From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Rafael J. Wysocki" Subject: Re: [PATCH] ACPI / GPIO: Driver GPIO mappings for ACPI GPIOs Date: Mon, 27 Oct 2014 23:34:35 +0100 Message-ID: <3242497.urQmuvpeyA@vostro.rjw.lan> References: <2758495.RYBbleVHkC@vostro.rjw.lan> Mime-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7Bit Return-path: In-Reply-To: Sender: linux-kernel-owner@vger.kernel.org To: Alexandre Courbot Cc: Mika Westerberg , Arnd Bergmann , Linux Kernel Mailing List , Greg Kroah-Hartman , Grant Likely , ACPI Devel Maling List , Aaron Lu , "devicetree@vger.kernel.org" , Linus Walleij , Dmitry Torokhov , Bryan Wu , Darren Hart , Mark Rutland List-Id: devicetree@vger.kernel.org On Monday, October 27, 2014 02:21:23 PM Alexandre Courbot wrote: > On Sat, Oct 25, 2014 at 7:05 AM, Rafael J. Wysocki wrote: > > From: Rafael J. Wysocki > > > > Provide a way for device drivers using GPIOs described by ACPI > > GpioIo resources in _CRS to tell the GPIO subsystem what names > > (connection IDs) to associate with specific GPIO pins defined > > in there. > > > > To do that, a driver needs to define a mapping table as a > > NULL-terminated array of struct acpi_gpio_mapping objects > > that each contain a name, a pointer to an array of pin data > > (struct acpi_gpio_params) objects and the size of that array. > > > > Each struct acpi_gpio_params object consists of three fields, > > crs_entry_index, pin_index, active_low, representing the index of > > the target GpioIo()/GpioInt() resource in _CRS starting from zero, > > the index of the target pin in that resource starting from zero, > > and the active-low flag for that pin, respectively. > > > > Next, the mapping table needs to be passed as the second argument to > > acpi_dev_add_driver_gpios() that will register it with the ACPI device > > object pointed to by its first argument. That object must represent > > the ACPI namespace node containing the _CRS object referred to by the > > GPIO mapping. That should be done in the driver's .probe() routine. > > > > On removal, the driver should unregister its GPIO mapping table > > by calling acpi_dev_remove_driver_gpios() on the ACPI device > > object where that table was previously registered. > > > > Included are fixes from Mika Westerberg. > > Acked-by: Alexandre Courbot > > As we discussed already, this is a great idea. The only thing that is > missing is a paragraph in Documentation/gpio/consumer.txt with an > explanation of the global mechanism and a simple example to illustrate > how and when this should be used. Yes, I'm going to provide documentation. One question, though. We're already adding gpio-properties.txt under Documentation/acpi/ containing analogous information for _DSD-based mappings. I thought I'd add a section to that file and a short paragraph pointing to it into consumer.txt, would that work? Rafael