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: Hard code map_buffer_batch_limit

Browse Source 
Add a hard coded #define for map_buffer_batch_limit and use that
insted of querying from GPU characteristics. Also add an
nvgpu_is_enabled() flag for disabling batch mapping, and set
map_buffer_batch_limit to zero if batch mapping is disabled.

JIRA NVGPU-388

Change-Id: Ic91feea638d0f47c5c22321886cfc75e97259dc3
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1593690
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
This commit is contained in:
Terje Bergstrom
2017-11-07 11:01:26 -08:00
committed by mobile promotions
parent e728fbecba
commit 8e611fb654
6 changed files with 13 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
drivers/gpu/nvgpu/common/linux/ioctl_as.h
View File

@@ -18,6 +18,10 @@
struct inode;
struct file;
/* MAP_BUFFER_BATCH_LIMIT: the upper limit for num_unmaps and
* num_maps */
#define NVGPU_IOCTL_AS_MAP_BUFFER_BATCH_LIMIT 256
/* struct file_operations driver interface */
int gk20a_as_dev_open(struct inode *inode, struct file *filp);
int gk20a_as_dev_release(struct inode *inode, struct file *filp);