Use spin_lock_bh for all spinlocks involved in message processing,
in preparation for softirq message processing. DLM lock requests
from user space involve dlm processing in user context, in addition
to the standard kernel context, necessitating bh variants.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
Get rid of the unnecessary refcounting on callback structs.
Copy interesting callback info into the lkb struct rather
than maintaining pointers to callback structs from the lkb.
This goes back to the way things were done prior to
commit 61bed0baa4 ("fs: dlm: use a non-static queue for callbacks").
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch fixes the following issue:
node 1 is dir
node 2 is master
node 3 is other
1->2: unlock
2: put final lkb, rsb moved to toss
2->1: unlock_reply
1: queue lkb callback with EUNLOCK
2->1: remove
1: receive_remove ignored (rsb on keep because of queued lkb callback)
1: complete lkb callback, put_lkb, move rsb to toss
3->1: lookup
1->3: lookup_reply master=2
3->2: request
2->3: request_reply EBADR
In summary:
An unexpected lkb reference causes the rsb to remain on the wrong list.
The rsb being on the wrong list causes receive_remove to be ignored.
An ignored receive_remove causes inconsistent dir and master state.
This sequence requires an unusually long delay in delivering the unlock
callback, because the remove message from 2->1 usually happens after
some seconds. So, it's not known exactly how frequently this sequence
occurs in pratice. It's possible that the same end result could also
have another unknown cause.
The solution for this issue is to further separate callback state
from the lkb, so that an lkb reference (and from that, an rsb ref)
are not held while a callback remains queued. Then, within the
unlock_reply, the lkb will be freed and the rsb moved to the toss
list. So, the receive_remove will not be ignored.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch combines the failure and default cases for enqueue and
dequeue a callback to the lkb callback queue that should end in both
cases as it should never happen.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
Save lkb callback info when queueing the callback so that the
lkb struct is not needed in the callback workqueue processing.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
Stop using lkb structs in the callback tracepoints so that lkb
references are not needed. This prepares for separating lkb
structs from callbacks.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch fixes the copy lvb decision for user space lock requests.
Checking dlm_lvb_operations is done earlier, where granted/requested
lock modes are available to use in the matrix.
The decision had been moved to the wrong location, where granted mode
and requested mode where the same, which causes the dlm_lvb_operations
matix to produce the wrong copy decision. For PW or EX requests, the
caller could get invalid lvb data.
Fixes: 61bed0baa4 ("fs: dlm: use a non-static queue for callbacks")
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch moves the dlm_purge_lkb_callbacks() function from ast to user
dlm module as it is only a function being used by dlm user
implementation. I got be hinted to hold specific locks regarding the
callback handling for dlm_purge_lkb_callbacks() but it was false
positive. It is confusing because ast dlm implementation uses a
different locking behaviour as user locks uses as DLM handles kernel and
user dlm locks differently. To avoid the confusing we move this function
to dlm user implementation.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch clears the DLM_IFL_CB_PENDING_BIT flag which will be set when
there is callback work queued when there was no callback to dequeue. It
is a buggy case and should never happen, that's why there is a
WARN_ON(). However if the case happens we are prepared to somehow
recover from it.
Cc: stable@vger.kernel.org
Fixes: 61bed0baa4 ("fs: dlm: use a non-static queue for callbacks")
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
Currently manipulating lkb_dflags assumes to held the rsb lock assigned
to the lkb. This is held by dlm message processing after certain
time to lookup the right rsb from the received lkb message id. For user
space locks flags, which is currently the only use case for lkb_dflags,
flags are also being set during dlm character device handling without
holding the rsb lock. To minimize the risk that bit operations are
getting corrupted we switch to atomic bit operations. This patch will
also introduce helpers to snapshot atomic bit values in an non atomic
way. There might be still issues with the flag handling e.g. running in
case of manipulating bit ops and snapshot them at the same time, but this
patch minimize them and will start to use atomic bit operations.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch stores lkb distributed flags value in an separate value
instead of sharing internal and distributed flags in lkb->lkb_flags value.
This has the advantage to not mask/write back flag values in
receive_flags() functionality. The dlm debug_fs does not provide the
distributed flags anymore, those can be added in future.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch introduce a new internal flag per lkb value to handle
internal flags which are handled not on wire. The current lkb internal
flags stored as lkb->lkb_flags are split in upper and lower bits, the
lower bits are used to share internal flags over wire for other cluster
wide lkb copies on other nodes.
In commit 61bed0baa4 ("fs: dlm: use a non-static queue for callbacks")
we introduced a new internal flag for pending callbacks for the dlm
callback queue. This flag is protected by the lkb->lkb_cb_lock lock.
This patch overlooked that on dlm receive path and the mentioned upper
and lower bits, that dlm will read the flags, mask it and write it
back. As example receive_flags() in fs/dlm/lock.c. This flag
manipulation is not done atomically and is not protected by
lkb->lkb_cb_lock. This has unknown side effects of the current callback
handling.
In future we should move to set/clear/test bit functionality and avoid
read, mask and writing back flag values. In later patches we will move
the upper parts to the new introduced internal lkb flags which are not
shared between other cluster nodes to the new non shared internal flag
field to avoid similar issues.
Cc: stable@vger.kernel.org
Fixes: 61bed0baa4 ("fs: dlm: use a non-static queue for callbacks")
Reported-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch renames DLM_IFL_NEED_SCHED to DLM_IFL_CB_PENDING because
CB_PENDING is a proper name to describe this flag. This flag is set when
callback enqueue will return DLM_ENQUEUE_CALLBACK_NEED_SCHED because the
callback worker need to be queued. The flag tells that callbacks are
currently pending to be called and will be unset if the callback work
for the specific lkb is done. The term need schedule is part of this
time but a proper name is to say that there are some callbacks pending
to being called.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch changes the ast hotpath functionality in very unlikely cases
that we do WARN_ON_ONCE() instead of WARN_ON() to not spamming the
console output if we run into states that it would occur over and over
again.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch will drop the lkb reference in an very unlikely case which
should in practice not happened. However if it happens we cleanup the
reference just in case.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch will introducde a queue implementation for callbacks by using
the Linux lists. The current callback queue handling is implemented by a
static limit of 6 entries, see DLM_CALLBACKS_SIZE. The sequence number
inside the callback structure was used to see if the entries inside the
static entry is valid or not. We don't need any sequence numbers anymore
with a dynamic datastructure with grows and shrinks during runtime to
offer such functionality.
We assume that every callback will be delivered to the DLM user if once
queued. Therefore the callback flag DLM_CB_SKIP was dropped and the
check for skipping bast was moved before worker handling and not skip
while the callback worker executes. This will reduce unnecessary queues
of the callback worker.
All last callback saves are pointers now and don't need to copied over.
There is a reference counter for callback structures which will care
about to free the callback structures at the right time if they are not
referenced anymore.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch moves the debugging information of the last cast and bast
time when calling the last and bast function call.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
There is no need to use a mutex in those hot path sections. We change it
to spin lock to serve callbacks more faster by not allowing schedule.
The locked sections will not be locked for a long time.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch converts the ls_cb_mutex mutex to a spinlock, there is no
sleepable context when this lock is held.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
We should allow dlm_add_cb() to call queue_work() only after the
recovery queued pending for delayed lkbs. This patch will move the
switch LSFL_CB_DELAY after the delayed lkb work was processed.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch only set/clear the LSFL_CB_DELAY bit when it's actually a
kernel lockspace signaled by if ls->ls_callback_wq is set or not set in
this case. User lockspaces will never evaluate this flag.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch fixes a race by using ls_cb_mutex around the bit
operations and conditional code blocks for LSFL_CB_DELAY.
The function dlm_callback_stop() expects to stop all callbacks and
flush all currently queued onces. The set_bit() is not enough because
there can still be queue_work() after the workqueue was flushed.
To avoid queue_work() after set_bit(), surround both by ls_cb_mutex.
Cc: stable@vger.kernel.org
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch removes a dereference of lksb of lkb when calling ast
tracepoint. First it reduces additional overhead, even if traces
are not active. Second we can deference it in TP_fast_assign from
the existing lkb parameter.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch moves the trace calls for ast and bast to before the
ast and bast callback functions are called rather than after.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch will use list_empty(&ls->ls_cb_delay) to check for last list
iteration. In case of a multiply count of MAX_CB_QUEUE and the list is
empty we do a extra goto more which we can avoid by checking on
list_empty().
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch adds initial support for dlm tracepoints. It will introduce
tracepoints to dlm main functionality dlm_lock()/dlm_unlock() and their
complete ast() callback or blocking bast() callback.
The lock/unlock functionality has a start and end tracepoint, this is
because there exists a race in case if would have a tracepoint at the
end position only the complete/blocking callbacks could occur before. To
work with eBPF tracing and using their lookup hash functionality there
could be problems that an entry was not inserted yet. However use the
start functionality for hash insert and check again in end functionality
if there was an dlm internal error so there is no ast callback. In further
it might also that locks with local masters will occur those callbacks
immediately so we must have such functionality.
I did not make everything accessible yet, although it seems eBPF can be
used to access a lot of internal datastructures if it's aware of the
struct definitions of the running kernel instance. We still can change
it, if you do eBPF experiments e.g. time measurements between lock and
callback functionality you can simple use the local lkb_id field as hash
value in combination with the lockspace id if you have multiple
lockspaces. Otherwise you can simple use trace-cmd for some functionality,
e.g. `trace-cmd record -e dlm` and `trace-cmd report` afterwards.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch makes dlm_callback_resume info printout less noisy by
accumulate all callback queues into one printout not in 25 times steps.
It seems this printout became lately quite noisy in relationship with
gfs2.
Before:
[241767.849302] dlm: bin: dlm_callback_resume 25
[241767.854846] dlm: bin: dlm_callback_resume 25
[241767.860373] dlm: bin: dlm_callback_resume 25
...
[241767.865920] dlm: bin: dlm_callback_resume 25
[241767.871352] dlm: bin: dlm_callback_resume 25
[241767.876733] dlm: bin: dlm_callback_resume 25
After the patch:
[ 385.485728] dlm: gfs2: dlm_callback_resume 175
if zero it will not be printed out.
Reported-by: Barry Marson <bmarson@redhat.com>
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
Based on 1 normalized pattern(s):
this copyrighted material is made available to anyone wishing to use
modify copy or redistribute it subject to the terms and conditions
of the gnu general public license v 2
extracted by the scancode license scanner the SPDX license identifier
GPL-2.0-only
has been chosen to replace the boilerplate/reference in 45 file(s).
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Richard Fontana <rfontana@redhat.com>
Reviewed-by: Allison Randal <allison@lohutok.net>
Reviewed-by: Steve Winslow <swinslow@gmail.com>
Reviewed-by: Alexios Zavras <alexios.zavras@intel.com>
Cc: linux-spdx@vger.kernel.org
Link: https://lkml.kernel.org/r/20190528170027.342746075@linutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Before this patch, recovery would cause all callbacks to be delayed,
put on a queue, and afterward they were all queued to the callback
work queue. This patch does the same thing, but occasionally takes
a break after 25 of them so it won't swamp the CPU at the expense
of other RT processes like corosync.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
dlm_cb_seq is 64 bits. If dlm_cb_seq overflows and returns to 0,
dlm_rem_lkb_callback() will not work properly.
Signed-off-by: Tadashi Miyauchi <miyauchi@toshiba-tops.co.jp>
Signed-off-by: Tsutomu Owa <tsutomu.owa@toshiba.co.jp>
Signed-off-by: David Teigland <teigland@redhat.com>
This patch removes the WQ_UNBOUND flag (which implies WQ_HIGHPRI)
from the DLM's ast work queue, in favor of just WQ_HIGHPRI.
This has been shown to cause a 19 percent performance increase for
simultaneous inode creates on GFS2 with fs_mark.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
The log messages relating to the progress of recovery
are minimal and very often useful. Change these to
the KERN_INFO level so they are always available.
Signed-off-by: David Teigland <teigland@redhat.com>
Include appropriate header file fs/dlm/ast.h in fs/dlm/ast.c because it
contains function prototypes of some functions defined in fs/dlm/ast.c.
This also eliminates the following warning in fs/dlm/ast:
fs/dlm/ast.c:52:5: warning: no previous prototype for ‘dlm_add_lkb_callback’ [-Wmissing-prototypes]
fs/dlm/ast.c:113:5: warning: no previous prototype for ‘dlm_rem_lkb_callback’ [-Wmissing-prototypes]
fs/dlm/ast.c:174:6: warning: no previous prototype for ‘dlm_add_cb’ [-Wmissing-prototypes]
fs/dlm/ast.c:212:6: warning: no previous prototype for ‘dlm_callback_work’ [-Wmissing-prototypes]
fs/dlm/ast.c:267:5: warning: no previous prototype for ‘dlm_callback_start’ [-Wmissing-prototypes]
fs/dlm/ast.c:278:6: warning: no previous prototype for ‘dlm_callback_stop’ [-Wmissing-prototypes]
fs/dlm/ast.c:284:6: warning: no previous prototype for ‘dlm_callback_suspend’ [-Wmissing-prototypes]
fs/dlm/ast.c:292:6: warning: no previous prototype for ‘dlm_callback_resume’ [-Wmissing-prototypes]
Signed-off-by: Rashika Kheria <rashika.kheria@gmail.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Signed-off-by: David Teigland <teigland@redhat.com>
dbf2576e37 ("workqueue: make all workqueues non-reentrant") made
WQ_NON_REENTRANT no-op and the flag is going away. Remove its usages.
This patch doesn't introduce any behavior changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: David Teigland <teigland@redhat.com>
The "nodir" mode (statically assign master nodes instead
of using the resource directory) has always been highly
experimental, and never seriously used. This commit
fixes a number of problems, making nodir much more usable.
- Major change to recovery: recover all locks and restart
all in-progress operations after recovery. In some
cases it's not possible to know which in-progess locks
to recover, so recover all. (Most require recovery
in nodir mode anyway since rehashing changes most
master nodes.)
- Change the way nodir mode is enabled, from a command
line mount arg passed through gfs2, into a sysfs
file managed by dlm_controld, consistent with the
other config settings.
- Allow recovering MSTCPY locks on an rsb that has not
yet been turned into a master copy.
- Ignore RCOM_LOCK and RCOM_LOCK_REPLY recovery messages
from a previous, aborted recovery cycle. Base this
on the local recovery status not being in the state
where any nodes should be sending LOCK messages for the
current recovery cycle.
- Hold rsb lock around dlm_purge_mstcpy_locks() because it
may run concurrently with dlm_recover_master_copy().
- Maintain highbast on process-copy lkb's (in addition to
the master as is usual), because the lkb can switch
back and forth between being a master and being a
process copy as the master node changes in recovery.
- When recovering MSTCPY locks, flag rsb's that have
non-empty convert or waiting queues for granting
at the end of recovery. (Rename flag from LOCKS_PURGED
to RECOVER_GRANT and similar for the recovery function,
because it's not only resources with purged locks
that need grant a grant attempt.)
- Replace a couple of unnecessary assertion panics with
error messages.
Signed-off-by: David Teigland <teigland@redhat.com>
Allow multiple workqueue items (locks with callbacks) to be
processed concurrently. There should be no reason not to
take advantage of this workqueue feature.
Signed-off-by: David Teigland <teigland@redhat.com>
Instead of creating our own kthread (dlm_astd) to deliver
callbacks for all lockspaces, use a per-lockspace workqueue
to deliver the callbacks. This eliminates complications and
slowdowns from many lockspaces sharing the same thread.
Signed-off-by: David Teigland <teigland@redhat.com>
Change how callbacks are recorded for locks. Previously, information
about multiple callbacks was combined into a couple of variables that
indicated what the end result should be. In some situations, we
could not tell from this combined state what the exact sequence of
callbacks were, and would end up either delivering the callbacks in
the wrong order, or suppress redundant callbacks incorrectly. This
new approach records all the data for each callback, leaving no
uncertainty about what needs to be delivered.
Signed-off-by: David Teigland <teigland@redhat.com>
When both blocking and completion callbacks are queued for lock,
the dlm would always deliver the completion callback (cast) first.
In some cases the blocking callback (bast) is queued before the
cast, though, and should be delivered first. This patch keeps
track of the order in which they were queued and delivers them
in that order.
This patch also keeps track of the granted mode in the last cast
and eliminates the following bast if the bast mode is compatible
with the preceding cast mode. This happens when a remotely mastered
lock is demoted, e.g. EX->NL, in which case the local node queues
a cast immediately after sending the demote message. In this way
a cast can be queued for a mode, e.g. NL, that makes an in-transit
bast extraneous.
Signed-off-by: David Teigland <teigland@redhat.com>
fs/dlm/ast.c: In function 'dlm_astd':
fs/dlm/ast.c:64: warning: 'bastmode' may be used uninitialized in this function
Cleans code up.
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: David Teigland <teigland@redhat.com>
The lkb bastmode value is set in the context of processing the
lock, and read by the dlm_astd thread. Because it's accessed
in these two separate contexts, the writing/reading ought to
be done under a lock. This is simple to do by setting it and
reading it when the lkb is added to and removed from dlm_astd's
callback list which is properly locked.
Signed-off-by: David Teigland <teigland@redhat.com>
Just before delivering a blocking callback (bast), the dlm_astd
thread checks again that the granted mode of the lkb actually
blocks the mode requested by the bast. The idea behind this was
originally that the granted mode may have changed since the bast
was queued, making the callback now unnecessary. Reasons for
removing this extra check are:
- dlm_astd doesn't lock the rsb before reading the lkb grmode, so
it's not technically safe (this removes the long standing FIXME)
- after running some tests, it doesn't appear the check ever actually
eliminates a bast
- delivering an unnecessary blocking callback isn't a bad thing and
can happen anyway
Signed-off-by: David Teigland <teigland@redhat.com>
This is a one-liner to use cond_resched() rather than schedule()
in the ast delivery loop. It should not be necessary to schedule
every time, so this will save some cpu time while continuing to
allow scheduling when required.
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
Every file should include the headers containing the prototypes for
it's global functions.
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: David Teigland <teigland@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
The down-conversion optimization was resulting in the lkb flags being
cleared because the stub message reply had no flags value set. Copy the
current flags into the stub message so they'll be copied back into the lkb
as part of processing the fake reply. Also add an assertion to catch this
error more directly if it exists elsewhere.
Signed-off-by: David Teigland <teigland@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
This changes the way the dlm handles user locks. The core dlm is now
aware of user locks so they can be dealt with more efficiently. There is
no more dlm_device module which previously managed its own duplicate copy
of every user lock.
Signed-off-by: Patrick Caulfield <pcaulfie@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
This is the core of the distributed lock manager which is required
to use GFS2 as a cluster filesystem. It is also used by CLVM and
can be used as a standalone lock manager independantly of either
of these two projects.
It implements VAX-style locking modes.
Signed-off-by: David Teigland <teigland@redhat.com>
Signed-off-by: Steve Whitehouse <swhiteho@redhat.com>
Alexander Aring