mirror of
git://nv-tegra.nvidia.com/linux-nvgpu.git
synced 2025-12-22 09:12:24 +03:00
3cd256b344
Add REMAP ioctl and accompanying support to the linux nvgpu driver. REMAP support provides per-page control over sparse VM areas using the concept of a virtual memory pool. The REMAP ioctl accepts a list of operations (each a map or unmap) that modify the VM area pages tracked by the virtual mmemory pool. Inclusion of REMAP support in the nvgpu build is controlled by the new CONFIG_NVGPU_REMAP flag. This flag is enabled by default for linux builds. A new NVGPU_GPU_FLAGS_SUPPORT_REMAP characteristics flag is added for use in detecting when REMAP support is available. When a VM allocation tagged with NVGPU_VM_AREA_ALLOC_SPARSE is made the base virtual memory pool resources are allocated. Per-page resources are later allocated when the NVGPU_AS_IOCTL_REMAP ioctl is issued. All REMAP resources are released when the corresponding VM area is freed. Jira NVGPU-6804 Change-Id: I1f2cdc0c06c1698a62640c1c6fbcb2f9db24a0bc Signed-off-by: scottl <scottl@nvidia.com> Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2542178 Tested-by: mobile promotions <svcmobile_promotions@nvidia.com> Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>