Ian Abbott [Fri, 22 May 2015 17:15:57 +0000 (18:15 +0100)]
staging: comedi: amplc_dio200.h: make self-reliant
The Comedi "amplc_dio200.h" header file included by drivers for Amplicon
DIO200 series cards does not compile cleanly when it is the first header
included by the ".c" file. It uses `struct comedi_device *` in the
parameter lists of some function prototypes, so just declare `struct
comedi_device` as an incomplete type. It also uses `bool`, so include
<linux/types.h> to declare it.
Signed-off-by: Ian Abbott <abbotti@mev.co.uk> Reviewed-by: H Hartley Sweeten <hsweeten@visionengravers.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Ian Abbott [Fri, 22 May 2015 15:21:38 +0000 (16:21 +0100)]
staging: comedi: comedi_8255: new module split from 8255
The Comedi "8255" module is both a standalone Comedi device driver
module for simple devices with one or more 8255 "Programmable Peripheral
Interface" chips at known I/O base addresses (configured at run-time),
and a helper module to configure a 8255-based digital I/O subdevice for
other Comedi drivers.
Split the "8255 subdevice helper" functionality into a new module:
"comedi_8255", leaving the standalone 8255 Comedi driver in the "8255"
module.
The Comedi "detach" routine of the standalone "8255" driver needs to
retrieve the I/O base address passed to the "comedi_8255" module to set
up each subdevice in order to release the I/O port regions it requested
in its "attach" routine. The "comedi_8255" module stores it in a
"subdevice private" data structure that is no longer known to the "8255"
module, so add a new, exported function `subdev_8255_regbase()` to
retrieve it.
Signed-off-by: Ian Abbott <abbotti@mev.co.uk> Reviewed-by: H Hartley Sweeten <hsweeten@visionengravers.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Several Comedi driver modules call `subdev_8255_init()` or
`subdev_8255_mm_init()` to set up a digital I/O subdevice based on the
"8255" chip. One of the parameters to these functions is an optional
pointer to an I/O callback function to perform the actual register
accesses (an internal default callback function is used if NULL).
The kerneldoc for `subdev_8255_init()` and `subdev_8255_mm_init()`
describe the prototype of the optional I/O callback function
incorrectly (my fault), adding a non-existent parameter of type `struct
comedi_subdevice *`. Fix the kerneldoc. Also add parameter names to
the callback function pointer type wherever it occurs to make the usage
clearer.
Signed-off-by: Ian Abbott <abbotti@mev.co.uk> Reviewed-by: H Hartley Sweeten <hsweeten@visionengravers.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Ian Abbott [Fri, 22 May 2015 15:21:36 +0000 (16:21 +0100)]
staging: comedi: 8255.h: don't include "../comedidev.h"
The Comedi "8255.h" header doesn't use anything from "comedidev.h" apart
from `struct comedi_device` and `struct comedi_subdevice`, which are
only used to construct corresponding pointer types within the parameter
lists of function prototypes. Just declare those structure types
incompletely and don't bother including "comedidev.h".
Signed-off-by: Ian Abbott <abbotti@mev.co.uk> Reviewed-by: H Hartley Sweeten <hsweeten@visionengravers.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Ian Abbott [Fri, 22 May 2015 15:21:35 +0000 (16:21 +0100)]
staging: comedi: 8255: fix I/O region leak on failure
The Comedi "8255" driver does not clean up properly on failure. It can
leave requested I/O port regions unreleased. Specifically, the Comedi
"attach" handler (`dev_8255_attach()`) requests a specified I/O port
region before calling `subdev_8255_init()` to set up the subdevice. If
that fails, the "attach" handler returns an error and the Comedi core
will call the "detach" handler (`dev_8255_detach()`) to clean up. The
"detach" handler is responsible for releasing the I/O port regions
successfully requested by the "attach" handler. Unfortunately, it is
unable to obtain the base address of the region if the call to
`subdev_8255_init()` failed.
Fix the I/O region leak by releasing the region in the "attach" handler
directly if the call to `subdev_8255_init()` fails.
Signed-off-by: Ian Abbott <abbotti@mev.co.uk> Reviewed-by: H Hartley Sweeten <hsweeten@visionengravers.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Arnd Bergmann [Tue, 19 May 2015 22:07:27 +0000 (00:07 +0200)]
staging: lustre: remove unused variable warning
A recent patch to simplify the lustre large memory allocation
causes new warnings as an unintended side-effect:
lustre/lov/lov_request.c: In function 'lov_finish_set':
lustre/lov/lov_request.c:78:7: warning: unused variable 'len' [-Wunused-variable]
int len = set->set_oabufs * sizeof(*set->set_pga);
^
lustre/obdclass/acl.c: In function 'lustre_ext_acl_xattr_reduce_space':
lustre/obdclass/acl.c:123:6: warning: unused variable 'old_size' [-Wunused-variable]
int old_size = CFS_ACL_XATTR_SIZE(old_count, ext_acl_xattr);
^
The reason is that the 'size' argument to OBD_FREE_LARGE()
is never needed, which was previously hidden by the extra
abstractions.
This avoids the warnings by adding a cast to void, to tell
the compiler that the argument is intentionally unused.
A better fix is probably to remove the entire set of allocation
macros and open-code the normal kernel interface calls.
Signed-off-by: Arnd Bergmann <arnd@arndb.de> Fixes: 99d56ff7c1c ("staging/lustre: Always try kmalloc first for OBD_ALLOC_LARGE") Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
In lov_unpackmd() there's this strange bit of code where we first try
to look inside of lmm striping pattern for it's type, and then
we check if the pattern is NULL which cannot be right.
Move the check under if (lmm) branch so that it's safe.
Oleg Drokin [Sat, 16 May 2015 07:38:31 +0000 (03:38 -0400)]
staging/lustre: Only set INTERRUPTIBLE state before calling schedule
In __l_wait_event the condition could be a complicated function that does
allocations and other potentialy blocking activities, so it sohuld
not be called in a task state other than RUNNABLE
Sasha Levin [Thu, 28 May 2015 15:03:56 +0000 (11:03 -0400)]
staging: wilc1000: off by one in wilc_wfi_cfg80211_mgmt_types
NL80211_IFTYPE_MAX represents the largest interface type number defined,
so declaring the array with that size will actually leave out the last
interface.
This causes invalid memory access whenever this array is used, which starts
happening at boot.
The driver version is meaningless, and in particular does not
have to be passed from the Makefile. This removes the macros,
but leaves the behavior of printing the 10.2 version untouched
for the moment.
Arnd Bergmann [Thu, 28 May 2015 14:35:42 +0000 (16:35 +0200)]
staging/wilc1000: fix Kconfig dependencies
The newly added wilc1000 driver lacks several Kconfig dependencies,
resulting in a multitude of randconfig build errors, e.g.:
drivers/built-in.o: In function `WILC_WFI_mgmt_tx_cancel_wait':
binder.c:(.text+0x12bd28): undefined reference to `cfg80211_remain_on_channel_expired'
drivers/built-in.o: In function `WILC_WFI_CfgSetChannel':
binder.c:(.text+0x12c9d8): undefined reference to `ieee80211_frequency_to_channel'
drivers/built-in.o: In function `WILC_WFI_CfgAlloc':
binder.c:(.text+0x132530): undefined reference to `wiphy_new_nm'
drivers/built-in.o: In function `wilc_netdev_init':
binder.c:(.text+0x1356d0): undefined reference to `register_inetaddr_notifier'
drivers/built-in.o: In function `linux_spi_init':
binder.c:(.text+0x210a68): undefined reference to `spi_register_driver'
This change ensures that we always have at least one of SPI or MMC
enabled, and are only able to pick an interface that works. It also
adds all the missing dependencies for networking infrastructure
(cfg80211, wext, and ipv4).
In order to make it readable, I also took the liberty of re-indenting
the Kconfig file to the normal conventions.
Reported-by: kbuild test robot <fengguang.wu@intel.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Nicolas Ferre <nicolas.ferre@atmel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Guenter Roeck [Thu, 28 May 2015 04:32:43 +0000 (21:32 -0700)]
staging: wilc1000: Disable for S390
The wilc1000 driver uses definitions such as DEBUG_LEVEL, DEBUG,
and PRINT_INFO. This causes compile errors on S390 which has similar
definitions in its core code. Disable the driver for S390 instead
of giving the non-standard messaging code credit by trying to fix it.
Johnny Kim [Mon, 11 May 2015 05:30:57 +0000 (14:30 +0900)]
staging: MAINTAINERS: add maintainer for wilc1000 device
Add myself as maintainer for atmel wilc1000
Signed-off-by: Johnny Kim <johnny.kim@atmel.com> Signed-off-by: Rachel Kim <rachel.kim@atmel.com> Signed-off-by: Dean Lee <dean.lee@atmel.com> Signed-off-by: Chris Park <chris.park@atmel.com> Acked-by: Nicolas Ferre <nicolas.ferre@atmel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Johnny Kim [Mon, 11 May 2015 05:30:56 +0000 (14:30 +0900)]
staging: wilc1000: Add SDIO/SPI 802.11 driver
This driver is for the wilc1000 which is a single chip IEEE 802.11
b/g/n device.
The driver works together with cfg80211, which is the kernel side of
configuration management for wireless devices because the wilc1000
chipset is fullmac where the MLME is managed in hardware.
The driver worked from kernel version 2.6.38 and being now ported
to several others since then.
A TODO file is included as well in this commit.
Signed-off-by: Johnny Kim <johnny.kim@atmel.com> Signed-off-by: Rachel Kim <rachel.kim@atmel.com> Signed-off-by: Dean Lee <dean.lee@atmel.com> Signed-off-by: Chris Park <chris.park@atmel.com> Acked-by: Nicolas Ferre <nicolas.ferre@atmel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Sudip Mukherjee [Tue, 12 May 2015 12:06:08 +0000 (17:36 +0530)]
staging: panel: fix stackdump
if we load the module, unload and then again try to load the module, we
will get a stackdump. In the module_exit function we are unregistering
the device and releasing the parport. So when we reach the detach
function parport is already null and the unregister_reboot_notifier()
is never called. When we again try to load the module it again tries
register_reboot_notifier() and gives us a stackdump as its earlier
registration is still not removed. It was caused by the
commit bb046fef9668 ('staging: panel: register reboot')
Fix this by moving all the unregistering and releasing in the detach
function, which should be the ideal case as the detach will be called if
we try to unregister the driver or if the parport is removed.
staging: sm750fb: use arch_phys_wc_add() and ioremap_wc()
The same area used for ioremap() is used for the MTRR area.
Convert the driver from using the x86 specific MTRR code to
the architecture agnostic arch_phys_wc_add(). arch_phys_wc_add()
will avoid MTRR if write-combining is available, in order to
take advantage of that also ensure the ioremap'd area is requested
as write-combining.
There are a few motivations for this:
a) Take advantage of PAT when available
b) Help bury MTRR code away, MTRR is architecture specific and on
x86 its replaced by PAT
c) Help with the goal of eventually using _PAGE_CACHE_UC over
_PAGE_CACHE_UC_MINUS on x86 on ioremap_nocache() (see commit de33c442e titled "x86 PAT: fix performance drop for glx,
use UC minus for ioremap(), ioremap_nocache() and
pci_mmap_page_range()")
The conversion done is expressed by the following Coccinelle
SmPL patch, it additionally required manual intervention to
address all the #ifdery and removal of redundant things which
arch_phys_wc_add() already addresses such as verbose message
about when MTRR fails and doing nothing when we didn't get
an MTRR.
Commit 53490b545cb0 ("staging: unisys: move periodic_work.c into the
visorbus directory") removed the Kconfig option UNISYS_VISORUTIL, but
left one reference in a Kconfig select. Remove this last reference.
Don Zickus [Wed, 13 May 2015 17:22:25 +0000 (13:22 -0400)]
staging: unisys: Convert device functions to pass dev_info pointer around
Most device functions pass bus_no and dev_no around and then do a lookup
inside each function to find the dev_info struct. Instead just pass the
pointer.
This prepares us for a later conversion to using visor device.
No real technical changes. Just function header changes and little
cleanups as a result.
Signed-off-by: Don Zickus <dzickus@redhat.com> Signed-off-by: Benjamin Romer <benjamin.romer@unisys.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Don Zickus [Wed, 13 May 2015 17:22:23 +0000 (13:22 -0400)]
staging: unisys: Convert the device attributes to visor_device
Convert the device attribute files to properly use visor_device.
This removes a whole bunch of checks and assumptions and simplifies
the code. Everything is straightforward.
No testing down as I can't mimic channel info correctl.
Signed-off-by: Don Zickus <dzickus@redhat.com> Signed-off-by: Benjamin Romer <benjamin.romer@unisys.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Don Zickus [Wed, 13 May 2015 17:22:22 +0000 (13:22 -0400)]
staging: unisys: Remove unused intr
The conversion to visor_device caused some compile issues.The main
problem was the new fields in 'struct visor_device' were not public.
Remove one that wasn't being used for now.
struct irq_info intr
Signed-off-by: Don Zickus <dzickus@redhat.com> Signed-off-by: Benjamin Romer <benjamin.romer@unisys.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Don Zickus [Wed, 13 May 2015 17:22:21 +0000 (13:22 -0400)]
staging: unisys: Add checks for creation
There was a bunch of channel creation checks before the
visorchannel_create function was called, moving some of those
checks inside. This keeps the outside code cleaner and handles
the situation where a caller forgets to make these checks.
Signed-off-by: Don Zickus <dzickus@redhat.com> Signed-off-by: Benjamin Romer <benjamin.romer@unisys.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Don Zickus [Wed, 13 May 2015 17:22:19 +0000 (13:22 -0400)]
staging: unisys: Add visor device find routine
If we are going to remove the bus_info structs than we need a way
to find the devices when the *_create/destroy cmds are sent over
the vmchannel.
This function crudely impements what pci has. It takes a bus_no
and dev_no and finds the matching 'struct visor_device'.
This function can/should be optimzed later once we get our heads
wrapped around its needs. For now, I am using dev_no=0 to mean
the visorbus itself.
The function is limited to chipset.c only because it is only needed
to do the lookups upon receiving a vmchannel command. Future patches
will make sure the resulting 'struct visor_device' is used every
where else.
Also allow visorbus_type to be more visible for use.
Signed-off-by: Don Zickus <dzickus@redhat.com> Signed-off-by: Benjamin Romer <benjamin.romer@unisys.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Don Zickus [Wed, 13 May 2015 17:22:18 +0000 (13:22 -0400)]
staging: unisys: Prep for removing 'info' structs
The visorbus driver has three _info structs lying around
(device, bus, channel) that store subsets of info from the
bigger structs.
Having these structs around make resource handling very difficult
and more complicated than it needs to be. Use the device
infrastructure and instead pass 'struct visor_device' all
over the place.
In order to do that 'struct visor_device' needs to get smarter.
This patch adds the pieces to prep for it. The new elements
will be used in later patches.
Signed-off-by: Don Zickus <dzickus@redhat.com> Signed-off-by: Benjamin Romer <benjamin.romer@unisys.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Don Zickus [Wed, 13 May 2015 17:22:17 +0000 (13:22 -0400)]
staging: unisys: Clean up device sysfs attributes
Properly hook into the struct device groups element. This allows the
core infrastructure to manage the files instead of the bus layer. And
makes the code easier to read.
I didn't clean up the _show functions just modified them a bit to handle
the different args for now and to prevent a build warning.
Signed-off-by: Don Zickus <dzickus@redhat.com> Signed-off-by: Benjamin Romer <benjamin.romer@unisys.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Don Zickus [Wed, 13 May 2015 17:22:14 +0000 (13:22 -0400)]
staging: unisys: Move the visorbus device underneath devices
Mimicing what other drivers do, this seems appropriate. Yeah, it
is a bus, but it is a bus _device_. This makes things work better
and smoother. Now the sysfs looks like
Don Zickus [Wed, 13 May 2015 17:22:13 +0000 (13:22 -0400)]
staging: unisys: Wire up proper device attr for bus
This patch moves the attributes to underneath the bus device correctly.
This will help remove a bunch of cruft from the code and let the kernel
infrastructure manage the sysfs files instead of the driver.
After the move remove all the leftover code.
Signed-off-by: Don Zickus <dzickus@redhat.com> Signed-off-by: Benjamin Romer <benjamin.romer@unisys.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
David Kershner [Wed, 13 May 2015 17:22:07 +0000 (13:22 -0400)]
staging: unisys: Move files out of common-spar
Move last three files out of common-spar
iochannel.h --> include (will be used by visorhba and visornic)
version.h --> moved to include
controlvmcompletionstatus.h --> moved to visorbus, part of
controlvmchannel.h
Signed-off-by: David Kershner <david.kershner@unisys.com> Signed-off-by: Benjamin Romer <benjamin.romer@unisys.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To prep for the moving of include files, temporarily add the
visorbus/ as a ccflags -I. Once the header files are all
transitioned, we can remove this.
Signed-off-by: Don Zickus <dzickus@redhat.com> Signed-off-by: Benjamin Romer <benjamin.romer@unisys.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Shailendra Verma [Tue, 19 May 2015 14:59:00 +0000 (20:29 +0530)]
Staging:Android:ion - Fix for memory leak if ion device registration get failed.
Fix to avoid possible memory leak if the ion device registration
get failed.Free the allocated device creation memory before return
in case the ion device registration get failed.
Merge tag 'iio-for-v4.2b' of git://git.kernel.org/pub/scm/linux/kernel/git/jic23/iio into staging-next
Jonathan writes:
Second set of new driver, functionality and cleanups for IIO in the 4.2 cycle.
Core functionality
* i and q modifiers from quadrature channels.
* IIO_CHAN_INFO_OVERSAMPLING_RATIO added.
* High pass filter attributes added to mirror the existing low pass filter
ones.
Core cleanups
* Make IIO tools building more cross compiler friendly.
* Substantial rework of the function __iio_update_buffers to greatly simplify
a hideously evolved function.
New drivers and support
* ACPI0008 ambient light sensor driver. This one has been around a long time to
will be good to finally get it into mainline.
* Berlin SOC ADC support.
* BMC150 magnetometer. The accelerometer in the same package has been supported
for quite some time, so good to have this half as well.
* m62332 DAC driver
* MEMSIC MMC35420 magnetometer.
* ROHM BH1710 and similar ambient light sensors.
* Sensortek STK3310 light sensor.
* Sensortek STK8312 accelerometer.
* Sensortek STK8BA50 accelerometer.
* ti-adc128s052 gains support form the adc122s021 2 channel ADC.
Driver cleanups and functionality.
* Allow various drivers to compile with !GPIOLIB if COMPILE_TEST enabled.
* bmc150 - decouple trigger from buffer to allow other triggers to be used.
* bmg160 - decouple trigger from buffer to allow other triggers to be used.
Fix a trivial unused field.
* Constify a load of platform_device_id structures.
* inv_mpu6050 - device tree bindings.
* hid-sensors - fix a memory leak during probe if certain errors occur.
* ltr501 - illuminance channel derived (in an non obvious fashion) from the
intensity channels.
* ltr501 - fix a boundary check on the proximity threshold.
* mlx90614 - drop a pointless return.
* mma8452 - Debugfs register access and fix a bug that had no effect (by
coincidence)
* ti_am335x_adc - add device tree bindings for sample-delay, open-delay and
averaging. The ideal settings for these tend to be board design specific.
Tiberiu Breana [Mon, 18 May 2015 11:49:50 +0000 (14:49 +0300)]
iio: accel: Add support for Sensortek STK8BA50
Minimal implementation of an IIO driver for the Sensortek
STK8BA50 3-axis accelerometer. Datasheet:
http://szgsensor.com/uploads/soft/141229/STK8BA50%D2%E5%BC%CE.pdf
Includes:
- ACPI support;
- read_raw for x,y,z axes;
- reading and setting the scale (range) parameter.
- power management
Signed-off-by: Tiberiu Breana <tiberiu.a.breana@intel.com> Signed-off-by: Jonathan Cameron <jic23@kernel.org>
iio: __iio_update_buffers: Leave device in sane state on error
Currently when something goes wrong at some step when disabling the buffers
we immediately abort. This has the effect that the enable/disable calls are
no longer balanced. So make sure that even if one step in the disable
sequence fails the other steps are still executed.
The other issue is that when either enable or disable fails buffers that
were active at that time stay active while the device itself is disabled.
This leaves things in a inconsistent state and can cause unbalanced
enable/disable calls. Furthermore when enable fails we restore the old scan
mask, but still keeps things disabled.
Given that verification of the configuration was performed earlier and it
is valid at the point where we try to enable/disable the most likely reason
of failure is a communication failure with the device or maybe a
out-of-memory situation. There is not really a good recovery strategy in
such a case, so it makes sense to leave the device disabled, but we should
still leave it in a consistent state.
What the patch does if disable/enable fails is to deactivate all buffers
and make sure that the device will be in the same state as if all buffers
had been manually disabled.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de> Signed-off-by: Jonathan Cameron <jic23@kernel.org>
iio: __iio_update_buffers: Split enable and disable path into helper functions
__iio_update_buffers is already a rather large function with many different
error paths and it is going to get even larger. This patch factors out the
device enable and device disable paths into separate helper functions.
The patch also re-implements iio_disable_all_buffers() using the new
iio_disable_buffers() function removing a fair bit of redundant code.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de> Signed-off-by: Jonathan Cameron <jic23@kernel.org>
iio: __iio_update_buffers: Verify configuration before starting to apply it
Currently __iio_update_buffers() verifies whether the new configuration
will work in the middle of the update sequence. This means if the new
configuration is invalid we need to rollback the changes already made. This
patch moves the validation of the new configuration at the beginning of
__iio_update_buffers() and will not start to make any changes if the new
configuration is invalid.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de> Signed-off-by: Jonathan Cameron <jic23@kernel.org>
Antoine Tenart [Mon, 18 May 2015 09:19:19 +0000 (11:19 +0200)]
Documentation: bindings: document the Berlin ADC driver
Following the addition of a Berlin ADC driver, this patch adds the
corresponding bindings documentation.
Signed-off-by: Antoine Tenart <antoine.tenart@free-electrons.com> Acked-by: Jonathan Cameron <jic23@kernel.org> Signed-off-by: Jonathan Cameron <jic23@kernel.org>
Antoine Tenart [Mon, 18 May 2015 09:19:18 +0000 (11:19 +0200)]
iio: adc: add support for Berlin
This patch adds the support of the Berlin ADC, available on Berlin SoCs.
This ADC has 8 channels available, with one connected to a temperature
sensor.
The particularity here, is that the temperature sensor connected to the
ADC has its own registers, and both the ADC and the temperature sensor
must be configured when using it.
Signed-off-by: Antoine Tenart <antoine.tenart@free-electrons.com> Signed-off-by: Jonathan Cameron <jic23@kernel.org>
Peter Zijlstra [Mon, 18 May 2015 09:31:50 +0000 (11:31 +0200)]
watchdog: Fix merge 'conflict'
Two watchdog changes that came through different trees had a non
conflicting conflict, that is, one changed the semantics of a variable
but no actual code conflict happened. So the merge appeared fine, but
the resulting code did not behave as expected.
Commit 195daf665a62 ("watchdog: enable the new user interface of the
watchdog mechanism") changes the semantics of watchdog_user_enabled,
which thereafter is only used by the functions introduced by b3738d293233 ("watchdog: Add watchdog enable/disable all functions").
There further appears to be a distinct lack of serialization between
setting and using watchdog_enabled, so perhaps we should wrap the
{en,dis}able_all() things in watchdog_proc_mutex.
This patch fixes a s2r failure reported by Michal; which I cannot
readily explain. But this does make the code internally consistent
again.
Reported-and-tested-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
projects / linux-beck.git / log