[PATCH 2/2] mtd: nand: Remove BUG() abuse in nand_scan_tail

[Ezequiel Garcia]

On 4 April 2016 at 12:30, Richard Weinberger <richard at nod.at> wrote:
> Am 04.04.2016 um 17:20 schrieb Boris Brezillon:
>> On Sat, 2 Apr 2016 15:55:24 +0200
>> Boris Brezillon <boris.brezillon at free-electrons.com> wrote:
>>
>>> On Fri,  1 Apr 2016 18:29:24 -0300
>>> Ezequiel Garcia <ezequiel at vanguardiasur.com.ar> wrote:
>>>
>>>> There's no reason to BUG() when parameters are being
>>>> validated. Drivers can get things wrong, and it's much nicer
>>>> to just throw a noisy warn and fail gracefully, than calling
>>>> BUG() and throwing the whole system down the drain.
>>>
>>> I'm fine with this change as long as all callers are checking
>>> nand_scan_tail() return value.
>>
>> Actually, the s3c2410 driver is not checking nand_scan_tail() return
>> value. Could you send a v2 addressing that?
>
> And maybe add __must_check to nand_scan_tail() such that we catch issues like
> these.
>

In fact, why not adding must_check to all the functions that can fail
in the kernel?

That'll help catch even more issues ;-)
-- 
Ezequiel García, VanguardiaSur
www.vanguardiasur.com.ar