| Message ID | 20240406114052.4884-1-hdegoede@redhat.com |
|---|---|
| State | Accepted |
| Commit | d730192ff0246356a2d7e63ff5bd501060670eec |
| Headers | show |
| Series | ACPI: scan: Do not increase dep_unmet for already met dependencies | expand |
On Sat, Apr 6, 2024 at 1:43 PM Hans de Goede <hdegoede@redhat.com> wrote: > > On the Toshiba Encore WT10-A tablet the BATC battery ACPI device depends > on 3 other devices: > > Name (_DEP, Package (0x03) // _DEP: Dependencies > { > I2C1, > GPO2, > GPO0 > }) > > acpi_scan_check_dep() adds all 3 of these to the acpi_dep_list and then > before an acpi_device is created for the BATC handle (and thus before > acpi_scan_dep_init() runs) acpi_scan_clear_dep() gets called for both > GPIO depenencies, with free_when_met not set for the dependencies. > > Since there is no adev for BATC yet, there also is no dep_unmet to > decrement. The only result of acpi_scan_clear_dep() in this case is > dep->met getting set. > > Soon after acpi_scan_clear_dep() has been called for the GPIO dependencies > the acpi_device gets created for the BATC handle and acpi_scan_dep_init() > runs, this sees 3 dependencies on the acpi_dep_list and initializes > unmet_dep to 3. Later when the dependency for I2C1 is met unmet_dep > becomes 2, but since the 2 GPIO deps where already met it never becomes 0 > causing battery monitoring to not work. > > Fix this by modifying acpi_scan_dep_init() to not increase dep_met for > dependencies which have already been marked as being met. > > Fixes: 3ba12d8de3fa ("ACPI: scan: Reduce overhead related to devices with dependencies") > Signed-off-by: Hans de Goede <hdegoede@redhat.com> > --- > drivers/acpi/scan.c | 3 ++- > 1 file changed, 2 insertions(+), 1 deletion(-) > > diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c > index 7c157bf92695..d1464324de95 100644 > --- a/drivers/acpi/scan.c > +++ b/drivers/acpi/scan.c > @@ -1843,7 +1843,8 @@ static void acpi_scan_dep_init(struct acpi_device *adev) > if (dep->honor_dep) > adev->flags.honor_deps = 1; > > - adev->dep_unmet++; > + if (!dep->met) > + adev->dep_unmet++; Nice catch! > } > } > } > -- Applied as 6.9-rc material, thanks!
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 7c157bf92695..d1464324de95 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1843,7 +1843,8 @@ static void acpi_scan_dep_init(struct acpi_device *adev) if (dep->honor_dep) adev->flags.honor_deps = 1; - adev->dep_unmet++; + if (!dep->met) + adev->dep_unmet++; } } }
On the Toshiba Encore WT10-A tablet the BATC battery ACPI device depends on 3 other devices: Name (_DEP, Package (0x03) // _DEP: Dependencies { I2C1, GPO2, GPO0 }) acpi_scan_check_dep() adds all 3 of these to the acpi_dep_list and then before an acpi_device is created for the BATC handle (and thus before acpi_scan_dep_init() runs) acpi_scan_clear_dep() gets called for both GPIO depenencies, with free_when_met not set for the dependencies. Since there is no adev for BATC yet, there also is no dep_unmet to decrement. The only result of acpi_scan_clear_dep() in this case is dep->met getting set. Soon after acpi_scan_clear_dep() has been called for the GPIO dependencies the acpi_device gets created for the BATC handle and acpi_scan_dep_init() runs, this sees 3 dependencies on the acpi_dep_list and initializes unmet_dep to 3. Later when the dependency for I2C1 is met unmet_dep becomes 2, but since the 2 GPIO deps where already met it never becomes 0 causing battery monitoring to not work. Fix this by modifying acpi_scan_dep_init() to not increase dep_met for dependencies which have already been marked as being met. Fixes: 3ba12d8de3fa ("ACPI: scan: Reduce overhead related to devices with dependencies") Signed-off-by: Hans de Goede <hdegoede@redhat.com> --- drivers/acpi/scan.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)