Skip to contentSkip to conversation

Dragging window in X causes soundcard interrupts to be lost

Unichrome-devel Lee Revell 2 participants 4 messages Aug 1, 2004 – Sep 1, 2004 10 messages not in the archive

lore
Share & tools
lore

A message that is not in the archive (sent off-list or not yet received): 1089952196.25689.7.camel@mindpipe

A message that is not in the archive (sent off-list or not yet received): [email protected]

A message that is not in the archive (sent off-list or not yet received): [email protected]

A message that is not in the archive (sent off-list or not yet received): 1090001316.27995.3.camel@mindpipe

A message that is not in the archive (sent off-list or not yet received): [email protected]

A message that is not in the archive (sent off-list or not yet received): 1090010147.30435.2.camel@mindpipe

A message that is not in the archive (sent off-list or not yet received): 1090107507.10795.1.camel@mindpipe

A message that is not in the archive (sent off-list or not yet received): [email protected]

A message that is not in the archive (sent off-list or not yet received): 1090190244.22282.8.camel@mindpipe

A message that is not in the archive (sent off-list or not yet received): [email protected]

Lee Revell

author
#10 lore raw
Quoted 6 lines · Thomas Hellstrom

Hi, Lee.

Most of the code is inherited from VIA, but as far as I know, there are no locks held except the DRM lock when DRI is used, which it isn't in your case.

Thomas,

Do you have the original driver source from VIA handy? This is looking more and more like a hardware bug - 2D acceleration engine activity causes interrupts from the PCI slot to be disabled for long periods. Maybe it disables interrupts to prevent other processes writing to the shared video/system RAM as it DMAs. I would like to verify that the problem still occurs with their driver, before I try to convince them there's a hardware issue with the EPIA boards.

On that note, assuming I verify the bug, does anyone have any recommendations for getting VIA to take me seriously? The problem is very easy to reproduce.

Lee

#11 lore raw
Quoted 3 lines · Lee Revell

Do you have the original driver source from VIA handy? This is looking more and more like a hardware bug - 2D acceleration engine activity causes interrupts from the PCI slot to be disabled for long periods.

I do. There is no code in the 2D engine that touches interrupt control at all.

Quoted 4 lines

Maybe it disables interrupts to prevent other processes writing to the shared video/system RAM as it DMAs. I would like to verify that the problem still occurs with their driver, before I try to convince them there's a hardware issue with the EPIA boards.

A similar problem occurs with some other chips when you write enough data to the chip that the FIFO fills and the PCI bus locks until the write can complete. Various vendors implemented this at one point for benchmarketing reasons and that would have a similar effect if so.

The 2D driver source is essentially the same as the source in Xorg CVS barring cleanups and the accelerator code has not changed at all. You might want to take a look at the fifo management side of things in that code.

Quoted 3 lines

On that note, assuming I verify the bug, does anyone have any recommendations for getting VIA to take me seriously? The problem is very easy to reproduce.

I have some contact with VIA however you need to understand that the graphics world moves rapidly. I would be suprised if the CLE266 saw any more development given the CN400 has been demoed, although I certainly can't speak for VIA on this matter.

Alan

author
#12 lore raw
Quoted 8 lines · Alan Cox
Quoted 3 lines · Lee Revell

Do you have the original driver source from VIA handy? This is looking more and more like a hardware bug - 2D acceleration engine activity causes interrupts from the PCI slot to be disabled for long periods.

I do. There is no code in the 2D engine that touches interrupt control at all.

Yes, I saw that. This basically means it has to be a hardware bug, correct?

Quoted 10 lines
Quoted 4 lines

Maybe it disables interrupts to prevent other processes writing to the shared video/system RAM as it DMAs. I would like to verify that the problem still occurs with their driver, before I try to convince them there's a hardware issue with the EPIA boards.

A similar problem occurs with some other chips when you write enough data to the chip that the FIFO fills and the PCI bus locks until the write can complete. Various vendors implemented this at one point for benchmarketing reasons and that would have a similar effect if so.

This was the first thing that occurred to me, but I am not really a video driver expert, and looking at the code it's just banging bits. I have hacked device drivers, just not video, and I don't have the bandwidth to learn right now.

Quoted 5 lines

The 2D driver source is essentially the same as the source in Xorg CVS barring cleanups and the accelerator code has not changed at all. You might want to take a look at the fifo management side of things in that code.

Quoted 9 lines
Quoted 3 lines

On that note, assuming I verify the bug, does anyone have any recommendations for getting VIA to take me seriously? The problem is very easy to reproduce.

I have some contact with VIA however you need to understand that the graphics world moves rapidly. I would be suprised if the CLE266 saw any more development given the CN400 has been demoed, although I certainly can't speak for VIA on this matter.

Yes, I would be happy to just get an acknowledgement of the issue. Actually I don't even need that, I just want to know if it's fixed in the newer ones. I have a perfectly acceptable workaround. The 2D acceleration is pretty shoddy anyway, many things seem to work better
with NoAccel. I still love the EPIA board.

Maybe you could forward this on to them? Off the record is fine.

Lee

author
#13 lore raw
In reply to Alan Cox
Quoted 18 lines · Alan Cox
Quoted 3 lines · Lee Revell

Do you have the original driver source from VIA handy? This is looking more and more like a hardware bug - 2D acceleration engine activity causes interrupts from the PCI slot to be disabled for long periods.

I do. There is no code in the 2D engine that touches interrupt control at all.

Quoted 4 lines

Maybe it disables interrupts to prevent other processes writing to the shared video/system RAM as it DMAs. I would like to verify that the problem still occurs with their driver, before I try to convince them there's a hardware issue with the EPIA boards.

A similar problem occurs with some other chips when you write enough data to the chip that the FIFO fills and the PCI bus locks until the write can complete. Various vendors implemented this at one point for benchmarketing reasons and that would have a similar effect if so.

Quoted 4 lines

The 2D driver source is essentially the same as the source in Xorg CVS barring cleanups and the accelerator code has not changed at all. You might want to take a look at the fifo management side of things in that code.

OK, turns out that my (and your, and Thomas Hellstrom, the Unichrome maintainer's) theory was correct - this is exactly what is happening:

Quoted 12 lines · Thomas Hellström

I've think I've found an answer to this, and it seems to be related to what I mentioned earlier, namely that any attemt to write over PCI to a busy video engine will halt the processor until the video accepts new data.

The wait-for-idle loop seems only to be used as a flush-and-sync, to make sure that accelerated rendering has completed. There is probably no check for ongoing engine activity before writing to the 2d engine. Same as for VIA's own mpeg2 code. Such a check will be implemented and will cause a very slight overhead compared to today's code.

Quoted 8 lines

I'm starting to fix this as part of compatibility with the new drm with AGP DMA transfers, when available. This will not go into "production" for about least two or three weeks, but if you are interested, I could send you an updated via_accel.c sooner to see if it cures your problem.

Regards
Thomas

So, it looks like vendors are still up to the same tricks...

Lee