[GIT PULL] Ceph fixes for -rc6

[GIT PULL] Ceph fixes for -rc6

[Sage Weil]

Hi Linus,

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

There is a lifecycle fix in the auth code, a fix for a narrow race 
condition on map, and a helpful message in the log when there is a feature 
mismatch (which happens frequently now that the default server-side 
options have changed).

Thanks!
sage



----------------------------------------------------------------
Ilya Dryomov (3):
      libceph: make authorizer destruction independent of ceph_auth_client
      rbd: fix rbd map vs notify races
      rbd: report unsupported features to syslog

 drivers/block/rbd.c             | 52 +++++++++++++++---------------
 fs/ceph/mds_client.c            |  6 ++--
 include/linux/ceph/auth.h       | 10 +++---
 include/linux/ceph/osd_client.h |  1 -
 net/ceph/auth.c                 |  8 ++---
 net/ceph/auth_none.c            | 71 ++++++++++++++++++++++-------------------
 net/ceph/auth_none.h            |  3 +-
 net/ceph/auth_x.c               | 21 ++++++------
 net/ceph/auth_x.h               |  1 +
 net/ceph/osd_client.c           |  6 ++--
 10 files changed, 87 insertions(+), 92 deletions(-)

[GIT PULL] Ceph fixes for -rc6

[Sage Weil]

Hi Linus,

Please pull the following Ceph fixes for -rc6 from

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

There are two small messenger bug fixes and a log spam regression fix.

Thanks!
sage

----------------------------------------------------------------
Ilya Dryomov (3):
      libceph: don't bail early from try_read() when skipping a message
      libceph: use the right footer size when skipping a message
      libceph: don't spam dmesg with stray reply warnings

 net/ceph/messenger.c  | 15 +++++++++++----
 net/ceph/osd_client.c |  4 ++--
 2 files changed, 13 insertions(+), 6 deletions(-)

[GIT PULL] Ceph fixes for -rc6

[Sage Weil]

Hi Linus,

The following changes since commit 25cb62b76430a91cc6195f902e61c2cb84ade622:

  Linux 4.3-rc5 (2015-10-11 11:09:45 -0700)

are available in the git repository at:

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

for you to fetch changes up to e30b7577bf1d338ca8a273bd2f881de5a41572b7:

  rbd: use writefull op for object size writes (2015-10-16 16:49:01 +0200)

Just two small items from Ilya:

The first patch fixes the RBD readahead to grab full objects.  The second 
fixes the write ops to prevent undue promotion when a cache tier is 
configured on the server side.

Thanks!
sage

----------------------------------------------------------------
Ilya Dryomov (2):
      rbd: set max_sectors explicitly
      rbd: use writefull op for object size writes

 drivers/block/rbd.c   | 10 ++++++++--
 net/ceph/osd_client.c | 13 +++++++++----
 2 files changed, 17 insertions(+), 6 deletions(-)

[GIT PULL] Ceph fixes for -rc6

[Sage Weil]

Hi Linus,

Please pull the following Ceph fixes from

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

There are two critical regression fixes for CephFS from Zheng, and an RBD 
completion fix for layered images from Ilya.

(Note: git request-pull is complaining that the for-linus branch isn't 
referencing the right commit even though it is... hopefully I'm not doing 
something stupid.  The right commit is 
2761713d35e370fd640b5781109f753066b746c4.)

Thanks!
sage

----------------------------------------------------------------
Ilya Dryomov (1):
      rbd: fix copyup completion race

Yan, Zheng (2):
      ceph: fix ceph_encode_locks_to_buffer()
      ceph: always re-send cap flushes when MDS recovers

 drivers/block/rbd.c | 22 +++++++++++++++++-----
 fs/ceph/caps.c      | 22 +++++-----------------
 fs/ceph/locks.c     |  2 +-
 fs/ceph/super.h     |  1 -
 4 files changed, 23 insertions(+), 24 deletions(-)

[GIT PULL] Ceph fixes for -rc6

[Sage Weil]

Hi Linus,

Please pull the following Ceph fixes from

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

The first patch fixes a problem when we have a page count of 0 for 
sendpage which is triggered by zfs.  The second fixes a bug in CRUSH that 
was resolved in the userland code a while back but fell through the cracks 
on the kernel side.

Thanks!
sage


----------------------------------------------------------------
Chunwei Chen (1):
      libceph: fix corruption when using page_count 0 page in rbd

Ilya Dryomov (1):
      crush: decode and initialize chooseleaf_vary_r

 net/ceph/messenger.c | 20 +++++++++++++++++++-
 net/ceph/osdmap.c    |  5 +++++
 2 files changed, 24 insertions(+), 1 deletion(-)

[GIT PULL] Ceph fixes for -rc6

[Sage Weil]

Hi Linus,

Please pull the following fixes for Ceph from

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

There is a pair of fixes for double-frees in the recent bundle for 3.10, a 
couple of fixes for long-standing bugs (sleep while atomic and an 
endianness fix), and a locking fix that can be triggered when osds are 
going down.

Thanks!
sage

----------------------------------------------------------------
Alex Elder (3):
      libceph: must hold mutex for reset_changed_osds()
      rbd: don't destroy ceph_opts in rbd_add()
      rbd: fix cleanup in rbd_add()

Jim Schutt (2):
      ceph: add cpu_to_le32() calls when encoding a reconnect capability
      ceph: ceph_pagelist_append might sleep while atomic

 drivers/block/rbd.c   | 33 ++++++++++++-----------
 fs/ceph/locks.c       | 73 +++++++++++++++++++++++++++++++++------------------
 fs/ceph/mds_client.c  | 65 ++++++++++++++++++++++++---------------------
 fs/ceph/super.h       |  9 +++++--
 net/ceph/osd_client.c |  2 +-
 5 files changed, 108 insertions(+), 74 deletions(-)

[GIT PULL] Ceph fixes for -rc6

[Sage Weil]

Hi Linus,

Please pull the following ceph fixes from

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

There are two biggish things here, unfortunately.  One is a locking fix 
that replaces i_lock use with a ceph-private inode spinlock.  This is 
necessary to work around lock ordering issues which unfortunately we 
didn't notice until now (it's from the lock scalability stuff a couple of 
kernels back).  The diffstat is large, but it's a mechanical replacement 
and has been pretty well tested.  The other big one is removing rbd 
rollback functionality from the kernel entirely (we found a minor bug but 
it is better done from userspace anyway).

There are also a handful of other small bug fixes (missing spin_unlock, 
typo), some error reporting/handling on a corrupt image, a fix for the 
CRUSH mapping calculation, and a fix for a the seek() regression in 3.1.

There will probably be one more lock ordering patch coming shortly, but I 
want to do some more testing first.

Thanks!
sage


Josh Durgin (2):
      rbd: return an error when an invalid header is read
      rbd: remove buggy rollback functionality

Sage Weil (4):
      ceph: fix rasize reporting by ceph_show_options
      ceph: use i_ceph_lock instead of i_lock
      crush: fix mapping calculation when force argument doesn't exist
      ceph: fix SEEK_CUR, SEEK_SET regression

Yehuda Sadeh (1):
      ceph: add missing spin_unlock at ceph_mdsc_build_path()

 Documentation/ABI/testing/sysfs-bus-rbd |    7 -
 drivers/block/rbd.c                     |  101 ++---------------
 fs/ceph/addr.c                          |    8 +-
 fs/ceph/caps.c                          |  187 ++++++++++++++++---------------
 fs/ceph/dir.c                           |   24 ++--
 fs/ceph/file.c                          |   23 ++--
 fs/ceph/inode.c                         |   53 +++++----
 fs/ceph/ioctl.c                         |    4 +-
 fs/ceph/mds_client.c                    |   33 +++---
 fs/ceph/mds_client.h                    |    2 +-
 fs/ceph/snap.c                          |   16 ++--
 fs/ceph/super.c                         |    2 +-
 fs/ceph/super.h                         |   31 +++---
 fs/ceph/xattr.c                         |   42 ++++----
 net/ceph/crush/mapper.c                 |   35 ++----
 15 files changed, 239 insertions(+), 329 deletions(-)