Date:	Tue, 27 Mar 2012 12:25:22 -0700 (PDT)
From:	Sage Weil <sage@...dream.net>
To:	torvalds@...ux-foundation.org
cc:	linux-kernel@...r.kernel.org, ceph-devel@...r.kernel.org
Subject: [GIT PULL] Ceph updates for 3.4-rc1

Hi Linus,

Please pull the following Ceph updates from

  git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git for-linus

Alex has been busy.  There are a range of rbd and libceph cleanups, 
especially surrounding device setup and teardown, and a few critical fixes 
in that code.  There are more cleanups in the messenger code, virtual 
xattrs, a fix for CRC calculation/checks, and lots of other miscellaneous 
stuff.

There's a patch from Amon Ott to make inos behave a bit better on 32-bit 
boxes, some decode check fixes from Xi Wang, and network throttling fix 
from Jim Schutt, and a couple RBD fixes from Josh Durgin.

No new functionality, just a lot of cleanup and bug fixing.

Thanks!
sage



----------------------------------------------------------------
Alex Elder (58):
      ceph: don't reset s_cap_ttl to zero
      ceph: use a shared zero page rather than one per messenger
      ceph: make use of "else" where appropriate
      ceph: kill addr_str_lock spinlock; use atomic instead
      ceph: eliminate some needless casts
      ceph: eliminate some abusive casts
      ceph: don't null-terminate xattr values
      ceph: pass inode rather than table to ceph_match_vxattr()
      ceph: use a symbolic name for "ceph." extended attribute namespace
      ceph: use macros to normalize vxattr table definitions
      ceph: drop "_cb" from name of struct ceph_vxattr_cb
      ceph: encode type in vxattr callback routines
      ceph: avoid repeatedly computing the size of constant vxattr names
      ceph: make ceph_setxattr() and ceph_removexattr() more alike
      rbd: a few small cleanups
      rbd: make ceph_parse_options() return a pointer
      rbd: do not duplicate ceph_client pointer in rbd_device
      rbd: encapsulate new rbd id selection
      rbd: rework calculation of new rbd id's
      rbd: protect the rbd_dev_list with a spinlock
      rbd: tie rbd_dev_list changes to rbd_id operations
      rbd: restore previous rbd id sequence behavior
      rbd: release client list lock sooner
      rbd: move ctl_mutex lock inside rbd_get_client()
      rbd: move ctl_mutex lock inside rbd_client_create()
      rbd: rename "node_lock"
      rbd: a few simple changes
      rbd: have rbd_get_client() return a rbd_client
      rbd: reduce memory used for rbd_dev fields
      rbd: simplify error handling in rbd_add()
      rbd: encapsulate argument parsing for rbd_add()
      rbd: don't use sscanf() in rbd_add_parse_args()
      rbd: do a few checks at build time
      rbd: have rbd_parse_args() report found mon_addrs size
      rbd: don't allocate mon_addrs buffer in rbd_add()
      rbd: fix module sysfs setup/teardown code
      rbd: do some refactoring
      rbd: small changes
      rbd: don't drop the rbd_id too early
      libceph: move prepare_write_banner()
      libceph: encapsulate connection kvec operations
      libceph: make ceph_msgr_wq private
      libceph: encapsulate some messenger cleanup code
      libceph: make ceph_tcp_connect() return int
      libceph: a few small changes
      ceph: ensure Boolean options support both senses
      libceph: use "do" in CRC-related Boolean variables
      libceph: separate CRC calculation from byte swapping
      libceph: do crc calculations outside loop
      libceph: small refactor in write_partial_kvec()
      libceph: some simple changes
      libceph: fix inverted crc option logic
      libceph: use kernel_sendpage() for sending zeroes
      libceph: only call kernel_sendpage() via helper
      libceph: get rid of zero_page_address
      libceph: rename "page_shift" variable to something sensible
      libceph: isolate kmap() call in write_partial_msg_pages()
      ceph: fix three bugs, two in ceph_vxattrcb_file_layout()

Amon Ott (1):
      ceph: use 2 instead of 1 as fallback for 32-bit inode number

Jim Schutt (1):
      net/ceph: Only clear SOCK_NOSPACE when there is sufficient space in the socket buffer

Josh Durgin (2):
      rbd: use a single value of snap_name to mean no snap
      rbd: move snap_rwsem to the device, rename to header_rwsem

Xi Wang (3):
      ceph: avoid panic with mismatched symlink sizes in fill_inode()
      libceph: fix overflow check in crush_decode()
      ceph: fix overflow check in build_snap_context()

 drivers/block/rbd.c            |  730 ++++++++++++++++++++++++----------------
 drivers/block/rbd_types.h      |    4 -
 fs/ceph/inode.c                |   11 +-
 fs/ceph/mds_client.c           |    7 +-
 fs/ceph/snap.c                 |    2 +-
 fs/ceph/super.c                |   19 +-
 fs/ceph/super.h                |    4 +-
 fs/ceph/xattr.c                |  202 ++++++++----
 include/linux/ceph/libceph.h   |    2 +-
 include/linux/ceph/messenger.h |    5 +-
 net/ceph/ceph_common.c         |   26 +-
 net/ceph/messenger.c           |  456 +++++++++++++------------
 net/ceph/osdmap.c              |    3 +-
 13 files changed, 868 insertions(+), 603 deletions(-)
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists