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
The POWER_SUPPLY_PROP_CURRENT_MAX is used to set max current draw on CHGIN,
and the new POWER_SUPPLY_PROP_CURRENT_MAX2 (added to power-supply core for
this purpose) is used to set max current draw on WCIN.
In order for the MAX77818 driver to be able to set the max current separately
for the two VBUS lines, a new property was added (POWER_SUPPLY_PROP_CURRENT_MAX2),
enabling POWER_SUPPLY_PROP_CURRENT_MAX to configure USB1 max current draw and
POWER_SUPPLY_PROP_CURRENT_MAX2 to configure USB2 max current respectively.
The max77818-charger driver is used to set updated max current on given
interface, flipping the FGCC bit appropriately to enable charger device config
temporarily.
- Remove duplicate code for reading and writing vcom voltage
- Don't interrupt resume command if vcom not set
- Add sysfs attribute for setting vcom runtime (HACK)
- Make regulator microvolts return microvolts (was millivolts)
- Remove i2c based PGOOD usage to simplify code
- Reduce timeout value to 100ms
- Add mutex locking for enable/disable, so they don't confuse each other
- Register GPIO before regulator, to avoid race
In order to reduce the overhead as much as possible in the wait loop, the
PGOOD GPIO is used if given in devicetree. If not, the wait loop reads the
FAULT FLAG register to obtain the PGOOD status.
In order to make sure that all the rails are valid from the EPD PMIC when
sending new frames to the EPD, a wait loop has been introduced in the
regulator enable op waiting max 500 ms for PWR GOOD signal from EPD PMIC
before returning from the enable op.
The lcdif driver can then check the return code from the regulator_enable
call and if good, all the EPD power rails are ready.
Steinar Bakkemo