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

[Brian Norris <computersforpeace@gmail.com>]

On Mon, Apr 04, 2016 at 05:20:48PM +0200, Boris Brezillon wrote:
> On Sat, 2 Apr 2016 15:55:24 +0200
> Boris Brezillon <boris.brezillon@free-electrons.com> wrote:
> 
> > On Fri,  1 Apr 2016 18:29:24 -0300
> > Ezequiel Garcia <ezequiel@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?

One could argue that we as a kernel community don't care about those
systems which are currently configured to hit 100%-reproducible BUG()
statements at boot time, and so this wouldn't really be a regression.
Also, there are already error cases in nand_scan_tail() that might
return non-zero, so such drivers are already broken.

Of course, it'd be nice to fix these drivers anyway.

Brian