ACPI/sbs: Fix GPE storm on recent MacBookPro's.
PATCH 1/1 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.
--- drivers/acpi/sbs.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)
drivers/acpi/sbs.c +6 -2
@@ -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 ;
Signature · 1 line
2.17.1
Rafael J. Wysocki
AppliedQuoted 31 lines · CEST Ronald Tschalär
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.CC Zhang Rui <[email protected]>Signed-off-by Ronald Tschalär <[email protected]>--- drivers/acpi/sbs.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)drivers/acpi/sbs.c +1
-1@@ -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.
drivers/acpi/sbs.c static int acpi_ac_get_present(struct acpi_sbs *sbs) · line 453
Quoted 10 lines
drivers/acpi/sbs.c +5
-1+* +* 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!