linux.git/net/ceph, branch v4.13

libceph: make RECOVERY_DELETES feature create a new interval

2017-08-01T14:46:45+00:00

This is needed so that the OSDs can regenerate the missing set at the
start of a new interval where support for recovery deletes changed.

Signed-off-by: Ilya Dryomov 
Reviewed-by: Sage Weil

libceph: upmap semantic changes

2017-08-01T14:46:45+00:00

- apply both pg_upmap and pg_upmap_items
- allow bidirectional swap of pg-upmap-items

Signed-off-by: Ilya Dryomov 
Reviewed-by: Sage Weil

crush: assume weight_set != null imples weight_set_size > 0

2017-08-01T14:46:44+00:00

Reflects ceph.git commit 5e8fa3e06b68fae1582c9230a3a8d1abc6146286.

Signed-off-by: Ilya Dryomov 
Reviewed-by: Sage Weil

libceph: fallback for when there isn't a pool-specific choose_arg

2017-08-01T14:46:44+00:00

There is now a fallback to a choose_arg index of -1 if there isn't
a pool-specific choose_arg set.  If you create a per-pool weight-set,
that works for that pool.  Otherwise we try the compat/default one.  If
that doesn't exist either, then we use the normal CRUSH weights.

Signed-off-by: Ilya Dryomov 
Reviewed-by: Sage Weil

libceph: don't call ->reencode_message() more than once per message

2017-08-01T14:46:43+00:00

Reencoding an already reencoded message is a bad idea.  This could
happen on Policy::stateful_server connections (!CEPH_MSG_CONNECT_LOSSY),
such as MDS sessions.

This didn't pop up in testing because currently only OSD requests are
reencoded and OSD sessions are always lossy.

Fixes: 98ad5ebd1505 ("libceph: ceph_connection_operations::reencode_message() method")
Signed-off-by: Ilya Dryomov 
Reviewed-by: "Yan, Zheng"

libceph: make encode_request_*() work with r_mempool requests

2017-08-01T14:46:31+00:00

Messages allocated out of ceph_msgpool have a fixed front length
(pool->front_len).  Asserting that the entire front has been filled
while encoding is thus wrong.

Fixes: 8cb441c0545d ("libceph: MOSDOp v8 encoding (actual spgid + full hash)")
Reported-by: "Yan, Zheng" 
Signed-off-by: Ilya Dryomov 
Reviewed-by: "Yan, Zheng"

libceph: potential NULL dereference in ceph_msg_data_create()

2017-07-17T12:54:59+00:00

If kmem_cache_zalloc() returns NULL then the INIT_LIST_HEAD(&data->links);
will Oops.  The callers aren't really prepared for NULL returns so it
doesn't make a lot of difference in real life.

Fixes: 5240d9f95dfe ("libceph: replace message data pointer with list")
Signed-off-by: Dan Carpenter 
Signed-off-by: Ilya Dryomov

libceph: don't call encode_request_finish() on MOSDBackoff messages

2017-07-17T12:54:59+00:00

encode_request_finish() is for MOSDOp messages.  Calling it on
MOSDBackoff ack-block messages corrupts them.

Fixes: a02a946dfe96 ("libceph: respect RADOS_BACKOFF backoffs")
Signed-off-by: Ilya Dryomov

libceph: use alloc_pg_mapping() in __decode_pg_upmap_items()

2017-07-17T12:54:58+00:00

... otherwise we die in insert_pg_mapping(), which wants pg->node to be
empty, i.e. initialized with RB_CLEAR_NODE.

Fixes: 6f428df47dae ("libceph: pg_upmap[_items] infrastructure")
Signed-off-by: Ilya Dryomov

libceph: set -EINVAL in one place in crush_decode()

2017-07-17T12:54:58+00:00

No sooner than Dan had fixed this issue in commit 293dffaad8d5
("libceph: NULL deref on crush_decode() error path"), I brought it
back.  Add a new label and set -EINVAL once, right before failing.

Fixes: 278b1d709c6a ("libceph: ceph_decode_skip_* helpers")
Reported-by: Dan Carpenter 
Signed-off-by: Ilya Dryomov