From: Thierry Reding <treding@xxxxxxxxxx> The Tegra DRM driver currently uses the IOMMU API explicitly. This means that it has fine-grained control over when exactly the translation through the IOMMU is enabled. This currently happens after the driver probes, so the driver is in a DMA quiesced state when the IOMMU translation is enabled. During the transition of the Tegra DRM driver to use the DMA API instead of the IOMMU API explicitly, it was observed that on certain platforms the display controllers were still actively fetching from memory. When a DMA IOMMU domain is created as part of the DMA/IOMMU API setup during boot, the IOMMU translation for the display controllers can be enabled a significant amount of time before the driver has had a chance to reset the hardware into a sane state. This causes the SMMU to detect faults on the addresses that the display controller is trying to fetch. To avoid this, and as a byproduct paving the way for seamless transition of display from the bootloader to the kernel, add support for reserved regions in the Tegra SMMU driver. This is implemented using the standard reserved memory device tree bindings, which let us describe regions of memory which the kernel is forbidden from using for regular allocations. The Tegra SMMU driver will parse the nodes associated with each device via the "memory-region" property and return reserved regions that the IOMMU core will then create direct mappings for prior to attaching the IOMMU domains to the devices. This ensures that a 1:1 mapping is in place when IOMMU translation starts and prevents the SMMU from detecting any faults. Signed-off-by: Thierry Reding <treding@xxxxxxxxxx> --- drivers/iommu/tegra-smmu.c | 50 +++++++++++++++++++++++++++++++++++++- 1 file changed, 49 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index a86e5c8da1b1..57b4f2b37447 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -10,6 +10,7 @@ #include <linux/kernel.h> #include <linux/of.h> #include <linux/of_device.h> +#include <linux/of_iommu.h> #include <linux/pci.h> #include <linux/platform_device.h> #include <linux/slab.h> @@ -471,6 +472,7 @@ static void tegra_smmu_as_unprepare(struct tegra_smmu *smmu, tegra_smmu_free_asid(smmu, as->id); dma_unmap_page(smmu->dev, as->pd_dma, SMMU_SIZE_PD, DMA_TO_DEVICE); + as->pd_dma = 0; as->smmu = NULL; @@ -534,6 +536,38 @@ static void tegra_smmu_set_pde(struct tegra_smmu_as *as, unsigned long iova, struct tegra_smmu *smmu = as->smmu; u32 *pd = page_address(as->pd); unsigned long offset = pd_index * sizeof(*pd); + bool unmap = false; + + /* + * XXX Move this outside of this function. Perhaps add a struct + * iommu_domain parameter to ->{get,put}_resv_regions() so that + * the mapping can be done there. + * + * The problem here is that as->smmu is only known once we attach + * the domain to a device (because then we look up the right SMMU + * instance via the dev->archdata.iommu pointer). When the direct + * mappings are created for reserved regions, the domain has not + * been attached to a device yet, so we don't know. We currently + * fix that up in ->apply_resv_regions() because that is the first + * time where we have access to a struct device that will be used + * with the IOMMU domain. However, that's asymmetric and doesn't + * take care of the page directory mapping either, so we need to + * come up with something better. + */ + if (WARN_ON_ONCE(as->pd_dma == 0)) { + as->pd_dma = dma_map_page(smmu->dev, as->pd, 0, SMMU_SIZE_PD, + DMA_TO_DEVICE); + if (dma_mapping_error(smmu->dev, as->pd_dma)) + return; + + if (!smmu_dma_addr_valid(smmu, as->pd_dma)) { + dma_unmap_page(smmu->dev, as->pd_dma, SMMU_SIZE_PD, + DMA_TO_DEVICE); + return; + } + + unmap = true; + } /* Set the page directory entry first */ pd[pd_index] = value; @@ -546,6 +580,12 @@ static void tegra_smmu_set_pde(struct tegra_smmu_as *as, unsigned long iova, smmu_flush_ptc(smmu, as->pd_dma, offset); smmu_flush_tlb_section(smmu, as->id, iova); smmu_flush(smmu); + + if (unmap) { + dma_unmap_page(smmu->dev, as->pd_dma, SMMU_SIZE_PD, + DMA_TO_DEVICE); + as->pd_dma = 0; + } } static u32 *tegra_smmu_pte_offset(struct page *pt_page, unsigned long iova) @@ -846,7 +886,6 @@ static struct iommu_device *tegra_smmu_probe_device(struct device *dev) smmu = tegra_smmu_find(args.np); if (smmu) { err = tegra_smmu_configure(smmu, dev, &args); - if (err < 0) { of_node_put(args.np); return ERR_PTR(err); @@ -864,6 +903,13 @@ static struct iommu_device *tegra_smmu_probe_device(struct device *dev) return &smmu->iommu; } +static void tegra_smmu_release_device(struct device *dev) +{ + struct tegra_smmu *smmu = dev_iommu_priv_get(dev); + + put_device(smmu->dev); +} + static const struct tegra_smmu_group_soc * tegra_smmu_find_group(struct tegra_smmu *smmu, unsigned int swgroup) { @@ -964,7 +1010,9 @@ static int tegra_smmu_of_xlate(struct device *dev, static const struct iommu_ops tegra_smmu_ops = { .domain_alloc = tegra_smmu_domain_alloc, .probe_device = tegra_smmu_probe_device, + .release_device = tegra_smmu_release_device, .device_group = tegra_smmu_device_group, + .get_resv_regions = of_iommu_get_resv_regions, .of_xlate = tegra_smmu_of_xlate, .pgsize_bitmap = SZ_4K, .default_domain_ops = &(const struct iommu_domain_ops) { -- 2.37.3