Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 3fbf4c0a authored by Ronald Tschalär's avatar Ronald Tschalär Committed by Greg Kroah-Hartman
Browse files

ACPI / SBS: Fix GPE storm on recent MacBookPro's 

[ Upstream commit ca1721c5bee77105829cbd7baab8ee0eab85b06d ]

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 3031cdde (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: default avatarRonald Tschalär <ronald@innovation.ch>
Signed-off-by: default avatarRafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: default avatarSasha Levin <sashal@kernel.org>
parent 5a576454

drivers/acpi/sbs.c

+6 −2
Original line number Diff line number Diff line
@@ -443,9 +443,13 @@ 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;