summaryrefslogtreecommitdiff
path: root/drivers/acpi/power.c
diff options
context:
space:
mode:
authorRafael J. Wysocki <rafael.j.wysocki@intel.com>2015-05-16 02:55:35 +0300
committerRafael J. Wysocki <rafael.j.wysocki@intel.com>2015-05-16 02:55:35 +0300
commit20dacb71ad283b9506ee7e01286a424999fb8309 (patch)
treed97ece1104f4647b0cc5205892b6313dc05bcb51 /drivers/acpi/power.c
parent6656bde5ec868d89cc803539f9edf85a89497b6a (diff)
downloadlinux-20dacb71ad283b9506ee7e01286a424999fb8309.tar.xz
ACPI / PM: Rework device power management to follow ACPI 6
The ACPI 6 specification has made some changes in the device power management area. In particular: * The D3hot power state is now supposed to be always available (instead of D3cold) and D3cold is only regarded as valid if the _PR3 object is present for the given device. * The required ordering of transitions into power states deeper than D0 is now such that for a transition into state Dx the _PSx method is supposed to be executed first, if present, and the states of the power resources the device depends on are supposed to be changed after that. * It is now explicitly forbidden to transition devices from lower-power (deeper) into higher-power (shallower) power states other than D0. Those changes have been made so the specification reflects the Windows' device power management code that the vast majority of systems using ACPI is validated against. To avoid artificial differences in ACPI device power management between Windows and Linux, modify the ACPI device power management code to follow the new specification. Add comments explaining the code flow in some unclear places. This only may affect some real corner cases in which the OS behavior expected by the firmware is different from the Windows one, but that's quite unlikely. The transition ordering change affects transitions to D1 and D2 which are rarely used (if at all) and into D3hot and D3cold for devices actually having _PR3, but those are likely to be validated against Windows anyway. The other changes may affect code calling acpi_device_get_power() or acpi_device_update_power() where ACPI_STATE_D3_HOT may be returned instead of ACPI_STATE_D3_COLD (that's why the ACPI fan driver needs to be updated too) and since transitions into ACPI_STATE_D3_HOT may remove power now, it is better to avoid this one in acpi_pm_device_sleep_state() if the "no power off" PM QoS flag is set. The only existing user of acpi_device_can_poweroff() really cares about the case when _PR3 is present, so the change in that function should not cause any problems to happen too. A plus is that PCI_D3hot can be mapped to ACPI_STATE_D3_HOT now and the compatibility with older systems should be covered automatically. In any case, if any real problems result from this, it still will be better to follow the Windows' behavior (which now is reflected by the specification too) in general and handle the cases when it doesn't work via quirks. Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Diffstat (limited to 'drivers/acpi/power.c')
-rw-r--r--drivers/acpi/power.c3
1 files changed, 2 insertions, 1 deletions
diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c
index 59a6bf707f91..1f8138f24d72 100644
--- a/drivers/acpi/power.c
+++ b/drivers/acpi/power.c
@@ -684,7 +684,8 @@ int acpi_power_get_inferred_state(struct acpi_device *device, int *state)
}
}
- *state = ACPI_STATE_D3_COLD;
+ *state = device->power.states[ACPI_STATE_D3_COLD].flags.valid ?
+ ACPI_STATE_D3_COLD : ACPI_STATE_D3_HOT;
return 0;
}