Re: [PATCH 3/4] ide: add struct ide_dma_ops

[Sergei Shtylyov <sshtylyov@ru.mvista.com>]

Hello.

Bartlomiej Zolnierkiewicz wrote:

>>>>   Now where is the code which selects the correct dma_ops for the 

>>>>>HPT36x/370/372/372N chip with device ID 4 I'm asking you?  :-) 

>>>fixed

>>    Not actually... :-/

> Arghhh.  I see now that the HPT370/370A needs a special handling...

    Yes, and a lot of. :-)

> (HPT372/372N has already been handled by 'idx++')

    Didn't grasp this at first - the init. code grew somewhat convoluted...

> [...]

>>>@@ -1483,6 +1489,7 @@ static const struct ide_port_info hpt366
>>> 		.enablebits	= {{0x50,0x04,0x04}, {0x54,0x04,0x04}},
>>> 		.udma_mask	= ATA_UDMA5,
>>> 		.port_ops	= &hpt3xx_port_ops,
>>>+		.dma_ops	= &hpt370_dma_ops,

>>    Wrong -- HPT374 should have hpt37x_dma_ops...

> Yep, thanks for catching it.

> interdiff between v2->v3:

> [...]
> v3:
> * Two bugs slipped in v2 (noticed by Sergei):
>   - use correct DMA ops for HPT374 (for real this time)
>   - handle HPT370/HPT370A properly

Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com>

MBR, Sergei