gpu: nvgpu: remove partial mapping capability flag

Remove NVGPU_SUPPORT_PARTIAL_MAPPINGS kernel flag and the
corresponding uapi gpu charaacteristics flag
NVGPU_GPU_FLAGS_SUPPORT_PARTIAL_MAPPINGS. This functionality is
supported by fixed mapping ioctl by default.

Jira NVGPU-9832
Bug 4034184

Change-Id: Ie887c753f152afb6a4a1e4aafb5f8f6fd3b7b398
Signed-off-by: Shashank Singh <shashsingh@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2879793
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
This commit is contained in:
Shashank Singh
2023-03-30 08:54:14 +00:00
committed by mobile promotions
parent 7cab0e7124
commit 28cbdcde73
4 changed files with 0 additions and 7 deletions

View File

@@ -95,8 +95,6 @@ struct nvgpu_gpu_zbc_query_table_args {
#define NVGPU_GPU_BUS_TYPE_AXI 32
#define NVGPU_GPU_FLAGS_HAS_SYNCPOINTS (1ULL << 0)
/* MAP_BUFFER_EX with partial mappings */
#define NVGPU_GPU_FLAGS_SUPPORT_PARTIAL_MAPPINGS (1ULL << 1)
/* MAP_BUFFER_EX with sparse allocations */
#define NVGPU_GPU_FLAGS_SUPPORT_SPARSE_ALLOCS (1ULL << 2)
/* sync fence FDs are available in, e.g., submit_gpfifo */