- Handle return code for regmap_write & regmap_read
- Rename some functions with misleading names
i.e "verify" when it actually writes, differentiate
between reading params from chip or device tree, etc
- Don't clear POR bit if writing data failed
- Set init complete even if "write custom params" fail,
as it will eventually time out and continue init anyhow
This prevents a screen freeze bug.
If the regulator checks the on-off bit at the same
time as the thermal driver, the regulator_enable
call will conclude that the regulator is already
active.
Then, when the thermal driver is done checking the
temperature, it will set the PMIC back to the state
it was when it started, which is off.
In this state, the regulator driver believes the
PMIC is on, and the thermal has turned it off.
This can be considered a bit of a quick fix, to make
minimal changes to the kernel at this point. The
correct way to solve this would be to make the
sy7636a_thermal driver use the regulator network, or
moving all register access code into the sy7636a mfd
and use a mutex from there.
The max77818 charger device reports a valid connection status for
the chgin interface, regardless of whether it has been disabled or not
with chgin_sel.
The charging status is thus not reported correct, as the device is not
charging from the pogo interface even if the connection state indicates
otherweiz.
In order to report a correct state to userspace, the charger connection
state is now always reported to be false for the chgin interface (as
this is always turned off as soon as the connection state changes)
In order to be able to synchronize initial register write with other
drivers possibly accessing the same registers during init, an option
to apply a mutex lock (defined at the mfd level) is introduced.
The config register is also given a requirement to be locked, as this
register holds the FGCC bit which is the main cause of this option.
Make initial sensing of device connection valid only for authenticated deviced.
Disable authenticated device connection precedure until finally implemented (TBD)
Due to uncertainty related to how safe it is to verify each custom
param during every boot, set the skip_verify flag for every custom param except
for the config register which is verified against current DT and reset if changed
for some reason since last boot.
This ensures that if an operation performed through the max77818 charger driver
was aborted by a reboot for instance, and the FGCC bit remained 0, it will be
restored to 1 after a reboot.
After changing from -fcommon which was the default in earlier gcc
releases, the dtc native build failed due to multiple declarations
of the form 'YYLTYPE yylloc'. Two of the declarations were removed,
which fixed the problem.
Quickfix.
The ci_hdrc crashes if the DR mode is set to HOST while
it is interpreting the "set MODE bits to 0xf" state.
Possible chip errata, where the ci_hdrc has to be
powered on and off to work again.
Fixed by adding a delay of 300-400ms between enabling
OTG power out and setting USB mode to HOST mode.
NOTE: This should be further investigated, as a
delay of 300-400ms in kernel code is A LOT.
Due to the normal FG driver init configuring FGCC to be enabled during its normal
run, where all custom params configured in DT are verified and restored to the
original value if changed since last boot, charger driver sync has to be done
after completion of normal init.
This is now done in a separate worker which waits for the other init to complete
using a simple completion obj.
Also, unlock mutex at early return errors.
The status_ex is read during driver initiation, but the local shadow
variable was not updated, causing the status_ex to be "not connected"
even if the device was powered on with USB-C charger connected.max77818-battery: fix initial status_ex read bug
Failed read from device is likely to occur when the charger driver
properties are read directly from the charger driver and not via
the FG driver which makes sure the FGCC mode is turned off before
trying to access the charger device.
The warnings generated clutters the journal, and cause suspicion that
the driver or device is not working properly.
Due to the USB-C connector introducing a slight delay between the detection of
a stable VBUS and the data lines making contact, the delay after setting the
USB PHY into charger detection mode before reading the detection status had to
be increased from 1 ms to 500 ms, enabling the user to use 500 ms to insert the
USB-C connector fully into the device and still get a positive CDP/DCP port
detection, enabling higher charge current where this is offered.
Operations done during FG driver initiation which address the charger driver is
collected in new init routine, which now reads initial status information required
to be shadowed in the FG driver (status_ex) and disables the chgin interface by
default.
When charger driver receives a request to set max current for the chgin
interface to 0, the CHGINSEL bit is set to 0 to disable the interface.
When it receives a request to set a non-zero max current for the chgin
interface, the CHGINSEL bit is reset to 1 to re-enable the interface.
When the FG driver receives a notification about a connection change
for the chgin interface, it set the max current for the chgin interface
to 0 (i.e turning it off) through the charger driver.
Let the kernel trigger an emergency power off when
a thermal driver reports critical temperature.
Set the timeout to 10 seconds, so that user space
can try to shutdown cleanly.
Delay for ~35ms after disabling the regulator,
to allow power ramp down to go undisturbed
Also prolong timeout of enable function to
500ms, in an attempt to recover from a bad
state where the PMIC does not report pgood
Check if lcd interface enable was a success before
setting current blank state. This fixes a bug where
the pan function failes when waiting for an interrupt,
when the driver believes the display is unblanked when
in fact it is not.
Also user space applications that call ioctl to do
blanking will be notified when the blanking failed.
During driver init, the default safe value is set rather than the max possible
input current, which might draw too much from a normal USB host not capable of
supplying extended charge current.
Add new default_current_limit param in DT.
Formerly used input_current_limit_chgin and input_current_limit_wcin params
given in DT is now used as an absolute max input current limit, in the new
dynamic max current adjustment scheme.
- Do initiation of the charger irq regmap in the MFD driver while disabling FGCC
- Initiate charger interrupts in battery driver while disabling FGCC
- Add new charger irq handler in battery driver requesting status_ex
property from charger driver while disabling FGCC
(enabling separate status for chgin/wcin)
POWER_SUPPLY_PROP_STATUS_EX_CHANGING and POWER_SUPPLY_PROP_STATUS_EX_UNKNOWN
is added to the set of defined values for the power supply status_ex property.
This is required to indicate to userspace that an interrupt has occured,
and that the connection state is changing, and if the new connection state
could not be read, the status is unknown.
In order to do a set of operations in sequence while disabling FGCC,
two macros are defined to start by disabling FGCC mode end finish by
re-enabling FGCC mode, while ensuring that the operation is not interrupted
by another similar sequence by applying the same lock as used in the
MAX77818_DO_NON_FGCC_OP macro when starting the operation and releasing
the lock when finishin the opration.
In order for the FGCC flag to be flipped from modules/drivers external to the
max77818-battery driver, the FGCC enable/disable routine and corresponding
macro doing a non-FGCC operation by flipping the FGCC bit to disable FGCC,
do the operation and re-enable FGCC is moved to an external module max77818-utils.
All operations performed by charger driver which require FGCC mode to be disabled
in order for the driver to be able to communicate with the charger device
basically do the following which now are done with the MAX77818_DO_NON_FGCC_OP
macro:
Disable FGCC
Do required operation
Re-enable FGCC
Lars Ivar Miljeteig