[techtalk] hdparm and DMA "not permitted"

[James Sutherland]

On Sun, 20 May 2001, Conor Daly wrote:

> On Sun, May 20, 2001 at 12:17:18PM +0100 or so it is rumoured hereabouts,
> James Sutherland thought:
> > On Sun, 20 May 2001, Conor Daly wrote:
> >
> > > Little problem here with hdparm and DMA.  I'm using an AMD K6-2 350MHz on
> > > some kind of amibios mobo with "Ultra DMA Enabled" in CMOS but I cannot
> > > set "using dma" for the drive(s).
> > >
> > > [root]# /sbin/hdparm -d 1 /dev/hda
> > >
> > > /dev/hda:
> > >  setting using_dma to 1 (on)
> > >  HDIO_SET_DMA failed: Operation not permitted
> > >  using_dma    =  0 (off)
> > >
> > >
> > > dmesg returns:
> > >
> > > PCI_IDE: unknown IDE controller on PCI bus 00 device 78, VID=10b9,
> > > DID=5229
> > > PCI_IDE: not 100% native mode: will probe irqs later
> > > PCI_IDE: simplex device:  DMA disabled
> > > hda: Maxtor 91021U2, 9770MB w/512kB Cache, CHS=1245/255/63
> > > hdb: FUJITSU MPD3084AT, 8063MB w/512kB Cache, CHS=1027/255/63
> > >
> > > Any thoughts?
> >
> > Enabling DMA requires the right driver in the kernel; there is an option
> > for "Generic PCI DMA support" or similar, which might be worth a try if
> > you can't find an exact match for your IDE chipset.
> >
> > What does /proc/pci have to say about your IDE controller? This should
> > tell you which driver to use - then just recompile, reboot, and you have
> > DMA...
>
> /proc/pci has this to say...
>
>   Bus  0, device  15, function  0:
>     IDE interface: Acer Labs M5229 TXpro (rev 193).
>       Medium devsel.  Fast back-to-back capable.  Master Capable.
> Latency=32.  Min Gnt=2.Max Lat=4.
>       I/O at 0xffa0 [0xffa1].
>
> will poke around the kernel and see what I come up with.

Hmm - can't see a specific driver. Enabling "Generic PCI bus-master DMA
support" and "Use PCI DMA by default when available" (under "Generic PCI
IDE chipset support") should give you DMA, though...

> Somebody else said something about
>
> ###########################
> hda: Maxtor 91021U2, ATA DISK drive
> hdb: FUJITSU MPD3084AT, ATA DISK drive
>
> Longshot here, but wasn't there at one stage a fairly serious problem
> with these makes of drive interoperating on the same IDE controller?
> ###########################
>
> Anyone know anything about that?  I haven't had any issues myself with
> these two drives.

I remember something similar, but can't recall the details ATM - trawling
the LKML archives should reveal more details, though?


James.
-- 
"Our attitude with TCP/IP is, `Hey, we'll do it, but don't make a big
system, because we can't fix it if it breaks -- nobody can.'"

"TCP/IP is OK if you've got a little informal club, and it doesn't make
any difference if it takes a while to fix it."
		-- Ken Olson, in Digital News, 1988