mirror of
git://nv-tegra.nvidia.com/linux-nvgpu.git
synced 2025-12-22 17:36:20 +03:00
8b133e098e
By always mapping gmmu kernel page using 4kB page, it'll be consistent with native nvgpu driver. It's a workaround for enabling 64KB os kernel page support. In long term solution, GMMU_PAGE_SIZE_KERNEL will be os kernel page size, and function nvgpu_gmmu_update_page_table will choose big page or small page by comparing the size of GMMU_PAGE_SIZE_KERNEL with the size of small or big pages. Regardingly vgpu will choose kernel page size by comparing the size too when send map commands to server. Bug 3015296 Bug 3015296 Signed-off-by: Richard Zhao <rizhao@nvidia.com> Change-Id: I5d25280a9410da3ef628e5914ea962a76b102273 Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2437193 Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com> Reviewed-by: svc-mobile-misra <svc-mobile-misra@nvidia.com> Reviewed-by: svc-mobile-cert <svc-mobile-cert@nvidia.com> Reviewed-by: Deepak Nibade <dnibade@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com> GVS: Gerrit_Virtual_Submit