git://git.whamcloud.com - fs/lustre-release.git/log

LU-15840 lov: return st_blocks=1 for HSM released files

The MDT will return st_blocks=1 for a HSM released file.
In the call ->coo_attr_get in LOV layer, the client should also
return st_blocks=1 for a HSM released file.

Otherwise, the client may get 0 block count. It is very easy to
reproduce this problem via the following commands for a archived
file:
# $LFS hsm_restore $file
# $LFS hsm_release $file
# $LFS hsm_release $file
After release a file twice, the reported block count via stat()
call will become 0.

Change-Id: Id1841147e40a7df0ca615e887f324cff8e613f11
Signed-off-by: Qian Yingjin <qian@ddn.com>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/47291
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Etienne AUJAMES <eaujames@ddn.com>

LU-15714 pcc: reserve layout intent flags for PCCRO

Add wirecheck checks for PCCRO data structures
struct lu_pcc_attach, lu_pcc_detach, lu_pcc_state

Test-Parameters: trivial
Signed-off-by: Qian Yingjin <qian@ddn.com>
Change-Id: If8a414103ab13155aa483179247c81908b6ced69
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/46981
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Feng Lei <flei@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-6142 lnet: SPDX for lnet/lnet/

Convert from verbose license text to SDPX.

Test-Parameters: trivial
Signed-off-by: Timothy Day <timday@amazon.com>
Change-Id: I8ef4aaabdd0a0b89a60a9187756b451c67a43492
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54252
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-6142 misc: SPDX for lustre-iokit

Convert from verbose license text to SPDX.

Test-Parameters: trivial
Signed-off-by: Timothy Day <timday@amazon.com>
Change-Id: I70f0c1387bcfe2dbe862a292ccb0f549e4e80d31
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54180
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-6142 lnet: SPDX for lnet/util/lnetconfig/

Convert from verbose license text to SDPX.

Test-Parameters: trivial
Signed-off-by: Timothy Day <timday@amazon.com>
Change-Id: I25c57a0db2554f551bda0b9b5f6c03893ff83646
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54172
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-12452 socklnd: allow setting IP ToS value

This patch add a new tuning to set the IP "Type of Service" value for
TCP QoS.

It adds the module parameter "tos":
...
options ksocklnd tos=106

tos=-1 means "disable": the LND will not try to set the ToS value.

Test-Parameters: trivial testlist=sanity-lnet
Signed-off-by: Etienne AUJAMES <eaujames@ddn.com>
Change-Id: I15d3d1dfb645cc778763713c5018f66bea8567c6
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54080
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Alexey Lyashkov <alexey.lyashkov@hpe.com>
Reviewed-by: Frank Sehr <fsehr@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17496 lnet: retry cleanup during shutdown

LNet can work a little harder to cleanup during teardown to
avoid an assert on module removal.

Signed-off-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Change-Id: Ic19c7774fa354b55bbfe21e8d87171dd024748c4
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53876
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Serguei Smirnov <ssmirnov@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17602 mdd: use correct fid in mdd_rename

mdd_rename() can re-insert target name back as a part of error
handling. use correct fid for that, not own target directory fid.

Signed-off-by: Alex Zhuravlev <bzzz@whamcloud.com>
Change-Id: I0662fa005459416b070157a2d049fcf5ed08ae91
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54260
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Lai Siyao <lai.siyao@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>

LU-17525 tests: sanity/133a interop version checking

sanity/133a with 2.15.4 and master fails with:
Error: 'The open counter on mds1 is 1, not 2'

Add a version check for at least 2.15.62 to exclude the extra
checks when the MDS does not have v2_15_61-63-g055f939979

Test-Parameters: testlist=sanity env=ONLY=133a clientarch=aarch64 clientdistro=el8.8
Test-Parameters: testlist=sanity env=ONLY=133a serverversion=2.15.4 serverdistro=el8.8
Test-Parameters: testlist=sanity env=ONLY=133a clientarch=aarch64 clientdistro=el8.8 serverversion=2.15.4 serverdistro=el8.8
Fixes: 055f939979 ("LU-17481 mdt: count all opens in mdt.*.md_stats")
Signed-off-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Change-Id: Ibb6eca7a5dcf295b419f7025a0167d70babe0f1f
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54466
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Patrick Farrell <patrick.farrell@oracle.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>

LU-17675 tests: skip sanity-flr/61a for el9.3

The atime update appears to be broken in this kernel, skip the test
for now.

Test-Parameters: trivial testlist=sanity env=ONLY=61 clientdistro=el9.3
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I2e27e2fbaa9a6a9e11049c4629b10998b3824c12
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54612
Tested-by: jenkins <devops@whamcloud.com>
Reviewed-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17392 build: compatibility updates for kernel 6.7

Linux commit v6.6-rc4-53-gc42d50aefd17
mm: shrinker: add infrastructure for dynamically allocating
shrinker

Users of struct shrinker must dynamically allocate shrinker objects
to avoid run-time warnings.

Provide a wrapper for older kernels to alloc+register shinkers
and unregister+free.

Use get_group_info() and put_group_info() wrappers instead of
open coding the reference counting on group_info.usage

Signed-off-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Change-Id: Ie07bdb7fe3eb6060bd84f95f860f1b53d120a605
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53621
Tested-by: Maloo <maloo@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>

LU-17243 build: compatibility updates for kernel 6.6

linux kernel v5.19-rc1-4-gc4f135d64382
  workqueue: Wrap flush_workqueue() using a macro
linux kernel v6.5-rc1-7-g20bdedafd2f6
  workqueue: Warn attempt to flush system-wide workqueues.
If __flush_workqueue(system_wq) is not available fall back to
flush_scheduled_work()

linux kernel v6.5-rc1-92-g13bc24457850
  fs: rename i_ctime field to __i_ctime
Use accessors for ctime. Provide replacements for older
kernels.

linux kernel v6.5-rc1-95-g0d72b92883c6
  fs: pass the request_mask to generic_fillattr
Provide request_mask argument where needed.

Linux commit v6.5-rc2-20-g2ddd3cac1fa9
  nsproxy: Convert nsproxy.count to refcount_t
Provide a wrapper for inc/dec of nsproxy.count

linux kernel v6.5-rc4-110-gcf95e337cb63
  mm: delete mmap_write_trylock() and vma_try_start_write()
Use down_write_trylock directly mmap_write_trylock

In preparation for kernel 6.7 the remaining inode time
accessors will be preferred:

linux kernel v6.6-rc5-86-g12cd44023651
  fs: rename inode i_atime and i_mtime fields
Use accessors for atime and mtime. Provide replacements for
older kernels.

Test-Parameters: trivial
Signed-off-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Change-Id: Ide6c2e3e8db532449850b145c2d61b972d21f649
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52908
Tested-by: Maloo <maloo@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Yang Sheng <ys@whamcloud.com>

LU-17081 build: Prefer folio_batch to pagevec

Linux commit v5.16-rc4-36-g10331795fb79
  pagevec: Add folio_batch

Linux commit v6.2-rc4-254-g811561288397
  mm: pagevec: add folio_batch_reinit()

Linux commit v6.4-rc4-438-g1e0877d58b1e
  mm: remove struct pagevec

Use folio_batch and provide wrappers for older kernels to use
pagevec handling, conditionally provide a folio_batch_reinit

Add macros to ease adding pages to folio_batch(es) as well
as unwinding batches of struct folio where struct page is
needed.

HPE-bug-id: LUS-11811
Signed-off-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Change-Id: Ie70e4851df00a73f194aaa6631678b54b5d128a1
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52259
Tested-by: Maloo <maloo@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Reviewed-by: Yang Sheng <ys@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>

LU-6142 osd-zfs: Fix style issues for osd_quota.c

This patch fixes issues reported by checkpatch
for file lustre/osd-zfs/osd_quota.c

Test-Parameters: trivial fstype=zfs
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: Idb21a3004fb6cb711b2b6a48b4bba735f28ecb31
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54265
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-6142 osd-zfs: Fix style issues for osd_scrub.c

This patch fixes issues reported by checkpatch
for file lustre/osd-zfs/osd_scrub.c

Test-Parameters: trivial fstype=zfs
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I5b14e20f07e43b36cf974fa358c49661a569ef8b
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54261
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-6142 osd: Fix style issues for osd_oi.c

This patch fixes issues reported by checkpatch
for file lustre/osd-zfs/osd_oi.c

Test-Parameters: trivial fstype=zfs
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I5a1292790007f921c206803dec5230ebda16ebf9
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54255
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-6142 osd: Fix style issues for osd_index.c

This patch fixes issues reported by checkpatch
for file lustre/osd-zfs/osd_index.c

Test-Parameters: trivial fstype=zfs
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: If2fa688443dd2d7528b6c2551f4f6cd21e39e8b3
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54231
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-6142 mdd: Fix style issues for mdd_orphans.c

This patch fixes issues reported by checkpatch
for file lustre/mdd/mdd_orphans.c

Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I4edbce9d25093afe5a6ab5293e9872b8f3681ae7
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54226
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>

LU-6142 lfsck: Fix style issues for lfsck_lib.c

This patch fixes issues reported by checkpatch
for file lustre/lfsck/lfsck_lib.c

Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I10e8d63c36221ffddc2258b54c86d2f64092c0ce
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54215
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-6142 lfsck: Fix style issues for lfsck_layout.c

This patch fixes issues reported by checkpatch
for file lustre/lfsck/lfsck_layout.c

Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I5d6f8156f4552ef8b89248a7a349eb43b74d7b9f
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54174
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-6142 selftest: SPDX for lnet/selftest/

Convert from verbose license text to SDPX.

Test-Parameters: trivial
Signed-off-by: Timothy Day <timday@amazon.com>
Change-Id: I131a74e146c02e601c2474f648550b1bedf37a28
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54171
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-6142 llite: Fix style issues for llite_mmap.c

This patch fixes issues reported by checkpatch
for file lustre/llite/llite_mmap.c

Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I9ead23aea0b13f91427a208feac3390d241f1b07
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54143
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-6142 osd: Fix style issues for lov_cl_internal.h

This patch fixes issues reported by checkpatch
for file lustre/lov/lov_cl_internal.h

Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I8a2a8266745cf75e819698ea794d27edf32fa8c2
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54124
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17572 lov: remove noise from lov_init_sub()

lov_init_sub() generates too many messages in applications like racer.
let's make it a bit less noisy.

Test-Parameters: trivial
Signed-off-by: Alex Zhuravlev <bzzz@whamcloud.com>
Change-Id: I00ae75597b550c29122d8fb9d34d4e0d24c38dd5
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54125
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>

LU-17632 o2iblnd: graceful handling of CM_EVENT_CONNECT_ERROR

There were examples in the field with RoCE setups which demonstrate
that RDMA_CM_EVENT_CONNECT_ERROR may be received when conn state
is neither IBLND_CONN_ACTIVE_CONNECT nor IBLND_CONN_PASSIVE_WAIT.
Handle this in a more gracious manner: report the event as unexpected
and allow the flow to continue.

Test-Parameters: trivial testlist=sanity-lnet
Signed-off-by: Serguei Smirnov <ssmirnov@whamcloud.com>
Change-Id: I58b2482207cfd821f6eac142bdefc8f5bc50f8b4
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54353
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Etienne AUJAMES <eaujames@ddn.com>
Reviewed-by: Frank Sehr <fsehr@whamcloud.com>
Reviewed-by: Cyril Bordage <cbordage@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-14869 test: improve sanity-flr/200a

Make sure "flock -x" successfully returned before running mirror
resync so that it won't get into running read holding shared flock.

Test-Parameters: trivial testlist=sanity-flr env=ONLY=200a,ONLY_REPEAT=10
Test-Parameters: trivial testlist=sanity-flr env=ONLY=200a,ONLY_REPEAT=10
Test-Parameters: trivial testlist=sanity-flr env=ONLY=200a,ONLY_REPEAT=10
Test-Parameters: trivial testlist=sanity-flr env=ONLY=200a,ONLY_REPEAT=10
Test-Parameters: trivial testlist=sanity-flr env=ONLY=200a,ONLY_REPEAT=10
Signed-off-by: Bobi Jam <bobijam@whamcloud.com>
Change-Id: I6383af5d5761980d24af19efd4a4ac899f369a7d
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54345
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Yang Sheng <ys@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17621 lnet: fix conns_per_peer bounds check

Logical opreator '||' would always result in 'TRUE',
allowing any arbitrary conns_per_peer value to be set.
Change Logical operator from '||' to '&&' to correctly
compare that the value is within range.

Test-Parameters: trivial testlist=sanity-lnet
Fixes: 9b05e872482e ("LU-10391 lnet: support updating LNet local NI settings")
CoverityID: 415060 ("Logically dead code")
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: Ibcaf18060cae1fc62fe41ee6237abaad1fd2de7f
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54326
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Chris Horn <chris.horn@hpe.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>

LU-17623 libcfs: save msg_fn pointer to avoid race

Save msgdata->msg_fn pointer at the start of libcfs_debug_msg() to
avoid a race condition if another thread calls CDEBUG_WITH_LOC()
at the same time and has a different calling function name. The
msg_file pointer was already being saved. Otherwise it is possible
to fail the __LASSERT(debug_buf == string_buf) check if formatted
string length changes between prep and write passes.

Use existing header.ph_mask and .ph_line instead of duplicating them.

Test-Parameters: testlist=sanity-scrub env=ONLY=4d,ONLY_REPEAT=25
Fixes: 1a9bd41846 ("LU-14518 libcfs: print CFS_FAIL_CHECK() location")
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I3fd30cc9eed2ec8dabd795e9622fe1908a3ebbe5
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54320
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-by: Aurelien Degremont <adegremont@nvidia.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17612 gss: always try to unlink key in error

In case of error in context negotiation carried out in userspace,
always try to unlink key to avoid leaking it.

Test-Parameters: trivial
Test-Parameters: kerberos=true testlist=sanity-krb5
Test-Parameters: testgroup=review-dne-selinux-ssk-part-2
Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Change-Id: Ic771f1e4f1b6474caaa89f63c3b02678e163d3d3
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54316
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Aurelien Degremont <adegremont@nvidia.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17057 tests: Fix "...endpoint shutdown" under sanity-sec

This patch fixes test_0 failing with "Cannot send after
transport endpoint shutdown" by introducing wait_ssk()
in sec_setup() to deterministicly applied SSK flavor.

Test-Parameters: trivial mdscount=2 mdtcount=4 osscount=1 ostcount=8 clientcount=2 testlist=sanity-sec env=SHARED_KEY=true,ONLY=0
Test-Parameters: trivial mdscount=2 mdtcount=4 osscount=1 ostcount=8 clientcount=2 testlist=sanity-sec env=SHARED_KEY=true,ONLY=0
Test-Parameters: trivial mdscount=2 mdtcount=4 osscount=1 ostcount=8 clientcount=2 testlist=sanity-sec env=SHARED_KEY=true,ONLY=0
Test-Parameters: trivial mdscount=2 mdtcount=4 osscount=1 ostcount=8 clientcount=2 testlist=sanity-sec env=SHARED_KEY=true,ONLY=0
Test-Parameters: trivial mdscount=2 mdtcount=4 osscount=1 ostcount=8 clientcount=2 testlist=sanity-sec env=SHARED_KEY=true,ONLY=0
Test-Parameters: trivial mdscount=2 mdtcount=4 osscount=1 ostcount=8 clientcount=2 testlist=sanity-sec env=SHARED_KEY=true,ONLY=0
Test-Parameters: trivial mdscount=2 mdtcount=4 osscount=1 ostcount=8 clientcount=2 testlist=sanity-sec env=SHARED_KEY=true,ONLY=0
Test-Parameters: trivial mdscount=2 mdtcount=4 osscount=1 ostcount=8 clientcount=2 testlist=sanity-sec env=SHARED_KEY=true,ONLY=0
Test-Parameters: trivial mdscount=2 mdtcount=4 osscount=1 ostcount=8 clientcount=2 testlist=sanity-sec env=SHARED_KEY=true,ONLY=0
Test-Parameters: trivial mdscount=2 mdtcount=4 osscount=1 ostcount=8 clientcount=2 testlist=sanity-sec env=SHARED_KEY=true,ONLY=0
Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: Ia14021ab82913507df02dbb5a12c8596663f15d9
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54311
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17612 sec: return keyring errors to userspace

In current code, Linux keyring errors, when using GSS Kerberos,
are all masked under a generic ECONNREFUSED error. That makes
it hard to understand the root cause of the problem
for the I/O caller.

Update the code to propagate errors from request_key() up to
the application.

struct ptlrpc_cli_ctx * gss_sec_lookup_ctx_kr(...) is modified
to now returns a NULL pointer or -errval. This is tested by callers
and propagated. NULL values are still converted to ECONNREFUSED.

Test-Parameters: trivial
Test-Parameters: kerberos=true testlist=sanity-krb5
Test-Parameters: testgroup=review-dne-selinux-ssk-part-2
Change-Id: I13792f141a961036bc9f7629a4a2db692e245c41
Signed-off-by: Aurelien Degremont <adegremont@nvidia.com>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54296
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Sebastien Buisson <sbuisson@ddn.com>

LU-930 ptlrpc: remove spurious error messages

Stop errors being printed when a disconnect RPC times out, since
this error is ignored anyway, and adds no value to be printed.

Remove -61 = -ENODATA error from seq_server_init() since this is an
"expected" event for a new target and the error code is not useful.

Test-Parameters: trivial
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I0f695409617061d46a1b910108cda05f863ebbe5
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54285
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Reviewed-by: Sebastien Buisson <sbuisson@ddn.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17609 sec: nodemap readonly_mount for remount

The readonly_mount property on nodemaps forces read-only mount from
clients. Clients trying rw remount (via mount -o remount,rw) should
also be forced to read-only.

Also improve sanity-sec test_61 to exercise client remount.

Fixes: e7ce67de92 ("LU-15451 sec: read-only nodemap flag")
Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Change-Id: I61f8141001d2ff9e832e5c93d8f5997479af98a6
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54282
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17317 sec: fix sanity-sec test_28

Improve sanity-sec test_28 to verify that srpc_contexts is valid
YAML output.
Also remove the ctx information from the output, as printing out a
kernel pointer is not ideal.

Fixes: f6687bafcb ("LU-17317 sec: add srpc_serverctx proc file")
Test-Parameters: trivial
Test-Parameters: kerberos=true testlist=sanity-krb5
Test-Parameters: testgroup=review-dne-selinux-ssk-part-2
Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Change-Id: Ie48dc61adfd5017a2313981f27407c9d3b69dd71
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54280
Reviewed-by: Aurelien Degremont <adegremont@nvidia.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>

LU-17606 ldiskfs: remove old el8.[123] patches/series

Remove the old ldiskfs el8.[123] patch series files, and the resulting
patch files that are no longer referenced by any patch series file:

./contrib/scripts/clearpatches.sh -d ldiskfs/kernel_patches

Test-Parameters: trivial
Change-Id: I0de7302e9de06ad557e9b35d7eea1b9c4084ecae
Signed-off-by: Jian Yu <yujian@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54272
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17606 ldiskfs: remove old el7.[678] patches/series

Remove the old ldiskfs el7.[678] patch series files, and the resulting
patch files that are no longer referenced by any patch series file:

./contrib/scripts/clearpatches.sh -d

Test-Parameters: trivial
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I6727d88af1261c9b4090984ad8cab51a5dce7057
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54271
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Jian Yu <yujian@whamcloud.com>
Reviewed-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17605 obdclass: do not wait forever acquiring entry

The process of refreshing an entry via refresh_entry() goes through
an upcall/downcall. If the upcall succeeds, we enter a wait queue.
If after that the downcall is never called, we hit the expiry timeout,
and we get removed from the wait queue.
But if the entry is not new, the expiry time will be
MAX_SCHEDULE_TIMEOUT == LONG_MAX, which means an infinite wait.
So avoid waiting forever if an entry could not be refreshed, and call
wake_up_all() if the wait for the ACQUIRING state failed.

Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Change-Id: I50ee59654adc221027c79cb68fa182b9abed50fa
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54269
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Yang Sheng <ys@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17510 obdclass: fix wake up when queuing close request.

The waitqueue for requests that need to be sent but that haven't been
allocated a slot is kept ordered by request arrival for fairness.  So
new requests are added to the end.

For requests other than 'close' there is a limit to the number of
active requests (slots) and requests are assigned to slot on a
first-come-first-served basis, so they are simply removed from the
head of the list.

For 'close' requests it is important that these not block indefinitely
behind other other requests so there is one slot that can only be used
by a close request - and only if no other slots are used by a close
request.  These requests do not follow a strict FIFO order.

When a non-"close" request completes we wake the first request on the
list.  There is no point searching all the way down the list for a
close request that could also be woken.  We only do that when a
"close" request completes.  This optimises the common case.

However: when a request is first queued we add it to the end of the
queue and then wake up the first deserving request if there is one.
When there are free slots, this is expected to wake the request just
queued.  When there are no free slots, nothing is woken.

When a "close" request is queued and added to the end of the queue
after other non-close requests, we need to potentially search to the
end of the queue for a close request to wake, just as we do when a
close request completes.  Unfortunately we don't.  This can result in
a close request blocking indefinitely.

So: change the wakeup in obd_get_mod_rpc_slot() to match the wakeup in
obd_put_mod_rpc_slot().  This ensure consistent handling and in
particular will handle a close request immediately if there are no
other close requests in flight.

Clarify comment in claim_mod_rpc_function() to make and perform minor
code cleanup there.

Fixes: b5fde4d6c023 ("LU-17197 obdclass: preserve fairness when waiting for rpc slot")
Signed-off-by: Mr NeilBrown <neilb@suse.de>
Change-Id: I7b658efc0298a091166f0f18ce460fc3148047eb
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54259
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17606 ldiskfs: remove old compatibility code

The JOURNAL_START_HAS_3ARGS and EXT4_HT_MISC checks are always true
for kernels since 3.10, and no longer have any value to keep around.

Test-Parameters: trivial
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I39333026b1f24c3d60fbc3f8c51be693353ebbe5
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54274
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Artem Blagodarenko <ablagodarenko@ddn.com>
Reviewed-by: Li Dongyang <dongyangli@ddn.com>

LU-17563 kernel: update SLES15 SP5 [5.14.21-150500.55.49.1]

Update SLES15 SP5 kernel to 5.14.21-150500.55.49.1 for Lustre client.

Test-Parameters: trivial mdtcount=4 mdscount=2 \
clientdistro=sles15sp5 testlist=sanity

Test-Parameters: optional clientdistro=sles15sp5 testgroup=full-part-1
Test-Parameters: optional clientdistro=sles15sp5 testgroup=full-part-2
Test-Parameters: optional clientdistro=sles15sp5 testgroup=full-part-3

Change-Id: I23868ff25ae093a52f004e556789805a644832ac
Signed-off-by: Jian Yu <yujian@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54240
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Yang Sheng <ys@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17593 kernel: update RHEL 8.9 [4.18.0-513.18.1.el8_9]

Update RHEL 8.9 kernel to 4.18.0-513.18.1.el8_9.

Test-Parameters: trivial fstype=ldiskfs mdtcount=4 mdscount=2 \
  clientdistro=el8.9 serverdistro=el8.8 testlist=sanity

Test-Parameters: trivial fstype=zfs mdtcount=4 mdscount=2 \
  clientdistro=el8.9 serverdistro=el8.8 testlist=sanity

Test-Parameters: trivial fstype=ldiskfs mdtcount=4 mdscount=2 \
  clientdistro=el8.8 serverdistro=el8.9 testlist=sanity

Test-Parameters: trivial fstype=zfs mdtcount=4 mdscount=2 \
  clientdistro=el8.8 serverdistro=el8.9 testlist=sanity

Test-Parameters: optional clientdistro=el8.9 serverdistro=el8.9 \
  testgroup=full-part-1

Test-Parameters: optional clientdistro=el8.9 serverdistro=el8.9 \
  testgroup=full-part-2

Test-Parameters: optional clientdistro=el8.9 serverdistro=el8.9 \
  testgroup=full-part-3

Change-Id: I2c928e4c08af278dacce1d1dc7a14fa77ffffa33
Signed-off-by: Jian Yu <yujian@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54238
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Yang Sheng <ys@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17561 kernel: update RHEL 9.3 [5.14.0-362.18.1.el9_3]

Update RHEL 9.3 kernel to 5.14.0-362.18.1.el9_3.

Test-Parameters: trivial fstype=ldiskfs mdtcount=4 mdscount=2 \
  clientdistro=el9.3 serverdistro=el9.2 testlist=sanity

Test-Parameters: trivial fstype=zfs mdtcount=4 mdscount=2 \
  clientdistro=el9.3 serverdistro=el9.2 testlist=sanity

Test-Parameters: trivial fstype=ldiskfs mdtcount=4 mdscount=2 \
  clientdistro=el9.2 serverdistro=el9.3 testlist=sanity

Test-Parameters: trivial fstype=zfs mdtcount=4 mdscount=2 \
  clientdistro=el9.2 serverdistro=el9.3 testlist=sanity

Test-Parameters: optional clientdistro=el9.3 serverdistro=el9.3 \
  testgroup=full-part-1

Test-Parameters: optional clientdistro=el9.3 serverdistro=el9.3 \
  testgroup=full-part-2

Test-Parameters: optional clientdistro=el9.3 serverdistro=el9.3 \
  testgroup=full-part-3

Change-Id: Iddfe57197d854e0be864c0ce64699f92fcc181d1
Signed-off-by: Jian Yu <yujian@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54236
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Yang Sheng <ys@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17589 flock: Flock blocking information becomes stale

Blocking information remains to point for already cancelled lock.

Find new blocker on each reprocess.

Change-Id: I8d353795170f4fd0ae55dd646035cf8feb4cc162
HPE-bug-id: LUS-11784, LUS-11999
Signed-off-by: Andriy Skulysh <andriy.skulysh@hpe.com>
Reviewed-by: Vitaly Fertman <vitaly.fertman@hpe.com>
Reviewed-by: Alexander Zarochentsev <alexander.zarochentsev@hpe.com>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54219
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Yang Sheng <ys@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-11085 tests: Add performance test for ldlm_extent code

Add a new test module "ldlm_extent" which exercises the extent code by
creating multiple extent locks, and discarding them.
Each run is timed and a number of runs are combined to provide a
mean and standard deviation.

Two different tests are performed, with a ramp of locks to keep to
allow seeing any scalability issues:
1/ create lots of non-overlapping extents in
   random order, keeping up to 8000 at a time.
2/ create both random tiny extents and whole-file
   extents, alternating.  Keep up to 1,000,000.
   These are PR and so don't conflict.

Each test runs for at most 5 minutes
(30 loops of 10 seconds each = 300 seconds).

Test-Parameters: trivial env=SLOW=yes env=ONLY=842 testlist=sanity
Signed-off-by: Mr NeilBrown <neilb@suse.de>
Change-Id: I552da3c64fb467cbefb7d25eee709dd038bd454f
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54204
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>

LU-17566 mdt: move squash code in new/old_init_ucred

Move the uid/gid squashing code at the same place,
at the bottom of the function, to make code refactoring
simpler later.

The squashing code is mostly clearing suppgids from ucred,
and no code was using between the old and new position in
the function. So that should be pretty safe.

Handle suppgids clearing the same way for both function
and for both UID or GID squashing.

Signed-off-by: Aurelien Degremont <adegremont@nvidia.com>
Change-Id: I29669af26cf68491bf1b6020548116acf318c0c7
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54194
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Sebastien Buisson <sbuisson@ddn.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17571 tests: set idle_timeout in sanity 77l, 812[ab], 816

sanity.sh:test_77l,812a,812b,816 rely on idle_timeout set to not
0. Have the tests to take care of that.

Test-Parameters: trivial
HPE-bug-id: LUS-10951
Signed-off-by: Vladimir Saveliev <vladimir.saveliev@hpe.com>
Change-Id: I6c0cf3e7264263221b5ec54292673868f4bda25c
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54123
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-14535 quota: free lvbo in a wq

Mutex lqe_glbl_data_lock holded in
qmt_lvbo_free might be the reason of
sleeping while atommic if
cfs_hash_for_each_relax is getting a
spinlock on an upper layer:

BUG: sleeping function called from invalid
context at kernel/mutex.c:104
...
Call Trace:
dump_stack+0x19/0x1b
__might_sleep+0xd9/0x100
mutex_lock+0x20/0x40
qmt_lvbo_free+0xc7/0x380 [lquota]
mdt_lvbo_free+0x12d/0x140 [mdt]
ldlm_resource_putref+0x189/0x250 [ptlrpc]
ldlm_lock_put+0x1c8/0x760 [ptlrpc]
ldlm_export_lock_put+0x12/0x20 [ptlrpc]
cfs_hash_for_each_relax+0x3ff/0x450 [libcfs]
cfs_hash_for_each_empty+0x9a/0x210 [libcfs]
ldlm_export_cancel_locks+0xc2/0x1a0 [ptlrpc]
ldlm_bl_thread_main+0x7c8/0xb00 [ptlrpc]
kthread+0xe4/0xf0
ret_from_fork_nospec_begin+0x7/0x21

Move freeing of lvbo to a workqueue. This
patch could be probably reverted as soon
as https://review.whamcloud.com/45882 will
be landed.

Fixes: 1dbcbd70f8 ("LU-15021 quota: protect lqe_glbl_data in lqe")
Signed-off-by: Sergey Cheremencev <scherementsev@ddn.com>
Change-Id: I56aee72a7adbc6514b40689bae30669e607b5ecd
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54107
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Hongchao Zhang <hongchao@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>

LU-17555 ptlrpc: removed unused lm_repsize accessors

ptlrpc_req_get_repsize() and ptlrpc_req_set_repsize() are unused.

ptlrpc_req_set_repsize() is superseded by
ptlrpc_request_set_replen() so remove the unused variants.

Test-Parameters: trivial
Signed-off-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Change-Id: Ib89a57c00605b110ec28040614aecba9826f5ffa
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54089
Reviewed-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>

LU-17517 lov: fix large shift in lov_update_statfs()

UBSAN detected:

shift exponent 65 is too large for
64-bit type 'long long unsigned int'

in lov_update_statfs() in lov_request.c. This
patch caps shift at 32 since os_bsize is of
type u32. This avoids the invocation of
undefined behavior.

Reported-by: Ake Sandgren <ake.sandgren@hpc2n.umu.se>
Signed-off-by: Timothy Day <timday@amazon.com>
Change-Id: I9ed6dd145279631e8a362c85c6fd46f147ab6946
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54043
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-12019 build: remove global depmod.d conf from debs

Lustre should not be creating a global depmod.d configuration
file that affects the load order of all modules installed
on the system.

Yet, Lustre has a depmod.d configuration file that attempts
to mirror the default configuration (the man page is
identical for Debian):

https://manpages.ubuntu.com/manpages/xenial/en/man5/depmod.d.5.html

"By default, depmod will give a higher priority to a
  directory with the name updates using this built-in
  search string: "updates built-in" but more complex
  arrangements are possible and are used in several
  popular distributions."

However, when we switched from:

search updates built-in

to:

search updates/kernel built-in

Ubuntu depmod was forced to prefer build-in modules, since
the modules are not in `updates/kernel` as in Debian. If a
user has third party modules installed on their system, this
could make Ubuntu load the wrong module by default.

This patch removes the lustre.conf depmod.d file. By
leaving these load-order decisions to the distribution, this
patch addresses the regression on Ubuntu.

Fixes: 7ea4e0c ("LU-12019 build: Recognize Debian Kernel and set KMP dir")
Test-Parameters: trivial clientdistro=ubuntu2204
Signed-off-by: Timothy Day <timday@amazon.com>
Change-Id: I96fe1c0e64c48d045d46d62a10e8c8bd6ad2cb7d
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54025
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Thomas Stibor <thomas@stibor.net>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17463 osc: add option to disable page cache shrinker

The pages mapped into VM_LOCKED [mlocked()ed] VMAs are unevictable
pages. Those pages are marked with PG_mlocked.
However, page cache shrinker in Lustre treats all cached pages
equally even some of them are unevictable. It may evict mlocked
pages by mlock() or mlockall() calls wrongly.

This patch adds an tunable option to enable or disable page cache
shrinker:
- osc.*.enable_page_cache_shrink
It is enabled by default.

Signed-off-by: Qian Yingjin <qian@ddn.com>
Change-Id: I23ebf6d438a71c7917b0cb3375407a64587e15db
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53795
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Vladimir Saveliev <vladimir.saveliev@hpe.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-16194 tests: set minversion of MDS for sanity/65q

There are 2 sanity/65p, rename one to 65q.
Checking for negative start/end is not expected for old
verson of MDS. So check the verson of MDS in 65q.

Signed-off-by: Lei Feng <flei@whamcloud.com>
Test-Parameters: trivial testlist=sanity env=ONLY=65 serverversion=2.15
Change-Id: I1cb7716c37a349f441ed248613f569dd5ab78330
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53771
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Alex Deiter
Reviewed-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-13642 lnet: Allow dynamic IP specification

Currently you can setup an NI only using the device interface.
It is possible that a device interface has more than one IP
address. This change updates lnet_net_cmd() to setup an NI using
a specific network address.

For further reference please read

IP specification in LNet
https://wiki.whamcloud.com/display/LNet/IP+specification+in+LNet

Test-Parameters: trivial testlist=sanity-lnet
Change-Id: I2c456790fe9534bbfe02b0330cce73e80318cc1c
Signed-off-by: James Simmons <jsimmons@infradead.org>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53605
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Chris Horn <chris.horn@hpe.com>
Reviewed-by: Frank Sehr <fsehr@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-16796 lfsck: Change lfsck_layout_slave_target to use kref

This patch changes struct lfsck_layout_slave_target
to use kref instead of atomic_t

Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I7ea87e2b94a72363971b71415c9430e5b7ded8cc
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53422
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17334 lmv: exclude newly added MDT in mkdir

Exclude newly added MDT in QoS mkdir for 30 seconds in case
connections between MDTs are not ready, which may cause lookup fail.

Signed-off-by: Lai Siyao <lai.siyao@whamcloud.com>
Change-Id: Ibb5e6eda29ddfff8f66708d72e33453a96f5e7ef
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53860
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Hongchao Zhang <hongchao@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17248 kernel: wait for pages under writeback for bdev

Since RHEL 8.6 wait_for_stable_page() is controlled by
a new flag SB_I_STABLE_WRITES on the super block.

However the new flag is not set on the bdev pseudo sb,
which mean when doing write directly to the block device
we are not waiting on page writeback, this could trigger
false block integrity errors, as page could be modified
again when under writeback, the integrity checksum does
not match the new data any more.

Upstream has a pending patch
https://lore.kernel.org/linux-mm/20231025141020.192413-1-hch@lst.de/
which works for RHEL 9 kernels.

For RHEL 8 kernels the changes for bdev made it difficult
to backport, a different patch is used to check and wait
for bdev stable_pages.

Change-Id: Ie088abf29f40b294c31f993bcfad56d6081a3fce
Test-Parameters: trivial
Signed-off-by: Li Dongyang <dongyangli@ddn.com>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52922
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-15367 llite: add 'rc' to all iotrace messages

It's easy to add the return code to iotrace, so let's do it.

Test-Parameters: trivial
Signed-off-by: Patrick Farrell <paf0187@gmail.com>
Change-Id: Ic2357d3d32fd4954e96878174f13b7fe907df2df
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52007
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Sebastien Buisson <sbuisson@ddn.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-15367 llite: add lseek to iotrace

Add iotrace messages for lseek.

Credit to Qian Yingjin <qian@ddn.com> for original patch.

Test-Parameters: trivial
Signed-off-by: Patrick Farrell <pfarrell@whamcloud.com>
Change-Id: I2beed5e80ea9a3d6278ddd40e9deb6b56754fabe
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52004
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Sebastien Buisson <sbuisson@ddn.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-16935 llite: avoid hopeless i/o repeats

On SLES12SP5 kernels (4.12.14_122.147, 4.12.14-122.162) a race between
ll_filemap_fault and ll_imp_inval may lead to the livelock:

  - ll_filemap_fault loops endlessly as filemap_fault()->readpage()
    returns VM_FAULT_SIGBUS (it is unable to send read rpc as import
    is invalid) and as ll_page_inv_lock gets incremented within
    cl_page_discard()->..->vvp_page_delete() called after readpage
    failure.

  - ll_imp_inval stucks in
    obd_import_event(IMP_EVENT_INVALIDATE)->..->osc_object_invalidate
    (before recovery) waiting for completion of i/o ll_filemap_fault
    can not complete.

@ll_page_inv_lock is used to check the page being read by kernel
after it has been deleted from Lustre, which avoids potential
stale data reads. This seqlock allows us to see that a page was
potentially deleted, catch it in this case and repeat the I/O in
ll_filemap_fault() or vvp_io_read_start().

To avoid endless I/O repeat wrongly, in this patch we only increse
@ll_page_inv_lock for the page in PageUptodate state when delete
the page in vvp_page_delete(). The page that not in PageUptodate
state is usually deleted due to the error that does not require
retry.
By this way, ll_filemap_fault() and vvp_io_read_start() will not loop
endless for those errors that does not need to repeat I/O as the
seqlock @ll_page_inv_lock does not have any change.

Test to illustrate the issus is added.

sanity.sh tests are to test i/o error handling.

cl_io_loop(): avoid restart if ci_tried_all_mirrors flag is set.

HPE-bug-id: LUS-11686
Signed-off-by: Vladimir Saveliev <vladimir.saveliev@hpe.com>
Signed-off-by: Qian Yingjin <qian@ddn.com>
Change-Id: I3b62bc95db01bf11f6098011bf29e4064c7e201e
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/51505
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Andrew Perepechko <andrew.perepechko@hpe.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-14535 quota: get all quota info in LFS

This patch adds option "-a" for LFS to get the quota info of
all quota IDs. it iterates quota setting saved in global quota
setting files "quota_master/md-0x0" and "quota_master/dt-0x0"
from QMT and iterates the quota usage info saved in acct quota
files in the backend FS (LDiskFS or ZFS) from QSDs, then merge
the two kinds of quota info at client and print it in the similar
way as "lfs quota -u|-g|-p".

  $lfs quota -a -u /mnt/lustre
  Filesystem /mnt/lustre, Disk usr quotas
  quota_id  kbytes   quota   limit   grace   files quota limit  grace
      root    9684       0       0       -    1019    0     0       -
       bin       4       0  102400       -       1    0  10240      -
    daemon       4       0  102400       -       1    0  10240      -
       adm       4       0  102400       -       1    0  10240      -
        lp       4       0  102400       -       1    0  10240      -
      sync       4       0  102400       -       1    0  10240      -
  shutdown       4       0  102400       -       1    0  10240      -
      halt       4       0  102400       -       1    0  10240      -
      mail       4       0  102400       -       1    0  10240      -

  $lfs quota -a -g /mnt/lustre
  Filesystem /mnt/lustre, Disk grp quotas
  quota_id  kbytes   quota   limit   grace   files quota limit  grace
      root    9684       0       0       -    1019    0      0      -
       bin       4       0  204800       -       1    0  20480      -
    daemon       4       0  204800       -       1    0  20480      -
       adm       4       0  204800       -       1    0  20480      -
        lp       4       0  204800       -       1    0  20480      -
      sync       4       0  204800       -       1    0  20480      -
  shutdown       4       0  204800       -       1    0  20480      -
      halt       4       0  204800       -       1    0  20480      -
      mail       4       0  204800       -       1    0  20480      -

This patch also fixes an deadlock issue in qmt_pool_recalc,
the rw_semaphore "qmt_pool_info.qpi_sarr.osts.op_rw_sem" has been
acquired in qmt_pool_recalc (read mode), but it was acquired once
more in qmt_seed_glbe_all (read mode) and will be stuck if there
is a pending write mode lock acquisition from another thread.

qsd_reint_qpool D
Call Trace:
    schedule+0x29/0x70
    rwsem_down_read_failed+0x105/0x1c0
    call_rwsem_down_read_failed+0x18/0x30
    down_read+0x20/0x40
    qmt_seed_glbe_all+0x3a0/0x800 [lquota]
    qmt_site_recalc_cb+0x3c7/0x800 [lquota]
    cfs_hash_for_each_tight+0x11e/0x330
    cfs_hash_for_each+0x10/0x20 [libcfs]
    qmt_pool_recalc+0x9fc/0x1310 [lquota]

llog_process_th D
Call Trace:
    schedule+0x29/0x70
    rwsem_down_write_failed+0x215/0x3c0
    call_rwsem_down_write_failed+0x17/0x30
    down_write+0x2d/0x3d
    lu_tgt_pool_remove+0x36/0x1e0 [obdclass]
    qmt_pool_add_rem+0x655/0x920 [lquota]
    qmt_pool_rem+0x10/0x20 [lquota]
    lod_pool_remove_q+0xd6/0x1d0 [lod]
    class_process_config+0x16f2/0x2b20
    class_config_llog_handler+0x839/0x1540
    llog_process_thread+0x913/0x1c10
    llog_process_thread_daemonize+0x9f/0xe0

Test-Parameters: testlist=sanity-quota env=SLOW=yes,ONLY=49,NUM_QIDS=20000
Change-Id: I08feb928fbf34635ec9c5c341de993c718798dc9
Signed-off-by: Hongchao Zhang <hongchao@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/42098
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Sergey Cheremencev <scherementsev@ddn.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>

LU-10499 pcc: add readonly mode for PCC

Readonly Persistent Client Cache (RO-PCC) shares the same framework
with Readwrite Persistent Client Cache, expect that no HSM mechanism
is used in readonly mode of PCC. Instead, RO-PCC adds a new flag
field in the file object's layout named LCM_FL_PCC_RDONLY to
indicate that the file is in PCC read-only state. It is protected
under the layout lock.

After introducing the readonly feature for the layout, the IO path
has some changes. For read, if the file has been valid RO-PCC
cached, the file data can be read from PCC directly; Otherwise, it
will read data using normal I/O path from OSTs. For data modifying
operations (write or truncate), it must clear the readonly flag of
the layout on MDT (which will invaliate the RO-PCC cached state on
clients via layout lock blocking callback), and then it can perform
I/O.

For RO-PCC, as the PCC cached file is actual a replication of
Lustre file, when data read on PCC failed, it can tolerate this
error by falling back to normal read path: read data from OSTs.

Refer to paper (LPCC: hierarchical persistent client caching for
Lustre) for more design details.

Test-Parameters: clientcount=3 testlist=sanity-pcc,sanity-pcc,sanity-pcc
Signed-off-by: Qian Yingjin <qian@ddn.com>
Change-Id: I6badd72e00a106a0f68950621ce6f82471731a95
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/38305
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>

LU-10003 lnet: migrate lnet setup and tear down to Netlink

Migrate the LNet setup and tear down functionality from ioctls to
Netlink. This change now means lnet_ioctl() is no longer needed but
we will keep it for now to support older tools. The work here will
be used in a follow on patch to tell lnet to setup large NIDs by
default for testing.

Test-Parameters: trivial testlist=sanity-lnet
Change-Id: Id69810e114818d423102d6e85ff93529f04c337f
Signed-off-by: James Simmons <jsimmons@infradead.org>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54359
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Chris Horn <chris.horn@hpe.com>
Reviewed-by: Serguei Smirnov <ssmirnov@whamcloud.com>
Reviewed-by: Frank Sehr <fsehr@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-10391 lnet: use correct type in nid_addr_is_set

For nid_addr_is_set() we use NID_ADDR_BYTES macro to scan the
nid_addrs in struct lnet_nid. Each nid_addr is actually u32
so we are going beyond the 4 nid_addr that exist to see if
the nid_addr is set. Fix this by casting nid_addr to u8 so we
can scan by each byte properly.

Fixes: 14cdcd61985 ("LU-13642 lnet: Allow IP specification")
Test-Parameters: trivial testlist=sanity-lnet
Signed-off-by: James Simmons <jsimmons@infradead.org>
Change-Id: I220bc9d2adad09225ce44f7c1b96fba5a8f6dd26
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54338
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Serguei Smirnov <ssmirnov@whamcloud.com>
Reviewed-by: Frank Sehr <fsehr@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-12452 lnet: inherit default lnd tunings from modparams

When a network is added dynamically (via Netlink), LNet assumes that
all the "unset" or default LND parameters are 0. But for some
use cases, 0 could be a valid value.

This patch modifies the callback lnet_lnd.lnd_nl_set() to set default
values: a NULL attr argument means "set the default value".

Test-Parameters: trivial testlist=sanity-lnet
Signed-off-by: Etienne AUJAMES <eaujames@ddn.com>
Change-Id: Ifb91ae63d96131ed87d9fae7d91b8b18df4c9ce9
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54078
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Serguei Smirnov <ssmirnov@whamcloud.com>
Reviewed-by: Frank Sehr <fsehr@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-13814 clio: Improve cl_io_submit_sync comments

Add notes on what cl_io_submit_sync is for.

Test-Parameters: trivial
Signed-off-by: Patrick Farrell <pfarrell@whamcloud.com>
Change-Id: I5e32f1a7e6893b63d82f14848a865f90d30fb079
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52073
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Sebastien Buisson <sbuisson@ddn.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>

LU-13814 osc: Remove most uses of oap_obj

Removing most uses of oap_obj makes it easier to do the
upcoming transient page cl_page removal.

Signed-off-by: Patrick Farrell <pfarrell@whamcloud.com>
Change-Id: Ic8acaed2ce3c6831f9a0d2bd13d859b9c564efdd
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52072
Reviewed-by: Sebastien Buisson <sbuisson@ddn.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>

LU-17638 util: remove newer lnetctl export handling

On the current maloo VMs lnetctl export ends up segfaulting. For
now go back to the original code until we figure out what is
different on this setup and yet it works elsewhere. The reason
for a partial reveret is other important works are ready to land
that would be delayed by a full revert.

Fixes: d3ef8f6993 ("LU-9680 lnet: add NLM_F_DUMP_FILTERED support")
Test-Parameters: trivial testlist=sanity-lnet
Signed-off-by: James Simmons <jsimmons@infradead.org>
Change-Id: Ibd3437ee619cde9667d049455d641a602ea50174
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54436
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Frank Sehr <fsehr@whamcloud.com>
Reviewed-by: Chris Horn <chris.horn@hpe.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>

LU-17600 lnet: delete lbstats and lnetunload

It's not likely that anyone still uses these scripts.

Test-Parameters: trivial
Signed-off-by: Timothy Day <timday@amazon.com>
Change-Id: I418bdf2a1428905d598fdffdf27dff80831350d0
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54250
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-16752 test: improve sanity 413a/b reliability

Set qos_maxage to 1 early in test_qos_mkdir() to ensure statfs are
updated in round-robin mkdir test, so that the subsequent QoS mkdir
behave as expected.

Test-Parameters: trivial
Test-Parameters: mdscount=2 mdtcount=4 testlist=sanity
Test-Parameters: mdscount=2 mdtcount=4 testlist=sanity
Test-Parameters: mdscount=2 mdtcount=4 testlist=sanity
Test-Parameters: mdscount=2 mdtcount=4 testlist=sanity
Test-Parameters: mdscount=2 mdtcount=4 testlist=sanity
Test-Parameters: mdscount=2 mdtcount=4 testlist=sanity
Test-Parameters: mdscount=2 mdtcount=4 testlist=sanity
Test-Parameters: mdscount=2 mdtcount=4 testlist=sanity
Fixes: 233344d451 ("LU-13417 test: generate uneven MDTs early for sanity 413")
Fixes: c1d0a355a6 ("LU-12624 lod: alloc dir stripes by QoS")
Signed-off-by: Lai Siyao <lai.siyao@whamcloud.com>
Change-Id: I08f94b5b4e355ffff0704bd0f661bb99a82a9234
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54168
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Hongchao Zhang <hongchao@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-16695 llite: remove O_APPEND check for sync

A check for O_APPEND in determining 'sync' or not was
accidentally introduced. This forces O_APPEND writes to
all be synchronous, which is of course wrong.

Fixes: dad7079dfd ("LU-16695 llite: switch to ki_flags from f_flags")
Signed-off-by: Patrick Farrell <pfarrell@whamcloud.com>
Change-Id: Iafae63ebda527834bd45d6fcbfb0cebb0340f4e4
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54128
Reviewed-by: Alexander Boyko <alexander.boyko@hpe.com>
Reviewed-by: Alexey Lyashkov <alexey.lyashkov@hpe.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Reviewed-by: Andrew Perepechko <andrew.perepechko@hpe.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>

LU-17566 mdt: remove duplicate call to mdt_init_ucred_reint()

Remove duplicate call to mdt_init_ucred_reint() from
mdt_reint_setxattr().

mdt_init_ucred_reint() is called in mdt_reint_internal() which is
covering all actual reinters. However, SETXATTR was converted to
reinters framework in fd908da and this call was not removed.
So mdt_init_ucred_reint() is called first in mdt_reint_internal() then
again in the specific mdt_reint_setxattr() handler, without anything
special being done on the ucred between them.

Also merge __mdt_init_ucred() and mdt_init_cred() which was
called only once, and with the same prototype.

Signed-off-by: Aurelien Degremont <adegremont@nvidia.com>
Change-Id: I90fed1d2709edf7337a27dd9c3cb0f75f7625135
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54111
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Sebastien Buisson <sbuisson@ddn.com>
Reviewed-by: Bruno Faccini <bfaccini@nvidia.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17490 tests: verify fanotify works for lustre

The fanotify API provides notification and interception of filesystem
events. Here we prepare a small util to monitor open/read/write/close
events of file in a filesystem. Verify it works for lustre
filesystem.

Signed-off-by: Lei Feng <flei@whamcloud.com>
Test-Parameters: trivial
Change-Id: Id57a59bca16133db645e6804024cba9f11d60f1d
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53869
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Alex Deiter
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17434 lmv: add exclude list for remote dir

Apache Spark creating a _temporary subdirectory for staging files, and
it should be created on the same MDT as its parent directory. Add a
tunable lmv.*.qos_exclude_prefixes, if directory prefix is in this
list, lmv_create() should put it on its parent MDT.

This prefix list follows the same rule of shell environment PATH: use
':' as separator for prefixes. And for convenience '+/-' can be used
to add/remove prefixes.

Add sanity 413k.

Signed-off-by: Lai Siyao <lai.siyao@whamcloud.com>
Change-Id: I4c8a118f0630c19054934a87bee3599bdb1fe7bb
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53780
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Sebastien Buisson <sbuisson@ddn.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17175 gss: start lsvcgssd from l_getauth

If l_getauth detects it cannot connect to the socket supposed
to be opened by lsvcgssd, it tries to launch the daemon, with
predefined default values.

Test-Parameters: trivial
Test-Parameters: kerberos=true testlist=sanity-krb5
Test-Parameters: testgroup=review-dne-selinux-ssk-part-2
Signed-off-by: Sebastien Buisson <sbuisson@ddn.com>
Change-Id: I3961ce0f548fb6ea23458edcb01a03fb8b3a617f
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53142
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Aurelien Degremont <adegremont@nvidia.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17179 tests: check the system is clean

Main part of tests cannot work correctly if the system
is not clean. So check this in the beginning of sanity-quota.

Test-Parameters: trivial
Signed-off-by: Sergey Cheremencev <scherementsev@ddn.com>
Change-Id: Ibfbe4663dee8476486e96eb99ccbcea13216861b
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52630
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Artem Blagodarenko <ablagodarenko@ddn.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-9859 lnet: move CPT handling to LNet

The CPT work is used for LNet and ptlrpc which is the Lustre LNet
interface. Move this work there and merge the lib-mem.c code as
well since they both work closely together. Move cpt debugfs
handling from libcfs to lnet. Now all remaining debugfs in libcfs
is for debugging.

Test-Parameters: trivial
Change-Id: I016a90520bd7c6428b45bafff8618bc864e9112b
Signed-off-by: James Simmons <jsimmons@infradead.org>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52923
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-14361 statahead: add connect flag check for batch RPC

The tests (sanity/test_123 test case series) are all failing for
servers that do not have batch RPC support.
In this patch we add the connect feature flag check in
mdc.*.import for batch RPC support and skip the batch stat-ahead
tests without this support.

Test-Parameters: trivial
Signed-off-by: Qian Yingjin <qian@ddn.com>
Change-Id: I54c95722df803131727e5882156570c9da5293ee
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54275
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Lai Siyao <lai.siyao@whamcloud.com>

LU-8066 obdclass: fix module load locking.

Safe module loading requires that we try_module_get() in a context
where the module cannot be unloaded, typically protected by
a spinlock that module-unload has to take.
This doesn't currently happen in class_get_type().

As free_module() calls synchronize_rcu() between calling the
exit function and freeing the module, we can use rcu_read_lock()
to check if the exit function has been called, and try_module_get()
if it hasn't.

We must also check the return status of try_module_get().

Linux-commit: 71707c276e0acff160e7f2bd38d5b61eb1f61ab2

Change-Id: Ia551a951db8fd97db51140123d340b1649a159cd
Signed-off-by: Mr. NeilBrown <neilb@suse.de>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/36043
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-6142 mdd: Fix style issues for mdd_dir.c

This patch fixes issues reported by checkpatch
for file lustre/mdd/mdd_dir.c

Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I255a2cfe2dd7c09ce421cb7c5387cef0bba73611
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54217
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-6142 lfsck: Fix style issues for lfsck_striped_dir.c

This patch fixes issues reported by checkpatch
for file lustre/lfsck/lfsck_striped_dir.c

Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I6469e5973a5ee33c408ced48bb9ab162307fdf07
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54214
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-6142 lfsck: Fix style issues for lfsck_namespace.c

This patch fixes issues reported by checkpatch
for file lustre/lfsck/lfsck_namespace.c

Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: Ie415d9ace24adaa845a4298499128b2766dc66aa
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54213
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-6142 lfsck: Fix style issues for lfsck_engine.c

This patch fixes issues reported by checkpatch
for file lustre/lfsck/lfsck_engine.c

Test-Parameters: trivial
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: Icf9941210e7e403088ac9216de38f8c49f52e72e
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54212
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-6142 lfsck: Fix style issues under lustre/lfsck

This patch fixes issues reported by checkpatch
for all files under folder lustre/lfsck

Test-Parameters: trivial testlist=sanity-lfsck
Signed-off-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Change-Id: I7fed1e66f82c691d94198390ad89e91db9bfcdea
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54165
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>

LU-17578 lnet: fix &the_lnet.ln_mt_peerNIRecovq race

To avoid race &the_lnet.ln_mt_peerNIRecovq must always be
accessed with lnet_net_lock(0) protection.

Test-Parameters: trivial
Fixes: da23037 ("LU-16563 lnet: use discovered ni status to set initial health")
Change-Id: Ic5e0194020200afdecba4cbf5afed274b14da388
Signed-off-by: Bruno Faccini <bfaccini@nvidia.com>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54163
Reviewed-by: Chris Horn <chris.horn@hpe.com>
Reviewed-by: Frank Sehr <fsehr@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>

LU-9680 lnet: add NLM_F_DUMP_FILTERED support

In addition to different API levels for the netlink packets we
can also filter the data sent back when user land sends the
NLM_F_DUMP_FILTERED. Support this across the various netlink
dumpit functions.

This work is needed for the proper support for lnetctl export
command. Update the export to work with the Netlink API. This
results in proper IPv6 support for the export command.

Test-Parameters: trivial testlist=sanity-lnet
Change-Id: I0e8993b1f9a08199f282965601781aa6fd0e4844
Signed-off-by: James Simmons <jsimmons@infradead.org>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53004
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Frank Sehr <fsehr@whamcloud.com>
Reviewed-by: Chris Horn <chris.horn@hpe.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-13814 osc: Remove oap_request

oap_request isn't actually per-page, it's per requet, so
move it up and associate it with the request async args.

The goal is to shift away from page lists at the RPC level
for DIO.

The first step of this is to move everything that can be
moved from osc_async_page to the osc_brw_async_args level.

Signed-off-by: Patrick Farrell <pfarrell@whamcloud.com>
Change-Id: I188039b0abd4b639755dbebfab02597da13d5ddf
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/52071
Reviewed-by: Sebastien Buisson <sbuisson@ddn.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>

LU-10391 obd: Update lmd_parse to handle IPv6 NIDs

lmd_find_delimiter()/lmd_parse_nidlist() are updated to handle IPv6
NIDs.

class_parse_value() is updated to handle IPv6 NIDs that begin with
'::'. Also, when parsing a Lustre network name, the buffer needn't
contain an '@', nor do we want to search for '@' when locating the
next delimiter.

Fixes: 101f6e8 ("LU-10391 obdclass: handle large NIDs for mount strings")
Signed-off-by: Chris Horn <chris.horn@hpe.com>
Change-Id: Ib9e5a0d161babfea368989dd9521d923ec592185
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53882
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>
Reviewed-by: Neil Brown <neilb@suse.de>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-16011 lnet: use preallocate bulk for server

Server side want to have a preallocate bulk to avoid large lock
contention on the page cache.
Without it LST limited with 35Gb/s speed with 3 rail host (HDR each)
due large CPU usage.
Preallocate bulks increase a memory consumption for small bulk,
but performance improved dramatically up to 74Gb/s with very low
cpu usage.

Test-Parameters: testgroup=review-ldiskfs-arm testlist=sanity-lnet,lnet-selftest
Signed-off-by: Alexey Lyashkov <alexey.lyashkov@hpe.com>
Change-Id: Icf396ba2ecfbded807b5722bb2c4cbe4d0084300
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/50276
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andrew Perepechko <andrew.perepechko@hpe.com>
Reviewed-by: Serguei Smirnov <ssmirnov@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17611 utils: fix wrong static declarations

Revert wrong changes made to zfs mount utils

Fixes: c7e9bdf8d4 ("LU-8191 utils: remove unused, fix non-static functions")
Signed-off-by: Mikhail Pershin <mpershin@whamcloud.com>
Change-Id: I162d349ebadbf93a89abf49bd41465979d561423
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54293
Tested-by: jenkins <devops@whamcloud.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Sebastien Buisson <sbuisson@ddn.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17576 nodemap: remove nodemap_rbtree.c

Remove nodemap_rbtree.c. This was a port of an
in-progress rbtree patch to the kernel. Every
kernel that Lustre supports should have the needed
macro. The rest of the stuff in the file is unused.

Signed-off-by: Timothy Day <timday@amazon.com>
Change-Id: I25d6eea90a1e9b983fb0be690384e50c6808cb7b
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54136
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Sebastien Buisson <sbuisson@ddn.com>
Reviewed-by: James Simmons <jsimmons@infradead.org>

LU-14391 utils: handle very large YAML data sets.

Some functionality for Lustre and even LNet can return huge
amounts of Netlink data that can overwhelm the internal libyaml
buffers. To resolve this we can create a resizable internal
buffer to collect all the Netlink data that is formated into
YAML. After the message has been completed we can feed this
data in chunk sizes the smaller internal libyaml library can
handle. The libyaml library internal buffer is a rolling buffer
so it will updated when we exceed its internal size. This will
allows collecting every single type of Lustre stat in one go
and for sites that have very large LNet router setups.

Test-Parameters: trivial
Change-Id: I20fdbb19b0f3de3ab52e8ad568c6926f61f627b9
Signed-off-by: James Simmons <jsimmons@infradead.org>
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54132
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Chris Horn <chris.horn@hpe.com>
Reviewed-by: Timothy Day <timday@amazon.com>
Reviewed-by: Frank Sehr <fsehr@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17560 build: with kfi check for kfabric or cray-kfabric

The default location of kfabric is either
/usr/src/kfabric
or
/usr/src/cray-kfabric

Check for either during rpmbuild --with kfi

Test-Parameters: trivial
HPE-bug-id: LUS-12160
Signed-off-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Change-Id: Ibcd21335d554b66ec925619c60e61f87d79be63d
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54097
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Petros Koutoupis <petros.koutoupis@hpe.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>

LU-17552 kernel: el9 rhashtable for revoke records in jbd2

The resizable hashtable journal replay is applicable to the
el9.x series of kernels as well.

Lustre-commit: c3bb2b778d6b40a5cecb01993b55fcc107305b4a
Lustre-change: https://review.whamcloud.com/45122
Lustre-author: Alex Zhuravlev <bzzz@whamcloud.com>

Signed-off-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Change-Id: I5a8fae6c14d50337c0c454e301112f100f611ab0
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54085
Reviewed-by: Andrew Perepechko <andrew.perepechko@hpe.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>

LU-17476 lnet: use bits only to match ME in all cases

If NIDs belong to the same peer and matchbits are matching,
declare a match even if matchbits are matched as not available
or ignored

Test-Parameters: testlist=sanity env=ONLY=350,ONLY_REPEAT=10
Signed-off-by: Serguei Smirnov <ssmirnov@whamcloud.com>
Change-Id: I394c492381a2d069b34516c473220192df05fbd2
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54082
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Frank Sehr <fsehr@whamcloud.com>
Reviewed-by: Cyril Bordage <cbordage@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17545 lnet: use unsafe_memcpy() when flexible array

To avoid <memcpy: detected field-spanning write (size 64)
of single field "&lp->lp_data->pb_info" at
.../lnet/lnet/peer.c:2456 (size 16)> false positive
msgs/error.

Signed-off-by: Bruno Faccini <bfaccini@nvidia.com>
Change-Id: I4e2fc58e31f60b434a9050393cd65b89c54f0798
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/54069
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Shaun Tancheff <shaun.tancheff@hpe.com>
Reviewed-by: Arshad Hussain <arshad.hussain@aeoncomputing.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17276 tests: Enqueue same range flocks

The ldlm_interval buffer will be released and referenced
between flocks or extent locks. Add a test case to trigger
such scene.

Signed-off-by: Yang Sheng <ys@whamcloud.com>
Change-Id: Ifa23ba7c16ad8601b1e3e7891a136589ea44e54a
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53881
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

LU-17476 lnet: prefer to use bits only to match ME

In some cases, it has been observed that a reply will arrive
at the portal with the correct match bits, but is dropped by
lnet_parse_put(). This appears to happen with LNet Multi-Rail
peers, each having two separate NIDs.

If a reply arrives with matchbits available and matching, but
the NIDs don't match, confirm the match if the NIDs are found
to belong to the same peer. This will only happen in cases
where the reply would be dropped entirely, causing hundreds of
seconds of delay until the RPC is resent, so the extra overhead
of checking for a peer match before dropping the request is
only in the error path and minimal compared to the alternative.

Add CFS_FAIL_CHECK() for exercising the match NIDs code.

That is in a hot codepath, but CFS_FAIL_CHECK() is marked unlikely()
and this check is in the error case and _should_ only be hit when
the message would have been dropped anyway, so it seems unlikely to
impact performance in any meaningful way.

Test-Parameters: testlist=sanity env=ONLY=350,ONLY_REPEAT=10
Signed-off-by: Serguei Smirnov <ssmirnov@whamcloud.com>
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Change-Id: I10e1a2142539ddf5dabc26ce962cec1f2cfcf3db
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/53843
Reviewed-by: Cyril Bordage <cbordage@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-by: Frank Sehr <fsehr@whamcloud.com>
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>