-
-
-
-
sound-3.16-rc116088cb6 · ·
sound updates for 3.16-rc1 At this time, majority of changes come from ASoC world while we got a few new drivers in other places for FireWire and USB. There have been lots of ASoC core cleanups / refactoring, but very little visible to external users. ASoC - Support for specifying aux CODECs in DT - Removal of the deprecated mux and enum macros - More moves towards full componentisation - Removal of some unused I/O code - Lots of cleanups, fixes and enhancements to the davinci, Freescale, Haswell and Realtek drivers - Several drivers exposed directly in Kconfig for use with simple-card - GPIO descriptor support for jacks - More updates and fixes to the Freescale SSI, Intel and rsnd drivers - New drivers for Cirrus CS42L56, Realtek RT5639, RT5642 and RT5651 and ST STA350, Analog Devices ADAU1361, ADAU1381, ADAU1761 and ADAU1781, and Realtek RT5677 HD-audio: - Clean up Dell headset quirks - Noise fixes for Dell and Sony laptops - Thinkpad T440 dock fix - Realtek codec updates (ALC293,ALC233,ALC3235) - Tegra HD-audio HDMI support FireWire-audio: - FireWire audio stack enhancement (AMDTP, MIDI), support for incoming isochronous stream and duplex streams with timestamp synchronization - BeBoB-based devices support - Fireworks-based device support USB-audio: - Behringer BCD2000 USB device support Misc: - Clean up of a few old drivers, atmel, fm801, etc
-
devicetree-for-3.1643cb4367 · ·
DeviceTree for 3.16: - Another round of clean-up of FDT related code in architecture code. This removes knowledge of internal FDT details from most architectures except powerpc. - Conversion of kernel's custom FDT parsing code to use libfdt. - DT based initialization for generic serial earlycon. The introduction of generic serial earlycon support went in thru tty tree. - Improve the platform device naming for DT probed devices to ensure unique naming and use parent names instead of a global index. - Fix a race condition in of_update_property. - Unify the various linker section OF match tables and fix several function prototype errors. - Update platform_get_irq_byname to work in deferred probe cases. - 2 binding doc updates
-
regulator-v3.16978371cb · ·
regulator: Updates for v3.16 The bulk of the changes for this release are a few new drivers however there are a couple of noticable core changes and the usual stream of cleanups and fixes: - Move disable of unused regulators later in init so it comes after deferred probe has iterated making startup smoother. - Fixes reference counting of the DT nodes for constraints from Charles Keepax. This has little practical impact since all real users of the regulator bindings use FDT which doesn't need the reference counting. - Lots of cleanups, especially to the Samsung drivers. - Support for Linear Technologies LTC3589, Texas Instruments TPS658640 and X-Powers AXP20x.
-
sound-3.15192a98e2 · ·
sound fixes for 3.15-final A few addition of HD-audio fixups for ALC260 and AD1986A codecs. All marked as stable fixes. The fixes are pretty local and they are old machines, so quite safe to apply.
-
gpio-v3.16-1fc346270 · ·
This is the bulk of GPIO changes for the v3.16 series: - We are finalizing and fixing up the gpiochip irqchip helpers bringing a helpful irqchip implementation into the gpiolib core and avoiding duplicate code and, more importantly, duplicate bug fixes: - Support for using the helpers with threaded interrupt handlers as used on sleeping GPIO-irqchips - Do not set up hardware triggers for edges or levels if the default IRQ type is IRQ_TYPE_NONE - some drivers would exploit the fact that you could get default initialization of the IRQ type from the core at probe() but if no default type is set up from the helper, we should not call the driver to configure anything. Wait until a consumer requests the interrupt instead. - Make the irqchip helpers put the GPIO irqs into their own lock class. The GPIO irqchips can often emit (harmless, but annoying) lockdep warnings about recursions when they are in fact just cascaded IRQs. By putting them into their own lock class we help the lockdep core to keep track of things. - Switch the tc3589x GPIO expanders to use the irqchip helpers - Switch the OMAP GPIO driver to use the irqchip helpers - Add some documentation for the irqchip helpers - select IRQ_DOMAIN when using the helpers since some platforms may not be using this by default and it's a strict dependency. - Continued GPIO descriptor refactoring: - Remove the one instance of gpio_to_desc() from the device tree code, making the OF GPIO code use GPIO descriptors only. - Introduce gpiod_get_optional() and gpiod_get_optional_index() akin to the similar regulator functions for cases where the use of GPIO is optional and not strictly required. - Make of_get_named_gpiod_flags() private - we do not want to unnecessarily expose APIs to drivers that make the gpiolib harder than necessary to maintain and refactor. Privatize this function. - Support "-gpio" suffix for the OF GPIO retrieveal path. We used to look for "foo-gpios" or just "gpios" in device tree nodes, but it turns out that some drivers with a single GPIO line will just state "foo-gpio" (singularis). Sigh. Support this with a fallback looking for it, as this simplifies driver code and handles it in core code. - Switch the ACPI GPIO core to fetch GPIOs with the *_cansleep function variants as the GPIO operation region handler can sleep, and shall be able to handle gpiochips that sleep. - Tons of cleanups and janitorial work from Jingoo Han, Axel Lin, Javier Martinez Canillas and Abdoulaye Berthe. Notably Jingoo cut off a ton of pointless OOM messages. - Incremental development and fixes for various drivers, nothing really special here.
-