search for: gk20a_instobj_func_iommu

Displaying 6 results from an estimated 6 matches for "gk20a_instobj_func_iommu".

2023 Dec 08
1
[PATCH] drm/nouveau: Fixup gk20a instobj hierarchy
..._alloc_attrs(dev, npages << PAGE_SHIFT, &node->handle, GFP_KERNEL, @@ -438,8 +438,8 @@ gk20a_instobj_ctor_iommu(struct gk20a_instmem *imem, u32 npages, u32 align, *_node = &node->base; node->dma_addrs = (void *)(node->pages + npages); - nvkm_memory_ctor(&gk20a_instobj_func_iommu, &node->base.memory); - node->base.memory.ptrs = &gk20a_instobj_ptrs; + nvkm_memory_ctor(&gk20a_instobj_func_iommu, &node->base.base.memory); + node->base.base.memory.ptrs = &gk20a_instobj_ptrs; /* Allocate backing memory */ for (i = 0; i < npages; i++) { @@...
2023 Dec 14
1
[PATCH] drm/nouveau: Fixup gk20a instobj hierarchy
...PAGE_SHIFT, > &node->handle, GFP_KERNEL, > @@ -438,8 +438,8 @@ gk20a_instobj_ctor_iommu(struct gk20a_instmem *imem, u32 npages, u32 align, > *_node = &node->base; > node->dma_addrs = (void *)(node->pages + npages); > > - nvkm_memory_ctor(&gk20a_instobj_func_iommu, &node->base.memory); > - node->base.memory.ptrs = &gk20a_instobj_ptrs; > + nvkm_memory_ctor(&gk20a_instobj_func_iommu, &node->base.base.memory); > + node->base.base.memory.ptrs = &gk20a_instobj_ptrs; > > /* Allocate backing memory */ > for...
2019 Sep 16
0
[PATCH 1/2] drm/nouveau: tegra: Fix NULL pointer dereference
...ruct nvkm_memory_func gk20a_instobj_func_dma = { .dtor = gk20a_instobj_dtor_dma, .target = gk20a_instobj_target, + .bar2 = gk20a_instobj_bar2_dma, .page = gk20a_instobj_page, .addr = gk20a_instobj_addr, .size = gk20a_instobj_size, @@ -365,6 +394,7 @@ static const struct nvkm_memory_func gk20a_instobj_func_iommu = { .dtor = gk20a_instobj_dtor_iommu, .target = gk20a_instobj_target, + .bar2 = gk20a_instobj_bar2_iommu, .page = gk20a_instobj_page, .addr = gk20a_instobj_addr, .size = gk20a_instobj_size, -- 2.23.0
2019 Sep 16
6
[PATCH 0/2] drm/nouveau: Two more fixes
From: Thierry Reding <treding at nvidia.com> Hi Ben, I messed up the ordering of patches in my tree a bit, so these two fixes got separated from the others. I don't consider these particularily urgent because the crash that the first one fixes only happens on gp10b which we don't enable by default yet and the second patch fixes a crash that only happens on module unload (or driver
2015 Nov 11
2
[PATCH] instmem/gk20a: use DMA API CPU mapping
...obj_addr, .size = gk20a_instobj_size, - .acquire = gk20a_instobj_acquire, - .release = gk20a_instobj_release, + .acquire = gk20a_instobj_acquire_dma, + .release = gk20a_instobj_release_dma, .rd32 = gk20a_instobj_rd32, .wr32 = gk20a_instobj_wr32, .map = gk20a_instobj_map, @@ -381,8 +361,8 @@ gk20a_instobj_func_iommu = { .target = gk20a_instobj_target, .addr = gk20a_instobj_addr, .size = gk20a_instobj_size, - .acquire = gk20a_instobj_acquire, - .release = gk20a_instobj_release, + .acquire = gk20a_instobj_acquire_iommu, + .release = gk20a_instobj_release_iommu, .rd32 = gk20a_instobj_rd32, .wr32 = gk20a...
2015 Nov 11
0
[PATCH] instmem/gk20a: use DMA API CPU mapping
...> - .acquire = gk20a_instobj_acquire, > - .release = gk20a_instobj_release, > + .acquire = gk20a_instobj_acquire_dma, > + .release = gk20a_instobj_release_dma, > .rd32 = gk20a_instobj_rd32, > .wr32 = gk20a_instobj_wr32, > .map = gk20a_instobj_map, > @@ -381,8 +361,8 @@ gk20a_instobj_func_iommu = { > .target = gk20a_instobj_target, > .addr = gk20a_instobj_addr, > .size = gk20a_instobj_size, > - .acquire = gk20a_instobj_acquire, > - .release = gk20a_instobj_release, > + .acquire = gk20a_instobj_acquire_iommu, > + .release = gk20a_instobj_release_iommu, > .rd...