Quiet compiler warning from casting pointer to integer of different size.
b=15981

port Adaptive Timeouts from b1_6 to HEAD.
b=14071
r=nathan
r=adilger

b=14975
i=green
i=huanghua

Openlock cache forward port

b=15940
i=isaac
i=oleg

Convert kp30.h to an internal libcfs include and change users of kp30.h to
include libcfs.h if they were not already.

b=15797
i=huanghua
i=vitaly

Misc fix for updating file {a/m/c}time as following policy:
1) Lustre file "{a/m/c}time" should base on client-side clock, including all
the file operations.
2) All the client-side clocks should be synchronized. It is no matter whether
the server-side clocks are synchronized with client-side ones or not.
3) File "ctime" is increased only.
4) File "{a,m}time" are increased only, except "utime()" operation can change
them backwards.

  i:nathan, adilger

fix sanity check in mdt_req_handle.
b=16076
r=wangdi
r=umka

r=nikita,shadow

- fixed handling for OBD_FAIL_$PREF_$OPC_NET fail_ids in mdt. Former code did not
check it correctly (due to typo with && instead of &) in mdt_req_handle() and
they all did not work. In same time, some handlers like mdt_close() and
mdt_enqueue() tried to check them again (result of some wrong fix) but again, did
it not correctly. They returned 0 error without doing anything. This should
have to emulate network failure. But as they did not allocate reply buffer and
returned 0 error, they caused rs != NULL assert in ptlrpc. Fxing this also fixed
replay-single.sh test_53* and replay_dual.sh test_12 and possibly others;

- removed checking for NET fail_id in mdt_close() and mdt_enqueue() - sources
of recent assert;

- added sanity check in mdt_req_handle() for any other invalid situation about
returning 0 error and not allocating reply buffers;

- removed mdt_reply(), move its one line call into mdt_req_handle(). This was
needed to simplify handling NET fail_ids in which case we should just return 0
and make sure that no reply is sent;

- comments and cleanups;

- in reply-dual.sh - remove test 8 from ALWAYS_EXCEPT. It passes in HEAD.
Originally for placed into ALWAYS_EXCEPT for old mds code and later moved to
HEAD test scripts but as mds in HEAD is completely new this bug is making any
sense there;

- in reply-single.sh - remove tests 0b 39 56 from ALWAYS_EXCEPT. They are
passing in HEAD. Also they are obsolete and related to closed bugs.

because LASSERT on both the data supplied by a client, and the data
on disk is dangerous and incorrect.

b=15574
i=adilger
i=shadow

r=shadow,nikita
- fixes issue with accessing freed @ns on behalf rpc handling when some late rpc comes in fini time;
- add new comments in functions, converts existing ones to be inline wigth doxygen comments policies.

b=11777
r=green, shadow

invalidate the import to halt request handling so the namespace can be safely
cleaned up

b=14230
i=amit.sharma
i=manoj.joseph

umds cleanup: use libcfs kmap api rather than kernel kmap apis.

b=14230
i=rahul.deshmukh
i=manoj.joseph

umds cleanup: use libcfs api.

b=14230
i=rahul.deshmukh
i=alex.zhuravlev

umds cleanup : use libcfs api rather than calling kernel functions.

b=14230
i=alex.zhuravlev
i=h.huang

following patch removes 1.6 dead code from head branch and moves some
function to respective layers.

diffstat:

 b/lustre/include/lustre_mds.h |   70 -
 b/lustre/mdd/mdd_lov.c        |  180 ++
 b/lustre/mds/Makefile.in      |    3
 b/lustre/mds/handler.c        | 2571 ------------------------------------------
 b/lustre/mds/mds_fs.c         |  654 ----------
 b/lustre/mds/mds_internal.h   |  209 ---
 b/lustre/mds/mds_log.c        |   84 -
 b/lustre/mds/mds_lov.c        |  295 ----
 b/lustre/mdt/mdt_handler.c    |  116 +
 b/lustre/mdt/mdt_recovery.c   |   53
 lustre/mds/commit_confd.c     |   98 -
 lustre/mds/mds_join.c         |  508 --------
 lustre/mds/mds_lib.c          |  488 -------
 lustre/mds/mds_open.c         | 1533 -------------------------
 lustre/mds/mds_reint.c        | 2419 ---------------------------------------
 lustre/mds/mds_unlink_open.c  |  287 ----
 lustre/mds/mds_xattr.c        |  358 -----
 17 files changed, 369 insertions(+), 9557 deletions(-)

b=14929
i=zam
i=nikita

r=Nathan Rutman, Alexey Lyashkov

Ported the patch 'to organize the stats on per-nid basis instead of the existing per-export basis' to HEAD.
This patch also includes all its related bug fixes(bug 14016, bug 14370, bug 14873).

b=13943
i=yury.umanets
i=nikita.danilov

- more generic lu_stack_fini().

b=14910
i=umka
i=tappro

update lock on lookup for aged files

b=13397
i=shadow
i=johann

Update Lustre server to support 2.6.22.14 vanilla kernel.

b=14230
i=h.huang
i=manoj.joseph

cleanup for umds, this patch replaces kernel api call with equivalent
api from lustre library.

b=13943
i=yong.fan
i=nikita.danilov

fini devices one by one, and then free them one by one.

b=14976
i=eric.mei
i=h.huang

(1) Miss to call "req_capsule_set_size()" in "mdc_get_remote_perm()".
(2) misc fix after mixed_layout_req landed.

b=14769
i=adilger
i=eric.mei

(1) Fix race condition between identity upcall disabled checking
    and the real identity upcall doing.
(2) Replace "CWARN" and "CERROR" about identity with "CDEBUG".
(3) Test scripts fix for SLES10 system and remote client test.
(4) Code indent related fix.

b=14844
i=adilger
i=deen

fix compile issue on PPC.

b=3462
i=johann
i=adilger

patch addressing replay-single test53 set port for HEAD.

b=13829
i=adilger
i=johann

i=yong.fan
i=rahul.deshmukh
i=nikita.danilov

- use req_capsule interface for client.
- add some interoperability support on server side.

- redesigned remote acl support, by FanYong
  b=11842
  r=pravin.shelar, eric.mei
- new sptlrpc configure interface
  b=13642
  r=yong.fan, rahul.deshmukh
- split kerberos keytab for lustre_root
  b=13873
  r=yong.fan, h.huang
- fix setuid for gss with linux keyring
  b=13899
  r=yong.fan, h.huang

i=adilger
i=nathan.rutman

This patch for lfs getstripe to return default values for
directories instead of "no stripe info".

r=Nathan, Adilger

to remove the use of LPROCFS_INIT_VARS and related macros

b=12974
i=nikita
i=adilger

1) set as "inline" for such large function ("obd_fail_check()") is not suitable,
   replaced with normal function "__obd_fail_check_set()".
2) atomic operations for obd_fail_count (replace "static count" in obd_fail_check).
3) use "test_and_set_bit()" for "OBD_FAILED/OBD_FAIL_ONCE" check and set to avoid
   unexpected racing condition between multi-thread ops.
4) some cleanup for OBD_FAIL_XXX macro.

b=13377
i=umka
i=nikita

"comments" patch.

b=14064

- readdir() for liblustre: i=nikita,fanyong
- flock for liblustre and various fixes for liblustre: i=umka,fanyong

b=14135
i=nathan
i=huanghua

Original "mgc_logname2resid" process both "logname" (which consists of fsname-nodetype)
and "fsname", it can not distinguish "-" contained fsname and the logname.
Split it into two functions: "mgc_logname2resid" and "mgs_fsname2resid" for that.

b=13568
i=johann
i=green

Remove 2.4 kernel check from lustre/mdt/mdt_lproc.c.

  b:14001
  i:nikita, yury

b=14007
i=nathan
i=tappro

check for MDS_OPEN_OWNEROVERRIDE in attr_pack()/attr_unpack()
since it is used in mds_fix_attr() (see bug 5781) for NFS.