[EXT] Re: [PATCH 1/2] mtd: rawnand: gpmi: Fix the driver only sense CS0 R/B issue

[Miquel Raynal]

Hello,

Sascha Hauer <s.hauer at pengutronix.de> wrote on Mon, 7 Dec 2020 17:43:46
+0100:

> On Mon, Dec 07, 2020 at 04:14:00PM +0000, Han Xu wrote:
> > 
> >   
> > > -----Original Message-----
> > > From: Sascha Hauer <s.hauer at pengutronix.de>
> > > Sent: Monday, December 7, 2020 3:50 AM
> > > To: Han Xu <han.xu at nxp.com>
> > > Cc: miquel.raynal at bootlin.com; linux-mtd at lists.infradead.org
> > > Subject: [EXT] Re: [PATCH 1/2] mtd: rawnand: gpmi: Fix the driver only sense
> > > CS0 R/B issue
> > > 
> > > Caution: EXT Email
> > > 
> > > On Sat, Dec 05, 2020 at 12:30:03AM -0600, Han Xu wrote:  
> > > > set the GPMI CTRL1 GANGED_RDYBUSY bit so dirver can sense the R/B
> > > > signal from all CS.
> > > >
> > > > For the NAND chip MT29F64G08AFAAAWP, only the first chip detected
> > > > without the patch.
> > > >
> > > > [    3.764118] nand: device found, Manufacturer ID: 0x2c, Chip ID: 0x68
> > > > [    3.770613] nand: Micron MT29F64G08AFAAAWP
> > > > [    3.774752] nand: 4096 MiB, SLC, erase size: 1024 KiB, page size: 8192, OOB  
> > > size: 448  
> > > > [    3.786421] Bad block table found at page 524160, version 0x01
> > > > [    3.792730] Bad block table found at page 524032, version 0x01
> > > >
> > > > After applying the patch
> > > >
> > > > [    3.764445] nand: device found, Manufacturer ID: 0x2c, Chip ID: 0x68
> > > > [    3.770941] nand: Micron MT29F64G08AFAAAWP
> > > > [    3.775080] nand: 4096 MiB, SLC, erase size: 1024 KiB, page size: 8192, OOB  
> > > size: 448  
> > > > [    3.784390] nand: 2 chips detected
> > > > [    3.790900] Bad block table found at page 524160, version 0x01
> > > > [    3.796776] Bad block table found at page 1048448, version 0x01
> > > >
> > > > Fixes: 3045f8e36963 ("mtd: rawnand: gpmi: move all driver code into
> > > > single file")  
> > > 
> > > I don't see how 3045f8e36963 changes his behaviour. Are you sure it worked
> > > without this patch?  
> > 
> > After several rounds files merge and code move, it's hard to find when
> > this issue first involved, the driver still works for single CS NAND
> > but CTRL1 GANGED_RDYBUSY must be set for multi-CS NAND chips.  
> 
> 3045f8e36963 only re-arranges the code without any functional change, so
> I strongly doubt that a commit writing a register with a newly
> introduced register bit ixes it.
> 
> Please drop this "Fixes:" tag.

I will drop the tag when applying.

> 
> Sascha
> 

Thanks,
Miquèl