iommu/arm-smmu: tegra: Detect number of instances at runtime

Parse the reg property in device tree and detect the number of instances
represented by a device tree node. This is subsequently needed in order
to support single-instance SMMUs with the Tegra implementation because
additional programming is needed to properly configure the SID override
registers in the memory controller.

Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://lore.kernel.org/r/20210603164632.1000458-5-thierry.reding@gmail.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com>

Author: thierryreding

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

@@ -20,13 +20,19 @@
  * The third instance usage is through standard arm-smmu driver itself and
  * is out of scope of this implementation.
  */
-#define NUM_SMMU_INSTANCES 2
+#define MAX_SMMU_INSTANCES 2
 
 struct nvidia_smmu {
-	struct arm_smmu_device	smmu;
-	void __iomem		*bases[NUM_SMMU_INSTANCES];
+	struct arm_smmu_device smmu;
+	void __iomem *bases[MAX_SMMU_INSTANCES];
+	unsigned int num_instances;
 };
 
+static inline struct nvidia_smmu *to_nvidia_smmu(struct arm_smmu_device *smmu)
+{
+	return container_of(smmu, struct nvidia_smmu, smmu);
+}
+
 static inline void __iomem *nvidia_smmu_page(struct arm_smmu_device *smmu,
 					     unsigned int inst, int page)
 {
@@ -47,9 +53,10 @@ static u32 nvidia_smmu_read_reg(struct arm_smmu_device *smmu,
 static void nvidia_smmu_write_reg(struct arm_smmu_device *smmu,
 				  int page, int offset, u32 val)
 {
+	struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
 	unsigned int i;
 
-	for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+	for (i = 0; i < nvidia->num_instances; i++) {
 		void __iomem *reg = nvidia_smmu_page(smmu, i, page) + offset;
 
 		writel_relaxed(val, reg);
@@ -67,9 +74,10 @@ static u64 nvidia_smmu_read_reg64(struct arm_smmu_device *smmu,
 static void nvidia_smmu_write_reg64(struct arm_smmu_device *smmu,
 				    int page, int offset, u64 val)
 {
+	struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
 	unsigned int i;
 
-	for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+	for (i = 0; i < nvidia->num_instances; i++) {
 		void __iomem *reg = nvidia_smmu_page(smmu, i, page) + offset;
 
 		writeq_relaxed(val, reg);
@@ -79,6 +87,7 @@ static void nvidia_smmu_write_reg64(struct arm_smmu_device *smmu,
 static void nvidia_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
 				 int sync, int status)
 {
+	struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
 	unsigned int delay;
 
 	arm_smmu_writel(smmu, page, sync, 0);
@@ -90,7 +99,7 @@ static void nvidia_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
 			u32 val = 0;
 			unsigned int i;
 
-			for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+			for (i = 0; i < nvidia->num_instances; i++) {
 				void __iomem *reg;
 
 				reg = nvidia_smmu_page(smmu, i, page) + status;
@@ -112,9 +121,10 @@ static void nvidia_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
 
 static int nvidia_smmu_reset(struct arm_smmu_device *smmu)
 {
+	struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
 	unsigned int i;
 
-	for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+	for (i = 0; i < nvidia->num_instances; i++) {
 		u32 val;
 		void __iomem *reg = nvidia_smmu_page(smmu, i, ARM_SMMU_GR0) +
 				    ARM_SMMU_GR0_sGFSR;
@@ -157,8 +167,9 @@ static irqreturn_t nvidia_smmu_global_fault(int irq, void *dev)
 	unsigned int inst;
 	irqreturn_t ret = IRQ_NONE;
 	struct arm_smmu_device *smmu = dev;
+	struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
 
-	for (inst = 0; inst < NUM_SMMU_INSTANCES; inst++) {
+	for (inst = 0; inst < nvidia->num_instances; inst++) {
 		irqreturn_t irq_ret;
 
 		irq_ret = nvidia_smmu_global_fault_inst(irq, smmu, inst);
@@ -202,11 +213,13 @@ static irqreturn_t nvidia_smmu_context_fault(int irq, void *dev)
 	struct arm_smmu_device *smmu;
 	struct iommu_domain *domain = dev;
 	struct arm_smmu_domain *smmu_domain;
+	struct nvidia_smmu *nvidia;
 
 	smmu_domain = container_of(domain, struct arm_smmu_domain, domain);
 	smmu = smmu_domain->smmu;
+	nvidia = to_nvidia_smmu(smmu);
 
-	for (inst = 0; inst < NUM_SMMU_INSTANCES; inst++) {
+	for (inst = 0; inst < nvidia->num_instances; inst++) {
 		irqreturn_t irq_ret;
 
 		/*
@@ -235,29 +248,41 @@ static const struct arm_smmu_impl nvidia_smmu_impl = {
 	.context_fault = nvidia_smmu_context_fault,
 };
 
+static const struct arm_smmu_impl nvidia_smmu_single_impl = {
+};
+
 struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu)
 {
 	struct resource *res;
 	struct device *dev = smmu->dev;
 	struct nvidia_smmu *nvidia_smmu;
 	struct platform_device *pdev = to_platform_device(dev);
+	unsigned int i;
 
 	nvidia_smmu = devm_krealloc(dev, smmu, sizeof(*nvidia_smmu), GFP_KERNEL);
 	if (!nvidia_smmu)
 		return ERR_PTR(-ENOMEM);
 
 	/* Instance 0 is ioremapped by arm-smmu.c. */
 	nvidia_smmu->bases[0] = smmu->base;
+	nvidia_smmu->num_instances++;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	if (!res)
-		return ERR_PTR(-ENODEV);
+	for (i = 1; i < MAX_SMMU_INSTANCES; i++) {
+		res = platform_get_resource(pdev, IORESOURCE_MEM, i);
+		if (!res)
+			break;
 
-	nvidia_smmu->bases[1] = devm_ioremap_resource(dev, res);
-	if (IS_ERR(nvidia_smmu->bases[1]))
-		return ERR_CAST(nvidia_smmu->bases[1]);
+		nvidia_smmu->bases[i] = devm_ioremap_resource(dev, res);
+		if (IS_ERR(nvidia_smmu->bases[i]))
+			return ERR_CAST(nvidia_smmu->bases[i]);
+
+		nvidia_smmu->num_instances++;
+	}
 
-	nvidia_smmu->smmu.impl = &nvidia_smmu_impl;
+	if (nvidia_smmu->num_instances == 1)
+		nvidia_smmu->smmu.impl = &nvidia_smmu_single_impl;
+	else
+		nvidia_smmu->smmu.impl = &nvidia_smmu_impl;
 
 	return &nvidia_smmu->smmu;
 }