| Message ID | 1466513435-11599-1-git-send-email-ard.biesheuvel@linaro.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On 21 June 2016 at 14:50, Ard Biesheuvel <ard.biesheuvel@linaro.org> wrote: > The 100c08 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, and set the streaming DMA > mask based on the MMU subdev parameters before performing the call. > > Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> > --- > > I am sure there is a much better way to address this, but this fixes the > problem I get on AMD Seattle with a GeForce 210 PCIe card: > > nouveau 0000:02:00.0: enabling device (0000 -> 0003) > nouveau 0000:02:00.0: NVIDIA GT218 (0a8280b1) > nouveau 0000:02:00.0: bios: version 70.18.a6.00.00 > nouveau 0000:02:00.0: fb ctor failed, -14 > nouveau: probe of 0000:02:00.0 failed with error -14 > > v2: replace incorrect comparison of dma_addr_t type var against NULL > Ping? > drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv50.c | 37 ++++++++++++++------ > 1 file changed, 26 insertions(+), 11 deletions(-) > > diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv50.c > index 1b5fb02eab2a..033ca0effb7e 100644 > --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv50.c > +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv50.c > @@ -216,11 +216,30 @@ nv50_fb_init(struct nvkm_fb *base) > struct nv50_fb *fb = nv50_fb(base); > struct nvkm_device *device = fb->base.subdev.device; > > + if (!fb->r100c08) { > + /* > + * We are calling the DMA api way before the TTM layer sets the > + * DMA mask based on the MMU subdev parameters. This means we > + * are using the default DMA mask of 32, which may cause > + * problems on systems with no RAM below the 4 GB mark. So set > + * the streaming DMA mask here as well. > + */ > + dma_set_mask(device->dev, DMA_BIT_MASK(device->mmu->dma_bits)); > + > + fb->r100c08 = dma_map_page(device->dev, fb->r100c08_page, 0, > + PAGE_SIZE, DMA_BIDIRECTIONAL); > + if (dma_mapping_error(device->dev, fb->r100c08)) { > + nvkm_warn(&fb->base.subdev, > + "dma_map_page() failed on 100c08 page\n"); > + } > + } > + > /* Not a clue what this is exactly. Without pointing it at a > * scratch page, VRAM->GART blits with M2MF (as in DDX DFS) > * cause IOMMU "read from address 0" errors (rh#561267) > */ > - nvkm_wr32(device, 0x100c08, fb->r100c08 >> 8); > + if (fb->r100c08 != DMA_ERROR_CODE) > + nvkm_wr32(device, 0x100c08, fb->r100c08 >> 8); > > /* This is needed to get meaningful information from 100c90 > * on traps. No idea what these values mean exactly. */ > @@ -233,11 +252,11 @@ nv50_fb_dtor(struct nvkm_fb *base) > struct nv50_fb *fb = nv50_fb(base); > struct nvkm_device *device = fb->base.subdev.device; > > - if (fb->r100c08_page) { > + if (fb->r100c08 && fb->r100c08 != DMA_ERROR_CODE) > dma_unmap_page(device->dev, fb->r100c08, PAGE_SIZE, > DMA_BIDIRECTIONAL); > - __free_page(fb->r100c08_page); > - } > + > + __free_page(fb->r100c08_page); > > return fb; > } > @@ -264,13 +283,9 @@ nv50_fb_new_(const struct nv50_fb_func *func, struct nvkm_device *device, > *pfb = &fb->base; > > fb->r100c08_page = alloc_page(GFP_KERNEL | __GFP_ZERO); > - if (fb->r100c08_page) { > - fb->r100c08 = dma_map_page(device->dev, fb->r100c08_page, 0, > - PAGE_SIZE, DMA_BIDIRECTIONAL); > - if (dma_mapping_error(device->dev, fb->r100c08)) > - return -EFAULT; > - } else { > - nvkm_warn(&fb->base.subdev, "failed 100c08 page alloc\n"); > + if (!fb->r100c08_page) { > + nvkm_error(&fb->base.subdev, "failed 100c08 page alloc\n"); > + return -ENOMEM; > } > > return 0; > -- > 2.7.4 >
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv50.c index 1b5fb02eab2a..033ca0effb7e 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv50.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv50.c @@ -216,11 +216,30 @@ nv50_fb_init(struct nvkm_fb *base) struct nv50_fb *fb = nv50_fb(base); struct nvkm_device *device = fb->base.subdev.device; + if (!fb->r100c08) { + /* + * We are calling the DMA api way before the TTM layer sets the + * DMA mask based on the MMU subdev parameters. This means we + * are using the default DMA mask of 32, which may cause + * problems on systems with no RAM below the 4 GB mark. So set + * the streaming DMA mask here as well. + */ + dma_set_mask(device->dev, DMA_BIT_MASK(device->mmu->dma_bits)); + + fb->r100c08 = dma_map_page(device->dev, fb->r100c08_page, 0, + PAGE_SIZE, DMA_BIDIRECTIONAL); + if (dma_mapping_error(device->dev, fb->r100c08)) { + nvkm_warn(&fb->base.subdev, + "dma_map_page() failed on 100c08 page\n"); + } + } + /* Not a clue what this is exactly. Without pointing it at a * scratch page, VRAM->GART blits with M2MF (as in DDX DFS) * cause IOMMU "read from address 0" errors (rh#561267) */ - nvkm_wr32(device, 0x100c08, fb->r100c08 >> 8); + if (fb->r100c08 != DMA_ERROR_CODE) + nvkm_wr32(device, 0x100c08, fb->r100c08 >> 8); /* This is needed to get meaningful information from 100c90 * on traps. No idea what these values mean exactly. */ @@ -233,11 +252,11 @@ nv50_fb_dtor(struct nvkm_fb *base) struct nv50_fb *fb = nv50_fb(base); struct nvkm_device *device = fb->base.subdev.device; - if (fb->r100c08_page) { + if (fb->r100c08 && fb->r100c08 != DMA_ERROR_CODE) dma_unmap_page(device->dev, fb->r100c08, PAGE_SIZE, DMA_BIDIRECTIONAL); - __free_page(fb->r100c08_page); - } + + __free_page(fb->r100c08_page); return fb; } @@ -264,13 +283,9 @@ nv50_fb_new_(const struct nv50_fb_func *func, struct nvkm_device *device, *pfb = &fb->base; fb->r100c08_page = alloc_page(GFP_KERNEL | __GFP_ZERO); - if (fb->r100c08_page) { - fb->r100c08 = dma_map_page(device->dev, fb->r100c08_page, 0, - PAGE_SIZE, DMA_BIDIRECTIONAL); - if (dma_mapping_error(device->dev, fb->r100c08)) - return -EFAULT; - } else { - nvkm_warn(&fb->base.subdev, "failed 100c08 page alloc\n"); + if (!fb->r100c08_page) { + nvkm_error(&fb->base.subdev, "failed 100c08 page alloc\n"); + return -ENOMEM; } return 0;
The 100c08 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, and set the streaming DMA mask based on the MMU subdev parameters before performing the call. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> --- I am sure there is a much better way to address this, but this fixes the problem I get on AMD Seattle with a GeForce 210 PCIe card: nouveau 0000:02:00.0: enabling device (0000 -> 0003) nouveau 0000:02:00.0: NVIDIA GT218 (0a8280b1) nouveau 0000:02:00.0: bios: version 70.18.a6.00.00 nouveau 0000:02:00.0: fb ctor failed, -14 nouveau: probe of 0000:02:00.0 failed with error -14 v2: replace incorrect comparison of dma_addr_t type var against NULL drivers/gpu/drm/nouveau/nvkm/subdev/fb/nv50.c | 37 ++++++++++++++------ 1 file changed, 26 insertions(+), 11 deletions(-)