[PATCH] ACPI/sbs: Fix GPE storm on recent MacBookPro's.

[PATCH] ACPI/sbs: Fix GPE storm on recent MacBookPro's.

[Ronald Tschalär]

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 <rui.zhang@intel.com>
Signed-off-by: Ronald Tschalär <ronald@innovation.ch>
---
 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

Re: [PATCH] ACPI/sbs: Fix GPE storm on recent MacBookPro's.

[Rafael J. Wysocki]

On Monday, October 1, 2018 4:52:51 AM CEST Ronald Tschalär 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 <rui.zhang@intel.com>
> Signed-off-by: Ronald Tschalär <ronald@innovation.ch>
> ---
>  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!