On Apple machines, plugging-in or unplugging the power triggers a GPE
for the EC. Since these machines expose an SBS device, this GPE ends
up triggering the acpi_sbs_callback(). This in turn tries to get the
status of the SBS charger. However, on MBP13,* and MBP14,* machines,
performing the smbus-read operation to get the charger's status triggers
the EC's GPE again. The result is an endless re-triggering and handling
of that GPE, consuming significant CPU resources (> 50% in irq).
In the end this is quite similar to commit 3031cddea633 (ACPI / SBS:
Don't assume the existence of an SBS charger), except that on the above
machines a status of all 1's is returned. And like there, we just want
ignore the charger here.
Link: https://bugzilla.kernel.org/show_bug.cgi?id=198169
CC: Zhang Rui <[email protected]>
Signed-off-by: Ronald Tschal?r <[email protected]>
---
drivers/acpi/sbs.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c
index 295b59271189..96c5e27967f4 100644
--- a/drivers/acpi/sbs.c
+++ b/drivers/acpi/sbs.c
@@ -441,9 +441,13 @@ static int acpi_ac_get_present(struct acpi_sbs *sbs)
/*
* The spec requires that bit 4 always be 1. If it's not set, assume
- * that the implementation doesn't support an SBS charger
+ * that the implementation doesn't support an SBS charger.
+ *
+ * And on some MacBooks a status of 0xffff is always returned, no
+ * matter whether the charger is plugged in or not, which is also
+ * wrong, so ignore the SBS charger for those too.
*/
- if (!((status >> 4) & 0x1))
+ if (!((status >> 4) & 0x1) || status == 0xffff)
return -ENODEV;
sbs->charger_present = (status >> 15) & 0x1;
--
2.17.1
On Monday, October 1, 2018 4:52:51 AM CEST Ronald Tschal?r wrote:
> On Apple machines, plugging-in or unplugging the power triggers a GPE
> for the EC. Since these machines expose an SBS device, this GPE ends
> up triggering the acpi_sbs_callback(). This in turn tries to get the
> status of the SBS charger. However, on MBP13,* and MBP14,* machines,
> performing the smbus-read operation to get the charger's status triggers
> the EC's GPE again. The result is an endless re-triggering and handling
> of that GPE, consuming significant CPU resources (> 50% in irq).
>
> In the end this is quite similar to commit 3031cddea633 (ACPI / SBS:
> Don't assume the existence of an SBS charger), except that on the above
> machines a status of all 1's is returned. And like there, we just want
> ignore the charger here.
>
> Link: https://bugzilla.kernel.org/show_bug.cgi?id=198169
> CC: Zhang Rui <[email protected]>
> Signed-off-by: Ronald Tschal?r <[email protected]>
> ---
> drivers/acpi/sbs.c | 8 ++++++--
> 1 file changed, 6 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c
> index 295b59271189..96c5e27967f4 100644
> --- a/drivers/acpi/sbs.c
> +++ b/drivers/acpi/sbs.c
> @@ -441,9 +441,13 @@ static int acpi_ac_get_present(struct acpi_sbs *sbs)
>
> /*
> * The spec requires that bit 4 always be 1. If it's not set, assume
> - * that the implementation doesn't support an SBS charger
> + * that the implementation doesn't support an SBS charger.
> + *
> + * And on some MacBooks a status of 0xffff is always returned, no
> + * matter whether the charger is plugged in or not, which is also
> + * wrong, so ignore the SBS charger for those too.
> */
> - if (!((status >> 4) & 0x1))
> + if (!((status >> 4) & 0x1) || status == 0xffff)
> return -ENODEV;
>
> sbs->charger_present = (status >> 15) & 0x1;
>
Applied, thanks!