From: Ronald Tschalär Date: Mon, 1 Oct 2018 02:52:51 +0000 (-0700) Subject: ACPI / SBS: Fix GPE storm on recent MacBookPro's X-Git-Tag: v4.20-rc1~176^2^3~1 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=ca1721c5bee77105829cbd7baab8ee0eab85b06d;p=thirdparty%2Fkernel%2Flinux.git ACPI / SBS: Fix GPE storm on recent MacBookPro's 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 Signed-off-by: Ronald Tschalär Signed-off-by: Rafael J. Wysocki --- diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c index 295b59271189d..96c5e27967f4f 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;