| Message ID | 20181001025251.GA9069@innovation.ch (mailing list archive) |
|---|---|
| State | Accepted, archived |
| Delegated to: | Rafael Wysocki |
| Headers | show |
| Series | ACPI/sbs: Fix GPE storm on recent MacBookPro's. | expand |
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!
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;
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(-)