Hi,
On Thu, Apr 12, 2018 at 12:01:59PM +0200, Hans de Goede wrote:
> On quite a few devices the battery code in the ACPI tables is buggy and
> first checks the charging status bits of the charger-IC, and if those
> report not charging it will report discharging, without looking at the
> presence of AC power or at the battery dis(charge) current from the
> fuel-gauge.
>
> This causes the wrong status to be reported for the battery in the
> following quite common scenario:
>
> 1) Plug in charger while battery is say half full, battery starts
> charging, charging state bits indicate: pre-charge or fast-charge,
> ACPI reported battery status is ok
>
> 2) When fully charged charging state bits indicate: end-of-charge,
> ACPI reported battery status is ok
>
> 3) unplug the charger, wait 1 minute, replug. Now the battery voltage is
> still above the start-charging threshold, so the charger will not start
> charging to avoid wrecking the battery by repeatedly recharging the last 1%
> capacity. The charger IC charging state bits now are all 0 (not-charging)
> and the broken ACPI code wrongly translate this to "discharging" and ends
> up setting the ACPI_BATTERY_STATE_DISCHARGING bit in its state field.
>
> Reporting this "not charging" state as discharging is confusing for users,
> making the user think his adapter/power-brick is broken or not properly
> plugged in.
>
> This commit adds a helper for handling the ACPI_BATTERY_STATE_DISCHARGING
> state. This helper checks if we're an AC and the current going out of the
> battery is 0 and in that case reports a status of "not charging" to
> userspace rather then "discharging".
>
> This replaces commit c68f0676ef7d ("ACPI / battery: Add quirk for Asus
> GL502VSK and UX305LA"), a previous fix for this which was reverted.
>
> Cc: Kai-Heng Feng <kai.heng.feng@xxxxxxxxxxxxx>
> Signed-off-by: Hans de Goede <hdegoede@xxxxxxxxxx>
> ---
Reviewed-by: Sebastian Reichel <sebastian.reichel@xxxxxxxxxxxxxxx>
-- Sebastian
> Changes in v2:
> -Report "not charging" rather then "full"
> ---
> drivers/acpi/battery.c | 15 ++++++++++++++-
> 1 file changed, 14 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
> index 1fc0feceafaf..3770ac09fd30 100644
> --- a/drivers/acpi/battery.c
> +++ b/drivers/acpi/battery.c
> @@ -200,6 +200,19 @@ static int acpi_battery_is_charged(struct acpi_battery *battery)
> return 0;
> }
>
> +static int acpi_battery_handle_discharging(struct acpi_battery *battery)
> +{
> + /*
> + * Some devices wrongly report discharging if the battery's charge level
> + * was above the device's start charging threshold atm the AC adapter
> + * was plugged in and the device thus did not start a new charge cycle.
> + */
> + if (power_supply_is_system_supplied() && battery->rate_now == 0)
> + return POWER_SUPPLY_STATUS_NOT_CHARGING;
> +
> + return POWER_SUPPLY_STATUS_DISCHARGING;
> +}
> +
> static int acpi_battery_get_property(struct power_supply *psy,
> enum power_supply_property psp,
> union power_supply_propval *val)
> @@ -215,7 +228,7 @@ static int acpi_battery_get_property(struct power_supply *psy,
> switch (psp) {
> case POWER_SUPPLY_PROP_STATUS:
> if (battery->state & ACPI_BATTERY_STATE_DISCHARGING)
> - val->intval = POWER_SUPPLY_STATUS_DISCHARGING;
> + val->intval = acpi_battery_handle_discharging(battery);
> else if (battery->state & ACPI_BATTERY_STATE_CHARGING)
> val->intval = POWER_SUPPLY_STATUS_CHARGING;
> else if (acpi_battery_is_charged(battery))
> --
> 2.17.0
>
Attachment:
signature.asc
Description: PGP signature
