nv-tegra-mirror/linux-nv-oot
1
0
Fork 0
mirror of git://nv-tegra.nvidia.com/linux-nv-oot.git synced 2025-12-22 17:25:35 +03:00
Code Issues Packages Projects Releases Wiki Activity

gpu: host1x: Increase pushbuffer slots to 1023

Browse Source 
To avoid CDMA waiting when many jobs are queued, double
pushbuffer size.

Bug 4386806

Signed-off-by: Mikko Perttunen <mperttunen@nvidia.com>
Change-Id: I80841fdec96ba3c203c070bcc1f5c7fd1c3a7cbc
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nv-oot/+/3032829
(cherry picked from commit 281f74c323)
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nv-oot/+/3152866
GVS: buildbot_gerritrpt <buildbot_gerritrpt@nvidia.com>
Reviewed-by: Santosh BS <santoshb@nvidia.com>
This commit is contained in:
Mikko Perttunen
2023-12-12 10:12:27 +02:00
committed by mobile promotions
parent 3c87c18fcf
commit 386aa2f039
1 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
drivers/gpu/host1x/cdma.c
View File

@@ -35,14 +35,14 @@
/*
* Typically the commands written into the push buffer are a pair of words. We
* use slots to represent each of these pairs and to simplify things. Note the
* strange number of slots allocated here. 512 slots will fit exactly within a
* single memory page. We also need one additional word at the end of the push
* strange number of slots allocated here. 1024 slots will fit exactly within a
* two memory pages. We also need one additional word at the end of the push
* buffer for the RESTART opcode that will instruct the CDMA to jump back to
* the beginning of the push buffer. With 512 slots, this means that we'll use
* 2 memory pages and waste 4092 bytes of the second page that will never be
* the beginning of the push buffer. With 1024 slots, this means that we'll use
* 3 memory pages and waste 4092 bytes of the third page that will never be
* used.
*/
#define HOST1X_PUSHBUFFER_SLOTS 511
#define HOST1X_PUSHBUFFER_SLOTS 1023
/*
* Clean up push buffer resources