drm/nouveau/pci: set streaming DMA mask early

Some subdevices (i.e., fb/nv50.c and fb/gf100.c) map a scratch page using
dma_map_page() way before the TTM layer has had a chance to set the DMA
mask. This may prevent the driver from loading at all on platforms whose
system memory is not covered by the default DMA mask of 32-bit (i.e., when
all RAM is above 4 GB).

So set a preliminary DMA mask right after constructing the PCI device, and
base it on the .dma_bits member of the MMU subdevice, which is what the TTM
layer will base the DMA mask on as well.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>

drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c

@@ -1664,14 +1664,31 @@ nvkm_device_pci_new(struct pci_dev *pci_dev, const char *cfg, const char *dbg,
 	*pdevice = &pdev->device;
 	pdev->pdev = pci_dev;
 
-	return nvkm_device_ctor(&nvkm_device_pci_func, quirk, &pci_dev->dev,
-				pci_is_pcie(pci_dev) ? NVKM_DEVICE_PCIE :
-				pci_find_capability(pci_dev, PCI_CAP_ID_AGP) ?
-				NVKM_DEVICE_AGP : NVKM_DEVICE_PCI,
-				(u64)pci_domain_nr(pci_dev->bus) << 32 |
-				     pci_dev->bus->number << 16 |
-				     PCI_SLOT(pci_dev->devfn) << 8 |
-				     PCI_FUNC(pci_dev->devfn), name,
-				cfg, dbg, detect, mmio, subdev_mask,
-				&pdev->device);
+	ret = nvkm_device_ctor(&nvkm_device_pci_func, quirk, &pci_dev->dev,
+			       pci_is_pcie(pci_dev) ? NVKM_DEVICE_PCIE :
+			       pci_find_capability(pci_dev, PCI_CAP_ID_AGP) ?
+			       NVKM_DEVICE_AGP : NVKM_DEVICE_PCI,
+			       (u64)pci_domain_nr(pci_dev->bus) << 32 |
+				    pci_dev->bus->number << 16 |
+				    PCI_SLOT(pci_dev->devfn) << 8 |
+				    PCI_FUNC(pci_dev->devfn), name,
+			       cfg, dbg, detect, mmio, subdev_mask,
+			       &pdev->device);
+
+	if (ret)
+		return ret;
+
+	/*
+	 * Set a preliminary DMA mask based on the .dma_bits member of the
+	 * MMU subdevice. This allows other subdevices to create DMA mappings
+	 * in their init() or oneinit() methods, which may be called before the
+	 * TTM layer sets the DMA mask definitively.
+	 * This is necessary for platforms where the default DMA mask of 32
+	 * does not cover any system memory, i.e., when all RAM is > 4 GB.
+	 */
+	if (subdev_mask & BIT(NVKM_SUBDEV_MMU))
+		dma_set_mask_and_coherent(&pci_dev->dev,
+				DMA_BIT_MASK(pdev->device.mmu->dma_bits));
+
+	return 0;
 }