAP_OP_FLUSHSNAP;
> arg.caps = capsnap->issued;
--
Jeff Layton <jlayton@xxxxxxxxxx>
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
