Avoid dropping and retaking con->mutex in the ceph_con_send() case by
leaving locking up to the caller.
Signed-off-by: Sage Weil <sage@inktank.com>

If we fault on a lossy connection, we should still close the socket
immediately, and do so under the con mutex.

We should also take the con mutex before printing out the state bits in
the debug output.
Signed-off-by: Sage Weil <sage@inktank.com>

rbd_req_sync_unwatch() only ever uses rbd_dev->header_name as the
value of its "object_name" parameter, and that value is available
within the function already.  So get rid of the parameter.
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

rbd_req_sync_notify_ack() only ever uses rbd_dev->header_name as the
value of its "object_name" parameter, and that value is available
within the function already.  So get rid of the parameter.
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

rbd_req_sync_notify() only ever uses rbd_dev->header_name as the
value of its "object_name" parameter, and that value is available
within the function already.  So get rid of the parameter.
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

rbd_req_sync_watch() is only called in one place, and in that place
it passes rbd_dev->header_name as the value of the "object_name"
parameter.  This value is available within the function already.

Having the extra parameter leaves the impression the object name
could take on different values, but it does not.

So get rid of the parameter.  We can always add it back again if
we find we want to watch some other object in the future.
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

Both rbd_register_snap_dev() and __rbd_remove_snap_dev() have
rbd_dev parameters that are unused.  Remove them.
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

The function rbd_header_from_disk() is only called in one spot, and
it passes GFP_KERNEL as its value for the gfp_flags parameter.

Just drop that parameter and substitute GFP_KERNEL everywhere within
that function it had been used.  (If we find we need the parameter
again in the future it's easy enough to add back again.)
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

The "snapc" parameter to in rbd_req_sync_read() is not used, so
get rid of it.
Reported-by: Josh Durgin <josh.durgin@inktank.com>
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

The "id" field of an rbd device structure represents the unique
client-local device id mapped to the underlying rbd image.  Each rbd
image will have another id--the image id--and each snapshot has its
own id as well.  The simple name "id" no longer conveys the
information one might like to have.

Rename the device "id" field in struct rbd_dev to be "dev_id" to
make it a little more obvious what we're dealing with without having
to think more about context.
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

If an rbd image header is read and it doesn't begin with the
expected magic information, a warning is displayed.  This is
a fairly simple test, but it could be extended at some point.
Fix the comparison so it actually looks at the "text" field
rather than the front of the structure.

In any case, encapsulate the validity test in its own function.
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

There are two structures in which a count of snapshots are
maintained:

    struct ceph_snap_context {
	...
        u32 num_snaps;
	...
    }
and
    struct ceph_snap_realm {
	...
        u32 num_prior_parent_snaps;   /*  had prior to parent_since */
	...
        u32 num_snaps;
	...
    }

These fields never take on negative values (e.g., to hold special
meaning), and so are really inherently unsigned.  Furthermore they
take their value from over-the-wire or on-disk formatted 32-bit
values.

So change their definition to have type u32, and change some spots
elsewhere in the code to account for this change.
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

There was a dout() call in rbd_do_request() that was reporting
the reporting the offset as the length and vice versa.  While
fixing that I did a quick scan of other dout() calls and fixed
a couple of other minor things.
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

This just replaces a while loop with list_for_each_entry_safe()
in __rbd_remove_all_snaps().
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

In commit c666601a there was inadvertently added an extra
initialization of rbd_dev->header_rwsem.  This gets rid of the
duplicate.
Reported-by: Guangliang Zhao <gzhao@suse.com>
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

The snap_seq field in an rbd_image_header structure held the value
from the rbd image header when it was last refreshed.  We now
maintain this value in the snapc->seq field.  So get rid of the
other one.
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

In rbd_header_add_snap() there is code to set snapc->seq to the
just-added snapshot id.  This is the only remnant left of the
use of that field for recording which snapshot an rbd_dev was
associated with.  That functionality is no longer supported,
so get rid of that final bit of code.

Doing so means we never actually set snapc->seq any more.  On the
server, the snapshot context's sequence value represents the highest
snapshot id ever issued for a particular rbd image.  So we'll make
it have that meaning here as well.  To do so, set this value
whenever the rbd header is (re-)read.  That way it will always be
consistent with the rest of the snapshot context we maintain.
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

In rbd_header_set_snap(), there is logic to make the snap context's
seq field get set to a particular snapshot id, or 0 if there is no
snapshot for the rbd image.

This seems to be an artifact of how the current snapshot id for an
rbd_dev was recorded before the rbd_dev->snap_id field began to be
used for that purpose.

There's no need to update the value of snapc->seq here any more, so
stop doing it.  Tidy up a few local variables in that function
while we're at it.
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

In what appears to be an artifact of a different way of encoding
whether an rbd image maps a snapshot, __rbd_refresh_header() has
code that arranges to update the seq value in an rbd image's
snapshot context to point to the first entry in its snapshot
array if that's where it was pointing initially.

We now use rbd_dev->snap_id to record the snapshot id--using the
special value CEPH_NOSNAP to indicate the rbd_dev is not mapping a
snapshot at all.

There is therefore no need to check for this case, nor to update the
seq value, in __rbd_refresh_header().  Just preserve the seq value
that rbd_read_header() provides (which, at the moment, is nothing).
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

Previously the original header version was sent. Now, we update it
when the header changes.
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
Reviewed-by: Alex Elder <elder@inktank.com>

This prevents a race between requests with a given snap context and
header updates that free it. The osd client was already expecting the
snap context to be reference counted, since it get()s it in
ceph_osdc_build_request and put()s it when the request completes.

Also remove the second down_read()/up_read() on header_rwsem in
rbd_do_request, which wasn't actually preventing this race or
protecting any other data.
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
Reviewed-by: Alex Elder <elder@inktank.com>

The image may have been resized.
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
Reviewed-by: Alex Elder <elder@inktank.com>

If an image was mapped to a snapshot, the size of the head version
would be shown. Protect capacity with header_rwsem, since it may
change.
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
Reviewed-by: Alex Elder <elder@inktank.com>

Snapshots cannot be resized, and the new capacity of head should not
be reflected by the snapshot.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Reviewed-by: Alex Elder <elder@inktank.com>

When a snapshot is deleted, the OSD will return ENOENT when reading
from it. This is normally interpreted as a hole by rbd, which will
return zeroes. To minimize the time in which this can happen, stop
requests early when we are notified that our snapshot no longer
exists.

[elder@inktank.com: updated __rbd_init_snaps_header() logic]
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Reviewed-by: Alex Elder <elder@inktank.com>

This is a trivial fix for the debug output, as it is inconsistent
with the function name so may confuse people when debugging.

[elder@inktank.com: switched to use __func__]
Signed-off-by: Jiaju Zhang <jjzhang@suse.de>
Reviewed-by: Alex Elder <elder@inktank.com>

We re-run the loop but we don't re-set the attrs pointer back to NULL.
Signed-off-by: Alan Cox <alan@linux.intel.com>
Reviewed-by: Alex Elder <elder@inktank.com>

We exponentially back off when we encounter connection errors.  If several
errors accumulate, we will eventually wait ages before even trying to
reconnect.

Fix this by resetting the backoff counter after a successful negotiation/
connection with the remote node.  Fixes ceph issue #2802.
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Reviewed-by: Alex Elder <elder@inktank.com>

Take the con mutex while we are initiating a ceph open.  This is necessary
because the may have previously been in use and then closed, which could
result in a racing workqueue running con_work().
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Reviewed-by: Alex Elder <elder@inktank.com>

When we detect a mds session reset, close the old ceph_connection before
reopening it.  This ensures we clean up the old socket properly and keep
the ceph_connection state correct.
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Alex Elder <elder@inktank.com>
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>

Previously, we were opportunistically initializing the bio_iter if it
appeared to be uninitialized in the middle of the read path.  The problem
is that a sequence like:

 - start reading message
 - initialize bio_iter
 - read half a message
 - messenger fault, reconnect
 - restart reading message
 - ** bio_iter now non-NULL, not reinitialized **
 - read past end of bio, crash

Instead, initialize the bio_iter unconditionally when we allocate/claim
the message for read.
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Alex Elder <elder@inktank.com>
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>

The linger op registration (i.e., watch) modifies the object state.  As
such, the OSD will reply with success if it has already applied without
doing the associated side-effects (setting up the watch session state).
If we lose the ACK and resubmit, we will see success but the watch will not
be correctly registered and we won't get notifies.

To fix this, always resubmit the linger op with a new tid.  We accomplish
this by re-registering as a linger (i.e., 'registered') if we are not yet
registered.  Then the second loop will treat this just like a normal
case of re-registering.

This mirrors a similar fix on the userland ceph.git, commit 5dd68b95, and
ceph bug #2796.
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Alex Elder <elder@inktank.com>
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>

Hold the mutex while twiddling all of the state bits to avoid possible
races.  While we're here, make not of why we cannot close the socket
directly.
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Alex Elder <elder@inktank.com>
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>

We need to set error_msg to something useful before calling ceph_fault();
do so here for try_{read,write}().  This is more informative than

libceph: osd0 192.168.106.220:6801 (null)
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Alex Elder <elder@inktank.com>
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>

The server side recently added support for tuning some magic
crush variables. Decode these variables if they are present, or use the
default values if they are not present.

Corresponds to ceph.git commit 89af369c25f274fe62ef730e5e8aad0c54f1e5a5.
Signed-off-by: caleb miles <caleb.miles@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Alex Elder <elder@inktank.com>
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>

This is simply cleanup that will keep things more closely synced with the
userland code.
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Alex Elder <elder@inktank.com>
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>

Several functions include a num_reply parameter, but it is never
used.  Just get rid of it everywhere--it seems to be something
that never got fully implemented.
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

Use the name "ceph_opts" consistently (rather than just "opt") for
pointers to a ceph_options structure.

Change the few spots that don't use "rbd_opts" for a rbd_options
pointer to match the rest.
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

Rename variables named "obj" which represent object names so they're
consistently named "object_name".

Rename the "cls" and "method" parameters in rbd_req_sync_exec()
to be "class_name" and "method_name", and make similar changes
to the names of local variables in that function representing
the lengths of those names.
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>

An rbd image is not a single object, but a logical construct made up
of an aggregation of objects.

Rename some fields in struct rbd_dev, in hopes of reinforcing this.
    obj         --> image_name
    obj_len     --> image_name_len
    obj_md_name --> header_name
Signed-off-by: Alex Elder <elder@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>