[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <1484828221.2133.231.camel@linux.intel.com>
Date: Thu, 19 Jan 2017 14:17:01 +0200
From: Andy Shevchenko <andriy.shevchenko@...ux.intel.com>
To: Mika Westerberg <mika.westerberg@...ux.intel.com>,
Linus Walleij <linus.walleij@...aro.org>
Cc: Alexandre Courbot <gnurou@...il.com>, linux-gpio@...r.kernel.org,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH 3/3] pinctrl / gpio: Introduce .set_config() callback
for GPIO chips
On Thu, 2017-01-19 at 12:48 +0300, Mika Westerberg wrote:
> Currently we already have two pin configuration related callbacks
> available for GPIO chips .set_single_ended() and .set_debounce(). In
> future we expect to have even more, which does not scale well if we
> need
> to add yet another callback to the GPIO chip structure for each
> possible
> configuration parameter.
>
> Better solution is to reuse what we already have available in the
> generic pinconf.
>
> To support this, we introduce a new .set_config() callback for GPIO
> chips. The callback takes a single packed pin configuration value as
> parameter. This can then be extended easily beyond what is currently
> supported by just adding new types to the generic pinconf enum.
>
> We then convert the existing drivers over .set_config() and finally
> remove the .set_single_ended() and .set_debounce() callbacks.
>
> +#ifdef CONFIG_GENERIC_PINCONF
> +
> +#ifdef CONFIG_DEBUG_FS
> +#define PCONFDUMP(a, b, c, d) { .param = a, .display = b, .format =
> c, \
> + .has_arg = d }
I understand you moved existing code, though 3 liner here would look
better.
--
Andy Shevchenko <andriy.shevchenko@...ux.intel.com>
Intel Finland Oy
Powered by blists - more mailing lists