Re: Alpha: virt_to_bus/GFP_DMA problem

Thomas Sailer (sailer@ife.ee.ethz.ch)
Fri, 10 Dec 1999 16:13:32 +0100


Jakub Jelinek wrote:

> That's hack as well, isn't it?
> The right solution IMHO is what David Miller introduced on sbus:
> instead of using virt_to_bus & co. drivers acquire a DMA handler before
> doing DMA using
> handle = pci_map_single(pci_dev *dev, void *addr, long len, int flags)
> or
> handle = pci_map_sg(pci_dev *dev, struct scatterlist *sg, int flags)

Hm? How is that supposed to work? In our case, the DMA controller
sits in the PCI device, and the problem is the inadequacy of this
controller.

In the SBUS case, it seems that the DMA controller sits in the
motherboard chipset, and its capabilities are independent from
the SBUS cards.

In the PCI case, the generic pci_map_* would have to know the
capabilities of the PCI card controller.

Tom

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/