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

From: Ronald Tschalär
Date: Sun Sep 30 2018 - 23:00:41 EST


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@xxxxxxxxx>
Signed-off-by: Ronald Tschalär <ronald@xxxxxxxxxxxxx>
---
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