[GIT PULL] Ceph updates for 5.1-rc1

From: Ilya Dryomov
Date: Tue Mar 12 2019 - 13:50:44 EST

Hi Linus,

The following changes since commit 1c163f4c7b3f621efff9b28a47abb36f7378d783:

Linux 5.0 (2019-03-03 15:21:29 -0800)

are available in the Git repository at:

https://github.com/ceph/ceph-client.git tags/ceph-for-5.1-rc1

for you to fetch changes up to d11ae8e0a76afc506071831854348f2ea1f3290e:

Documentation: modern versions of ceph are not backed by btrfs (2019-03-05 18:55:18 +0100)

The highlights are:

- rbd will now ignore discards that aren't aligned and big enough to
actually free up some space (myself). This is controlled by the new
alloc_size map option and can be disabled if needed.

- support for rbd deep-flatten feature (myself). Deep-flatten allows
"rbd flatten" to fully disconnect the clone image and its snapshots
from the parent and make the parent snapshot removable.

- a new round of cap handling improvements (Zheng Yan). The kernel
client should now be much more prompt about releasing its caps and
it is possible to put a limit on the number of caps held.

- support for getting ceph.dir.pin extended attribute (Zheng Yan)

Gustavo A. R. Silva (1):
libceph: use struct_size() for kmalloc() in crush_decode()

Ilya Dryomov (11):
rbd: get rid of obj_req->obj_request_count
rbd: handle DISCARD and WRITE_ZEROES separately
rbd: round off and ignore discards that are too small
rbd: remove experimental designation from kernel layering
rbd: clear ->xferred on error from rbd_obj_issue_copyup()
rbd: factor out __rbd_osd_req_create()
rbd: stop copying num_osd_ops in rbd_obj_issue_copyup()
rbd: introduce rbd_obj_issue_copyup_ops()
rbd: copyup with an empty snapshot context (aka deep-copyup)
rbd: whole-object write and zeroout should copyup when snapshots exist
rbd: advertise support for RBD_FEATURE_DEEP_FLATTEN

Jeff Layton (1):
Documentation: modern versions of ceph are not backed by btrfs

Yan, Zheng (12):
ceph: set special inode's blocksize to page size
ceph: decode feature bits in session message
ceph: split large reconnect into multiple messages
ceph: map snapid to anonymous bdev ID
ceph: support versioned reply
ceph: support getting ceph.dir.pin vxattr
ceph: send cap releases more aggressively
ceph: touch existing cap when handling reply
ceph: remove dentry_lru file from debugfs
ceph: delete stale dentry when last reference is dropped
ceph: periodically trim stale dentries
ceph: add mount option to limit caps count

zhengbin (1):
ceph: pass inclusive lend parameter to filemap_write_and_wait_range()

Documentation/filesystems/ceph.txt | 14 +-
drivers/block/rbd.c | 400 +++++++++++++++------
fs/ceph/caps.c | 72 ++--
fs/ceph/debugfs.c | 27 --
fs/ceph/dir.c | 455 +++++++++++++++++++-----
fs/ceph/file.c | 13 +-
fs/ceph/inode.c | 52 +--
fs/ceph/mds_client.c | 698 ++++++++++++++++++++++++++++++-------
fs/ceph/mds_client.h | 43 ++-
fs/ceph/snap.c | 159 ++++++++-
fs/ceph/super.c | 21 +-
fs/ceph/super.h | 43 ++-
fs/ceph/xattr.c | 20 +-
include/linux/ceph/types.h | 1 +
net/ceph/osdmap.c | 5 +-
15 files changed, 1597 insertions(+), 426 deletions(-)