Re: HPA and failed opcode was: 0x37 ?

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

Hello.

Steven Scholz wrote:

>>>Hmm. Don't think so. Since the use of ioremap() I think the MMU treats the
>>>area as none-cacheable, right?

>>Thats only the first half of the story. If you don't decode byte level
>>fetches in the FPGA or the code is doing something like

>>		read 16 bit value
>>		shift 8
>>		return half

>>for 8 bit reads you'll get wrong answers.

> I have connected HDD's A[2..0] to CPU's A[3..1] and do something like

>         for (i = IDE_DATA_OFFSET; i <= IDE_STATUS_OFFSET; i++) {
>                 hw.io_ports[i] = ide_virt_base + (i << 1);
>         }

> thus all HDD registers are accessed on a 16bit aligned address. Thus
> ide_inb() should return the correct value.
> And btw are things like identify driver use 8bit transfers?

    No, 8-bit transfers are used only for taskfile access. The data register 
is accessed as 16-bit.

> How could one then explain

> current capacity is 78140160 sectors would be           0x000004A85300
> native  capacity is 185074430006016 sectors would be    0xA852FFA85300
> 
> ? First three bytes ok, then the other three bytes rubbish?

    Note that they're not complete garbage but equal the value of the lower 3 
bytes minus 1. What is clear is that Read Native Max Address Ext command must 
be mistreating the HOB bit... :-)

> Steven

MBR, Sergei