[RFC] spi-nor: fix cross die reads on Micron multi-die devices

[Bean Huo 霍斌斌 (beanhuo)]

> Hi Bean,
> 
> On Thu, 21 Jan 2016 01:06:48 +0000
> Bean Huo 霍斌斌 (beanhuo) <beanhuo at micron.com> wrote:
> 
> >  Hi, Adam and Boris
> >
> > For Micron MT25Q ,MT25T and MT35Q, they does not exist this action
> > even they are Multi-die devices. So when the last byte of the die
> > selected is read, the next byte output is the first byte of next die(not the
> same die).
> > You can check this by extended address register chapter in our
> > datasheet, there are detail Information.
> 
> I never said you were wrong ;), I just asked if it was relevant to differentiate
> the two cases. IOW, would the implementation proposed by Adam work
> correctly on all chips? And what is the real performance penalty for
> MT25Q ,MT25T and MT35Q if we decide to split the read command in several
> reads to handle this cross die case?
For this , performance penalty is tiny, can ignore. 
SPI NOR read performance only depends on SPI I/O clock. Not the same as NAND.
> Best Regards,
> 
> Boris
> 
> --
> Boris Brezillon, Free Electrons
> Embedded Linux and Kernel engineering
> http://free-electrons.com