Writing thread already locked page #1, and then wait for the
Writeback bit of page #2;
Ptlrpc thread is composing a write RPC, so it sets Writeback on
page #2 and tries to lock page #1 to make it ready.
Deadlocked.
Signed-off-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-on: http://review.whamcloud.com/9036
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4540
Reviewed-by: wangdi <di.wang@intel.com>
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The original code was wrong which clipped page incorrectly for
partial pages started with zero.
Signed-off-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-on: http://review.whamcloud.com/8531
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4201
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: wangdi <di.wang@intel.com>
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
In this patch, the cl_lock cache is eliminated. cl_lock is turned
into a cacheless data container for the requirements of locks to
complete the IO. cl_lock is created before I/O starts and destroyed
when the I/O is complete.
cl_lock depends on LDLM lock to fulfill lock semantics. LDLM lock
is attached to cl_lock at OSC layer. LDLM lock is still cacheable.
Two major methods are supported for cl_lock: clo_enqueue and
clo_cancel. A cl_lock is enqueued by cl_lock_request(), which will
call clo_enqueue() methods for each layer to enqueue the lock.
At the LOV layer, if a cl_lock consists of multiple sub cl_locks,
each sub locks will be enqueued correspondingly. At OSC layer, the
lock enqueue request will tend to reuse cached LDLM lock; otherwise
a new LDLM lock will have to be requested from OST side.
cl_lock_cancel() must be called to release a cl_lock after use.
clo_cancel() method will be called for each layer to release the
resource held by this lock. At OSC layer, the reference count of LDLM
lock, which is held at clo_enqueue time, is released.
LDLM lock can only be canceled if there is no cl_lock using it.
Signed-off-by: Bobi Jam <bobijam.xu@intel.com>
Signed-off-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-on: http://review.whamcloud.com/10858
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3259
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To make cl_sync_io interfaces not just wait for pages, but to be
a generic synchronization mechanism.
Also remove cl_io_cancel that became not used.
Signed-off-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-on: http://review.whamcloud.com/8656
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4198
Reviewed-by: Bobi Jam <bobijam@gmail.com>
Reviewed-by: Lai Siyao <lai.siyao@intel.com>
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This was a compat code from the time it had ia_attr_flags.
Instead convert all the cryptic callers that did
((struct ll_iattr *)&op_data->op_attr)->ia_attr_flags into
direct access to op_data->op_attr_flags
This also makes lustre/include/linux/obd.h not needed anymore,
so remove it.
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Remove the definition of struct client_obd_lock and the functions
client_obd_list_{init,lock,unlock,done}(). Use spinlock_t for the
cl_{loi,lru}_list_lock members of struct client_obd and call
spin_{lock,unlock}() directly.
Signed-off-by: John L. Hammond <john.hammond@intel.com>
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
In struct lmv_obd rename the init_mutex member to
lmv_init_mutex. Remove the compat macros lmv_init_{lock,unlock}() and
use mutex_{lock,unlock}(&lmv->lmv_init_mutex) instead.
Signed-off-by: John L. Hammond <john.hammond@intel.com>
Reviewed-on: http://review.whamcloud.com/12115
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-2675
Reviewed-by: Bob Glossman <bob.glossman@intel.com>
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Reviewed-by: Dmitry Eremin <dmitry.eremin@intel.com>
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
In struct ll_inode_info remove the struct ost_lvb lli_lvb member and
replace it with obd_time lli_{a,m,c}time. Rename ll_merge_lvb() to
ll_merge_attr(). Remove cl_merge_lvb() and replace calls to it with
calls to ll_merge_attr().
Signed-off-by: John L. Hammond <john.hammond@intel.com>
Reviewed-on: http://review.whamcloud.com/12849
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-2675
Reviewed-by: Bobi Jam <bobijam@gmail.com>
Reviewed-by: Lai Siyao <lai.siyao@intel.com>
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
It used to check each page in the readahead window is covered by
a lock underneath, now cpo_page_is_under_lock() provides @max_index
to help decide the maximum ra window. @max_index can be modified by
OSC to extend the maximum lock region, to align stripe boundary at
LOV, and to make sure the readahead region at least covers read
region at LLITE layer.
After this is done, usually readahead code calls
cpo_page_is_under_lock() for each stripe.
Signed-off-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-on: http://review.whamcloud.com/8523
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3321
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
>From now on, cl_page becomes one to one mapping of vmpage.
Signed-off-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-on: http://review.whamcloud.com/7895
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3321
Reviewed-by: Bobi Jam <bobijam@gmail.com>
Reviewed-by: Lai Siyao <lai.siyao@intel.com>
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Use weigh_ast to decide if a lock covers any pages.
In recovery, weigh_ast will be used to decide if a DLM read lock
covers any locked pages, or it will be canceled instead being
recovered.
The problem with the original implementation is that it attached
each osc_page to an osc_lock also changed lock state to add every
pages for readahead.
Signed-off-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-on: http://review.whamcloud.com/7894
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3321
Reviewed-by: Bobi Jam <bobijam@gmail.com>
Reviewed-by: Lai Siyao <lai.siyao@intel.com>
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
in ll_write_end(), instead of adding the page into writeback
cache directly, it will be held in a page list. After enough
pages have been collected, issue them all with cio_commit_async().
Signed-off-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-on: http://review.whamcloud.com/7893
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3321
Reviewed-by: Bobi Jam <bobijam@gmail.com>
Reviewed-by: Lai Siyao <lai.siyao@intel.com>
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This change adds support for a single preallocated cl_env per CPU
which can be used in circumstances where reschedule is not possible.
Currently this interface is only used by the ll_releasepage function.
Signed-off-by: Jinshan Xiong <jinshan.xiong@intel.com>
Signed-off-by: Prakash Surya <surya1@llnl.gov>
Reviewed-on: http://review.whamcloud.com/8174
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3321
Reviewed-by: Lai Siyao <lai.siyao@intel.com>
Reviewed-by: Bobi Jam <bobijam@gmail.com>
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This way we can drop it async.
Signed-off-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-on: http://review.whamcloud.com/7891
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3321
Reviewed-by: Lai Siyao <lai.siyao@intel.com>
Reviewed-by: Bobi Jam <bobijam@gmail.com>
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This reverts a patch that was merged before lustre client
was introduced into the stagign tree, so it's not in the history.
The performance dropped a lot when memory reclaim process kicked
in as ll_releasepage() was called to destroy lustre pages. It turned
out that big overhead to allocate cl_env and keys on the fly so we
have to revert this patch.
The original problem for the reverted patch would be solved in a
follow on patch instead.
Signed-off-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-on: http://review.whamcloud.com/7888
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3321
Reviewed-by: Niu Yawei <yawei.niu@intel.com>
Reviewed-by: Lai Siyao <lai.siyao@intel.com>
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Separate lclient was necessary to be shared between
different client implementations, make no sense to have
them separate in Linux kernel.
Signed-off-by: John L. Hammond <john.hammond@intel.com>
Based-on: http://review.whamcloud.com/10171
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
CFS_PAGE_MASK is the same as PAGE_MASK, so get rid of it.
We are replacing it with PAGE_MASK instead of PAGE_CACHE_MASK
because PAGE_CACHE_* stuff is apparently going away.
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Allocating a big hash table using the formula for osd
does not really work for clients. We will create new
hash table for each mount on a single client which is
a lot of memory more than expected.
This patch limits the hash table up to 8M which has
524288 entries
Signed-off-by: Li Dongyang <dongyang.li@anu.edu.au>
Reviewed-on: http://review.whamcloud.com/18048
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-7689
Reviewed-by: Fan Yong <fan.yong@intel.com>
Reviewed-by: Alex Zhuravlev <alexey.zhuravlev@intel.com>
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
fix checkpatch.pl warning about 'Block comments use a trailing */ on a
separate line' and 'Block comments use * on subsequent lines'
Signed-off-by: Clifton Barnes <clifton.a.barnes@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
fix checkpatch.pl warning about
'Logical continuations should be on the previous line'
Signed-off-by: Daeseok Youn <daeseok.youn@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
fix checkpatch.pl warning about 'line over 80 characters'.
I just moved all line comment to above if statement.
Signed-off-by: Daeseok Youn <daeseok.youn@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
remove parenthesis around the CONST | CONST.
It will be also fixed checkpatch.pl warning about
"Alignment should match open parenthesis" becasue
parenthesis were removed by this patch.
Signed-off-by: Daeseok Youn <daeseok.youn@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
the dgnc_offset_table has a same value with (1 << port).
So I tried to replace dgnc_offset_table array with 1 << port.
And also there are redundant assignments(tmp and current_port)
inside while loop for checking uart port, and remove them.
Signed-off-by: Daeseok Youn <daeseok.youn@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Fix the checkpatch.pl issues by using the BIT macro and defining some
macros for the multi-bit fields.
Signed-off-by: H Hartley Sweeten <hsweeten@visionengravers.com>
Cc: Ian Abbott <abbotti@mev.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
For completeness, define the registers used by this driver and remove
the magic numbers.
Signed-off-by: H Hartley Sweeten <hsweeten@visionengravers.com>
Reviewed-by: Ian Abbott <abbotti@mev.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
For aesthetics, add some whitespace to the digital output subdevice
initialization.
Signed-off-by: H Hartley Sweeten <hsweeten@visionengravers.com>
Reviewed-by: Ian Abbott <abbotti@mev.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Fix the checkpatch.pl issues:
WARNING: Block comments use * on subsequent lines
Signed-off-by: H Hartley Sweeten <hsweeten@visionengravers.com>
Reviewed-by: Ian Abbott <abbotti@mev.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This function assumes that the async subdevice has a cancel() function.
It looks like all the current comedi drivers implement a cancel() for
the async subdevices except for the dt2814 analog input usbdevice.
Fix comedi_handle_events() so it does not try to call a non-existent
cancel() function.
Add a dev_warn() to __comedi_device_postconfig_async() so that any new
driver authors will be reminded to implement the cancel().
Signed-off-by: H Hartley Sweeten <hsweeten@visionengravers.com>
Reviewed-by: Ian Abbott <abbotti@mev.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Tidy up this function and fix the checkpatch.pl issues:
WARNING: Prefer 'unsigned int' to bare use of 'unsigned'
Signed-off-by: H Hartley Sweeten <hsweeten@visionengravers.com>
Reviewed-by: Ian Abbott <abbotti@mev.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Fix the checkpatch.pl issues by using the BIT macro and defining some
macros for the multi-bit fields.
Signed-off-by: H Hartley Sweeten <hsweeten@visionengravers.com>
Reviewed-by: Ian Abbott <abbotti@mev.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Fix the checkpatch.pl issues:
WARNING: Block comments use * on subsequent lines
Signed-off-by: H Hartley Sweeten <hsweeten@visionengravers.com>
Reviewed-by: Ian Abbott <abbotti@mev.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
For completeness, define the registers used by this driver and remove
the magic numbers.
Signed-off-by: H Hartley Sweeten <hsweeten@visionengravers.com>
Reviewed-by: Ian Abbott <abbotti@mev.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
For aesthetics, add some whitespace to the comedi_driver definition.
Signed-off-by: H Hartley Sweeten <hsweeten@visionengravers.com>
Reviewed-by: Ian Abbott <abbotti@mev.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
For aesthetics, add some whitespace to the digital output subdevice
initialization.
Signed-off-by: H Hartley Sweeten <hsweeten@visionengravers.com>
Reviewed-by: Ian Abbott <abbotti@mev.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Chnages memory allocation style in order to silence a checkpatch.pl
warning.
Signed-off-by: Ben Marsh <bmarsh94@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
timed_output was only used by the Android vibrator HAL which has now
learned how to use LED triggers instead[1]. Any users of it in AOSP are
on ancient kernels. Adding support for LED triggers is purely DT changes
and proper kernel config.
[1] https://android.googlesource.com/platform%2Fhardware%2Flibhardware/+/61701df363310a5cbd95e3e1638baa9526e42c9b
Cc: John Stultz <john.stultz@linaro.org>
Cc: "Arve Hjønnevåg" <arve@android.com>
Cc: Riley Andrews <riandrews@android.com>
Signed-off-by: Rob Herring <robh@kernel.org>
Acked-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Don't need to have a wmb() in visordriver_remove_device. Also removed
an unnecessary check for drv being null.
Signed-off-by: David Kershner <david.kershner@unisys.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The channel_bytes attribute in the visor_device struct was meant to keep
track of the number of bytes in the associated channel of the device.
Not only is the variable never set nor used, but the information can
already be accessed by referencing visor_device->visorchannel->nbytes.
Signed-off-by: Alexander Curtin <alexander.curtin@unisys.com>
Signed-off-by: David Kershner <david.kershner@unisys.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The 'visor_device.devnodes' field was used for displaying driver version
information through the devmajorminor sysfs attribute, which has recently
been removed, rendering the field unnecessary.
Signed-off-by: Alexander Curtin <alexander.curtin@unisys.com>
Signed-off-by: David Kershner <david.kershner@unisys.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The visor_device.type field was included when preparing to remove
the device_info struct. However, it's not used at all, and was already
redundant by the existence of the 'visor_device.channel_type_guid'
field.
Signed-off-by: Alexander Curtin <alexander.curtin@unisys.com>
Signed-off-by: David Kershner <david.kershner@unisys.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The 'description' variable in visor_device was added in preparation for
removing the 'device_info' struct when the uislib files were removed.
That attribute is never accessed nor set, and the 'name' attribute
provides enough information to correctly identify the driver, it is not
needed.
Signed-off-by: Alexander Curtin <alexander.curtin@unisys.com>
Signed-off-by: David Kershner <david.kershner@unisys.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The fields 'switch_no' and 'internal_port_no' were originally added to the
visor_device struct in preparation of removing the 'device_info' struct
in the now removed 'uislib' library. After the refactoring was complete,
these attributes are not referenced anywhere, and there are no plans to
use them.
Signed-off-by: Alexander Curtin <alexander.curtin@unisys.com>
Signed-off-by: David Kershner <david.kershner@unisys.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Jinshan Xiong