This reverts commit 95f5a6b816857ad5b607a1be25cb41ce7c4ff4b2.
Caused a two second delay before the touch screen would
work after using the pen. Disturbed the gestures.
When going into LPSR sleep, the power is taken from the GPIO bank used for the
charge state GPIOs.
When returning from LPSR sleep, the GPIO pinctrl state has to be re-initialized
in order to enable the internal pull-up.
As the GPIOs are used as inputs and no other initialization is done during the
initial probe/init of the driver, no further action is required.
Add support for recognizing all expected read back charger_mode values.
Remove unwanted side-effect causing charger_mode to be written when
unrecognized value is read back.
When reading back charger_mode and the batery is (nearly) full,
the read back charger_mode from the charger device is not necessarily the same
as the written value due to internal states being triggered by current state
if charge. A mode 0x05 (Charger) written might yield a read back value of 0x04,
which is ok when the capacity is 100% but still an indication that the charger_mode
is set to "Charger".
Also when writing mode 0x00 (Off), the read back value might yield 0x01..0x03,
which has to be accepted as "Off".
Add post_fgcc_change_delay_us module parameter with default value
100000 us.
Move delay into FGCC enable/disable function.
Add delay both after FGCC enable and disable.
Differentiate SNVS button click time for LPSR sleep
and power on:
Power off -> On - 500ms
LPSR Sleep -> Wake-up - 50ms
Turn off GPIO wake-up hack when not in LPSR sleep
This reverts commit cc7fffa6e20c6b90568f745c51e6f33e0b91c694.
Code is moved to pm-imx7.
We want to have 500ms ON_TIME for power on, and
50ms ON_TIME from LPSR sleep
This reverts commit a5410575ebbde14b55f66af5782779f31e14efe7.
Caused some partial updates, and touch didn't work for a couple of
seconds after boot when waiting for firmware update.
As the dpacc and dqacc registers change over time, these are skipped in addition
to other learned values to prevent them from being overwritten on every boot.
Unlock and re-lock of extra config registers were separated into common
functions to be used both in initial write_custom_params and new verify/write
routine.
Verification of the RelaxCfg register was also added to the new verify/write routine.
- Set 'verify' as the default config-update mode
- Add flag in max77818_of_property (is_learned_value) in order to prevent config
values given in DT as initial values that is expected to change from being
reset when device reboots and params are synced to curent DT.
The power_supply get_property handler is protected by a flag indicating
when the config init/update thread is complete, but this flag was not
synchronized.
In addition to this, the flag is now cleared before the driver is registered
as a power_supply device to properly tell the power_supply initiation to wait.
Add module parameter enabling complete FG config rewrite from DT or
only custom params update from DT depending on what is required.
The driver may be given either "max77818_battery.config_update=complete" or
"max77818_battery.config_update=partial" respectively through the kernel commandline
from u-boot.
Versioning scheme may then be implemented outside of the kernel if required,
and which update to apply to a given device will then be chosen by update scripts.
It adds a separate dts/dtb for wifi calibration, which works with BCMDHD
wifi driver instead of BRCMFMAC. Comparing to mainstream zero-sugar.dts,
it adds 'wifi-host' property for SDIO slot and deletes bcrmf child node
from there, as the node is only required by BRCMFMAC driver.
Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
To make the change history clear, let's copy zero-sugar_defconfig as
zero-sugar-wifi-cal_defconfig with zero change first, and make necessary
changes on top of it later.
Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
As the first step of syncing up with mainstream dts and defconfig, let's
remove the outdated versions and add updated ones back later.
Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
It operates on GPIO DIGITIZER_PWR_EN via regulator API to turn off
VDD_3V3_DIGITIZER for 'mem' sleep. While at it, let's call pinctrl
functions and wacom_setup_device() for 'mem' sleep only, as they are not
required for 'standby' sleep.
Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
To get GPIO1/2 LPSR wakeup work, we have commit 57673afb8d27 ("zero-sugar:
init SNVS for LPSR GPIO wakeup") in U-Boot to set bit 7 of SNVS register
0x48. Unfortunately, it brings us a side effect, that is setting TOP
(Turn off System Power) bit of SNVS LPCR register results in an immeidate
reset instead of poweroff. To work around the issue, let's clear the bit
right before setting TOP bit for powering system off.
Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
In order to read the current GPIO state regardless of the current controller
mode, and thus regardless of whether the GPIO irq is enabled, a direct
read of the raw GPIO state is done directly from the sysfs attribute_show
method.
Required synchronization was added to the access method to prevent race
if the attribute is read at the same time the irq handler is running.
When reading the otg1_chargermode property, a list of valid strings are
returned.
Valid enum values may be given when writing to the otg1_chargermode
property, in addition to one of the strings returned when reading
the property (Charger, OTG_supply, Off).
Fix flaw in probe causing IRQ init to be performed in FGCC mode and not when
FGCC is disabled (which is the intension).
Simplify FGCC re-enable code during FG driver init.
The current_max property was not read correctly in FGCC mode,
due to missing errorhandling when charger device is not accessible
over the I2C bus.
An error message is now returned instead of a false value when FGCC
mode is active.
The charger regmap should not be NULL, but to be sure that the regmap is never used
if NULL or ERR_PTR, a check for this has been introduced wherever this is used in
the charger driver.
A check is also done in the MFD driver before trying to initialize the charger irq.
In addition to this, a bug causing a stack dump during boot was found, causing
the powersupply subsystem's initial calls to get_property to fail due to the
mutex was created too late in the probe routine.
MAX77818 MFD driver:
- Let drvdata->regmap_chg remain NULL if not initialized,
for simple validity check
- Remove no longer used label
MAX77818 charger driver:
- Indicate error if chgin_stat_gpio state/wcin_stat_gpio states cannot be read
- Let chgin_stat_gpio/wcin_stat_gpio remain NULL if not initialized,
for simple validity check
- Define MODE_ALL_OFF = 0x00 (POWER_SUPPLY_MODE_ALL_OFF)
- Add initial charger_mode read from device during initialization,
and set to Charger if unknown mode is read
(not corresponding to defined power supply charger modes)
- charger_update routine no longer returns a value
MAX77818 battery/FG driver:
- Define CONFIG_FGCC_BIT
- Add mutex to drvdata
- Improve variable naming
- Add mutex locking to charger_mode get/set functions
- Add proper FGCC mode restoration check in charger_mode get function
- Add warnings if regmap read/writes fails during custom param init
charger_mode property was added to FG driver in order to disable
FGCC mode before forwarding the property change request to the charger driver,
before turning the FGCC mode back on after successfully changing the charger mode.
Add support for "zombie" max77818-charger driver with GPIO based con-stat
- The max77818-battery and the max77818-charger drivers are now loaded regardless
of the failed communication with the charger device over I2C.
Adapt status_ex property to use GPIO based connection status when charger
device is offline from the I2C bus.
Tune JEITA configuration (mainly) and other settings, FGCC mode seems to work
as expected.
Disable regulator definition for SAFEOUT signals, thus leave the SAFEOUT
config as default, following CHGIN charger presence.
Add required pinctrl config for GPIO based connection status read from charger
device when this is offline from the I2C bus (100K PU).
Parameters are verified, and not-given parameters now results in
a warning and default values are kept instead of writing 0 for all
properties not found in DT.