[lkml]   [2003]   [Jul]   [28]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRE: Problems related to DMA or DDR memory on Intel 845 chipset?


>> then "hang". I had discovered that upon this failure, the logic analyzer
>> shows that our device is asserting the interrupt. However, I also found
>> adding my own debug to the kernel) that the 8259 Programmable Interrupt
>> Controller never received the interrupt (it's bit was not set in the

>OK, so the problem is strictly on the PCI bus, between your device
>and the PIC (or apic?)

That would appear to be the case. But as I said, it appears to be a nasty
side affect from something that has gone wrong during a DMA transfer. BTW,
we are using PIC

>> interrupt on the device). At this point of failure, no other IRQs are
>> getting through, so the system appears to be completely hard hung even
>> though various software components are still running. We are operating
in a

>so why do you think this is a software problem?

I made this posting to see if anyone else has had problems with this
hardware or to see if there were any known issues similar to what I've

>> employs the DDR memory technology) running Linux 2.4.20-8. Further
>> has shown that "not receiving an interrupt" is just a nasty side affect
>> something that has gone wrong during a DMA transfer by our device. This
>> discovered when I changed the driver to poll for a DMA completion rather
>> than have it interrupt me. Our system still hung. We are have tried

>that one mystifies me: how do you conclude the problem is a broken
>DMA transfer if, when you convert to polling, the problem remains?

Why? The device is _still_ a DMA device. In this particular test I told it
to initiate the DMA, but I did not enable it's ability to interrupt me when
it was finished with the DMA. I poll to watch for it's completion.

>my conclusion would be that your device has somehow managed to lock
>up the PIC's state-machine, or is somehow playing nasty with the bus.

I haven't ruled that out.

. . . Meanwhile, I made another discovery on the internet that indicates
that DMA is not supported with an ICH4 controller (which is what this system
has) until Linux version 2.5.12 (we're using 2.4.20-8). See: I posted a
question concerning this to linux-kernel. See thread: DMA not supported
with Intel ICH4 I/O controller? Unfortunately, I have not received any
response that supports or refutes this. Any thoughts?


To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to
More majordomo info at
Please read the FAQ at

 \ /
  Last update: 2005-03-22 13:47    [W:0.050 / U:0.008 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site