Skip to content

GitLab

Switch branch/tag
  1. 18 Feb, 2017 3 commits
  3. 06 Oct, 2015 1 commit
  5. 03 Oct, 2015 1 commit
  7. 05 Mar, 2015 1 commit
  9. 20 Sep, 2014 1 commit
  11. 31 Mar, 2014 1 commit
  13. 29 Mar, 2014 1 commit
  15. 12 Jan, 2014 3 commits
  17. 09 Dec, 2013 1 commit
    • Siarhei Siamashka's avatar
      mali: detect and workaround mismatch between back and front buffers · eed17d55
      Siarhei Siamashka authored 
      After window creation or resize, the mali blob on the client side
requests two dri2 buffers (for back and front) from the ddx. The
problem is that the 'swap' and 'get_buffer' operations are executed
out of order relative to each other and we may have different
possible patterns of dri2 communication:

1. swap swap swap swap get_buffer swap get_buffer swap swap ...
2. swap swap swap get_buffer swap swap get_buffer swap swap ...

A major annoyance is that both mali blob on the client side and
the ddx driver in xserver need have the same idea about which one
of there two buffers goes to front and which goes to back. Older
commit https://github.com/ssvb/xf86-video-fbturbo/commit/30b4ca27d1c4


tried to address this problem in a mostly empirical way and managed
to solve it at least for the synthetic test gles-rgb-cycle-demo and
for most of the real programs (such as Qt5 applications, etc.)

However appears that this heuristics is not 100% reliable in all
cases. The Extreme Tux Racer game run in glshim manages to trigger
the back and front buffers mismatch. Which manifests itself as
erratic penguin movement.

This patch adds a special check, which now randomly samples certain
bytes from the dri2 buffers to see which one of them has been
modified by the client application between buffer swaps. If we see
that the rendering actually happens to the front buffer instead of
the back buffer, then we just change the roles of these buffers.
Signed-off-by: default avatarSiarhei Siamashka <siarhei.siamashka@gmail.com>
      eed17d55
  19. 15 Nov, 2013 1 commit
  21. 26 Oct, 2013 1 commit
  23. 19 Oct, 2013 3 commits
  25. 17 Oct, 2013 1 commit
  27. 16 Oct, 2013 1 commit
  29. 08 Oct, 2013 1 commit
    • Siarhei Siamashka's avatar
      RPi: implement threshold for deciding between CPU and DMA blits · 102957f9
      Siarhei Siamashka authored 
      

Benchmarking with x11perf, modified to support wider range of sizes
for the scroll operation. Tests have been run at the stock 700MHz CPU
clock frequency and with 1280x720 32bpp desktop.

$ DISPLAY=:0 ./x11perf -scroll5 -scroll10 -scroll15 -scroll20 \
                       -scroll30 -scroll50 -scroll100

== CPU ==

1000000 trep @   0.0289 msec ( 34600.0/sec): Scroll 5x5 pixels
1000000 trep @   0.0387 msec ( 25800.0/sec): Scroll 10x10 pixels
1000000 trep @   0.0459 msec ( 21800.0/sec): Scroll 15x15 pixels
 450000 trep @   0.0576 msec ( 17300.0/sec): Scroll 20x20 pixels
 350000 trep @   0.0817 msec ( 12200.0/sec): Scroll 30x30 pixels
 200000 trep @   0.1564 msec (  6390.0/sec): Scroll 50x50 pixels
 100000 trep @   0.4446 msec (  2250.0/sec): Scroll 100x100 pixels

== fb_copyarea (DMA) acceleration ==

1000000 trep @   0.0307 msec ( 32500.0/sec): Scroll 5x5 pixels
1000000 trep @   0.0353 msec ( 28300.0/sec): Scroll 10x10 pixels
1000000 trep @   0.0397 msec ( 25200.0/sec): Scroll 15x15 pixels
1000000 trep @   0.0464 msec ( 21600.0/sec): Scroll 20x20 pixels
 400000 trep @   0.0645 msec ( 15500.0/sec): Scroll 30x30 pixels
 250000 trep @   0.1177 msec (  8500.0/sec): Scroll 50x50 pixels
 100000 trep @   0.2783 msec (  3590.0/sec): Scroll 100x100 pixels

This shows that the ioctls overhead and the DMA setup cost is not so
significant for the Raspberry Pi. DMA already becomes a bit faster
than CPU at 10x10 size of the blit operation.

Even though there is no significant difference between CPU and DMA
for extremely small sizes of operations (the other overhead is clearly
dominating), setting a threshold is not going to harm:

== mixed CPU / fb_copyarea (DMA) with 90 pixels threshold ==

1000000 trep @   0.0291 msec ( 34300.0/sec): Scroll 5x5 pixels
1000000 trep @   0.0345 msec ( 29000.0/sec): Scroll 10x10 pixels
1000000 trep @   0.0395 msec ( 25300.0/sec): Scroll 15x15 pixels
1000000 trep @   0.0466 msec ( 21400.0/sec): Scroll 20x20 pixels
 400000 trep @   0.0650 msec ( 15400.0/sec): Scroll 30x30 pixels
 250000 trep @   0.1181 msec (  8470.0/sec): Scroll 50x50 pixels
 100000 trep @   0.2784 msec (  3590.0/sec): Scroll 100x100 pixels

If some other ARM devices also implement Raspberry Pi compatible
accelerated fb_copyarea ioctl, then the threshold selection may
be reconsidered.
Signed-off-by: default avatarSiarhei Siamashka <siarhei.siamashka@gmail.com>
      102957f9
  31. 07 Oct, 2013 1 commit
  33. 03 Oct, 2013 2 commits
  35. 22 Sep, 2013 1 commit
  37. 09 Sep, 2013 2 commits
  39. 07 Sep, 2013 3 commits
  41. 06 Sep, 2013 1 commit
    • Siarhei Siamashka's avatar
      sunxi: Only enable scaler for the layer when it is really necessary · 64a0d642
      Siarhei Siamashka authored 
      

Now the scaler is enabled for the sunxi disp layer only when we want
to use it for YUV format with XV. Whenever the layer is configured
for RGB format or deactivated, the scaler gets disabled.

This should make the driver more friendly to the other potential
scaled layer users. The total number of available scalers is only
2 for Allwinner A10 and only 1 for Allwinner A13.

The potential drawback is that now we may get an error when trying
to enable the scaler (if somebody else has used up all the available
scalers) instead of always having it reserved and ready for use.
Signed-off-by: default avatarSiarhei Siamashka <siarhei.siamashka@gmail.com>
      64a0d642
  43. 13 Aug, 2013 1 commit
  45. 04 Aug, 2013 3 commits
  47. 03 Aug, 2013 1 commit
  49. 31 Jul, 2013 3 commits
  51. 30 Jul, 2013 1 commit