[6479] in linux-scsi channel archive
Re: raw I/O with device memory
daemon@ATHENA.MIT.EDU (Alan Cox)
Thu May 6 23:38:26 1999
From: alan@lxorguk.ukuu.org.uk (Alan Cox)
To: sct@redhat.com (Stephen C. Tweedie)
Date: Fri, 7 May 1999 02:00:51 +0100 (BST)
Cc: mbatle@iname.com, linux-kernel@vger.rutgers.edu,
linux-scsi@vger.rutgers.edu, sct@redhat.com
In-Reply-To: <14129.52281.449200.452727@dukat.scot.redhat.com> from "Stephen C. Tweedie" at May 6, 99 06:07:05 pm
> > 1st) It does not work with memory located in a PCI device.
>
> Linux cannot perform IO on such memory right now. End of story. It
> will in the future: this is just one of a whole raft of related problems
> we have due to the backwards-compatible way virt_to_phys works.
You also need a blacklist of chipsets, and some work arounds. PCI-PCI DMA
is a gigantic can of worms. On some chipsets PCI->PCI DMA just doesnt happen
on others it locks up occasionally.
-
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a message to majordomo@vger.rutgers.edu
