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

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-ID: <20181001025251.GA9069@innovation.ch>
Date:   Sun, 30 Sep 2018 19:52:51 -0700
From:   Ronald Tschalär <ronald@...ovation.ch>
To:     "Rafael J. Wysocki" <rjw@...ysocki.net>,
        Len Brown <lenb@...nel.org>
Cc:     Zhang Rui <rui.zhang@...el.com>, linux-acpi@...r.kernel.org,
        linux-kernel@...r.kernel.org
Subject: [PATCH] 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
CC: Zhang Rui <rui.zhang@...el.com>
Signed-off-by: Ronald Tschalär <ronald@...ovation.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