nv-tegra-mirror/linux-nvgpu
1
0
Fork 0
mirror of git://nv-tegra.nvidia.com/linux-nvgpu.git synced 2025-12-23 01:50:07 +03:00
Code Issues Packages Projects Releases Wiki Activity

gpu: nvgpu: gk20a: Set lockboost size for compute

Browse Source 
For compute channel on gk20a, set lockboost size to zero.

Bug 1573856

Change-Id: I369cebf72241e4017e7d380c82caff6014e42984
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/594843
GVS: Gerrit_Virtual_Submit
This commit is contained in:
Terje Bergstrom
2014-11-06 12:58:00 +02:00
committed by Dan Willemsen
parent 5df3d09e16
commit c3892ff917
4 changed files with 39 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
include/uapi/linux/nvgpu.h
View File

@@ -459,9 +459,11 @@ struct nvgpu_set_nvmap_fd_args {
__u32 fd;
} __packed;
#define NVGPU_ALLOC_OBJ_FLAGS_LOCKBOOST_ZERO (1 << 0)
struct nvgpu_alloc_obj_ctx_args {
__u32 class_num; /* kepler3d, 2d, compute, etc */
__u32 padding;
__u32 flags; /* input, output */
__u64 obj_id; /* output, used to free later */
};