iommu/arm-smmu: tegra: Implement SID override programming

The secure firmware keeps some SID override registers set as passthrough
in order to allow devices such as the display controller to operate with
no knowledge of SMMU translations until an operating system driver takes
over. This is needed in order to seamlessly transition from the firmware
framebuffer to the OS framebuffer.

Upon successfully attaching a device to the SMMU and in the process
creating identity mappings for memory regions that are being accessed,
the Tegra implementation will call into the memory controller driver to
program the override SIDs appropriately.
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://lore.kernel.org/r/20210603164632.1000458-6-thierry.reding@gmail.comSigned-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com>

drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c

@@ -7,6 +7,8 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 
+#include <soc/tegra/mc.h>
+
 #include "arm-smmu.h"
 
 /*
@@ -15,10 +17,17 @@
  * interleaved IOVA accesses across them and translates accesses from
  * non-isochronous HW devices.
  * Third one is used for translating accesses from isochronous HW devices.
+ *
+ * In addition, the SMMU driver needs to coordinate with the memory controller
+ * driver to ensure that the right SID override is programmed for any given
+ * memory client. This is necessary to allow for use-case such as seamlessly
+ * handing over the display controller configuration from the firmware to the
+ * kernel.
+ *
  * This implementation supports programming of the two instances that must
- * be programmed identically.
- * The third instance usage is through standard arm-smmu driver itself and
- * is out of scope of this implementation.
+ * be programmed identically and takes care of invoking the memory controller
+ * driver for SID override programming after devices have been attached to an
+ * SMMU instance.
  */
 #define MAX_SMMU_INSTANCES 2
 
@@ -26,6 +35,7 @@ struct nvidia_smmu {
 	struct arm_smmu_device smmu;
 	void __iomem *bases[MAX_SMMU_INSTANCES];
 	unsigned int num_instances;
+	struct tegra_mc *mc;
 };
 
 static inline struct nvidia_smmu *to_nvidia_smmu(struct arm_smmu_device *smmu)
@@ -237,6 +247,17 @@ static irqreturn_t nvidia_smmu_context_fault(int irq, void *dev)
 	return ret;
 }
 
+static void nvidia_smmu_probe_finalize(struct arm_smmu_device *smmu, struct device *dev)
+{
+	struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
+	int err;
+
+	err = tegra_mc_probe_device(nvidia->mc, dev);
+	if (err < 0)
+		dev_err(smmu->dev, "memory controller probe failed for %s: %d\n",
+			dev_name(dev), err);
+}
+
 static const struct arm_smmu_impl nvidia_smmu_impl = {
 	.read_reg = nvidia_smmu_read_reg,
 	.write_reg = nvidia_smmu_write_reg,
@@ -246,9 +267,11 @@ static const struct arm_smmu_impl nvidia_smmu_impl = {
 	.tlb_sync = nvidia_smmu_tlb_sync,
 	.global_fault = nvidia_smmu_global_fault,
 	.context_fault = nvidia_smmu_context_fault,
+	.probe_finalize = nvidia_smmu_probe_finalize,
 };
 
 static const struct arm_smmu_impl nvidia_smmu_single_impl = {
+	.probe_finalize = nvidia_smmu_probe_finalize,
 };
 
 struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu)
@@ -263,6 +286,10 @@ struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu)
 	if (!nvidia_smmu)
 		return ERR_PTR(-ENOMEM);
 
+	nvidia_smmu->mc = devm_tegra_memory_controller_get(dev);
+	if (IS_ERR(nvidia_smmu->mc))
+		return ERR_CAST(nvidia_smmu->mc);
+
 	/* Instance 0 is ioremapped by arm-smmu.c. */
 	nvidia_smmu->bases[0] = smmu->base;
 	nvidia_smmu->num_instances++;