kernel/linux.git/include/linux/ceph/messenger.h, branch v4.12.14

Merge tag 'ceph-for-4.10-rc1' of git://github.com/ceph/ceph-client

2016-12-16T19:23:34+00:00

Pull ceph updates from Ilya Dryomov: "A varied set of changes: - a large rework of cephx auth code to cope with CONFIG_VMAP_STACK (myself). Also fixed a deadlock caused by a bogus allocation on the writeback path and authorize reply verification. - a fix for long stalls during fsync (Jeff Layton). The client now has a way to force the MDS log flush, leading to ~100x speedups in some synthetic tests. - a new [no]require_active_mds mount option (Zheng Yan). On mount, we will now check whether any of the MDSes are available and bail rather than block if none are. This check can be avoided by specifying the "no" option. - a couple of MDS cap handling fixes and a few assorted patches throughout" * tag 'ceph-for-4.10-rc1' of git://github.com/ceph/ceph-client: (32 commits) libceph: remove now unused finish_request() wrapper libceph: always signal completion when done ceph: avoid creating orphan object when checking pool permission ceph: properly set issue_seq for cap release ceph: add flags parameter to send_cap_msg ceph: update cap message struct version to 10 ceph: define new argument structure for send_cap_msg ceph: move xattr initialzation before the encoding past the ceph_mds_caps ceph: fix minor typo in unsafe_request_wait ceph: record truncate size/seq for snap data writeback ceph: check availability of mds cluster on mount ceph: fix splice read for no Fc capability case ceph: try getting buffer capability for readahead/fadvise ceph: fix scheduler warning due to nested blocking ceph: fix printing wrong return variable in ceph_direct_read_write() crush: include mapper.h in mapper.c rbd: silence bogus -Wmaybe-uninitialized warning libceph: no need to drop con->mutex for ->get_authorizer() libceph: drop len argument of *verify_authorizer_reply() libceph: verify authorize reply on connect ...

libceph: drop len argument of *verify_authorizer_reply()

2016-12-12T22:09:21+00:00

The length of the reply is protocol-dependent - for cephx it's ceph_x_authorize_reply. Nothing sensible can be passed from the messenger layer anyway. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil

ceph: don't include blk_types.h in messenger.h

2016-11-01T15:43:26+00:00

The file only needs the struct bvec_iter delcaration, which is available from bvec.h. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe

libceph: fix ceph_msg_revoke()

2016-01-21T18:36:08+00:00

There are a number of problems with revoking a "was sending" message: (1) We never make any attempt to revoke data - only kvecs contibute to con->out_skip. However, once the header (envelope) is written to the socket, our peer learns data_len and sets itself to expect at least data_len bytes to follow front or front+middle. If ceph_msg_revoke() is called while the messenger is sending message's data portion, anything we send after that call is counted by the OSD towards the now revoked message's data portion. The effects vary, the most common one is the eventual hang - higher layers get stuck waiting for the reply to the message that was sent out after ceph_msg_revoke() returned and treated by the OSD as a bunch of data bytes. This is what Matt ran into. (2) Flat out zeroing con->out_kvec_bytes worth of bytes to handle kvecs is wrong. If ceph_msg_revoke() is called before the tag is sent out or while the messenger is sending the header, we will get a connection reset, either due to a bad tag (0 is not a valid tag) or a bad header CRC, which kind of defeats the purpose of revoke. Currently the kernel client refuses to work with header CRCs disabled, but that will likely change in the future, making this even worse. (3) con->out_skip is not reset on connection reset, leading to one or more spurious connection resets if we happen to get a real one between con->out_skip is set in ceph_msg_revoke() and before it's cleared in write_partial_skip(). Fixing (1) and (3) is trivial. The idea behind fixing (2) is to never zero the tag or the header, i.e. send out tag+header regardless of when ceph_msg_revoke() is called. That way the header is always correct, no unnecessary resets are induced and revoke stands ready for disabled CRCs. Since ceph_msg_revoke() rips out con->out_msg, introduce a new "message out temp" and copy the header into it before sending. Cc: stable@vger.kernel.org # 4.0+ Reported-by: Matt Conner Signed-off-by: Ilya Dryomov Tested-by: Matt Conner Reviewed-by: Sage Weil

libceph: stop duplicating client fields in messenger

2015-11-02T22:37:46+00:00

supported_features and required_features serve no purpose at all, while nocrc and tcp_nodelay belong to ceph_options::flags. Signed-off-by: Ilya Dryomov

libceph: msg signing callouts don't need con argument

2015-11-02T22:37:45+00:00

We can use msg->con instead - at the point we sign an outgoing message or check the signature on the incoming one, msg->con is always set. We wouldn't know how to sign a message without an associated session (i.e. msg->con == NULL) and being able to sign a message using an explicitly provided authorizer is of no use. Signed-off-by: Ilya Dryomov

libceph: don't access invalid memory in keepalive2 path

2015-09-17T17:14:15+00:00

This struct ceph_timespec ceph_ts; ... con_out_kvec_add(con, sizeof(ceph_ts), &ceph_ts); wraps ceph_ts into a kvec and adds it to con->out_kvec array, yet ceph_ts becomes invalid on return from prepare_write_keepalive(). As a result, we send out bogus keepalive2 stamps. Fix this by encoding into a ceph_timespec member, similar to how acks are read and written. Signed-off-by: Ilya Dryomov Reviewed-by: Yan, Zheng

libceph: use keepalive2 to verify the mon session is alive

2015-09-08T20:14:30+00:00

Signed-off-by: Yan, Zheng Signed-off-by: Ilya Dryomov

libceph: enable ceph in a non-default network namespace

2015-07-09T17:30:34+00:00

Grab a reference on a network namespace of the 'rbd map' (in case of rbd) or 'mount' (in case of ceph) process and use that to open sockets instead of always using init_net and bailing if network namespace is anything but init_net. Be careful to not share struct ceph_client instances between different namespaces and don't add any code in the !CONFIG_NET_NS case. This is based on a patch from Hong Zhiguo . Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil

libceph: tcp_nodelay support

2015-02-19T10:31:40+00:00

TCP_NODELAY socket option set on connection sockets, disables Nagle’s algorithm and improves latency characteristics. tcp_nodelay(default)/notcp_nodelay option flags provided to enable/disable setting the socket option. Signed-off-by: Chaitanya Huilgol [idryomov@redhat.com: NO_TCP_NODELAY -> TCP_NODELAY, minor adjustments] Signed-off-by: Ilya Dryomov