On 01/04/2010 12:38 PM, Alan Cox wrote:
Early SATA controllers are just PATA controllers in disguise. All SFF
controllers want that 400ns delay. The 400ns delay should -not- be avoided.
Its a signalling protocol requirement for PATA or a PATA controller with
a PATA/SATA bridge. What makes you think a SATA controller cares one
iota ?
Because first gen SATA controllers, notably the Promise ones, were often
just the same old PATA silicon logic with additional PATA<->SATA
translation glue logic, rather than a pure SATA SFF implementation.
Because several SATA controllers are SFF and use the code in question,
the MMIO issue is relevant for the code change, even if it is irrelevant
to drivers/ata/pata_*.c.
and to SATA. It's simply not relevant at a protocol level to SATA which
is message passing anyway.
It is not relevant to FIS-based SATA (SiI 3124, AHCI), sure. But SFF is
not FIS-based SATA.
Jeff
--
To unsubscribe from this list: send the line "unsubscribe linux-ide" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
