[PATCH] serial: samsung: Fix serial config dependencies for exynos7

Abhilash Kesavan kesavan.abhilash at gmail.com
Sat Nov 15 18:17:02 PST 2014


Hello Greg,

On Tue, Nov 11, 2014 at 7:55 PM, Abhilash Kesavan
<kesavan.abhilash at gmail.com> wrote:
> Hi Greg,
>
> On Tue, Sep 30, 2014 at 8:02 PM, Abhilash Kesavan
> <kesavan.abhilash at gmail.com> wrote:
>> Hi Tomasz,
>>
>> On Tue, Sep 30, 2014 at 4:08 AM, Tomasz Figa <tomasz.figa at gmail.com> wrote:
>>> Hi Abhilash,
>>>
>>> The patch itself seems fine, but I wonder if those config options aren't
>>> really just leftovers from the past and couldn't be completely removed.
>>>
>>> On 29.09.2014 07:16, Abhilash Kesavan wrote:
>>>> From: Pankaj Dubey <pankaj.dubey at samsung.com>
>>>>
>>>> Exynos7 has a similar serial controller to that present in older Samsung
>>>> SoCs. To re-use the existing serial driver on Exynos7 we need to have
>>>> SERIAL_SAMSUNG_UARTS_4 and SERIAL_SAMSUNG_UARTS selected. This is not
>>>> possible because these symbols are dependent on PLAT_SAMSUNG which is
>>>> not present for the ARMv8 based exynos7.
>>>>
>>>> Change the dependency of these symbols from PLAT_SAMSUNG to the serial
>>>> driver thus making it available on exynos7. As the existing platform
>>>> specific code making use of these symbols is related to uart driver this
>>>> change in dependency should not cause any issues.
>>>>
>>>> Signed-off-by: Pankaj Dubey <pankaj.dubey at samsung.com>
>>>> Signed-off-by: Naveen Krishna Chatradhi <ch.naveen at samsung.com>
>>>> Signed-off-by: Abhilash Kesavan <a.kesavan at samsung.com>
>>>> Cc: Greg Kroah-Hartman <gregkh at linuxfoundation.org>
>>>> ---
>>>> Build tested with s3c6400_defconfig, exynos_defconfig and arm64's defconfig
>>>> with and without the serial driver enabled.
>>>>
>>>>  drivers/tty/serial/Kconfig |    4 ++--
>>>>  1 file changed, 2 insertions(+), 2 deletions(-)
>>>>
>>>> diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
>>>> index 81f6ee7..e6c0bcb 100644
>>>> --- a/drivers/tty/serial/Kconfig
>>>> +++ b/drivers/tty/serial/Kconfig
>>>> @@ -249,14 +249,14 @@ config SERIAL_SAMSUNG
>>>>
>>>>  config SERIAL_SAMSUNG_UARTS_4
>>>>       bool
>>>> -     depends on PLAT_SAMSUNG
>>>> +     depends on SERIAL_SAMSUNG
>>>>       default y if !(CPU_S3C2410 || CPU_S3C2412 || CPU_S3C2440 || CPU_S3C2442)
>>>>       help
>>>>         Internal node for the common case of 4 Samsung compatible UARTs
>>>
>>> The only place where this symbol is used is below.
>>>
>>>>
>>>>  config SERIAL_SAMSUNG_UARTS
>>>>       int
>>>> -     depends on PLAT_SAMSUNG
>>>> +     depends on SERIAL_SAMSUNG
>>>>       default 4 if SERIAL_SAMSUNG_UARTS_4 || CPU_S3C2416
>>>>       default 3
>>>>       help
>>>>
>>>
>>> With this symbol the situation isn't that easy, but still should be
>>> manageable.
>>>
>>> Looking at the serial-samsung driver, all occurrences of
>>> CONFIG_SERIAL_SAMSUNG_UARTS could be simply replaced with a locally
>>> defined number equal to the maximum value - in this case 4.
>>>
>>> There are also two places in arch/arm where this symbol is used:
>>>
>>> 1) In arch/arm/mach-s3c64xx/irq-pm.c it's used as the number of serial
>>> ports which need suspend/resume handling. Since on s3c64xx the number is
>>> always 4, it can be simply defined locally as a constant.
>>>
>>> 2) In arch/arm/plat-samsung/init.c it is used to determine size of a
>>> static array of UART ports and to check whether the UART driver is
>>> enabled. In former case I believe it should be safe to hardcode it to 4
>>> as well, in latter CONFIG_SERIAL_SAMSUNG can be used.
>>
>> I will post patches removing these two symbols.
>
> I posted a couple of patches handling Tomasz' comments but Kukjin
> prefers the approach in this patch (Discussion here:
> http://www.spinics.net/lists/linux-samsung-soc/msg38742.html).
> Can you please review the patch.

This is a gentle reminder. The patch is required for serial enablement
on the new exynos7 SoC, kindly take a look.

Thanks,
Abhilash



More information about the linux-arm-kernel mailing list