Re: PCI DMA into USER space

• Next message: bug1: "Re: ide performance limits"
• Previous message: Blusjune Jung: "[Q.] sk_buff headroom size increases by 16, why?"
• In reply to: Richard B. Johnson: "Re: PCI DMA into USER space"
• Next in thread: Richard B. Johnson: "Re: PCI DMA into USER space"
• Reply: Richard B. Johnson: "Re: PCI DMA into USER space"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

"Richard B. Johnson" wrote:
> On Tue, 13 Jun 2000, Mayhall, Tony wrote:
> > Does anyone have an example (that works) of how to DMA from a PCI card into
> > user space on a PC running Linux? We do this on Unix systems and need to be
> > able to do this under Linux.

> Hmm. From what Unix Systems? Suns don't have 'ports'. All memory-mapped
> I/O. The PCI spec was designed around shared memory. Once you got shared
> memory, all you have to do is mmap it. No DMA required.

DMA is generally faster though since it doesn't have to involve the host
CPU when slinging data around..

        Jeff

-- 
Jeff Garzik              | Liberty is always dangerous, but
Building 1024            | it is the safest thing we have.
MandrakeSoft, Inc.       |      -- Harry Emerson Fosdick
-
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/

• Next message: bug1: "Re: ide performance limits"
• Previous message: Blusjune Jung: "[Q.] sk_buff headroom size increases by 16, why?"
• In reply to: Richard B. Johnson: "Re: PCI DMA into USER space"
• Next in thread: Richard B. Johnson: "Re: PCI DMA into USER space"
• Reply: Richard B. Johnson: "Re: PCI DMA into USER space"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

This archive was generated by hypermail 2b29 : Thu Jun 15 2000 - 21:00:31 EST