linux.git/fs/ceph, branch v2.6.36

ceph: update issue_seq on cap grant

2010-10-07T15:01:50+00:00

We need to update the issue_seq on any grant operation, be it via an MDS
reply or a separate grant message.  The update in the grant path was
missing.  This broke cap release for inodes in which the MDS sent an
explicit grant message that was not soon after followed by a successful
MDS reply on the same inode.

Also fix the signedness on seq locals.

Signed-off-by: Sage Weil

ceph: send cap release message early on failed revoke.

2010-10-07T15:00:24+00:00

If an MDS tries to revoke caps that we don't have, we want to send
releases early since they probably contain the caps message the MDS
is looking for.

Previously, we only sent the messages if we didn't have the inode either. But
in a multi-mds system we can retain the inode after dropping all caps for
a single MDS.

Signed-off-by: Greg Farnum 
Signed-off-by: Sage Weil

ceph: Update max_len with minimum required size

2010-10-07T15:00:24+00:00

encode_fh on error should update max_len with minimum required
size, so that caller can redo the call with the reallocated buffer.
This is required with open by handle patch series

Signed-off-by: Aneesh Kumar K.V 
Signed-off-by: Sage Weil

ceph: Fix return value of encode_fh function

2010-10-07T15:00:23+00:00

encode_fh function should return 255 on error as done by other file
system to indicate EOVERFLOW. Also max_len is in sizeof(u32) units
and not in bytes.

Signed-off-by: Aneesh Kumar K.V 
Signed-off-by: Sage Weil

ceph: avoid null deref in osd request error path

2010-10-07T15:00:23+00:00

If we interrupt an osd request, we call __cancel_request, but it wasn't
verifying that req->r_osd was non-NULL before dereferencing it.  This could
cause a crash if osds were flapping and we aborted a request on said osd.

Reported-by: Henry C Chang 
Signed-off-by: Sage Weil

ceph: fix list_add usage on unsafe_writes list

2010-10-07T15:00:23+00:00

Fix argument order.

Signed-off-by: Henry C Chang 
Signed-off-by: Sage Weil

ceph: select CRYPTO

2010-09-17T19:30:31+00:00

We select CRYPTO_AES, but not CRYPTO.

Signed-off-by: Sage Weil

ceph: check mapping to determine if FILE_CACHE cap is used

2010-09-17T16:54:31+00:00

See if the i_data mapping has any pages to determine if the FILE_CACHE
capability is currently in use, instead of assuming it is any time the
rdcache_gen value is set (i.e., issued -> used).

This allows the MDS RECALL_STATE process work for inodes that have cached
pages.

Signed-off-by: Sage Weil

ceph: only send one flushsnap per cap_snap per mds session

2010-09-17T15:03:08+00:00

Sending multiple flushsnap messages is problematic because we ignore
the response if the tid doesn't match, and the server may only respond to
each one once.  It's also a waste.

So, skip cap_snaps that are already on the flushing list, unless the caller
tells us to resend (because we are reconnecting).

Signed-off-by: Sage Weil

ceph: fix cap_snap and realm split

2010-09-16T23:26:51+00:00

The cap_snap creation/queueing relies on both the current i_head_snapc
_and_ the i_snap_realm pointers being correct, so that the new cap_snap
can properly reference the old context and the new i_head_snapc can be
updated to reference the new snaprealm's context.  To fix this, we:

 - move inodes completely to the new (split) realm so that i_snap_realm
   is correct, and
 - generate the new snapc's _before_ queueing the cap_snaps in
   ceph_update_snap_trace().

Signed-off-by: Sage Weil