03 Feb, 2015
1 commit
-
Revert commit 6c17ee44d524 (ACPI / LPSS: introduce a 'proxy' device
to power on LPSS for DMA), as it introduced registration and probe
ordering problems between devices on the LPSS that may lead to full
hard system hang on boot in some cases.
04 Dec, 2014
1 commit
-
After commit b2b49ccbdd54 (PM: Kconfig: Set PM_RUNTIME if PM_SLEEP is
selected) PM_RUNTIME is always set if PM is set, so quite a few
depend on CONFIG_PM.Replace CONFIG_PM_RUNTIME with CONFIG_PM in the ACPI core code.
Reviewed-by: Ulf Hansson
Acked-by: Kevin Hilman
Signed-off-by: Rafael J. Wysocki
12 Nov, 2014
3 commits
-
The LPSS DMA controller does not have _PS0 and _PS3 methods. Moreover it can be
powered off automatically whenever the last LPSS device goes down. In case of
no power any access to the DMA controller will hang the system. The behaviour
is reproduced on some HP laptops based on Intel Bay Trail [1] as well as on
Asus T100 transformer.This patch introduces a so called 'proxy' device that has the knobs to handle a
power of the LPSS island. When the system needs to program the DMA controller
it calls to the ACPI LPSS power domain callbacks that wake or suspend the
'proxy' device.[1] http://www.spinics.net/lists/dmaengine/msg01514.html
Suggested-by: Rafael J. Wysocki
Signed-off-by: Andy Shevchenko
Tested-by: Scott Ashcroft
Signed-off-by: Rafael J. Wysocki -
The LPSS DMA controller would like to use the specific PM domain callbacks
during early stage, namely in ->probe(). This patch moves the specific PM
domain assignment early to be accessible during a whole life time of the device
in the system.Suggested-by: Rafael J. Wysocki
Signed-off-by: Andy Shevchenko
Tested-by: Scott Ashcroft
Signed-off-by: Rafael J. Wysocki -
Currently the LPSS devices are located in the different power domains depends
on LPSS_SAVE_CTX flag. We would like to use the specific power domain for all
LPSS devices.The LPSS DMA controller has no knobs to control its power state. The specific
power domain implementation will handle this case. The patch does a preparation
for that.Signed-off-by: Andy Shevchenko
Tested-by: Scott Ashcroft
Signed-off-by: Rafael J. Wysocki
29 Sep, 2014
1 commit
25 Sep, 2014
2 commits
-
Adding a check for UART Auto Flow Control feature and only
enabling the RTS override when it's not supported. RTS
override is not needed when Auto Flow Control is used and
they shouldn't be used together.Signed-off-by: Heikki Krogerus
Signed-off-by: Rafael J. Wysocki -
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
Cc: 3.16+ # 3.16+
[ rjw: Changelog ]
Signed-off-by: Rafael J. Wysocki
21 Sep, 2014
1 commit
09 Sep, 2014
1 commit
-
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
Cc: 3.16+ # 3.16+
Signed-off-by: Rafael J. Wysocki
03 Sep, 2014
4 commits
-
Nothing requires it anymore. The PWM driver no longer
uses clk framework to get the rate.Signed-off-by: Heikki Krogerus
Reviewed-by: Andy Shevchenko
Acked-by: Mika Westerberg
Signed-off-by: Rafael J. Wysocki -
The I2C controllers on Baytrail can get the clock from
100MHz or 133MHz source clock. The first bits in the private
clock parameter register indicates which one is being used.Signed-off-by: Heikki Krogerus
Acked-by: Mika Westerberg
Signed-off-by: Rafael J. Wysocki -
It was used to provide the correct con_id for the dma
driver, but it's not needed. Even if the driver requests a
clock with the con_id, it still gets the correct clock. The
device name is enough to match a single clock.Signed-off-by: Heikki Krogerus
Acked-by: Andy Shevchenko
Acked-by: Mika Westerberg
Signed-off-by: Rafael J. Wysocki -
Replace the booleans with a single flags member variable.
Signed-off-by: Heikki Krogerus
Reviewed-by: Andy Shevchenko
Acked-by: Mika Westerberg
Signed-off-by: Rafael J. Wysocki
26 Aug, 2014
1 commit
-
Enable more identifiers for the existing devices for Intel Braswell and
Cherryview.Signed-off-by: Alan Cox
Signed-off-by: Mika Westerberg
Signed-off-by: Rafael J. Wysocki
01 Aug, 2014
1 commit
-
INT3438 is the ADSP device on Wildcat Point platform
with 2 DW DMA engines built In. The DMA engines are
used for DSP FW loading and audio data transferring.
These DMA engine probing need the clock, without it,
probing may failed and can't go forward.Add LPSS device "INT3438" for Wildcat Point PCH, to
provide clock for its ADSP DMA engine probing.Signed-off-by: Jie Yang
Signed-off-by: Rafael J. Wysocki
17 Jun, 2014
1 commit
-
On Intel Baytrail, some I2C host controllers are held in reset when the OS
gets control. This causes the driver to fail to detect the hardware
properly.Fix this so that we make sure that the I2C host controller is not in reset
when the driver gets probe'd.Signed-off-by: Mika Westerberg
Signed-off-by: Rafael J. Wysocki
04 Jun, 2014
1 commit
-
…fael/linux-pm into next
Pull ACPI and power management updates from Rafael Wysocki:
"ACPICA is the leader this time (63 commits), followed by cpufreq (28
commits), devfreq (15 commits), system suspend/hibernation (12
commits), ACPI video and ACPI device enumeration (10 commits each).We have no major new features this time, but there are a few
significant changes of how things work. The most visible one will
probably be that we are now going to create platform devices rather
than PNP devices by default for ACPI device objects with _HID. That
was long overdue and will be really necessary to be able to use the
same drivers for the same hardware blocks on ACPI and DT-based systems
going forward. We're not expecting fallout from this one (as usual),
but it's something to watch nevertheless.The second change having a chance to be visible is that ACPI video
will now default to using native backlight rather than the ACPI
backlight interface which should generally help systems with broken
Win8 BIOSes. We're hoping that all problems with the native backlight
handling that we had previously have been addressed and we are in a
good enough shape to flip the default, but this change should be easy
enough to revert if need be.In addition to that, the system suspend core has a new mechanism to
allow runtime-suspended devices to stay suspended throughout system
suspend/resume transitions if some extra conditions are met
(generally, they are related to coordination within device hierarchy).
However, enabling this feature requires cooperation from the bus type
layer and for now it has only been implemented for the ACPI PM domain
(used by ACPI-enumerated platform devices mostly today).Also, the acpidump utility that was previously shipped as a separate
tool will now be provided by the upstream ACPICA along with the rest
of ACPICA code, which will allow it to be more up to date and better
supported, and we have one new cpuidle driver (ARM clps711x).The rest is improvements related to certain specific use cases,
cleanups and fixes all over the place.Specifics:
- ACPICA update to upstream version 20140424. That includes a number
of fixes and improvements related to things like GPE handling,
table loading, headers, memory mapping and unmapping, DSDT/SSDT
overriding, and the Unload() operator. The acpidump utility from
upstream ACPICA is included too. From Bob Moore, Lv Zheng, David
Box, David Binderman, and Colin Ian King.- Fixes and cleanups related to ACPI video and backlight interfaces
from Hans de Goede. That includes blacklist entries for some new
machines and using native backlight by default.- ACPI device enumeration changes to create platform devices rather
than PNP devices for ACPI device objects with _HID by default. PNP
devices will still be created for the ACPI device object with
device IDs corresponding to real PNP devices, so that change should
not break things left and right, and we're expecting to see more
and more ACPI-enumerated platform devices in the future. From
Zhang Rui and Rafael J Wysocki.- Updates for the ACPI LPSS (Low-Power Subsystem) driver allowing it
to handle system suspend/resume on Asus T100 correctly. From
Heikki Krogerus and Rafael J Wysocki.- PM core update introducing a mechanism to allow runtime-suspended
devices to stay suspended over system suspend/resume transitions if
certain additional conditions related to coordination within device
hierarchy are met. Related PM documentation update and ACPI PM
domain support for the new feature. From Rafael J Wysocki.- Fixes and improvements related to the "freeze" sleep state. They
affect several places including cpuidle, PM core, ACPI core, and
the ACPI battery driver. From Rafael J Wysocki and Zhang Rui.- Miscellaneous fixes and updates of the ACPI core from Aaron Lu,
Bjørn Mork, Hanjun Guo, Lan Tianyu, and Rafael J Wysocki.- Fixes and cleanups for the ACPI processor and ACPI PAD (Processor
Aggregator Device) drivers from Baoquan He, Manuel Schölling, Tony
Camuso, and Toshi Kani.- System suspend/resume optimization in the ACPI battery driver from
Lan Tianyu.- OPP (Operating Performance Points) subsystem updates from Chander
Kashyap, Mark Brown, and Nishanth Menon.- cpufreq core fixes, updates and cleanups from Srivatsa S Bhat,
Stratos Karafotis, and Viresh Kumar.- Updates, fixes and cleanups for the Tegra, powernow-k8, imx6q,
s5pv210, nforce2, and powernv cpufreq drivers from Brian Norris,
Jingoo Han, Paul Bolle, Philipp Zabel, Stratos Karafotis, and
Viresh Kumar.- intel_pstate driver fixes and cleanups from Dirk Brandewie, Doug
Smythies, and Stratos Karafotis.- Enabling the big.LITTLE cpufreq driver on arm64 from Mark Brown.
- Fix for the cpuidle menu governor from Chander Kashyap.
- New ARM clps711x cpuidle driver from Alexander Shiyan.
- Hibernate core fixes and cleanups from Chen Gang, Dan Carpenter,
Fabian Frederick, Pali Rohár, and Sebastian Capella.- Intel RAPL (Running Average Power Limit) driver updates from Jacob
Pan.- PNP subsystem updates from Bjorn Helgaas and Fabian Frederick.
- devfreq core updates from Chanwoo Choi and Paul Bolle.
- devfreq updates for exynos4 and exynos5 from Chanwoo Choi and
Bartlomiej Zolnierkiewicz.- turbostat tool fix from Jean Delvare.
- cpupower tool updates from Prarit Bhargava, Ramkumar Ramachandra
and Thomas Renninger.- New ACPI ec_access.c tool for poking at the EC in a safe way from
Thomas Renninger"* tag 'pm+acpi-3.16-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (187 commits)
ACPICA: Namespace: Remove _PRP method support.
intel_pstate: Improve initial busy calculation
intel_pstate: add sample time scaling
intel_pstate: Correct rounding in busy calculation
intel_pstate: Remove C0 tracking
PM / hibernate: fixed typo in comment
ACPI: Fix x86 regression related to early mapping size limitation
ACPICA: Tables: Add mechanism to control early table checksum verification.
ACPI / scan: use platform bus type by default for _HID enumeration
ACPI / scan: always register ACPI LPSS scan handler
ACPI / scan: always register memory hotplug scan handler
ACPI / scan: always register container scan handler
ACPI / scan: Change the meaning of missing .attach() in scan handlers
ACPI / scan: introduce platform_id device PNP type flag
ACPI / scan: drop unsupported serial IDs from PNP ACPI scan handler ID list
ACPI / scan: drop IDs that do not comply with the ACPI PNP ID rule
ACPI / PNP: use device ID list for PNPACPI device enumeration
ACPI / scan: .match() callback for ACPI scan handlers
ACPI / battery: wakeup the system only when necessary
power_supply: allow power supply devices registered w/o wakeup source
...
30 May, 2014
1 commit
-
Prevent platform devices from being created for ACPI LPSS devices
if CONFIG_X86_INTEL_LPSS is unset by compiling out the LPSS scan
handler's callbacks only in that case and still compiling its device
ID list in and registering the scan handler in either case.This change is based on a prototype from Zhang Rui.
Signed-off-by: Rafael J. Wysocki
Reviewed-by: Mika Westerberg
25 May, 2014
4 commits
-
This creates fractional divider type clock for the ones that
have it. It is needed by the UART driver as the clock rate must
accommodate to the requested baud rate.Signed-off-by: Heikki Krogerus
Signed-off-by: Rafael J. Wysocki -
A power domain where we save the context of the additional
LPSS registers. We need to do this or all LPSS devices are
left in reset state when resuming from D3 on some Baytrails.
The devices with the fractional clock divider also have
zeros for N and M values after resuming unless they are
reset.Li Aubrey found the root cause for the issue. The idea of
using power domain for LPSS came from Mika Westerberg.Reported-by: Jin Yao
Suggested-by: Li Aubrey
Suggested-by: Mika Westerberg
Tested-by: Mika Westerberg
Signed-off-by: Heikki Krogerus
[rjw: Added the .complete() callback to the PM domain, fixed build
warning on 32-bit.]
Signed-off-by: Rafael J. Wysocki -
To seed up suspend and resume of devices included into Intel SoCs
handled by the ACPI LPSS driver during system suspend, make
acpi_lpss_create_device() call device_enable_async_suspend() for
every device created by it.This requires acpi_create_platform_device() to be modified to return
a pointer to struct platform_device instead of an int. As a result,
acpi_create_platform_device() cannot be pointed to by the .attach
pointer in platform_handler directly any more, so a simple wrapper
around it is necessary for this purpose. That, in turn, allows the
second unused argument of acpi_create_platform_device() to be
dropped, which is an improvement.Tested-by: Heikki Krogerus
Signed-off-by: Rafael J. Wysocki
23 May, 2014
1 commit
-
Now that the x86 dynamic IRQ allocation problem has been resolved with
commmit 62a08ae2a576 (genirq: x86: Ensure that dynamic irq allocation does
not conflict), we can add back Baytrail-T ACPI ID to the pinctrl driver.This makes the driver to work on Asus T100 where it is needed for several
things like ACPI GPIO events and SD card detection.References: https://bugzilla.kernel.org/show_bug.cgi?id=68291
Acked-by: Rafael J. Wysocki
Signed-off-by: Jin Yao
Signed-off-by: Mika Westerberg
Signed-off-by: Linus Walleij
20 Mar, 2014
1 commit
-
* pm-qos:
PM / QoS: Add type to dev_pm_qos_add_ancestor_request() arguments
ACPI / LPSS: Support for device latency tolerance PM QoS
ACPI / scan: Add bind/unbind callbacks to struct acpi_scan_handler
PM / QoS: Introcuce latency tolerance device PM QoS type
PM / QoS: Add no_constraints_value field to struct pm_qos_constraints
PM / QoS: Rename device resume latency QoS items* pm-domains:
PM / domains: Turn latency warning into debug message* pm-drivers:
PM: Add pm_runtime_suspend|resume_force functions
PM / runtime: Fetch runtime PM callbacks using a macro
19 Feb, 2014
1 commit
-
Intel BayTrail LPSS consists of two PWM controllers which can
be enumerated from ACPI namespace. This change will cause
platform device objects to be created for Intel BayTrail PWM
controllers which will allow the pwm-lpss driver to bind to them
and handle those devices.Signed-off-by: Chew, Chiau Ee
Signed-off-by: Rafael J. Wysocki
11 Feb, 2014
1 commit
-
Add a new routine, acpi_lpss_set_ltr(), for setting latency tolerance
values for LPSS devices having LTR (Latency Tolerance Reporting)
registers. Add .bind()/.unbind() callbacks to lpss_handler to set
the LPSS devices' power.set_latency_tolerance callback pointers to
acpi_lpss_set_ltr() during device addition and to clear them on
device removal, respectively.That will cause the device latency tolerance PM QoS to work for
the devices in question as documented.This changeset includes a fix from Mika Westerberg.
Signed-off-by: Rafael J. Wysocki
18 Jan, 2014
1 commit
-
This reverts commit f6308b36c411 (ACPI: Add BayTrail SoC GPIO and LPSS
ACPI IDs), because it causes the Alan Cox' ASUS T100TA to "crash and
burn" during boot if the Baytrail pinctrl driver is compiled in.Fixes: f6308b36c411 (ACPI: Add BayTrail SoC GPIO and LPSS ACPI IDs)
Reported-by: One Thousand Gnomes
Requested-by: Linus Walleij
Signed-off-by: Rafael J. Wysocki
30 Nov, 2013
1 commit
-
This adds the new ACPI ID (INT33FC) for the BayTrail GPIO
banks as seen on a BayTrail M System-On-Chip platform. This
ACPI ID is used by the BayTrail GPIO (pinctrl) driver to
manage the Low Power Subsystem (LPSS).Signed-off-by: Paul Drews
Acked-by: Linus Walleij
Signed-off-by: Rafael J. Wysocki
16 Nov, 2013
1 commit
-
* acpi-lpss:
ACPI / LPSS: add ACPI IDs for newer Intel PCHs
13 Nov, 2013
1 commit
-
Some recent Intel PCHs with LPSS have different ACPI IDs for the LPSS
devices, so add these to the list as well.Signed-off-by: Mika Westerberg
Signed-off-by: Rafael J. Wysocki
11 Oct, 2013
1 commit
-
There is an additional bit in the GENERAL register on newer
silicon that needs to be set or UART's RTS pin fails to
reflect the flow control settings in the Modem Control
Register.This will fix an issue where the RTS pin of the UART stays
always at 1.8V, regardless of the register settings.Signed-off-by: Heikki Krogerus
Signed-off-by: Rafael J. Wysocki
02 Sep, 2013
1 commit
-
Intel LPSS devices that are enumerated from ACPI have both MMIO and IRQ
resources returned in their _CRS method. However, Apple Macbook Air with
Haswell has LPSS devices enumerated from PCI bus instead and _CRS method
returns only an interrupt number (but the device has _HID set that causes
the scan handler to match it).The current ACPI / LPSS code sets pdata->dev_desc only when MMIO resource
is found for the device and in case of Macbook Air it is never found. That
leads to a NULL pointer dereference in register_device_clock().Correct this by always setting the pdata->dev_desc.
Reported-and-tested-by: Imre Kaloz
Signed-off-by: Mika Westerberg
Cc: 3.10+ # 3.10+
Signed-off-by: Rafael J. Wysocki
28 Jun, 2013
1 commit
-
* acpi-lpss:
ACPI / LPSS: override SDIO private register space size from ACPI tables
ACPI / LPSS: mask the UART TX completion interrupt
ACPI / LPSS: add support for Intel BayTrailConflicts:
drivers/acpi/acpi_lpss.c (with commit b9e95fc)
20 Jun, 2013
1 commit
-
Commit 7cd8407 (ACPI / PM: Do not execute _PS0 for devices without
_PSC during initialization) introduced a regression on some systems
with Intel Lynxpoint Low-Power Subsystem (LPSS) where some devices
need to be powered up during initialization, but their device objects
in the ACPI namespace have _PS0 and _PS3 only (without _PSC or power
resources).To work around this problem, make the ACPI LPSS driver power up
devices it knows about by using a new helper function
acpi_device_fix_up_power() that does all of the necessary
sanity checks and calls acpi_dev_pm_explicit_set() to put the
device into D0.Reported-and-tested-by: Mika Westerberg
Signed-off-by: Rafael J. Wysocki
19 Jun, 2013
3 commits
-
The SDIO device in Lynxpoint has its LTR registers reserved for a
WiFi device (a child of the SDIO device) in the ACPI namespace even
though those registers physically belong to the SDIO device itself.
In order to be able to access the SDIO LTR registers from the ACPI
LPSS driver for diagnostic purposes we need to use a size override
for the SDIO private register space.Add a possibility to override the size of the private register space
of an LPSS device provided by the ACPI tables in the ACPI LPSS driver
and set the correct size for the SDIO device in there.[rjw: Changelog]
Signed-off-by: Mika Westerberg
Signed-off-by: Rafael J. Wysocki -
Intel LPSS provides an extra TX byte counter and an extra TX
completion interrupt for some of its bus controllers. However,
there is no use for the extra UART interrupt and it has to be
masked out during initialization.Otherwise, if the firmware does not mask the interrupt and
the driver does not clear it, it may cause an interrupt flood
freezing the board to happen.Add code masking that problematic interrupt to the ACPI LPSS driver.
[rjw: Changelog]
Signed-off-by: Heikki Krogerus
Signed-off-by: Rafael J. Wysocki -
Intel BayTrail has almost the same Low Power Subsystem than Lynxpoint with
few differences. Peripherals are clocked with different speeds (typically
lower) and the clock is not always gated. To support this we add
possibility to share a common fixed rate clock and make clock gating
optional.Signed-off-by: Mika Westerberg
Acked-by: Mike Turquette
Signed-off-by: Rafael J. Wysocki
14 May, 2013
1 commit
-
The DMA controller in Lynxpoint is enumerated as a regular ACPI device now. To
work properly it is using the LPSS root clock as a functional clock. That's why
we have to register the clock device accordingly to the ACPI ID of the DMA
controller. The acpi_lpss.c module is responsible to do the job.This patch also removes hardcoded name of the DMA device in clk-lpt.c and the
name of the root clock in acpi_lpss.c.Signed-off-by: Rafael J. Wysocki
Signed-off-by: Andy Shevchenko
Signed-off-by: Vinod Koul
25 Mar, 2013
1 commit
-
The excerpt like this:
if (err) {
err = 0;
goto error_out;
}makes a reader confused even if it's commented. Let's do necessary actions and
return no error explicitly.Signed-off-by: Andy Shevchenko
Signed-off-by: Rafael J. Wysocki