[Bug 83500] New: si_dma_copy_tile causes GPU hangs

[Bug 83500] New: si_dma_copy_tile causes GPU hangs

[bugzilla-daemon]

[-- Attachment #1.1: Type: text/plain, Size: 1098 bytes --]

https://bugs.freedesktop.org/show_bug.cgi?id=83500

          Priority: medium
            Bug ID: 83500
          Assignee: dri-devel@lists.freedesktop.org
           Summary: si_dma_copy_tile causes GPU hangs
          Severity: normal
    Classification: Unclassified
                OS: Linux (All)
          Reporter: greg@chown.ath.cx
          Hardware: x86-64 (AMD64)
            Status: NEW
           Version: git
         Component: Drivers/Gallium/radeonsi
           Product: Mesa

Created attachment 105745
  --> https://bugs.freedesktop.org/attachment.cgi?id=105745&action=edit
Workaround

Async DMA linear to tiled copies are causing GPU hangs in some cases. On Cape
Verde, I can easily triggers this as described in [1]. The game Brutal Legend
also triggers similar hangs when it streams assets while gameplay.

Disabling usage of this function and using the resource_copy_region fallback
instead fixes all hangs. The attached patch does that.

[1] https://bugs.freedesktop.org/show_bug.cgi?id=79980#c124

-- 
You are receiving this mail because:
You are the assignee for the bug.

[-- Attachment #1.2: Type: text/html, Size: 2635 bytes --]

[-- Attachment #2: Type: text/plain, Size: 159 bytes --]

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[Bug 83500] si_dma_copy_tile causes GPU hangs

[bugzilla-daemon]

[-- Attachment #1.1: Type: text/plain, Size: 237 bytes --]

https://bugs.freedesktop.org/show_bug.cgi?id=83500

--- Comment #1 from Marek Olšák <maraeo@gmail.com> ---
Thank you very much for tracking this down.

-- 
You are receiving this mail because:
You are the assignee for the bug.

[-- Attachment #1.2: Type: text/html, Size: 996 bytes --]

[-- Attachment #2: Type: text/plain, Size: 159 bytes --]

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[Bug 83500] si_dma_copy_tile causes GPU hangs

[bugzilla-daemon]

[-- Attachment #1.1: Type: text/plain, Size: 399 bytes --]

https://bugs.freedesktop.org/show_bug.cgi?id=83500

--- Comment #2 from Grigori Goronzy <greg@chown.ath.cx> ---
Created attachment 105755
  --> https://bugs.freedesktop.org/attachment.cgi?id=105755&action=edit
Better fix

This is a possibly better fix that only disables DMA if 1D tiling is involved.
Please give it a try.

-- 
You are receiving this mail because:
You are the assignee for the bug.

[-- Attachment #1.2: Type: text/html, Size: 1339 bytes --]

[-- Attachment #2: Type: text/plain, Size: 159 bytes --]

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[Bug 83500] si_dma_copy_tile causes GPU hangs

[bugzilla-daemon]

[-- Attachment #1.1: Type: text/plain, Size: 494 bytes --]

https://bugs.freedesktop.org/show_bug.cgi?id=83500

--- Comment #3 from Michel Dänzer <michel@daenzer.net> ---
Maybe we need to determine the other tiling parameters differently for 1D
tiling? IIRC Marek fixed things like that before.

Anyway, in the command stream dump you provided before, it looked like the
tiling parameters were totally bogus, mostly all 0. I suspect this needs more
investigation.

-- 
You are receiving this mail because:
You are the assignee for the bug.

[-- Attachment #1.2: Type: text/html, Size: 1256 bytes --]

[-- Attachment #2: Type: text/plain, Size: 159 bytes --]

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[Bug 83500] si_dma_copy_tile causes GPU hangs

[bugzilla-daemon]

[-- Attachment #1.1: Type: text/plain, Size: 687 bytes --]

https://bugs.freedesktop.org/show_bug.cgi?id=83500

--- Comment #4 from Christian König <deathsimple@vodafone.de> ---
(In reply to comment #3)
> Anyway, in the command stream dump you provided before, it looked like the
> tiling parameters were totally bogus, mostly all 0. I suspect this needs
> more investigation.

Yeah, that's what I noticed immediately as well. Maybe attach a gdb to X, set a
breakpoint to si_dma_copy_tile and check what those parameters usually look
like.

If they aren't usually all zero (which is likely) we should figure out why they
are zero in this special case.

-- 
You are receiving this mail because:
You are the assignee for the bug.

[-- Attachment #1.2: Type: text/html, Size: 1532 bytes --]

[-- Attachment #2: Type: text/plain, Size: 159 bytes --]

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[Bug 83500] si_dma_copy_tile causes GPU hangs

[bugzilla-daemon]

[-- Attachment #1.1: Type: text/plain, Size: 286 bytes --]

https://bugs.freedesktop.org/show_bug.cgi?id=83500

--- Comment #5 from Michel Dänzer <michel@daenzer.net> ---
You can just make the breakpoint conditional, e.g.:

 b si_dma.c:228 if array_mode == 0

-- 
You are receiving this mail because:
You are the assignee for the bug.

[-- Attachment #1.2: Type: text/html, Size: 1048 bytes --]

[-- Attachment #2: Type: text/plain, Size: 159 bytes --]

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[Bug 83500] si_dma_copy_tile causes GPU hangs

[bugzilla-daemon]

[-- Attachment #1.1: Type: text/plain, Size: 747 bytes --]

https://bugs.freedesktop.org/show_bug.cgi?id=83500

--- Comment #6 from Grigori Goronzy <greg@chown.ath.cx> ---
The tiling parameters don't look bogus and they certainly aren't zero. In the
dumped IB there's mt = 1, num_banks = 3, tile_split = 3 in DW 7. Looking at DW
3, there is array_mode = 2, bankw = 0, bankh = 0, mtilea = 0. That might as
well be completely wrong for the given surface, but it's not bogus in the sense
that the values are invalid.

At first I thought bankw/bankh/mtilea being all set to zero was strange, but
this seems to match how libdrm sets up 1D tiled surfaces.

For reference, this is the IB we're talking about:
http://pastebin.com/jFWk9bU5

-- 
You are receiving this mail because:
You are the assignee for the bug.

[-- Attachment #1.2: Type: text/html, Size: 1532 bytes --]

[-- Attachment #2: Type: text/plain, Size: 159 bytes --]

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[Bug 83500] si_dma_copy_tile causes GPU hangs

[bugzilla-daemon]

[-- Attachment #1.1: Type: text/plain, Size: 272 bytes --]

https://bugs.freedesktop.org/show_bug.cgi?id=83500

--- Comment #7 from Michel Dänzer <michel@daenzer.net> ---
Yeah, sorry, I misread DW 3 as having array_mode == 0 when it's actually 2.

-- 
You are receiving this mail because:
You are the assignee for the bug.

[-- Attachment #1.2: Type: text/html, Size: 1034 bytes --]

[-- Attachment #2: Type: text/plain, Size: 159 bytes --]

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[Bug 83500] si_dma_copy_tile causes GPU hangs

[bugzilla-daemon]

[-- Attachment #1.1: Type: text/plain, Size: 533 bytes --]

https://bugs.freedesktop.org/show_bug.cgi?id=83500

--- Comment #8 from Christian König <deathsimple@vodafone.de> ---
Oh, yeah you're right got that wrong as well.

But what I hoped to have checked as well is that it sounded like this copy
command worked correctly in 90% of all cases and only in a minority just locked
up.

Is that correct? Or in other words what makes this special case lock up? Does
it work for other resolutions? etc...

-- 
You are receiving this mail because:
You are the assignee for the bug.

[-- Attachment #1.2: Type: text/html, Size: 1302 bytes --]

[-- Attachment #2: Type: text/plain, Size: 159 bytes --]

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[Bug 83500] si_dma_copy_tile causes GPU hangs

[bugzilla-daemon]

[-- Attachment #1.1: Type: text/plain, Size: 295 bytes --]

https://bugs.freedesktop.org/show_bug.cgi?id=83500

--- Comment #9 from Michel Dänzer <michel@daenzer.net> ---
Do the fixes from
http://lists.freedesktop.org/archives/mesa-dev/2014-September/068738.html help?

-- 
You are receiving this mail because:
You are the assignee for the bug.

[-- Attachment #1.2: Type: text/html, Size: 1145 bytes --]

[-- Attachment #2: Type: text/plain, Size: 159 bytes --]

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[Bug 83500] si_dma_copy_tile causes GPU hangs

[bugzilla-daemon]

[-- Attachment #1.1: Type: text/plain, Size: 827 bytes --]

https://bugs.freedesktop.org/show_bug.cgi?id=83500

Michel Dänzer <michel@daenzer.net> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|NEW                         |RESOLVED
         Resolution|---                         |FIXED

--- Comment #10 from Michel Dänzer <michel@daenzer.net> ---
Module: Mesa
Branch: master
Commit: ae4536b4f71cbe76230ea7edc7eb4d6041e651b4
URL:   
http://cgit.freedesktop.org/mesa/mesa/commit/?id=ae4536b4f71cbe76230ea7edc7eb4d6041e651b4

Author: Michel Dänzer <michel.daenzer@amd.com>
Date:   Tue Nov 11 16:10:20 2014 +0900

radeonsi: Disable asynchronous DMA except for PIPE_BUFFER

-- 
You are receiving this mail because:
You are the assignee for the bug.

[-- Attachment #1.2: Type: text/html, Size: 2448 bytes --]

[-- Attachment #2: Type: text/plain, Size: 159 bytes --]

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel