Merge tag 'arm-smmu-updates' of git://git.kernel.org/pub/scm/linux/kernel/git/will/linux into arm/smmu

Arm SMMU updates for 5.9

- Support for SMMU-500 implementation in Marvell Armada-AP806 SoC

- Support for SMMU-500 implementation in NVIDIA Tegra194 SoC

- DT compatible string updates

- Remove unused IOMMU_SYS_CACHE_ONLY flag

11 files changed, 403 insertions, 30 deletions

diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst
index 936cf2a59ca4..157214d3abe1 100644
--- a/Documentation/arm64/silicon-errata.rst
+++ b/Documentation/arm64/silicon-errata.rst
@@ -125,6 +125,9 @@ stable kernels.
 | Cavium         | ThunderX2 Core  | #219            | CAVIUM_TX2_ERRATUM_219      |
 +----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+
+| Marvell        | ARM-MMU-500     | #582743         | N/A                         |
++----------------+-----------------+-----------------+-----------------------------+
++----------------+-----------------+-----------------+-----------------------------+
 | Freescale/NXP  | LS2080A/LS1043A | A-008585        | FSL_ERRATUM_A008585         |
 +----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+
diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
index d7ceb4c34423..503160a7b9a0 100644
--- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
@@ -37,7 +37,18 @@ properties:
           - enum:
               - qcom,sc7180-smmu-500
               - qcom,sdm845-smmu-500
+              - qcom,sm8150-smmu-500
+              - qcom,sm8250-smmu-500
           - const: arm,mmu-500
+      - description: Marvell SoCs implementing "arm,mmu-500"
+        items:
+          - const: marvell,ap806-smmu-500
+          - const: arm,mmu-500
+      - description: NVIDIA SoCs that program two ARM MMU-500s identically
+        items:
+          - enum:
+              - nvidia,tegra194-smmu
+          - const: nvidia,smmu-500
       - items:
           - const: arm,mmu-500
           - const: arm,smmu-v2
@@ -55,7 +66,8 @@ properties:
           - cavium,smmu-v2
 
   reg:
-    maxItems: 1
+    minItems: 1
+    maxItems: 2
 
   '#global-interrupts':
     description: The number of global interrupts exposed by the device.
@@ -138,6 +150,23 @@ required:
 
 additionalProperties: false
 
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - nvidia,tegra194-smmu
+    then:
+      properties:
+        reg:
+          minItems: 2
+          maxItems: 2
+    else:
+      properties:
+        reg:
+          maxItems: 1
+
 examples:
   - |+
     /* SMMU with stream matching or stream indexing */
diff --git a/MAINTAINERS b/MAINTAINERS
index 496fd4eafb68..ee2c0ba13a0f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16810,8 +16810,10 @@ 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
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index 342190196dfb..2b8203db73ec 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -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
diff --git a/drivers/iommu/arm-smmu-impl.c b/drivers/iommu/arm-smmu-impl.c
index c75b9d957b70..f4ff124a1967 100644
--- a/drivers/iommu/arm-smmu-impl.c
+++ b/drivers/iommu/arm-smmu-impl.c
@@ -147,16 +147,57 @@ static const struct arm_smmu_impl arm_mmu500_impl = {
 	.reset = arm_mmu500_reset,
 };
 
+static u64 mrvl_mmu500_readq(struct arm_smmu_device *smmu, int page, int off)
+{
+	/*
+	 * Marvell Armada-AP806 erratum #582743.
+	 * Split all the readq to double readl
+	 */
+	return hi_lo_readq_relaxed(arm_smmu_page(smmu, page) + off);
+}
+
+static void mrvl_mmu500_writeq(struct arm_smmu_device *smmu, int page, int off,
+			       u64 val)
+{
+	/*
+	 * Marvell Armada-AP806 erratum #582743.
+	 * Split all the writeq to double writel
+	 */
+	hi_lo_writeq_relaxed(val, arm_smmu_page(smmu, page) + off);
+}
+
+static int mrvl_mmu500_cfg_probe(struct arm_smmu_device *smmu)
+{
+
+	/*
+	 * Armada-AP806 erratum #582743.
+	 * Hide the SMMU_IDR2.PTFSv8 fields to sidestep the AArch64
+	 * formats altogether and allow using 32 bits access on the
+	 * interconnect.
+	 */
+	smmu->features &= ~(ARM_SMMU_FEAT_FMT_AARCH64_4K |
+			    ARM_SMMU_FEAT_FMT_AARCH64_16K |
+			    ARM_SMMU_FEAT_FMT_AARCH64_64K);
+
+	return 0;
+}
+
+static const struct arm_smmu_impl mrvl_mmu500_impl = {
+	.read_reg64 = mrvl_mmu500_readq,
+	.write_reg64 = mrvl_mmu500_writeq,
+	.cfg_probe = mrvl_mmu500_cfg_probe,
+	.reset = arm_mmu500_reset,
+};
+
 
 struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu)
 {
 	const struct device_node *np = smmu->dev->of_node;
 
 	/*
-	 * We will inevitably have to combine model-specific implementation
-	 * quirks with platform-specific integration quirks, but everything
-	 * we currently support happens to work out as straightforward
-	 * mutually-exclusive assignments.
+	 * Set the impl for model-specific implementation quirks first,
+	 * such that platform integration quirks can pick it up and
+	 * inherit from it if necessary.
 	 */
 	switch (smmu->model) {
 	case ARM_MMU500:
@@ -168,12 +209,21 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu)
 		break;
 	}
 
+	/* This is implicitly MMU-400 */
 	if (of_property_read_bool(np, "calxeda,smmu-secure-config-access"))
 		smmu->impl = &calxeda_impl;
 
+	if (of_device_is_compatible(np, "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"))
+	    of_device_is_compatible(np, "qcom,sc7180-smmu-500") ||
+	    of_device_is_compatible(np, "qcom,sm8150-smmu-500") ||
+	    of_device_is_compatible(np, "qcom,sm8250-smmu-500"))
 		return qcom_smmu_impl_init(smmu);
 
+	if (of_device_is_compatible(np, "marvell,ap806-smmu-500"))
+		smmu->impl = &mrvl_mmu500_impl;
+
 	return smmu;
 }
diff --git a/drivers/iommu/arm-smmu-nvidia.c b/drivers/iommu/arm-smmu-nvidia.c
new file mode 100644
index 000000000000..31368057e9be
--- /dev/null
+++ b/drivers/iommu/arm-smmu-nvidia.c
@@ -0,0 +1,278 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// 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 and must be programmed identically for
+ * interleaved IOVA accesses across them and translates accesses from
+ * non-isochronous HW devices.
+ * Third one is used for translating accesses from isochronous HW devices.
+ * 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.
+ */
+#define NUM_SMMU_INSTANCES 2
+
+struct nvidia_smmu {
+	struct arm_smmu_device	smmu;
+	void __iomem		*bases[NUM_SMMU_INSTANCES];
+};
+
+static inline void __iomem *nvidia_smmu_page(struct arm_smmu_device *smmu,
+					     unsigned int inst, int page)
+{
+	struct nvidia_smmu *nvidia_smmu;
+
+	nvidia_smmu = container_of(smmu, struct nvidia_smmu, smmu);
+	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;
+
+	for (i = 0; i < NUM_SMMU_INSTANCES; 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;
+
+	for (i = 0; i < NUM_SMMU_INSTANCES; 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; delay *= 2) {
+		unsigned int spin_cnt;
+
+		for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) {
+			u32 val = 0;
+			unsigned int i;
+
+			for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+				void __iomem *reg;
+
+				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 < NUM_SMMU_INSTANCES; 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 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);
+	if (!gfsr)
+		return IRQ_NONE;
+
+	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);
+
+	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)
+{
+	unsigned int inst;
+	irqreturn_t ret = IRQ_NONE;
+	struct arm_smmu_device *smmu = dev;
+
+	for (inst = 0; inst < NUM_SMMU_INSTANCES; inst++) {
+		irqreturn_t irq_ret;
+
+		irq_ret = nvidia_smmu_global_fault_inst(irq, smmu, inst);
+		if (irq_ret == IRQ_HANDLED)
+			ret = IRQ_HANDLED;
+	}
+
+	return 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 = readl_relaxed(cb_base + 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 idx;
+	unsigned int inst;
+	irqreturn_t ret = IRQ_NONE;
+	struct arm_smmu_device *smmu;
+	struct iommu_domain *domain = dev;
+	struct arm_smmu_domain *smmu_domain;
+
+	smmu_domain = container_of(domain, struct arm_smmu_domain, domain);
+	smmu = smmu_domain->smmu;
+
+	for (inst = 0; inst < NUM_SMMU_INSTANCES; inst++) {
+		irqreturn_t irq_ret;
+
+		/*
+		 * Interrupt line is shared between all contexts.
+		 * 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)
+				ret = IRQ_HANDLED;
+		}
+	}
+
+	return ret;
+}
+
+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,
+	.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)
+{
+	struct resource *res;
+	struct device *dev = smmu->dev;
+	struct nvidia_smmu *nvidia_smmu;
+	struct platform_device *pdev = to_platform_device(dev);
+
+	nvidia_smmu = devm_kzalloc(dev, sizeof(*nvidia_smmu), GFP_KERNEL);
+	if (!nvidia_smmu)
+		return ERR_PTR(-ENOMEM);
+
+	/*
+	 * Copy the data from struct arm_smmu_device *smmu allocated in
+	 * arm-smmu.c. The smmu from struct nvidia_smmu replaces the smmu
+	 * pointer used in arm-smmu.c once this function returns.
+	 * This is necessary to derive nvidia_smmu from smmu pointer passed
+	 * through arm_smmu_impl function calls subsequently.
+	 */
+	nvidia_smmu->smmu = *smmu;
+	/* Instance 0 is ioremapped by arm-smmu.c. */
+	nvidia_smmu->bases[0] = smmu->base;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	if (!res)
+		return ERR_PTR(-ENODEV);
+
+	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->smmu.impl = &nvidia_smmu_impl;
+
+	/*
+	 * Free the struct arm_smmu_device *smmu allocated in arm-smmu.c.
+	 * Once this function returns, arm-smmu.c would use arm_smmu_device
+	 * allocated as part of struct nvidia_smmu.
+	 */
+	devm_kfree(dev, smmu);
+
+	return &nvidia_smmu->smmu;
+}
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index f578677a5c41..a8e814c652fe 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -1479,7 +1479,7 @@ static int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu,
 		}
 
 		/*
-		 * Try to unlock the cmq lock. This will fail if we're the last
+		 * Try to unlock the cmdq lock. This will fail if we're the last
 		 * reader, in which case we can safely update cmdq->q.llq.cons
 		 */
 		if (!arm_smmu_cmdq_shared_tryunlock(cmdq)) {
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 243bc4cb2705..56b7103e1368 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -52,9 +52,6 @@
  */
 #define QCOM_DUMMY_VAL -1
 
-#define TLB_LOOP_TIMEOUT		1000000	/* 1s! */
-#define TLB_SPIN_COUNT			10
-
 #define MSI_IOVA_BASE			0x8000000
 #define MSI_IOVA_LENGTH			0x100000
 
@@ -673,6 +670,7 @@ 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 +833,13 @@ 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",
@@ -1728,7 +1732,7 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 	unsigned int size;
 	u32 id;
 	bool cttw_reg, cttw_fw = smmu->features & ARM_SMMU_FEAT_COHERENT_WALK;
-	int i;
+	int i, ret;
 
 	dev_notice(smmu->dev, "probing hardware configuration...\n");
 	dev_notice(smmu->dev, "SMMUv%d with:\n",
@@ -1891,6 +1895,12 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 			smmu->features |= ARM_SMMU_FEAT_FMT_AARCH64_64K;
 	}
 
+	if (smmu->impl && smmu->impl->cfg_probe) {
+		ret = smmu->impl->cfg_probe(smmu);
+		if (ret)
+			return ret;
+	}
+
 	/* Now we've corralled the various formats, what'll it do? */
 	if (smmu->features & ARM_SMMU_FEAT_FMT_AARCH32_S)
 		smmu->pgsize_bitmap |= SZ_4K | SZ_64K | SZ_1M | SZ_16M;
@@ -1918,9 +1928,6 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 		dev_notice(smmu->dev, "\tStage-2: %lu-bit IPA -> %lu-bit PA\n",
 			   smmu->ipa_size, smmu->pa_size);
 
-	if (smmu->impl && smmu->impl->cfg_probe)
-		return smmu->impl->cfg_probe(smmu);
-
 	return 0;
 }
 
@@ -1946,6 +1953,7 @@ static const struct of_device_id arm_smmu_of_match[] = {
 	{ .compatible = "arm,mmu-401", .data = &arm_mmu401 },
 	{ .compatible = "arm,mmu-500", .data = &arm_mmu500 },
 	{ .compatible = "cavium,smmu-v2", .data = &cavium_smmuv2 },
+	{ .compatible = "nvidia,smmu-500", .data = &arm_mmu500 },
 	{ .compatible = "qcom,smmu-v2", .data = &qcom_smmuv2 },
 	{ },
 };
@@ -2107,6 +2115,7 @@ 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) {
@@ -2123,10 +2132,6 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	smmu = arm_smmu_impl_init(smmu);
-	if (IS_ERR(smmu))
-		return PTR_ERR(smmu);
-
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	ioaddr = res->start;
 	smmu->base = devm_ioremap_resource(dev, res);
@@ -2138,6 +2143,10 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 	 */
 	smmu->numpage = resource_size(res);
 
+	smmu = arm_smmu_impl_init(smmu);
+	if (IS_ERR(smmu))
+		return PTR_ERR(smmu);
+
 	num_irqs = 0;
 	while ((res = platform_get_resource(pdev, IORESOURCE_IRQ, num_irqs))) {
 		num_irqs++;
@@ -2193,9 +2202,14 @@ 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);
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index d172c024be61..d890a4a968e8 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -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>
@@ -236,6 +237,8 @@ enum arm_smmu_cbar_type {
 /* Maximum number of context banks per SMMU */
 #define ARM_SMMU_MAX_CBS		128
 
+#define TLB_LOOP_TIMEOUT		1000000	/* 1s! */
+#define TLB_SPIN_COUNT			10
 
 /* Shared driver definitions */
 enum arm_smmu_arch_version {
@@ -387,6 +390,8 @@ 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)
@@ -450,6 +455,7 @@ 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);
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 04fbd4bf0ff9..8f175c02f8e3 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -438,9 +438,6 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data,
 		else if (prot & IOMMU_CACHE)
 			pte |= (ARM_LPAE_MAIR_ATTR_IDX_CACHE
 				<< ARM_LPAE_PTE_ATTRINDX_SHIFT);
-		else if (prot & IOMMU_SYS_CACHE_ONLY)
-			pte |= (ARM_LPAE_MAIR_ATTR_IDX_INC_OCACHE
-				<< ARM_LPAE_PTE_ATTRINDX_SHIFT);
 	}
 
 	if (prot & IOMMU_CACHE)
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 5f0b7859d2eb..bee1a8fa1fb1 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -31,12 +31,6 @@
  * if the IOMMU page table format is equivalent.
  */
 #define IOMMU_PRIV	(1 << 5)
-/*
- * Non-coherent masters can use this page protection flag to set cacheable
- * memory attributes for only a transparent outer level of cache, also known as
- * the last-level or system cache.
- */
-#define IOMMU_SYS_CACHE_ONLY	(1 << 6)
 
 struct iommu_ops;
 struct iommu_group;