tech-kern archive

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]

Re: write alignment matters?

On Tue, Jun 21, 2011 at 08:57:33PM -0600, Michael L. Hitch wrote:
> On Tue, 21 Jun 2011, der Mouse wrote:
> >>It's a 53c8xx:  we load the "firmware" into it from our own driver.
> >
> >I just had a look at, and it looks high-level enough that it's
> >plausible to me that the problem is with whatever's backing that code,
> >whether silicon or ROMed firmware or whatever.
> I just verified that I see the same on a 53c875 using esiop(4), and
> it also does the same thing with siop(4).  I also found that it
> works fine if the buffer is at an even address and only failed on
> odd addresses.  It's been quite a while since I was working on the
> Amiga driver with similar chips, and I don't remember if there was
> anything special needed with odd addresses.  Next time I've got my
> Amiga on, I'll try the test program there.  I've also got a 53c875
> in an Alpha that I plan on testing.

I suspect most disk controllers will have issues if the buffer
is not aligned on at last 16bits. For example, AHCI requires a word-aligned

Manuel Bouyer <>
     NetBSD: 26 ans d'experience feront toujours la difference

Home | Main Index | Thread Index | Old Index