linux-stable.git/drivers/acpi, branch v3.16.4

ACPI / video: disable native backlight for ThinkPad X201s

2014-10-05T20:41:02+00:00

commit 789eeea128925741e0a105357bebf8855d3bcdee upstream.

The ThinkPad X201s has a working ACPI video backlight interface and is
shipped before Win8; then there is BIOS update that starts to query
_OSI("Windows 2012") and that would make our video module stop creating
backlight interface and caused problem for the user. Add it to the DMI
table to disable native backlight to fix this problem.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=81691
Link: https://bugzilla.kernel.org/show_bug.cgi?id=51231
Reported-and-tested-by: Yves-Alexis Perez 
Signed-off-by: Aaron Lu 
Signed-off-by: Rafael J. Wysocki 
Signed-off-by: Greg Kroah-Hartman

ACPI / scan: Correct error return value of create_modalias()

2014-10-05T20:41:02+00:00

commit 98d28d0e59160d2d6cb3f6a9050723ac40f89669 upstream.

There is a typo, it should be negative -errno instead.

Signed-off-by: Mika Westerberg 
Signed-off-by: Rafael J. Wysocki 
Signed-off-by: Greg Kroah-Hartman

ACPI / hotplug: Generate online uevents for ACPI containers

2014-10-05T20:41:02+00:00

commit 8ab17fc92e49bc2b8fff9d220c19bf50ec9c1158 upstream.

Commit 46394fd01 (ACPI / hotplug: Move container-specific code out of
the core) removed the generation of "online" uevents for containers,
because "add" uevents are now generated for them automatically when
container system devices are registered.  However, there are user
space tools that need to be notified when the container and all of
its children have been enumerated, which doesn't happen any more.

For this reason, add a mechanism allowing "online" uevents to be
generated for ACPI containers after enumerating the container along
with all of its children.

Fixes: 46394fd01 (ACPI / hotplug: Move container-specific code out of the core)
Reported-and-tested-by: Yasuaki Ishimatsu 
Signed-off-by: Rafael J. Wysocki 
Signed-off-by: Greg Kroah-Hartman

ACPI / platform / LPSS: disable async suspend/resume of LPSS devices

2014-10-05T20:41:02+00:00

commit 457920817e645a7dee42c2a75c81c5ed8e12ee1c upstream.

On some systems (Asus T100 in particular) there are strict ordering
dependencies between LPSS devices with respect to power management
that break if they suspend/resume asynchronously.

In theory it should be possible to follow those dependencies in the
async suspend/resume case too (the ACPI tables tell as that the
dependencies are there), but since we're missing infrastructure
for that at the moment, disable async suspend/resume for all of
the LPSS devices for the time being.

Link: http://marc.info/?l=linux-acpi&m=141158962321905&w=2
Fixes: 8ce62f85a81f (ACPI / platform / LPSS: Enable async suspend/resume of LPSS devices)
Signed-off-by: Li Aubrey 
Signed-off-by: Fu Zhonghui 
[ rjw: Changelog ]
Signed-off-by: Rafael J. Wysocki 
Signed-off-by: Greg Kroah-Hartman

ACPICA: Update to GPIO region handler interface.

2014-10-05T20:41:02+00:00

commit 75ec6e55f1384548311a13ce4fcb39c516053314 upstream.

Changes to correct several GPIO issues:

1) The update_rule in a GPIO field definition is now ignored;
a read-modify-write operation is never performed for GPIO fields.
(Internally, this means that the field assembly/disassembly
code is completely bypassed for GPIO.)

2) The Address parameter passed to a GPIO region handler is
now the bit offset of the field from a previous Connection()
operator. Thus, it becomes a "Pin Number Index" into the
Connection() resource descriptor.

3) The bit_width parameter passed to a GPIO region handler is
now the exact bit width of the GPIO field. Thus, it can be
interpreted as "number of pins".

Overall, we can now say that the region handler interface
to GPIO handlers is a raw "bit/pin" addressed interface, not
a byte-addressed interface like the system_memory handler interface.

Signed-off-by: Bob Moore 
Signed-off-by: Lv Zheng 
Signed-off-by: Rafael J. Wysocki 
Signed-off-by: Greg Kroah-Hartman

Revert "ACPI / battery: fix wrong value of capacity_now reported when fully charged"

2014-10-05T20:40:59+00:00

commit 508b3c677601797f2d51df3df5caa436dd235cb9 upstream.

This reverts commit 232de5143790 ("ACPI / battery: fix wrong value of
capacity_now reported when fully charged")

There is nothing wrong or unexpected about 'capacity_now' increasing above
the last 'full_charge_capacity' value. Different charging cycles will cause
'full_charge_capacity' to vary, both up and down.  Good battery firmwares
will update 'full_charge_capacity' when the current charging cycle is
complete, increasing it if necessary. It might even go above
'design_capacity' on a fresh and healthy battery.

Capping 'capacity_now' to 'full_charge_capacity' is plain wrong, and
printing a warning if this doesn't happen to match the 'design_capacity'
is both annoying and terribly wrong.

This results in bogus warnings on perfectly working systems/firmwares:

 [Firmware Bug]: battery: reported current charge level (39800) is higher than reported maximum charge level (39800).

and wrong values being reported for 'capacity_now' and
'full_charge_capacity' after the warning has been triggered.

Fixes: 232de5143790 ("ACPI / battery: fix wrong value of capacity_now reported when fully charged")
Signed-off-by: Bjørn Mork 
Signed-off-by: Rafael J. Wysocki 
Signed-off-by: Greg Kroah-Hartman

ACPI / LPSS: complete PM entries for LPSS power domain

2014-10-05T20:40:59+00:00

commit f4168b617ac09986c4333accaff5d8ba5a9db7bf upstream.

PM entries of LPSS power domain were not implemented correctly
in commit c78b0830667a "ACPI / LPSS: custom power domain for LPSS".

This patch fixes and completes these PM entries.

Fixes: c78b0830667a (ACPI / LPSS: custom power domain for LPSS)
Signed-off-by: Li Aubrey 
Signed-off-by: Mika Westerberg 
Signed-off-by: Fu Zhonghui 
Signed-off-by: Rafael J. Wysocki 
Signed-off-by: Greg Kroah-Hartman

ACPI / RTC: Fix CMOS RTC opregion handler accesses to wrong addresses

2014-10-05T20:40:59+00:00

commit 9389f46e9782ea5e56fbd7b2e59ba7c08f3ba86b upstream.

The value64 parameter is an u64 point that used to transfer the value
for write to CMOS, or used to return the value that's read from CMOS.

The value64 is an u64 point, so don't need get address again. It causes
acpi_cmos_rtc_space_handler always return 0 to reader and didn't write
expected value to CMOS.

Signed-off-by: Lee, Chun-Yi 
Signed-off-by: Rafael J. Wysocki 
Signed-off-by: Greg Kroah-Hartman

ACPI / video: Disable native_backlight on HP ENVY 15 Notebook PC

2014-09-17T16:22:11+00:00

commit 84c34858a85ecf9dabd72847d860c7d3fb7536e7 upstream.

Link: https://bugs.freedesktop.org/show_bug.cgi?id=81515
Reported-and-tested-by: Hohahiu 
Signed-off-by: Hans de Goede 
Signed-off-by: Rafael J. Wysocki 
Signed-off-by: Greg Kroah-Hartman

ACPI / video: Add a disable_native_backlight quirk

2014-09-17T16:22:11+00:00

commit 5f24079b021cd3147c8d24ba65833f7a0df7e80d upstream.

Some laptops have a working acpi_video backlight control, and using native
backlight on these causes a regression where backlight control does not work
when userspace is not handling brightness key events. Disable native_backlight
on these to fix this.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=81691
Reported-and-tested-by: Andre Müller 
Signed-off-by: Hans de Goede 
Signed-off-by: Rafael J. Wysocki 
Signed-off-by: Greg Kroah-Hartman