[PATCH v7 0/3] Nvidia Arm SMMUv2 Implementation

@@ -16808,8 +16808,10 @@ F:	drivers/i2c/busses/i2c-tegra.c
 
 TEGRA IOMMU DRIVERS
 M:	Thierry Reding <thierry.reding@gmail.com>
+R:	Krishna Reddy <vdumpa@nvidia.com>
 L:	linux-tegra@vger.kernel.org
 S:	Supported
+F:	drivers/iommu/arm-smmu-nvidia.c
 F:	drivers/iommu/tegra*
 
 TEGRA KBC DRIVER

@@ -15,7 +15,7 @@ obj-$(CONFIG_AMD_IOMMU) += amd/iommu.o amd/init.o amd/quirks.o
 obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += amd/debugfs.o
 obj-$(CONFIG_AMD_IOMMU_V2) += amd/iommu_v2.o
 obj-$(CONFIG_ARM_SMMU) += arm_smmu.o
-arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-qcom.o
+arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-nvidia.o arm-smmu-qcom.o
 obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o
 obj-$(CONFIG_DMAR_TABLE) += intel/dmar.o
 obj-$(CONFIG_INTEL_IOMMU) += intel/iommu.o intel/pasid.o

@@ -171,6 +171,9 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu)
 	if (of_property_read_bool(np, "calxeda,smmu-secure-config-access"))
 		smmu->impl = &calxeda_impl;
 
+	if (of_device_is_compatible(smmu->dev->of_node, "nvidia,tegra194-smmu"))
+		return nvidia_smmu_impl_init(smmu);
+
 	if (of_device_is_compatible(np, "qcom,sdm845-smmu-500") ||
 	    of_device_is_compatible(np, "qcom,sc7180-smmu-500"))
 		return qcom_smmu_impl_init(smmu);

@@ -0,0 +1,195 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// NVIDIA ARM SMMU v2 implementation quirks
+// Copyright (C) 2019-2020 NVIDIA CORPORATION.  All rights reserved.
+
+#include <linux/bitfield.h>
+#include <linux/delay.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include "arm-smmu.h"
+
+/*
+ * Tegra194 has three ARM MMU-500 Instances.
+ * Two of them are used together for interleaved IOVA accesses and
+ * used by non-isochronous HW devices for SMMU translations.
+ * Third one is used for SMMU translations from isochronous HW devices.
+ * It is possible to use this implementation to program either
+ * all three or two of the instances identically as desired through
+ * DT node.
+ *
+ * Programming all the three instances identically comes with redundant TLB
+ * invalidations as all three never need to be TLB invalidated for a HW device.
+ *
+ * When Linux kernel supports multiple SMMU devices, the SMMU device used for
+ * isochornous HW devices should be added as a separate ARM MMU-500 device
+ * in DT and be programmed independently for efficient TLB invalidates.
+ */
+#define MAX_SMMU_INSTANCES 3
+
+#define TLB_LOOP_TIMEOUT_IN_US		1000000	/* 1s! */
+#define TLB_SPIN_COUNT			10
+
+struct nvidia_smmu {
+	struct arm_smmu_device	smmu;
+	unsigned int		num_inst;
+	void __iomem		*bases[MAX_SMMU_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)
+{
+	struct nvidia_smmu *nvidia_smmu = to_nvidia_smmu(smmu);
+
+	if (!nvidia_smmu->bases[0])
+		nvidia_smmu->bases[0] = smmu->base;
+
+	return nvidia_smmu->bases[inst] + (page << smmu->pgshift);
+}
+
+static u32 nvidia_smmu_read_reg(struct arm_smmu_device *smmu,
+			      int page, int offset)
+{
+	void __iomem *reg = nvidia_smmu_page(smmu, 0, page) + offset;
+
+	return readl_relaxed(reg);
+}
+
+static void nvidia_smmu_write_reg(struct arm_smmu_device *smmu,
+			    int page, int offset, u32 val)
+{
+	unsigned int i;
+	struct nvidia_smmu *nvidia_smmu = to_nvidia_smmu(smmu);
+
+	for (i = 0; i < nvidia_smmu->num_inst; i++) {
+		void __iomem *reg = nvidia_smmu_page(smmu, i, page) + offset;
+
+		writel_relaxed(val, reg);
+	}
+}
+
+static u64 nvidia_smmu_read_reg64(struct arm_smmu_device *smmu,
+				int page, int offset)
+{
+	void __iomem *reg = nvidia_smmu_page(smmu, 0, page) + offset;
+
+	return readq_relaxed(reg);
+}
+
+static void nvidia_smmu_write_reg64(struct arm_smmu_device *smmu,
+				  int page, int offset, u64 val)
+{
+	unsigned int i;
+	struct nvidia_smmu *nvidia_smmu = to_nvidia_smmu(smmu);
+
+	for (i = 0; i < nvidia_smmu->num_inst; i++) {
+		void __iomem *reg = nvidia_smmu_page(smmu, i, page) + offset;
+
+		writeq_relaxed(val, reg);
+	}
+}
+
+static void nvidia_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
+			   int sync, int status)
+{
+	unsigned int delay;
+
+	arm_smmu_writel(smmu, page, sync, 0);
+
+	for (delay = 1; delay < TLB_LOOP_TIMEOUT_IN_US; delay *= 2) {
+		unsigned int spin_cnt;
+
+		for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) {
+			u32 val = 0;
+			unsigned int i;
+			struct nvidia_smmu *nvidia_smmu = to_nvidia_smmu(smmu);
+
+			for (i = 0; i < nvidia_smmu->num_inst; i++) {
+				void __iomem *reg =
+					nvidia_smmu_page(smmu, i, page) + status;
+
+				val |= readl_relaxed(reg);
+			}
+
+			if (!(val & ARM_SMMU_sTLBGSTATUS_GSACTIVE))
+				return;
+
+			cpu_relax();
+		}
+
+		udelay(delay);
+	}
+
+	dev_err_ratelimited(smmu->dev,
+			    "TLB sync timed out -- SMMU may be deadlocked\n");
+}
+
+static int nvidia_smmu_reset(struct arm_smmu_device *smmu)
+{
+	unsigned int i;
+
+	for (i = 0; i < to_nvidia_smmu(smmu)->num_inst; i++) {
+		u32 val;
+		void __iomem *reg = nvidia_smmu_page(smmu, i, ARM_SMMU_GR0) +
+				    ARM_SMMU_GR0_sGFSR;
+
+		/* clear global FSR */
+		val = readl_relaxed(reg);
+		writel_relaxed(val, reg);
+	}
+
+	return 0;
+}
+
+static const struct arm_smmu_impl nvidia_smmu_impl = {
+	.read_reg = nvidia_smmu_read_reg,
+	.write_reg = nvidia_smmu_write_reg,
+	.read_reg64 = nvidia_smmu_read_reg64,
+	.write_reg64 = nvidia_smmu_write_reg64,
+	.reset = nvidia_smmu_reset,
+	.tlb_sync = nvidia_smmu_tlb_sync,
+};
+
+struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu)
+{
+	unsigned int i;
+	struct nvidia_smmu *nvidia_smmu;
+	struct platform_device *pdev = to_platform_device(smmu->dev);
+
+	nvidia_smmu = devm_kzalloc(smmu->dev, sizeof(*nvidia_smmu), GFP_KERNEL);
+	if (!nvidia_smmu)
+		return ERR_PTR(-ENOMEM);
+
+	nvidia_smmu->smmu = *smmu;
+	/* Instance 0 is ioremapped by arm-smmu.c after this function returns */
+	nvidia_smmu->num_inst = 1;
+
+	for (i = 1; i < MAX_SMMU_INSTANCES; i++) {
+		struct resource *res;
+
+		res = platform_get_resource(pdev, IORESOURCE_MEM, i);
+		if (!res)
+			break;
+
+		nvidia_smmu->bases[i] = devm_ioremap_resource(smmu->dev, res);
+		if (IS_ERR(nvidia_smmu->bases[i]))
+			return ERR_CAST(nvidia_smmu->bases[i]);
+
+		nvidia_smmu->num_inst++;
+	}
+
+	nvidia_smmu->smmu.impl = &nvidia_smmu_impl;
+	/* Free the arm_smmu_device struct allocated in arm-smmu.c.
+	 * Once this function returns, arm-smmu.c would use arm_smmu_device
+	 * allocated as part of nvidia_smmu struct.
+	 */
+	devm_kfree(smmu->dev, smmu);
+
+	return &nvidia_smmu->smmu;
+}

@@ -450,6 +450,7 @@ static inline void arm_smmu_writeq(struct arm_smmu_device *smmu, int page,
 	arm_smmu_writeq((s), ARM_SMMU_CB((s), (n)), (o), (v))
 
 struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu);
+struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu);
 struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu);
 
 int arm_mmu500_reset(struct arm_smmu_device *smmu);

@@ -38,6 +38,11 @@ properties:
               - qcom,sc7180-smmu-500
               - qcom,sdm845-smmu-500
           - const: arm,mmu-500
+      - description: NVIDIA SoCs that use more than one "arm,mmu-500"
+        items:
+          - enum:
+              - nvdia,tegra194-smmu
+          - const: arm,mmu-500
       - items:
           - const: arm,mmu-500
           - const: arm,smmu-v2

@@ -147,6 +147,102 @@ static int nvidia_smmu_reset(struct arm_smmu_device *smmu)
 	return 0;
 }
 
+static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct arm_smmu_domain, domain);
+}
+
+static irqreturn_t nvidia_smmu_global_fault_inst(int irq,
+					       struct arm_smmu_device *smmu,
+					       int inst)
+{
+	u32 gfsr, gfsynr0, gfsynr1, gfsynr2;
+	void __iomem *gr0_base = nvidia_smmu_page(smmu, inst, 0);
+
+	gfsr = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSR);
+	gfsynr0 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR0);
+	gfsynr1 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR1);
+	gfsynr2 = readl_relaxed(gr0_base + ARM_SMMU_GR0_sGFSYNR2);
+
+	if (!gfsr)
+		return IRQ_NONE;
+
+	dev_err_ratelimited(smmu->dev,
+		"Unexpected global fault, this could be serious\n");
+	dev_err_ratelimited(smmu->dev,
+		"\tGFSR 0x%08x, GFSYNR0 0x%08x, GFSYNR1 0x%08x, GFSYNR2 0x%08x\n",
+		gfsr, gfsynr0, gfsynr1, gfsynr2);
+
+	writel_relaxed(gfsr, gr0_base + ARM_SMMU_GR0_sGFSR);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t nvidia_smmu_global_fault(int irq, void *dev)
+{
+	int inst;
+	irqreturn_t irq_ret = IRQ_NONE;
+	struct arm_smmu_device *smmu = dev;
+	struct nvidia_smmu *nvidia_smmu = to_nvidia_smmu(smmu);
+
+	for (inst = 0; inst < nvidia_smmu->num_inst; inst++) {
+		irq_ret = nvidia_smmu_global_fault_inst(irq, smmu, inst);
+		if (irq_ret == IRQ_HANDLED)
+			return irq_ret;
+	}
+
+	return irq_ret;
+}
+
+static irqreturn_t nvidia_smmu_context_fault_bank(int irq,
+					    struct arm_smmu_device *smmu,
+					    int idx, int inst)
+{
+	u32 fsr, fsynr, cbfrsynra;
+	unsigned long iova;
+	void __iomem *gr1_base = nvidia_smmu_page(smmu, inst, 1);
+	void __iomem *cb_base = nvidia_smmu_page(smmu, inst, smmu->numpage + idx);
+
+	fsr = arm_smmu_cb_read(smmu, idx, ARM_SMMU_CB_FSR);
+	if (!(fsr & ARM_SMMU_FSR_FAULT))
+		return IRQ_NONE;
+
+	fsynr = readl_relaxed(cb_base + ARM_SMMU_CB_FSYNR0);
+	iova = readq_relaxed(cb_base + ARM_SMMU_CB_FAR);
+	cbfrsynra = readl_relaxed(gr1_base + ARM_SMMU_GR1_CBFRSYNRA(idx));
+
+	dev_err_ratelimited(smmu->dev,
+	"Unhandled context fault: fsr=0x%x, iova=0x%08lx, fsynr=0x%x, cbfrsynra=0x%x, cb=%d\n",
+			    fsr, iova, fsynr, cbfrsynra, idx);
+
+	writel_relaxed(fsr, cb_base + ARM_SMMU_CB_FSR);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t nvidia_smmu_context_fault(int irq, void *dev)
+{
+	int inst, idx;
+	irqreturn_t irq_ret = IRQ_NONE;
+	struct iommu_domain *domain = dev;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+
+	for (inst = 0; inst < to_nvidia_smmu(smmu)->num_inst; inst++) {
+		/*
+		 * Interrupt line shared between all context faults.
+		 * Check for faults across all contexts.
+		 */
+		for (idx = 0; idx < smmu->num_context_banks; idx++) {
+			irq_ret = nvidia_smmu_context_fault_bank(irq, smmu,
+								 idx, inst);
+
+			if (irq_ret == IRQ_HANDLED)
+				return irq_ret;
+		}
+	}
+
+	return irq_ret;
+}
+
 static const struct arm_smmu_impl nvidia_smmu_impl = {
 	.read_reg = nvidia_smmu_read_reg,
 	.write_reg = nvidia_smmu_write_reg,

@@ -154,6 +250,8 @@ static const struct arm_smmu_impl nvidia_smmu_impl = {
 	.write_reg64 = nvidia_smmu_write_reg64,
 	.reset = nvidia_smmu_reset,
 	.tlb_sync = nvidia_smmu_tlb_sync,
+	.global_fault = nvidia_smmu_global_fault,
+	.context_fault = nvidia_smmu_context_fault,
 };
 
 struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu)

@@ -185,7 +283,8 @@ struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu)
 	}
 
 	nvidia_smmu->smmu.impl = &nvidia_smmu_impl;
-	/* Free the arm_smmu_device struct allocated in arm-smmu.c.
+	/*
+	 * Free the arm_smmu_device struct allocated in arm-smmu.c.
 	 * Once this function returns, arm-smmu.c would use arm_smmu_device
 	 * allocated as part of nvidia_smmu struct.
 	 */

@@ -673,6 +673,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	enum io_pgtable_fmt fmt;
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
+	irqreturn_t (*context_fault)(int irq, void *dev);
 
 	mutex_lock(&smmu_domain->init_mutex);
 	if (smmu_domain->smmu)

@@ -835,7 +836,13 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	 * handler seeing a half-initialised domain state.
 	 */
 	irq = smmu->irqs[smmu->num_global_irqs + cfg->irptndx];
-	ret = devm_request_irq(smmu->dev, irq, arm_smmu_context_fault,
+
+	if (smmu->impl && smmu->impl->context_fault)
+		context_fault = smmu->impl->context_fault;
+	else
+		context_fault = arm_smmu_context_fault;
+
+	ret = devm_request_irq(smmu->dev, irq, context_fault,
 			       IRQF_SHARED, "arm-smmu-context-fault", domain);
 	if (ret < 0) {
 		dev_err(smmu->dev, "failed to request context IRQ %d (%u)\n",

@@ -2107,6 +2114,7 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 	struct arm_smmu_device *smmu;
 	struct device *dev = &pdev->dev;
 	int num_irqs, i, err;
+	irqreturn_t (*global_fault)(int irq, void *dev);
 
 	smmu = devm_kzalloc(dev, sizeof(*smmu), GFP_KERNEL);
 	if (!smmu) {

@@ -2193,9 +2201,14 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 		smmu->num_context_irqs = smmu->num_context_banks;
 	}
 
+	if (smmu->impl && smmu->impl->global_fault)
+		global_fault = smmu->impl->global_fault;
+	else
+		global_fault = arm_smmu_global_fault;
+
 	for (i = 0; i < smmu->num_global_irqs; ++i) {
 		err = devm_request_irq(smmu->dev, smmu->irqs[i],
-				       arm_smmu_global_fault,
+				       global_fault,
 				       IRQF_SHARED,
 				       "arm-smmu global fault",
 				       smmu);

@@ -18,6 +18,7 @@
 #include <linux/io-64-nonatomic-hi-lo.h>
 #include <linux/io-pgtable.h>
 #include <linux/iommu.h>
+#include <linux/irqreturn.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>

@@ -387,6 +388,8 @@ struct arm_smmu_impl {
 	void (*tlb_sync)(struct arm_smmu_device *smmu, int page, int sync,
 			 int status);
 	int (*def_domain_type)(struct device *dev);
+	irqreturn_t (*global_fault)(int irq, void *dev);
+	irqreturn_t (*context_fault)(int irq, void *dev);
 };
 
 static inline void __iomem *arm_smmu_page(struct arm_smmu_device *smmu, int n)