diff --git a/drivers/gpu/nvgpu/common/linux/nvgpu_mem.c b/drivers/gpu/nvgpu/common/linux/nvgpu_mem.c index 8d8909dd2..8cf3011e0 100644 --- a/drivers/gpu/nvgpu/common/linux/nvgpu_mem.c +++ b/drivers/gpu/nvgpu/common/linux/nvgpu_mem.c @@ -284,6 +284,14 @@ static u64 nvgpu_mem_get_addr_sysmem(struct gk20a *g, struct nvgpu_mem *mem) * Return the base address of %mem. Handles whether this is a VIDMEM or SYSMEM * allocation. * + * Note: this API does not make sense to use for _VIDMEM_ buffers with greater + * than one scatterlist chunk. If there's more than one scatterlist chunk then + * the buffer will not be contiguous. As such the base address probably isn't + * very useful. This is true for SYSMEM as well, if there's no IOMMU. + * + * However! It _is_ OK to use this on discontiguous sysmem buffers _if_ there's + * an IOMMU present and enabled for the GPU. + * * %attrs can be NULL. If it is not NULL then it may be inspected to determine * if the address needs to be modified before writing into a PTE. */ @@ -305,6 +313,23 @@ u64 nvgpu_mem_get_addr(struct gk20a *g, struct nvgpu_mem *mem) return alloc->base; } +/* + * This should only be used on contiguous buffers regardless of whether + * there's an IOMMU present/enabled. This applies to both SYSMEM and + * VIDMEM. + */ +u64 nvgpu_mem_get_phys_addr(struct gk20a *g, struct nvgpu_mem *mem) +{ + /* + * For a VIDMEM buf, this is identical to simply get_addr() so just fall + * back to that. + */ + if (mem->aperture == APERTURE_VIDMEM) + return nvgpu_mem_get_addr(g, mem); + + return sg_phys(mem->priv.sgt->sgl); +} + /* * Be careful how you use this! You are responsible for correctly freeing this * memory. diff --git a/drivers/gpu/nvgpu/common/mm/gmmu.c b/drivers/gpu/nvgpu/common/mm/gmmu.c index f68dfc0ae..ab9d0d411 100644 --- a/drivers/gpu/nvgpu/common/mm/gmmu.c +++ b/drivers/gpu/nvgpu/common/mm/gmmu.c @@ -212,7 +212,7 @@ u64 nvgpu_pde_phys_addr(struct gk20a *g, struct nvgpu_gmmu_pd *pd) u64 page_addr; if (g->mm.has_physical_mode) - page_addr = sg_phys(pd->mem->priv.sgt->sgl); + page_addr = nvgpu_mem_get_phys_addr(g, pd->mem); else page_addr = nvgpu_mem_get_addr(g, pd->mem); diff --git a/drivers/gpu/nvgpu/include/nvgpu/nvgpu_mem.h b/drivers/gpu/nvgpu/include/nvgpu/nvgpu_mem.h index 154142781..b939cc333 100644 --- a/drivers/gpu/nvgpu/include/nvgpu/nvgpu_mem.h +++ b/drivers/gpu/nvgpu/include/nvgpu/nvgpu_mem.h @@ -291,6 +291,7 @@ void nvgpu_memset(struct gk20a *g, struct nvgpu_mem *mem, u32 offset, u32 c, u32 size); u64 nvgpu_mem_get_addr(struct gk20a *g, struct nvgpu_mem *mem); +u64 nvgpu_mem_get_phys_addr(struct gk20a *g, struct nvgpu_mem *mem); u32 __nvgpu_aperture_mask(struct gk20a *g, enum nvgpu_aperture aperture, u32 sysmem_mask, u32 vidmem_mask);