| Message ID | 1474893160-12321-3-git-send-email-ard.biesheuvel@linaro.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On Mon, Sep 26, 2016 at 9:32 PM, Ard Biesheuvel <ard.biesheuvel@linaro.org> wrote: > The 100c10 scratch page is mapped using dma_map_page() before the TTM > layer has had a chance to set the DMA mask. This means we are still > running with the default of 32 when this code executes, and this causes > problems for platforms with no memory below 4 GB (such as AMD Seattle) > > So move the dma_map_page() to the .init hook, which executes after the > DMA mask has been set. > > Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> > --- > drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c | 26 ++++++++++++++------ > 1 file changed, 18 insertions(+), 8 deletions(-) > > diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c > index 76433cc66fff..5c8132873e60 100644 > --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c > +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c > @@ -93,7 +93,18 @@ gf100_fb_init(struct nvkm_fb *base) > struct gf100_fb *fb = gf100_fb(base); > struct nvkm_device *device = fb->base.subdev.device; > > - if (fb->r100c10_page) > + if (!fb->r100c10) { > + dma_addr_t addr = dma_map_page(device->dev, fb->r100c10_page, 0, > + PAGE_SIZE, DMA_BIDIRECTIONAL); > + if (!dma_mapping_error(device->dev, addr)) { > + fb->r100c10 = addr; > + } else { > + nvkm_warn(&fb->base.subdev, > + "dma_map_page() failed on 100c10 page\n"); > + } > + } > + > + if (fb->r100c10) > nvkm_wr32(device, 0x100c10, fb->r100c10 >> 8); gf100_fb_oneinit() seems to be a better place for this, since it will be executed exactly once, which is what you want for a memory allocation. As you can see other memory allocations are also performed there, which hints it should have been done there (and not in ctor) in the first place. Maybe you can also move the alloc_page() there so everything is done in the same place. > } > > @@ -103,12 +114,13 @@ gf100_fb_dtor(struct nvkm_fb *base) > struct gf100_fb *fb = gf100_fb(base); > struct nvkm_device *device = fb->base.subdev.device; > > - if (fb->r100c10_page) { > + if (fb->r100c10) { > dma_unmap_page(device->dev, fb->r100c10, PAGE_SIZE, > DMA_BIDIRECTIONAL); > - __free_page(fb->r100c10_page); > } > > + __free_page(fb->r100c10_page); > + If you move the allocation/mapping to gf100_fb_oneinit() then I suppose you don't need this change.
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c index 76433cc66fff..5c8132873e60 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c @@ -93,7 +93,18 @@ gf100_fb_init(struct nvkm_fb *base) struct gf100_fb *fb = gf100_fb(base); struct nvkm_device *device = fb->base.subdev.device; - if (fb->r100c10_page) + if (!fb->r100c10) { + dma_addr_t addr = dma_map_page(device->dev, fb->r100c10_page, 0, + PAGE_SIZE, DMA_BIDIRECTIONAL); + if (!dma_mapping_error(device->dev, addr)) { + fb->r100c10 = addr; + } else { + nvkm_warn(&fb->base.subdev, + "dma_map_page() failed on 100c10 page\n"); + } + } + + if (fb->r100c10) nvkm_wr32(device, 0x100c10, fb->r100c10 >> 8); } @@ -103,12 +114,13 @@ gf100_fb_dtor(struct nvkm_fb *base) struct gf100_fb *fb = gf100_fb(base); struct nvkm_device *device = fb->base.subdev.device; - if (fb->r100c10_page) { + if (fb->r100c10) { dma_unmap_page(device->dev, fb->r100c10, PAGE_SIZE, DMA_BIDIRECTIONAL); - __free_page(fb->r100c10_page); } + __free_page(fb->r100c10_page); + return fb; } @@ -124,11 +136,9 @@ gf100_fb_new_(const struct nvkm_fb_func *func, struct nvkm_device *device, *pfb = &fb->base; fb->r100c10_page = alloc_page(GFP_KERNEL | __GFP_ZERO); - if (fb->r100c10_page) { - fb->r100c10 = dma_map_page(device->dev, fb->r100c10_page, 0, - PAGE_SIZE, DMA_BIDIRECTIONAL); - if (dma_mapping_error(device->dev, fb->r100c10)) - return -EFAULT; + if (!fb->r100c10_page) { + nvkm_error(&fb->base.subdev, "failed 100c10 page alloc\n"); + return -ENOMEM; } return 0;
The 100c10 scratch page is mapped using dma_map_page() before the TTM layer has had a chance to set the DMA mask. This means we are still running with the default of 32 when this code executes, and this causes problems for platforms with no memory below 4 GB (such as AMD Seattle) So move the dma_map_page() to the .init hook, which executes after the DMA mask has been set. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> --- drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c | 26 ++++++++++++++------ 1 file changed, 18 insertions(+), 8 deletions(-)