iio:chemical:pms7003: Fix timestamp alignment and prevent data leak.

One of a class of bugs pointed out by Lars in a recent review.
iio_push_to_buffers_with_timestamp assumes the buffer used is aligned
to the size of the timestamp (8 bytes).  This is not guaranteed in
this driver which uses an array of smaller elements on the stack.
As Lars also noted this anti pattern can involve a leak of data to
userspace and that indeed can happen here.  We close both issues by
moving to a suitable structure in the iio_priv() data with alignment
explicitly requested.  This data is allocated with kzalloc so no
data can leak appart from previous readings.

Fixes: a1d642266c14 ("iio: chemical: add support for Plantower PMS7003 sensor")
Reported-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: <Stable@vger.kernel.org>
Acked-by: Tomasz Duszynski <tomasz.duszynski@octakon.com>

iio:chemical:sps30: Fix timestamp alignment

One of a class of bugs pointed out by Lars in a recent review.
iio_push_to_buffers_with_timestamp assumes the buffer used is aligned
to the size of the timestamp (8 bytes).  This is not guaranteed in
this driver which uses an array of smaller elements on the stack.

Fixes: 232e0f6ddeae ("iio: chemical: add support for Sensirion SPS30 sensor")
Reported-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: <Stable@vger.kernel.org>
Acked-by: Tomasz Duszynski <tomasz.duszynski@octakon.com>

iio: adc: stm32-adc: fix a wrong error message when probing interrupts

A wrong error message is printed out currently, like on STM32MP15:
- stm32-adc-core 48003000.adc: IRQ index 2 not found.

This is seen since commit 7723f4c5ecdb ("driver core: platform: Add an
error message to platform_get_irq*()").
The STM32 ADC core driver wrongly requests up to 3 interrupt lines. It
should request only the necessary IRQs, based on the compatible:
- stm32f4/h7 ADCs share a common interrupt
- stm32mp1, has one interrupt line per ADC.
So add the number of required interrupts to the compatible data.

Fixes: d58c67d1d851 ("iio: adc: stm32-adc: add support for STM32MP1")
Signed-off-by: Fabrice Gasnier <fabrice.gasnier@st.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

iio: light: gp2ap002: Take runtime PM reference on light read

The light sensor needs the regulators to be enabled which means
the runtime PM needs to be on.  This only happened when the
proximity part of the chip was enabled.

As fallout from this change, only report changes to the prox
state in the interrupt handler when it is explicitly enabled.

Fixes: 97d642e23037 ("iio: light: Add a driver for Sharp GP2AP002x00F")
Signed-off-by: Jonathan Bakker <xc-racer2@live.ca>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

iio: proximity: ping: pass reference to IIO device as param to ping_read()

Since there will be some changes to how iio_priv_to_dev() is implemented,
it could be that the helper becomes a bit slower, as it will be hidden away
in the IIO core.

But even without that rework, this looks like it can pass the 'indio_dev'
object to ping_read() and obtain the state struct via iio_priv() which is a
preferred practice than going back-n-forth (getting the state-struct, then
using iio_priv_to_dev() to get the indio_dev object back).

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

iio: dac: ad5592r-base: Replace indio_dev->mlock with own device lock

As part of the general cleanup of indio_dev->mlock, this change replaces
it with a local lock on the device's state structure.
This also removes unused iio_dev pointers.

Signed-off-by: Sergiu Cuciurean <sergiu.cuciurean@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

iio: proximity: Add driver support for vcnl3020 proximity sensor

Proximity sensor driver based on light/vcnl4000.c code.
For now supports only the single on-demand measurement.

The VCNL3020 is a fully integrated proximity sensor. Fully
integrated means that the infrared emitter is included in the
package. It has 16-bit resolution. It includes a signal
processing IC and features standard I2C communication
interface. It features an interrupt function.

Datasheet: http://www.vishay.com/docs/84150/vcnl3020.pdf
Signed-off-by: Ivan Mikhaylov <i.mikhaylov@yadro.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

dt-bindings: proximity: provide vcnl3020 device tree binding document

Mostly standard i2c driver with some additional led-current option
for vcnl3020.

Signed-off-by: Ivan Mikhaylov <i.mikhaylov@yadro.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

iio: buffer: remove attrcount_orig var from sysfs creation

The variable no longer does anything.
It should have been removed with commit 2e036804d773e ("iio: buffer: remove
'scan_el_attrs' attribute group from buffer struct").
That was about the last time this was needed.

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

iio: chemical: add atlas-ezo-sensor initial support

Add driver for Atlas EZO line of sensors with initial support for
CO2 the sensor. This is effectively ASCII strings proxied over I2C
due to these series of sensors being by default UART.

Signed-off-by: Matt Ranostay <matt.ranostay@konsulko.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

dt-bindings: iio: chemical: add CO2 EZO module documentation

Cc: devicetree@vger.kernel.org
Signed-off-by: Matt Ranostay <matt.ranostay@konsulko.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

iio: adc: exynos: Simplify Exynos7-specific init

The Exynos7-specific code bits in ADC driver do not play with PHY:
the field exynos_adc_data.needs_adc_phy is not set in exynos7_adc_data
instance.  Therefore the initialization code does not have to check if
it is true.

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Reviewed-by: Alim Akhtar <alim.akhtar@samsung.com>
Tested-by: Alim Akhtar <alim.akhtar@samsung.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

iio: adc: Add scaling support to exynos adc driver

Currently the driver only exposes the raw counts.  As we
have the regulator voltage and the maximum value (stored in
the data mask), we can trivially produce a scaling fraction
of voltage / max value.

This assumes that the regulator voltage is in fact the max
voltage, which appears to be the case for all mainline dts
and cross referenced with the public Exynos4412 and S5PV210
datasheets.

Signed-off-by: Jonathan Bakker <xc-racer2@live.ca>
Reviewed-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

iio: __iio_update_buffers: Update mode before preenable/after postdisable

It is clear that we transition to INDIO_DIRECT_MODE when disabling the
buffer(s) and it is also clear that we transition from INDIO_DIRECT_MODE
when enabling the buffer(s). So leaving the currentmode field
INDIO_DIRECT_MODE until after the preenable() callback and updating it to
INDIO_DIRECT_MODE before the postdisable() callback doesn't add additional
value. On the other hand some drivers will need to perform different
actions depending on which mode the device is going to operate in/was
operating in.

Moving the update of currentmode before preenable() and after postdisable()
enables us to have drivers which perform mode dependent actions in those
callbacks.

Note, was originally not intended as such, but fixes an issue introduced
in the at91-sama5d2 adc driver.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Fixes: 065056cb0d0a ("iio: at91-sama5d2_adc: split at91_adc_current_chan_is_touch() helper")
Tested-by: Eugen Hristev <eugen.hristev@microchip.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

iio: dac: vf610_dac: Replace indio_dev->mlock with own device lock

As part of the general cleanup of indio_dev->mlock, this change replaces
it with a local lock on the device's state structure.

Signed-off-by: Sergiu Cuciurean <sergiu.cuciurean@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

iio: dac: ad5686: Replace indio_dev->mlock with own device lock

As part of the general cleanup of indio_dev->mlock, this change replaces
it with a local lock on the device's state structure.

Signed-off-by: Sergiu Cuciurean <sergiu.cuciurean@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

iio: dac: ad5421: Replace indio_dev->mlock with own device lock

As part of the general cleanup of indio_dev->mlock, this change replaces
it with a local lock on the device's state structure.

Signed-off-by: Sergiu Cuciurean <sergiu.cuciurean@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

iio: dac: ad5380: Replace indio_dev->mlock with own device lock

As part of the general cleanup of indio_dev->mlock, this change replaces
it with a local lock on the device's state structure.

Signed-off-by: Sergiu Cuciurean <sergiu.cuciurean@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

iio: dac: ad5764: Replace indio_dev->mlock with own device lock

As part of the general cleanup of indio_dev->mlock, this change replaces
it with a local lock on the device's state structure.

Signed-off-by: Sergiu Cuciurean <sergiu.cuciurean@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

iio: dac: ad5761: Replace indio_dev->mlock with own device lock

As part of the general cleanup of indio_dev->mlock, this change replaces
it with a local lock on the device's state structure.

Signed-off-by: Sergiu Cuciurean <sergiu.cuciurean@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

iio: dac: ad5755: Replace indio_dev->mlock with own device lock

As part of the general cleanup of indio_dev->mlock, this change replaces
it with a local lock on the device's state structure.
This also changes some internal functions to pass the pointer to the
state-struct vs a ref to indio_dev just to access the state-struct again.

Signed-off-by: Sergiu Cuciurean <sergiu.cuciurean@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

iio: dac: ad5449: Replace indio_dev->mlock with own device lock

As part of the general cleanup of indio_dev->mlock, this change replaces
it with a local lock on the device's state structure.

Signed-off-by: Sergiu Cuciurean <sergiu.cuciurean@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

iio: dac: ad5446: Replace indio_dev->mlock with own device lock

As part of the general cleanup of indio_dev->mlock, this change replaces
it with a local lock on the device's state structure.

Signed-off-by: Sergiu Cuciurean <sergiu.cuciurean@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

iio: dac: ad5360: Replace indio_dev->mlock with own device lock

As part of the general cleanup of indio_dev->mlock, this change replaces
it with a local lock on the device's state structure.
This also changes some internal functions to pass the pointer to the
state-struct vs a ref to indio_dev just to access the state-struct again.

Signed-off-by: Sergiu Cuciurean <sergiu.cuciurean@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

iio: accel: Add bma150/smb380 support to bma180

The bma150/smb380 are very similar to the bma023 but have a temperature
channel as well.

Signed-off-by: Jonathan Bakker <xc-racer2@live.ca>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

iio: accel: bma180: Rename center_temp to temp_offset

The bma180 driver is being extended to support the bma150.
Its temperature channel is unsigned so the center_temp naming
no longer makes.

Signed-off-by: Jonathan Bakker <xc-racer2@live.ca>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

iio: accel: bma180: Add support for bma023

The bma023 chip is similar enough to the bma180 and bma25x that the
same driver can support all of them.  The biggest differences are
the lack of a temperature channel and no low power but still working
mode.

The bma150 is a close relative of the bma023, but it does have a
temperature channel so support is not added for it.

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Jonathan Bakker <xc-racer2@live.ca>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

dt-bindings: iio: accel: Add required regulators to bma180

The bma180 and related chips should have two regulators attached to
them.  The IIO driver currently uses them, document them here as
well.

Acked-by: Rob Herring <robh@kernel.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Jonathan Bakker <xc-racer2@live.ca>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

dt-bindings: iio: accel: Add bma150 family compatibles to bma180

The bma023, bma150, and smb380 are in the same family as the bma180
and support is being added to the bma180 IIO driver for them.

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Jonathan Bakker <xc-racer2@live.ca>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

iio: accel: Make bma180 conflict with input's bma150

The bma180 IIO driver is being extended for support for the chips
support by input's bma150 driver (bma023, bma150, smb380). Don't
allow both drivers to be enabled simultaneously as they're for the
same hardware.

Signed-off-by: Jonathan Bakker <xc-racer2@live.ca>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

iio: accel: bma180: Prepare for different reset values

Some variants of the bma180 (eg bma023) have different reset
values.  In preparation for adding support for them, factor
out the reset value into the chip specific data.

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Jonathan Bakker <xc-racer2@live.ca>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

Merge tag 'iio-for-5.8b' of git://git./linux/kernel/git/jic23/iio into staging-next

Jonathan writes:

Second set of new device support, cleanups and features for IIO in the 5.8 cycle

Usual mixed back but with a few subsystem wide or device type
wide cleanups.

New device support

* adis16475
  - New driver supporting adis16470, adis16475, adis16477, adis16465,
    adis16467, adis16500, adis16505 and adis16507.
    Includes some rework of the adis library to simplify using it
    for this new driver.
* ak8974
  - Add support for Alps hscdt008a. ID only. Related patches add support
    for scale.
* atlas-sensor
  - Add support for RTD-SM OEM temperature sensor.
* cm32181
  - Add support for CM3218 including support for SMBUS alert via
    ACPI resources.
* ltc2632
  - Add support for ltc2634-12/10/8 DACS including handling per
    device type numbers of channels.

Major Features

* cm32181
  - ACPI bindings including parsing CPM0 and CPM1 custom ACPI tables.
    Includes minor tidy ups and fixes.
* vcnl4000
  - Add event support
  - Add buffered data capture support
  - Add control of sampling frequency

Cleanups and minor fixes.

* core
  - Trivial rework of iio_device_alloc to use an early return and
    improve readability.
  - Precursors to addition of multiple buffer support. So far
    minor refactoring.
* subsystem wide
  - Use get_unaligned_be24 slightly improve readability over open
    coding it.
* adis drivers
  - Use iio_get_debugfs_dentry access function.
* bh1780, cm32181, cm3232, gp2ap02a00f, opt3001, st_uvis25, vl6180,
  dmard06, kxsd9
  - Drop use of of_match_ptr to allow ACPI based probing via PRP0001.
    Part of clear out of this to avoid cut and paste into new drivers.
* ad5592r, ad5593r
  - Fix typos
* ad5933
  - Use managed interfaces to automate error handling and remove.
* ak8974
  - Fix wrong number of 'real bits' for buffered data.
  - Refactor to pull measurement code out as separate function.
    bmp280
  - Fix lack of clamp on range during data capture.
* at91-sama5d2_adc
  - Handle unfinished conversions correctly.
  - Allow use of triggers other than it's own.
  - Reorganize buffer setup and tear down as part of long running
    subsystem wide rework.
* ccs811
  - Add DT binding docs and match table.
  - Support external reset and wakeup pins.
* hid-sensors
  - Reorganize buffer setup and tear down as part of long running
    subsystem wide rework.
* ltr501
  - Constify some structs.
* vcnl4000
  - Fix an endian issue by using explicit byte swapped i2c accessors.

* tag 'iio-for-5.8b' of git://git.kernel.org/pub/scm/linux/kernel/git/jic23/iio: (74 commits)
  iio: light: ltr501: Constify structs
  staging: iio: ad5933: attach life-cycle of kfifo buffer to parent device and use managed calls throughout
  iio: bmp280: fix compensation of humidity
  iio: light: cm32181: Fix integartion time typo
  iio: light: cm32181: Add support for parsing CPM0 and CPM1 ACPI tables
  iio: light: cm32181: Make lux_per_bit and lux_per_bit_base_it runtime settings
  iio: light: cm32181: Use units of 1/100000th for calibscale and lux_per_bit
  iio: light: cm32181: Change reg_init to use a bitmap of which registers to init
  iio: light: cm32181: Handle CM3218 ACPI devices with 2 I2C resources
  iio: light: cm32181: Clean up the probe function a bit
  iio: light: cm32181: Add support for the CM3218
  iio: light: cm32181: Add some extra register defines
  iio: light: cm32181: Add support for ACPI enumeration
  iio: light: cm32181: Switch to new style i2c-driver probe function
  iio: hid-sensors: move triggered buffer setup into hid_sensor_setup_trigger
  iio: vcnl4000: Add buffer support for VCNL4010/20.
  iio: vcnl4000: Add sampling frequency support for VCNL4010/20.
  iio: vcnl4000: Add event support for VCNL4010/20.
  iio: vcnl4000: Factorize data reading and writing.
  iio: vcnl4000: Fix i2c swapped word reading.
  ...

staging: wfx: remove false positive warning

When a station is removed, the driver check that all the Tx frames were
correctly sent. However, the station can be removed before all the Tx
frames were acknowledged and a false positive warning can be emitted.

The previous commit has added a trace when driver received an
acknowledge for a non-existent station. It appear that these events
are perfectly correlated and there is no leak.

Now, the subject is perfectly understood. Remove the warning. Just keep
a debug trace in case we have any doubt in the future.

In the past, the subject has already been discussed here:
   https://lore.kernel.org/driverdev-devel/6287924.ghGFUMk3OD@pc-42/

Fixes: 4bbc6a3e7ad0 ("staging: wfx: make warning about pending frame less scary")
Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200515083325.378539-20-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: trace acknowledges not linked to any stations

Some resources are associated to the outgoing of the stations. To avoid
any resource leaks. It is important to understand why an acknowledge is
not associated to any station.

Add a trace for that purpose.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200515083325.378539-19-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: remove false-positive WARN()

The function wfx_tx_flush() wait for there is no more queued frames in
hardware queue. Then, for the sanity, it checks that there is no more
pending frame on any AC queue.

However, there is a race here. It may happens that hardware queues are
empty, but the counters of the AC queues are not yet updated. So, it may
produce false-positive warning.

The easiest way to solve the problem is just to remove the sanity check.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200515083325.378539-18-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix error reporting in wfx_start_ap()

If AP did not start, the error was not reported to mac80211.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200515083325.378539-17-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: drop unnecessary filter configuration when disabling filter

Currently, when mac80211 want to disable beacon filtering, the driver
reset the filter table and disable the beacon filtering. Only the latter
action is required.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200515083325.378539-16-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix PS parameters when multiple vif are in use

When multiple vif are in use (= one access point and one station), and
when the channels are different, it is necessary to enable power save on
station.

The firmware check that steps are done in the correct order:
  - AP can't start if PS is not enable on the station
  - PS can't set on the station before the association has finished
    (= before the call set_bss_params)

Obviously, in add, when one of the interface disappears, it is necessary to
restore the power save status.

wfx_update_pm() is able to set the correct PS configuration. But it has
to be called at the right time:
   1. before hif_start(), but after the channel configuration is known
   2. after hif_set_bss_params()
   3. after hif_reset()

Therefore, the call to wfx_update_pm() from wfx_add_interface() is too
early to address 1.

The call after hif_set_bss_params() already exists.

For the symmetry, the call from wfx_remove_interface() (that handle 3.)
is also relocated.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200515083325.378539-15-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix potential dead lock between join and scan

The device disallows to start a scan request between hif_join() and
hif_set_bss_params(). The driver is not protected against that. The
worst case happens when association is aborted and hif_set_bss_params()
never happens.

mac80211 would never ask for scan during the association process. So,
this patch just aborts the association in progress when scan is
requested.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200515083325.378539-14-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: merge wfx_stop_ap() with wfx_reset()

wfx_stop_ap() and wfx_reset() do the same thing. Merge them.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200515083325.378539-13-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: rename wfx_do_unjoin() into wfx_reset()

In fact, wfx_do_unjoin() resets the interface. This mechanism can be
used in more cases than just disassociating from a BSS. So, rename it to
reflect that fact.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200515083325.378539-12-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix potential use-after-free

wfx_tx_policy_put() use data from the skb. However, the call to
skb_pull() has just discarded them (even if the memory is in fact not
really discarded).

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200515083325.378539-11-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: call wfx_tx_update_sta() before to destroy tx_priv

The function wfx_notify_buffered_tx() need to know if the frame was
associated to a station. This information is available in the Control
Buffer (CB) of the skb. However, when wfx_notify_buffered_tx() is
called, the CB is no more available. Thus, the caller has to take care
of this information.

wfx_notify_buffered_tx() is a specific case. All the other function are
called before the destruction of the CB. So, this patch align the API of
wfx_notify_buffered_tx() with the other functions. Call it before the CB
was destroyed and drop the extra argument 'has_sta'.

It is also the right time to rename it into wfx_tx_update_sta() (which
is closer to the behavior of the function).

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200515083325.378539-10-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: split out wfx_tx_fill_rates() from wfx_tx_confirm_cb()

wfx_tx_confirm_cb() is a big function. A big part of its body aims to
fill the rates list. So, create a new function wfx_tx_fill_rates() and
make wfx_tx_confirm_cb() smaller.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200515083325.378539-9-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix status of dropped frames

When wfx_flush() is called, the status of pending frames are reported to
mac80211 with random status. mac80211 probably won't interpret this
status in this case, but it is cleaner to return a correctly initialized
status.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200515083325.378539-8-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix indentation

Fix indention of wfx_skb_dtor().

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200515083325.378539-7-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix value of scan timeout

Before to start the scan request, the firmware signals (with a null
frame) to the AP it won't be able to receive data. This frame can be
long to send: up to 512TU. The current calculus of the scan timeout does
not take into account this delay.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200515083325.378539-5-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: check pointers returned by allocations

Until now, the driver did not always check if the allocations success.

The issue was discussed here:
   https://lore.kernel.org/netdev/2026476.QLiXXEGFCf@pc-42/

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200515083325.378539-4-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: apply 80-columns rule to strings

Strings are allowed to exceed 80 columns but, in this case, the format
arguments should be placed on a new line. Apply this rule to the whole
code of the driver.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200515083325.378539-3-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix warning when unregister a frozen device

The device does not answer to the command hif_shutdown. Therefore,
hif_shutdown() is a bit special. It bypasses some of work normally made
by wfx_cmd_send(). In particularly, it unlock hif_cmd.lock and
hif_cmd.key_renew_lock.

However, if the driver notice that the device is frozen, wfx_cmd_send()
stops to send data and doesn't lock the mutexes. Then, it produced a
warning when hif_shutdown() tried to unlock these mutexes.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200515083325.378539-2-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: vt6656: vt6655: removing unused macros definition Makefiles

This patch is removing definition of CFLAGS in Makefile of vt6656 and
vt6655, as those are defining macros that are not used. This will remove
undef of one macro from vt6655/device_main.c, as it is only undef and it is
not used anywhere else, so it is safe to remove it.

Macros are removed from vt665x/Makefile and vt6655/device_main.c.

Signed-off-by: Matej Dujava <mdujava@kocurkovo.cz>
Link: https://lore.kernel.org/r/1589397351-24655-2-git-send-email-mdujava@kocurkovo.cz
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: fbtft: fb_st7789v: Initialize the Display

Set Gamma Values and Register Values for the HSD20_IPS Panel

Signed-off-by: Oliver Graute <oliver.graute@kococonnector.com>
Link: https://lore.kernel.org/r/1589380299-21871-1-git-send-email-oliver.graute@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: qlge: Remove unnecessary spaces in qlge_main.c

Fix checkpatch.pl check:

  CHECK: No space is necessary after a cast

Signed-off-by: Xiangyang Zhang <xyz.sun.ok@gmail.com>
Link: https://lore.kernel.org/r/20200513130042.13185-1-xyz.sun.ok@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: vc04_services: Block comment alignment

Coding style issue reported by checkpatch.pl
This patch clears the checkpatch.pl "Block comments should align
the * on each line" warning.
Also cleared /****** and blank line.

Signed-off-by: John Oldman <john.oldman@polehill.co.uk>
Link: https://lore.kernel.org/r/20200513125405.28242-1-john.oldman@polehill.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: greybus: uart: replace driver line-coding struct

Drop the driver version of the line-coding request and use the protocol
definition directly as was originally intended instead.

This specifically avoids having the two versions of what is supposed to
be the same struct ever getting out of sync.

Note that this has in fact already happened once when the protocol
definition had its implicit padding removed while the driver struct
wasn't updated. The fact that we used the size of the then larger driver
struct when memcpying its content to the stack didn't exactly make
things better. A later addition of a flow-control field incidentally
made the structures match again.

Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20200514070548.4423-1-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Documentation: ABI: correct sysfs attribute description of MOST driver

This patch fixes the ABI description file sysfs-bus-most.

Signed-off-by: Christian Gromm <christian.gromm@microchip.com>
Link: https://lore.kernel.org/r/1589534465-7423-8-git-send-email-christian.gromm@microchip.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: most: usb: use macro ATTRIBUTE_GROUPS

This patch makes use of the macro ATTRIBUTE_GROUPS to create the groups
instead of defining them manually.

Signed-off-by: Christian Gromm <christian.gromm@microchip.com>
Reported-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/1589534465-7423-7-git-send-email-christian.gromm@microchip.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: most: fix typo in Kconfig

This patch corrects the typo in the Kconfig file where it says
tranceiver instead of transceiver.

Signed-off-by: Christian Gromm <christian.gromm@microchip.com>
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://lore.kernel.org/r/1589534465-7423-6-git-send-email-christian.gromm@microchip.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: most: usb: use dev_dbg function

This patch replaces the functions dev_notice with dev_dbg to silence
the driver during normal operation.

Signed-off-by: Christian Gromm <christian.gromm@microchip.com>
Reported-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/1589534465-7423-5-git-send-email-christian.gromm@microchip.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: most: usb: check number of reported endpoints

This patch checks the number of endpoints reported by the USB
interface descriptor and throws an error if the number exceeds
MAX_NUM_ENDPOINTS.

Signed-off-by: Christian Gromm <christian.gromm@microchip.com>
Reported-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/1589534465-7423-4-git-send-email-christian.gromm@microchip.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: most: usb: remove reference to USB error codes

This patch removes the reference to the driver API file for USB error
codes.

Signed-off-by: Christian Gromm <christian.gromm@microchip.com>
Reported-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/1589534465-7423-3-git-send-email-christian.gromm@microchip.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: most: usb: use dev_*() functions to print messages

This patch removes the pr_*() functions and uses dev_*() instead.

Signed-off-by: Christian Gromm <christian.gromm@microchip.com>
Reported-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/1589534465-7423-2-git-send-email-christian.gromm@microchip.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: vt6656: Remove logically dead code

In the start of the "vnt_rf_set_txpower" function the "power" variable
is set at most to VNT_RF_MAX_POWER (hex = 0x3f, dec = 63). Then, in the
switch statement there are four comparisons with the "power" variable
against AL7230_PWR_IDX_LEN (dec = 64), VT3226_PWR_IDX_LEN (dec = 64),
VT3342_PWR_IDX_LEN (dec = 64). Due to all the commented comparisons are
to check if the "power" variable is "greater than or equal" to 64, this
never happens. So, remove the logically dead code.

Also, remove all the defines that are no longer required.

Addresses-Coverity-ID: 1230228 ("Logically dead code")
Fixes: f53d9f12c51a ("staging: vt6656: rf.c additional power.")
Signed-off-by: Oscar Carter <oscar.carter@gmx.com>
Link: https://lore.kernel.org/r/20200510090950.7633-1-oscar.carter@gmx.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: bcm2835-camera: insert emty line after declaration

Missing empty line after variable declaration

Signed-off-by: Houssem KADI <kadi.houssem.eddine@gmail.com>
Link: https://lore.kernel.org/r/20200509180849.GA30426@houssem-MS-7808
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: vt6656: remove difs / sifs adjustments.

Now mac89211 is doing frame timing in rxtx these vendor adjustments need
to be removed.

Signed-off-by: Malcolm Priestley <tvboxspy@gmail.com>
Link: https://lore.kernel.org/r/034e445c-b245-52c4-c855-431b9783bcff@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: vt6656: vnt_get_rtscts_rsvtime_le replace with rts/cts duration.

rsvtime is the time needed in firmware to process the received
frame time in firmware so they can be the same as vnt_get_rts_duration
or vnt_get_cts_duration where appropriate.

The rts_rrv_time are now all the same timing in vnt_rxtx_rts.

So vnt_get_rtscts_rsvtime_le and and vnt_get_frame_time are no longer
required.

Signed-off-by: Malcolm Priestley <tvboxspy@gmail.com>
Link: https://lore.kernel.org/r/4c0fe356-7e08-bf66-58b7-5ab683ba9536@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: vt6656: Split RTS and CTS Duration functions

split vnt_get_rtscts_duration_le into vnt_get_rts_duration and
vnt_get_cts_duration.

The duration's are all the same in vnt_rxtx_rts_g_head.

Signed-off-by: Malcolm Priestley <tvboxspy@gmail.com>
Link: https://lore.kernel.org/r/d2983161-7935-48ce-c0ca-a26ebafa3997@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: vt6656: vnt_get_rtscts_duration_le use ieee80211_ctstoself_duration

use the mac80211 ieee80211_ctstoself_duration for CTS to self frames.

Signed-off-by: Malcolm Priestley <tvboxspy@gmail.com>
Link: https://lore.kernel.org/r/f12b3d71-eb61-340b-e473-83509d9bc38a@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: vt6656: vnt_rxtx_rsvtime_le16 to use ieee80211_generic_frame_duration.

ieee80211_generic_frame_duration is the mac80211 equivalent to
vnt_get_rsvtime use this to get our frame time.

There is a change where there is rrv_time_a and rrv_time_b
the frame duration is always the same so both are equal.

Signed-off-by: Malcolm Priestley <tvboxspy@gmail.com>
Link: https://lore.kernel.org/r/acff7fcc-0add-652b-7d07-22001b641257@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: vt6656: vnt_get_rtscts_duration_le use ieee80211_rts_duration

use the mac80211 ieee80211_rts_duration for RTS frames.

Signed-off-by: Malcolm Priestley <tvboxspy@gmail.com>
Link: https://lore.kernel.org/r/377a4cc3-cfe3-91aa-cf71-1063f311426a@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: most: usb: sanity check channel before using it as an index into arrays

Currently channel is being sanity checked after it has been used as
an index into some arrays. Fix this by moving the sanity check of
channel before the arrays are indexed with it.

Addresses-Coverity: ("Negative array index read")
Fixes: 59ed0480b950 ("Staging: most: replace pr_*() functions by dev_*()")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Link: https://lore.kernel.org/r/20200507150652.52238-1-colin.king@canonical.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: most: usb: add PM functions

This patch adds the implementation of the PM functions resume and suspend.

Signed-off-by: Christian Gromm <christian.gromm@microchip.com>
Link: https://lore.kernel.org/r/1588680892-9413-1-git-send-email-christian.gromm@microchip.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: update TODO

Update the TODO list associated to the wfx driver with the last
progresses.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200512150414.267198-18-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix endianness of the field 'channel_number'

The field 'channel_number' from the structs hif_ind_rx and hif_req_start
is a __le32. Sparse complains this field is not always correctly
accessed:

    drivers/staging/wfx/data_rx.c:95:55: warning: incorrect type in argument 1 (different base types)
    drivers/staging/wfx/data_rx.c:95:55:    expected int chan
    drivers/staging/wfx/data_rx.c:95:55:    got restricted __le16 const [usertype] channel_number

However, the value of channel_number cannot be greater than 14 (this
device only support 2.4Ghz band). So, we only have to access to the
least significant byte. It is finally easier to declare it as an array
of bytes and only access to the first one.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200512150414.267198-17-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix endianness of the field 'num_tx_confs'

The field 'num_tx_confs' from the struct hif_cnf_multi_transmit is a
__le32. Sparse complains this field is not always correctly accessed:

    drivers/staging/wfx/hif_rx.c:82:9: warning: restricted __le32 degrades to integer
    drivers/staging/wfx/hif_rx.c:87:29: warning: restricted __le32 degrades to integer

However, the value of num_tx_confs cannot be greater than 15. So, we
only have to access to the least significant byte. It is finally easier
to declare it as an array of bytes and only access to the first one.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200512150414.267198-16-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix endianness of the field 'status'

The field 'status' appears in most of structs returned by the hardware.
This field is encoded as little endian. Sparse complains this field is
not always correctly accessed:

    drivers/staging/wfx/data_rx.c:53:16: warning: restricted __le32 degrades to integer
    drivers/staging/wfx/data_rx.c:84:16: warning: restricted __le32 degrades to integer
    drivers/staging/wfx/data_tx.c:526:24: warning: restricted __le32 degrades to integer
    drivers/staging/wfx/data_tx.c:569:23: warning: restricted __le32 degrades to integer
    drivers/staging/wfx/hif_rx.c:128:33: warning: restricted __le32 degrades to integer
    drivers/staging/wfx/./traces.h:401:1: warning: restricted __le32 degrades to integer
    drivers/staging/wfx/./traces.h:401:1: warning: restricted __le32 degrades to integer

In most of cases, this field is only compared with HIF_STATUS values.
Finally, it is more convenient to solve the problem by defining the
HIF_STATUS values directly in little endian.

It is also the right time to make some clean up in the HIF_STATUS names.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200512150414.267198-15-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix access to le32 attribute 'len'

Sparse complains about the accesses to the field 'len' from struct hif_msg:

    drivers/staging/wfx/bh.c:88:32: warning: restricted __le16 degrades to integer
    drivers/staging/wfx/bh.c:88:32: warning: restricted __le16 degrades to integer
    drivers/staging/wfx/bh.c:93:32: warning: restricted __le16 degrades to integer
    drivers/staging/wfx/bh.c:93:32: warning: cast to restricted __le16
    drivers/staging/wfx/bh.c:93:32: warning: restricted __le16 degrades to integer
    drivers/staging/wfx/bh.c:121:25: warning: incorrect type in argument 2 (different base types)
    drivers/staging/wfx/bh.c:121:25:    expected unsigned int len
    drivers/staging/wfx/bh.c:121:25:    got restricted __le16 [usertype] len
    drivers/staging/wfx/hif_rx.c:27:22: warning: restricted __le16 degrades to integer
    drivers/staging/wfx/hif_rx.c:347:39: warning: incorrect type in argument 7 (different base types)
    drivers/staging/wfx/hif_rx.c:347:39:    expected unsigned int [usertype] len
    drivers/staging/wfx/hif_rx.c:347:39:    got restricted __le16 const [usertype] len
    drivers/staging/wfx/hif_rx.c:365:39: warning: incorrect type in argument 7 (different base types)
    drivers/staging/wfx/hif_rx.c:365:39:    expected unsigned int [usertype] len
    drivers/staging/wfx/hif_rx.c:365:39:    got restricted __le16 const [usertype] len
    drivers/staging/wfx/./traces.h:195:1: warning: incorrect type in assignment (different base types)
    drivers/staging/wfx/./traces.h:195:1:    expected int msg_len
    drivers/staging/wfx/./traces.h:195:1:    got restricted __le16 const [usertype] len
    drivers/staging/wfx/./traces.h:195:1: warning: incorrect type in assignment (different base types)
    drivers/staging/wfx/./traces.h:195:1:    expected int msg_len
    drivers/staging/wfx/./traces.h:195:1:    got restricted __le16 const [usertype] len
    drivers/staging/wfx/debug.c:319:20: warning: restricted __le16 degrades to integer
    drivers/staging/wfx/secure_link.c:85:27: warning: restricted __le16 degrades to integer
    drivers/staging/wfx/secure_link.c:85:27: warning: restricted __le16 degrades to integer

Indeed, the attribute len is little-endian. We have to take to the
endianness when we access it.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200512150414.267198-14-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix endianness of the struct hif_ind_startup

The struct hif_ind_startup is received from the hardware. So it is
declared as little endian. However, it is also stored in the main driver
structure and used on different places in the driver. Sparse complains
about that:

    drivers/staging/wfx/data_tx.c:388:43: warning: restricted __le16 degrades to integer
    drivers/staging/wfx/bh.c:199:9: warning: restricted __le16 degrades to integer
    drivers/staging/wfx/bh.c:221:62: warning: restricted __le16 degrades to integer

In order to make Sparse happy and to keep access from the driver easy,
this patch declare hif_ind_startup with native endianness.

On reception of this struct, this patch takes care to do byte-swap and
keep Sparse happy.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200512150414.267198-13-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: declare the field 'packet_id' with native byte order

The field packet_id is not interpreted by the device. It is only used as
identifier for the device answer. So it is not necessary to declare it
little endian. It fixes some warnings raised by Sparse without
complexifying the code.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200512150414.267198-12-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix access to le32 attribute 'indication_type'

The attribute indication_type is little-endian. We have to take to the
endianness when we access it.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200512150414.267198-11-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix access to le32 attribute 'event_id'

The attribute event_id is little-endian. We have to take to the
endianness when we access it.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200512150414.267198-10-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix access to le32 attribute 'ps_mode_error'

The attribute ps_mode_error is little-endian. We have to take to the
endianness when we access it.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200512150414.267198-9-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix endianness of hif_req_read_mib fields

The structs hif_{req,cnf}_read_mib contain only little endian values.
Thus, it is necessary to fix byte ordering before to use them.
Especially, sparse detected wrong accesses to fields mib_id and length.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200512150414.267198-8-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix endianness of fields media_delay and tx_queue_delay

The struct hif_cnf_tx contains only little endian values. Thus, it is
necessary to fix byte ordering before to use them. Especially, sparse
detected wrong access to fields media_delay and tx_queue_delay.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200512150414.267198-7-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix output of rx_stats on big endian hosts

The struct hif_rx_stats contains only little endian values. Thus, it is
necessary to fix byte ordering before to use them.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200512150414.267198-6-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix wrong bytes order

The field wakeup_period_max from struct hif_mib_beacon_wake_up_period is
a u8. So, assigning it a __le16 produces a nasty bug on big-endian
architectures.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200512150414.267198-5-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix cast operator

Sparse detects that le16_to_cpup() expects a __le16 * as argument.

Change the cast operator to be compliant with sparse.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200512150414.267198-4-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: take advantage of le32_to_cpup()

le32_to_cpu(*x) can be advantageously converted in le32_to_cpup(x).

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200512150414.267198-3-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix use of cpu_to_le32 instead of le32_to_cpu

Sparse detected that le32_to_cpu should be used instead of cpu_to_le32.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200512150414.267198-2-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: use kernel types instead of c99 ones

The kernel coding style promotes the use of kernel types (u8, u16, u32,
etc...) instead of the C99 ones.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200505123757.39506-16-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: remove spaces after cast operator

The kernel coding style expects no space after cast operator. This patch
make the wfx driver compliant with this rule.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200505123757.39506-15-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix alignements of function prototypes

Some function prototypes were not correctly aligned and/or exceed 80
columns.

In some other cases, the prototypes were written on more lines than
necessary.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200505123757.39506-14-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: remove useless header inclusions

In order to keep the compilation times reasonable, we try to only
include the necessary headers (especially header included from other
headers).

This patch clean up unnecessary headers inclusions.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200505123757.39506-13-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: prefer ARRAY_SIZE instead of a magic number

When possible, we prefer to use the macro ARRAY_SIZE rather than hard
coding the number of elements.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200505123757.39506-12-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix missing 'static' keyword

Sparse tool noticed that wfx_enable_beacon() is never used outside of
sta.c. Therefore, it can be declared static.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200505123757.39506-11-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: fix missing 'static' statement

The function get_firmware() is only used from fwio.c. It can be declared
static.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200505123757.39506-10-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: poll IRQ during init

When the chip starts in SDIO mode, the external IRQ (aka Out-Of-Band
IRQ) cannot be used before to configure it. Therefore, the first
exchanges with the chip have to be done without the OOB IRQ.

This patch allow to poll the data until the OOB IRQ is correctly setup.
In order to keep the code simpler, this patch also poll data even if OOB
IRQ is not used.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200505123757.39506-9-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: introduce a way to poll IRQ

It is possible to check if an IRQ is ending by polling the control
register. This function must used with care: if an IRQ fires while the
host reads control register, the IRQ can be lost. However, it could be
useful in some cases.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200505123757.39506-8-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: use threaded IRQ with SPI

Currently, the SPI implementation use a workqueue to acknowledge IRQ
while the SDIO-OOB implementation use a threaded IRQ.

The threaded also offers the advantage to allow level triggered IRQs.

Uniformize the code and use threaded IRQ in both case. Therefore, prefer
level triggered IRQs if the user does not specify it in the DT.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200505123757.39506-7-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

staging: wfx: repair external IRQ for SDIO

When used over SDIO bus, device is able to use an external line to
signal IRQs (also called Out-Of-Band IRQ). The current code have several
problems:
  1. The ISR cannot directly acknowledge IRQ since access to the bus is
     not atomic. This patch use a threaded IRQ to solve that issue.
  2. On certain platforms, it is necessary to keep SDIO interruption
     enabled (with register SDIO_CCCR_IENx) (this part has inspired from
     the brcmfmac driver).

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://lore.kernel.org/r/20200505123757.39506-6-Jerome.Pouiller@silabs.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>