Date: Tue, 25 Aug 1998 14:52:34 -0700 From: Parag Patel <parag@cgt.com> To: john hood <cgull@owl.org> Cc: Joe Gleason <freebsd.list@bug.tasam.com>, freebsd-hardware@FreeBSD.ORG Subject: Re: UDMA Support Message-ID: <199808252152.OAA04488@pinhead.parag.codegen.com> In-Reply-To: Your message of "Tue, 25 Aug 1998 02:10:26 EDT." <19980825021026.12093@owl.org>
next in thread | previous in thread | raw e-mail | index | archive | help
>-current supports DMA, but not Ultra DMA, which is faster and has >CRC error checking. That's odd - I thought it supported UDMA. Perhaps you meant -stable? My reading of the file /sys/pci/ide_pci.c suggests that 3.0 does support UDMA for PCI-IDE chips. I made some additions to it to support the newer CMD646U2 PCI-UIDE chip but they haven't made it into the source tree yet (I don't know who the new owner of this code is). The individual chip dmainit routines are supposed to turn on udma mode if possible. It doesn't look like the plain ISA /sys/i386/isa/wd.c driver turns on UDMA. If you have a newer motherboard with PCI-based IDE controller the code should turn on UDMA mode for those drives that support it, unless I've missed something. (The throughput on my UDMA Quantum on the CMD646U2 card in my 486 test machine seems to suggest that it is running in UDMA mode. I have dumped various registers etc when I was debugging my driver mods that claimed it was in UDMA mode.) -- Parag To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199808252152.OAA04488>