[PATCH v3 0/7] Nvidia Arm SMMUv2 Implementation

[PATCH v3 0/7] Nvidia Arm SMMUv2 Implementation

[Krishna Reddy]

Changes in v3:
Rebased on top of https://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git/ next.
Resolved compile error seen with tegra194.dtsi changes after rebase.

v2 - https://lkml.org/lkml/2019/9/2/980
v1 - https://lkml.org/lkml/2019/8/29/1588

Krishna Reddy (7):
  iommu/arm-smmu: prepare arm_smmu_flush_ops for override
  iommu/arm-smmu: add NVIDIA implementation for dual ARM MMU-500 usage
  dt-bindings: arm-smmu: Add binding for Tegra194 SMMU
  iommu/arm-smmu: Add global/context fault implementation hooks
  arm64: tegra: Add Memory controller DT node on T194
  arm64: tegra: Add DT node for T194 SMMU
  arm64: tegra: enable SMMU for SDHCI and EQOS on T194

 .../devicetree/bindings/iommu/arm,smmu.txt         |   4 +
 MAINTAINERS                                        |   2 +
 arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi     |   4 +
 arch/arm64/boot/dts/nvidia/tegra194.dtsi           |  88 +++++++
 drivers/iommu/Makefile                             |   2 +-
 drivers/iommu/arm-smmu-impl.c                      |   3 +
 drivers/iommu/arm-smmu-nvidia.c                    | 287 +++++++++++++++++++++
 drivers/iommu/arm-smmu.c                           |  27 +-
 drivers/iommu/arm-smmu.h                           |   8 +-
 9 files changed, 413 insertions(+), 12 deletions(-)
 create mode 100644 drivers/iommu/arm-smmu-nvidia.c

-- 
2.7.4

[PATCH v3 1/7] iommu/arm-smmu: prepare arm_smmu_flush_ops for override

[Krishna Reddy]

Remove const keyword for arm_smmu_flush_ops in arm_smmu_domain
and replace direct references to arm_smmu_tlb_sync* functions with
arm_smmu_flush_ops->tlb_sync().
This is necessary for vendor specific implementations that
need to override arm_smmu_flush_ops in part or full.

Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
---
 drivers/iommu/arm-smmu.c | 16 ++++++++--------
 drivers/iommu/arm-smmu.h |  4 +++-
 2 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 91af695..fc0b27d 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
 
@@ -290,6 +287,8 @@ static void arm_smmu_tlb_sync_vmid(void *cookie)
 static void arm_smmu_tlb_inv_context_s1(void *cookie)
 {
 	struct arm_smmu_domain *smmu_domain = cookie;
+	const struct arm_smmu_flush_ops *ops = smmu_domain->flush_ops;
+
 	/*
 	 * The TLBI write may be relaxed, so ensure that PTEs cleared by the
 	 * current CPU are visible beforehand.
@@ -297,18 +296,19 @@ static void arm_smmu_tlb_inv_context_s1(void *cookie)
 	wmb();
 	arm_smmu_cb_write(smmu_domain->smmu, smmu_domain->cfg.cbndx,
 			  ARM_SMMU_CB_S1_TLBIASID, smmu_domain->cfg.asid);
-	arm_smmu_tlb_sync_context(cookie);
+	ops->tlb_sync(cookie);
 }
 
 static void arm_smmu_tlb_inv_context_s2(void *cookie)
 {
 	struct arm_smmu_domain *smmu_domain = cookie;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	const struct arm_smmu_flush_ops *ops = smmu_domain->flush_ops;
 
 	/* See above */
 	wmb();
 	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_TLBIVMID, smmu_domain->cfg.vmid);
-	arm_smmu_tlb_sync_global(smmu);
+	ops->tlb_sync(cookie);
 }
 
 static void arm_smmu_tlb_inv_range_s1(unsigned long iova, size_t size,
@@ -410,7 +410,7 @@ static void arm_smmu_tlb_add_page(struct iommu_iotlb_gather *gather,
 	ops->tlb_inv_range(iova, granule, granule, true, cookie);
 }
 
-static const struct arm_smmu_flush_ops arm_smmu_s1_tlb_ops = {
+static struct arm_smmu_flush_ops arm_smmu_s1_tlb_ops = {
 	.tlb = {
 		.tlb_flush_all	= arm_smmu_tlb_inv_context_s1,
 		.tlb_flush_walk	= arm_smmu_tlb_inv_walk,
@@ -421,7 +421,7 @@ static const struct arm_smmu_flush_ops arm_smmu_s1_tlb_ops = {
 	.tlb_sync		= arm_smmu_tlb_sync_context,
 };
 
-static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v2 = {
+static struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v2 = {
 	.tlb = {
 		.tlb_flush_all	= arm_smmu_tlb_inv_context_s2,
 		.tlb_flush_walk	= arm_smmu_tlb_inv_walk,
@@ -432,7 +432,7 @@ static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v2 = {
 	.tlb_sync		= arm_smmu_tlb_sync_context,
 };
 
-static const struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v1 = {
+static struct arm_smmu_flush_ops arm_smmu_s2_tlb_ops_v1 = {
 	.tlb = {
 		.tlb_flush_all	= arm_smmu_tlb_inv_context_s2,
 		.tlb_flush_walk	= arm_smmu_tlb_inv_walk,
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index b19b6ca..b2d6c7f 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -207,6 +207,8 @@ 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 {
@@ -314,7 +316,7 @@ struct arm_smmu_flush_ops {
 struct arm_smmu_domain {
 	struct arm_smmu_device		*smmu;
 	struct io_pgtable_ops		*pgtbl_ops;
-	const struct arm_smmu_flush_ops	*flush_ops;
+	struct arm_smmu_flush_ops	*flush_ops;
 	struct arm_smmu_cfg		cfg;
 	enum arm_smmu_domain_stage	stage;
 	bool				non_strict;
-- 
2.7.4

[PATCH v3 2/7] iommu/arm-smmu: add NVIDIA implementation for dual ARM MMU-500 usage

[Krishna Reddy]

NVIDIA's Tegra194 soc uses two ARM MMU-500s together to interleave
IOVA accesses across them.
Add NVIDIA implementation for dual ARM MMU-500s and add new compatible
string for Tegra194 soc.

Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
---
 MAINTAINERS                     |   2 +
 drivers/iommu/Makefile          |   2 +-
 drivers/iommu/arm-smmu-impl.c   |   3 +
 drivers/iommu/arm-smmu-nvidia.c | 187 ++++++++++++++++++++++++++++++++++++++++
 drivers/iommu/arm-smmu.h        |   1 +
 5 files changed, 194 insertions(+), 1 deletion(-)
 create mode 100644 drivers/iommu/arm-smmu-nvidia.c

diff --git a/MAINTAINERS b/MAINTAINERS
index a69e6db..b61dbda 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15974,9 +15974,11 @@ 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/tegra*
+F:	drivers/iommu/arm-smmu-nvidia.c
 
 TEGRA KBC DRIVER
 M:	Laxman Dewangan <ldewangan@nvidia.com>
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index 35d1709..4ef8b74 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -14,7 +14,7 @@ obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o
 obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o amd_iommu_quirks.o
 obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += amd_iommu_debugfs.o
 obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o
-obj-$(CONFIG_ARM_SMMU) += arm-smmu.o arm-smmu-impl.o
+obj-$(CONFIG_ARM_SMMU) += arm-smmu.o arm-smmu-impl.o arm-smmu-nvidia.o
 obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o
 obj-$(CONFIG_DMAR_TABLE) += 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 5c87a38..1a19687 100644
--- a/drivers/iommu/arm-smmu-impl.c
+++ b/drivers/iommu/arm-smmu-impl.c
@@ -158,6 +158,9 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu)
 	 */
 	switch (smmu->model) {
 	case ARM_MMU500:
+		if (of_device_is_compatible(smmu->dev->of_node,
+					    "nvidia,tegra194-smmu"))
+			return nvidia_smmu_impl_init(smmu);
 		smmu->impl = &arm_mmu500_impl;
 		break;
 	case CAVIUM_SMMUV2:
diff --git a/drivers/iommu/arm-smmu-nvidia.c b/drivers/iommu/arm-smmu-nvidia.c
new file mode 100644
index 0000000..ca871dc
--- /dev/null
+++ b/drivers/iommu/arm-smmu-nvidia.c
@@ -0,0 +1,187 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Nvidia ARM SMMU v2 implementation quirks
+// Copyright (C) 2019 NVIDIA CORPORATION.  All rights reserved.
+
+#define pr_fmt(fmt) "nvidia-smmu: " fmt
+
+#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
+
+struct nvidia_smmu {
+	struct arm_smmu_device	smmu;
+	unsigned int		num_inst;
+	void __iomem		*bases[MAX_SMMU_INSTANCES];
+};
+
+#define to_nvidia_smmu(s) container_of(s, struct nvidia_smmu, smmu)
+
+#define nsmmu_page(smmu, inst, page) \
+	(((inst) ? to_nvidia_smmu(smmu)->bases[(inst)] : smmu->base) + \
+	((page) << smmu->pgshift))
+
+static u32 nsmmu_read_reg(struct arm_smmu_device *smmu,
+			      int page, int offset)
+{
+	return readl_relaxed(nsmmu_page(smmu, 0, page) + offset);
+}
+
+static void nsmmu_write_reg(struct arm_smmu_device *smmu,
+			    int page, int offset, u32 val)
+{
+	unsigned int i;
+
+	for (i = 0; i < to_nvidia_smmu(smmu)->num_inst; i++)
+		writel_relaxed(val, nsmmu_page(smmu, i, page) + offset);
+}
+
+static u64 nsmmu_read_reg64(struct arm_smmu_device *smmu,
+				int page, int offset)
+{
+	return readq_relaxed(nsmmu_page(smmu, 0, page) + offset);
+}
+
+static void nsmmu_write_reg64(struct arm_smmu_device *smmu,
+				  int page, int offset, u64 val)
+{
+	unsigned int i;
+
+	for (i = 0; i < to_nvidia_smmu(smmu)->num_inst; i++)
+		writeq_relaxed(val, nsmmu_page(smmu, i, page) + offset);
+}
+
+static void nsmmu_tlb_sync(struct arm_smmu_device *smmu, int page,
+			   int sync, int status)
+{
+	u32 reg;
+	unsigned int i;
+	unsigned int spin_cnt, delay;
+
+	arm_smmu_writel(smmu, page, sync, 0);
+
+	for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) {
+		for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) {
+			reg = 0;
+			for (i = 0; i < to_nvidia_smmu(smmu)->num_inst; i++) {
+				reg |= readl_relaxed(
+					nsmmu_page(smmu, i, page) + status);
+			}
+			if (!(reg & sTLBGSTATUS_GSACTIVE))
+				return;
+			cpu_relax();
+		}
+		udelay(delay);
+	}
+	dev_err_ratelimited(smmu->dev,
+			    "TLB sync timed out -- SMMU may be deadlocked\n");
+}
+
+static void nsmmu_tlb_sync_context(void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = cookie;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	unsigned long flags;
+
+	spin_lock_irqsave(&smmu_domain->cb_lock, flags);
+	nsmmu_tlb_sync(smmu, ARM_SMMU_CB(smmu, smmu_domain->cfg.cbndx),
+		       ARM_SMMU_CB_TLBSYNC, ARM_SMMU_CB_TLBSTATUS);
+	spin_unlock_irqrestore(&smmu_domain->cb_lock, flags);
+}
+
+static void nsmmu_tlb_sync_global(struct arm_smmu_device *smmu)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&smmu->global_sync_lock, flags);
+	nsmmu_tlb_sync(smmu, ARM_SMMU_GR0, ARM_SMMU_GR0_sTLBGSYNC,
+		       ARM_SMMU_GR0_sTLBGSTATUS);
+	spin_unlock_irqrestore(&smmu->global_sync_lock, flags);
+}
+
+static int nsmmu_reset(struct arm_smmu_device *smmu)
+{
+	u32 reg;
+	unsigned int i;
+
+	for (i = 0; i < to_nvidia_smmu(smmu)->num_inst; i++) {
+		/* clear global FSR */
+		reg = readl_relaxed(nsmmu_page(smmu, i, ARM_SMMU_GR0) +
+				    ARM_SMMU_GR0_sGFSR);
+		writel_relaxed(reg, nsmmu_page(smmu, i, ARM_SMMU_GR0) +
+				    ARM_SMMU_GR0_sGFSR);
+	}
+
+	nsmmu_tlb_sync_global(smmu);
+	return 0;
+}
+
+static int nsmmu_init_context(struct arm_smmu_domain *smmu_domain)
+{
+	smmu_domain->flush_ops->tlb_sync = nsmmu_tlb_sync_context;
+	return 0;
+}
+
+static const struct arm_smmu_impl nvidia_smmu_impl = {
+	.read_reg = nsmmu_read_reg,
+	.write_reg = nsmmu_write_reg,
+	.read_reg64 = nsmmu_read_reg64,
+	.write_reg64 = nsmmu_write_reg64,
+	.reset = nsmmu_reset,
+	.init_context = nsmmu_init_context,
+};
+
+struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu)
+{
+	unsigned int i;
+	struct nvidia_smmu *nsmmu;
+	struct resource *res;
+	struct device *dev = smmu->dev;
+	struct platform_device *pdev = to_platform_device(smmu->dev);
+
+	nsmmu = devm_kzalloc(smmu->dev, sizeof(*nsmmu), GFP_KERNEL);
+	if (!nsmmu)
+		return ERR_PTR(-ENOMEM);
+
+	nsmmu->smmu = *smmu;
+	/* Instance 0 is ioremapped by arm-smmu.c */
+	nsmmu->num_inst = 1;
+
+	for (i = 1; i < MAX_SMMU_INSTANCES; i++) {
+		res = platform_get_resource(pdev, IORESOURCE_MEM, i);
+		if (!res)
+			break;
+		nsmmu->bases[i] = devm_ioremap_resource(dev, res);
+		if (IS_ERR(nsmmu->bases[i]))
+			return (struct arm_smmu_device *)nsmmu->bases[i];
+		nsmmu->num_inst++;
+	}
+
+	nsmmu->smmu.impl = &nvidia_smmu_impl;
+	devm_kfree(smmu->dev, smmu);
+	pr_info("NVIDIA ARM SMMU Implementation, Instances=%d\n",
+		nsmmu->num_inst);
+
+	return &nsmmu->smmu;
+}
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index b2d6c7f..4520ef7 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -400,5 +400,6 @@ 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);
 
 #endif /* _ARM_SMMU_H */
-- 
2.7.4

[PATCH v3 3/7] dt-bindings: arm-smmu: Add binding for Tegra194 SMMU

[Krishna Reddy]

Add binding for NVIDIA's Tegra194 Soc SMMU that is based
on ARM MMU-500.

Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
---
 Documentation/devicetree/bindings/iommu/arm,smmu.txt | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.txt b/Documentation/devicetree/bindings/iommu/arm,smmu.txt
index 3133f3b..1d72fac 100644
--- a/Documentation/devicetree/bindings/iommu/arm,smmu.txt
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu.txt
@@ -31,6 +31,10 @@ conditions.
                   as below, SoC-specific compatibles:
                   "qcom,sdm845-smmu-500", "arm,mmu-500"
 
+                  NVIDIA SoCs that use more than one ARM MMU-500 together
+                  needs following SoC-specific compatibles along with "arm,mmu-500":
+                  "nvidia,tegra194-smmu"
+
 - reg           : Base address and size of the SMMU.
 
 - #global-interrupts : The number of global interrupts exposed by the
-- 
2.7.4

[PATCH v3 4/7] iommu/arm-smmu: Add global/context fault implementation hooks

[Krishna Reddy]

Add global/context fault hooks to allow NVIDIA SMMU implementation
handle faults across multiple SMMUs.

Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
---
 drivers/iommu/arm-smmu-nvidia.c | 100 ++++++++++++++++++++++++++++++++++++++++
 drivers/iommu/arm-smmu.c        |  11 ++++-
 drivers/iommu/arm-smmu.h        |   3 ++
 3 files changed, 112 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/arm-smmu-nvidia.c b/drivers/iommu/arm-smmu-nvidia.c
index ca871dc..2a19d41 100644
--- a/drivers/iommu/arm-smmu-nvidia.c
+++ b/drivers/iommu/arm-smmu-nvidia.c
@@ -143,6 +143,104 @@ static int nsmmu_init_context(struct arm_smmu_domain *smmu_domain)
 	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 nsmmu_global_fault_inst(int irq,
+					       struct arm_smmu_device *smmu,
+					       int inst)
+{
+	u32 gfsr, gfsynr0, gfsynr1, gfsynr2;
+
+	gfsr = readl_relaxed(nsmmu_page(smmu, inst, 0) + ARM_SMMU_GR0_sGFSR);
+	gfsynr0 = readl_relaxed(nsmmu_page(smmu, inst, 0) +
+				ARM_SMMU_GR0_sGFSYNR0);
+	gfsynr1 = readl_relaxed(nsmmu_page(smmu, inst, 0) +
+				ARM_SMMU_GR0_sGFSYNR1);
+	gfsynr2 = readl_relaxed(nsmmu_page(smmu, inst, 0) +
+				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, nsmmu_page(smmu, inst, 0) + ARM_SMMU_GR0_sGFSR);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t nsmmu_global_fault(int irq, void *dev)
+{
+	int inst;
+	irqreturn_t irq_ret = IRQ_NONE;
+	struct arm_smmu_device *smmu = dev;
+
+	for (inst = 0; inst < to_nvidia_smmu(smmu)->num_inst; inst++) {
+		irq_ret = nsmmu_global_fault_inst(irq, smmu, inst);
+		if (irq_ret == IRQ_HANDLED)
+			return irq_ret;
+	}
+
+	return irq_ret;
+}
+
+static irqreturn_t nsmmu_context_fault_bank(int irq,
+					    struct arm_smmu_device *smmu,
+					    int idx, int inst)
+{
+	u32 fsr, fsynr, cbfrsynra;
+	unsigned long iova;
+
+	fsr = arm_smmu_cb_read(smmu, idx, ARM_SMMU_CB_FSR);
+	if (!(fsr & FSR_FAULT))
+		return IRQ_NONE;
+
+	fsynr = readl_relaxed(nsmmu_page(smmu, inst, smmu->numpage + idx) +
+			      ARM_SMMU_CB_FSYNR0);
+	iova = readq_relaxed(nsmmu_page(smmu, inst, smmu->numpage + idx) +
+			     ARM_SMMU_CB_FAR);
+	cbfrsynra = readl_relaxed(nsmmu_page(smmu, inst, 1) +
+				  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, nsmmu_page(smmu, inst, smmu->numpage + idx) +
+			    ARM_SMMU_CB_FSR);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t nsmmu_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 = nsmmu_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 = nsmmu_read_reg,
 	.write_reg = nsmmu_write_reg,
@@ -150,6 +248,8 @@ static const struct arm_smmu_impl nvidia_smmu_impl = {
 	.write_reg64 = nsmmu_write_reg64,
 	.reset = nsmmu_reset,
 	.init_context = nsmmu_init_context,
+	.global_fault = nsmmu_global_fault,
+	.context_fault = nsmmu_context_fault,
 };
 
 struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu)
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index fc0b27d..2fd8848 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -635,6 +635,7 @@ 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)
@@ -797,7 +798,9 @@ 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,
+	context_fault = (smmu->impl && smmu->impl->context_fault) ?
+			 smmu->impl->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",
@@ -2008,6 +2011,7 @@ 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) {
@@ -2096,9 +2100,12 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 		smmu->num_context_irqs = smmu->num_context_banks;
 	}
 
+	global_fault = (smmu->impl && smmu->impl->global_fault) ?
+			smmu->impl->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 4520ef7..cfd5f22 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -17,6 +17,7 @@
 #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>
@@ -337,6 +338,8 @@ struct arm_smmu_impl {
 	int (*cfg_probe)(struct arm_smmu_device *smmu);
 	int (*reset)(struct arm_smmu_device *smmu);
 	int (*init_context)(struct arm_smmu_domain *smmu_domain);
+	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)
-- 
2.7.4

[PATCH v3 5/7] arm64: tegra: Add Memory controller DT node on T194

[Krishna Reddy]

Add Memory controller DT node on T194 and enable it.
This patch is a prerequisite for SMMU enable on T194.

Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
---
 arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi | 4 ++++
 arch/arm64/boot/dts/nvidia/tegra194.dtsi       | 6 ++++++
 2 files changed, 10 insertions(+)

diff --git a/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi b/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi
index 4c38426..82a02490 100644
--- a/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi
@@ -47,6 +47,10 @@
 			};
 		};
 
+		memory-controller@2c00000 {
+			status = "okay";
+		};
+
 		serial@3110000 {
 			status = "okay";
 		};
diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
index 3c0cf54..1e0b54b 100644
--- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
@@ -163,6 +163,12 @@
 			};
 		};
 
+		memory-controller@2c00000 {
+			compatible = "nvidia,tegra186-mc";
+			reg = <0x02c00000 0xb0000>;
+			status = "disabled";
+		};
+
 		uarta: serial@3100000 {
 			compatible = "nvidia,tegra194-uart", "nvidia,tegra20-uart";
 			reg = <0x03100000 0x40>;
-- 
2.7.4

[PATCH v3 6/7] arm64: tegra: Add DT node for T194 SMMU

[Krishna Reddy]

Add DT node for T194 SMMU to enable SMMU support.

Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
---
 arch/arm64/boot/dts/nvidia/tegra194.dtsi | 77 ++++++++++++++++++++++++++++++++
 1 file changed, 77 insertions(+)

diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
index 1e0b54b..6f81e90 100644
--- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
@@ -1436,6 +1436,83 @@
 			  0x82000000 0x0  0x40000000 0x1f 0x40000000 0x0 0xc0000000>; /* non-prefetchable memory (3GB) */
 	};
 
+	smmu: iommu@12000000 {
+		compatible = "arm,mmu-500","nvidia,tegra194-smmu";
+		reg = <0 0x12000000 0 0x800000>,
+		      <0 0x11000000 0 0x800000>,
+		      <0 0x10000000 0 0x800000>;
+		interrupts = <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 232 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 240 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 232 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 240 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>;
+		stream-match-mask = <0x7f80>;
+		#global-interrupts = <3>;
+		#iommu-cells = <1>;
+	};
+
 	sysram@40000000 {
 		compatible = "nvidia,tegra194-sysram", "mmio-sram";
 		reg = <0x0 0x40000000 0x0 0x50000>;
-- 
2.7.4

[PATCH v3 7/7] arm64: tegra: enable SMMU for SDHCI and EQOS on T194

[Krishna Reddy]

Enable SMMU translations for SDHCI and EQOS transactions on T194.

Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
---
 arch/arm64/boot/dts/nvidia/tegra194.dtsi | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
index 6f81e90..bf8ed7a 100644
--- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
@@ -3,6 +3,7 @@
 #include <dt-bindings/gpio/tegra194-gpio.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 #include <dt-bindings/mailbox/tegra186-hsp.h>
+#include <dt-bindings/memory/tegra186-mc.h>
 #include <dt-bindings/pinctrl/pinctrl-tegra.h>
 #include <dt-bindings/power/tegra194-powergate.h>
 #include <dt-bindings/reset/tegra194-reset.h>
@@ -51,6 +52,7 @@
 			clock-names = "master_bus", "slave_bus", "rx", "tx", "ptp_ref";
 			resets = <&bpmp TEGRA194_RESET_EQOS>;
 			reset-names = "eqos";
+			iommus = <&smmu TEGRA186_SID_EQOS>;
 			status = "disabled";
 
 			snps,write-requests = <1>;
@@ -413,6 +415,7 @@
 			clock-names = "sdhci";
 			resets = <&bpmp TEGRA194_RESET_SDMMC1>;
 			reset-names = "sdhci";
+			iommus = <&smmu TEGRA186_SID_SDMMC1>;
 			nvidia,pad-autocal-pull-up-offset-3v3-timeout =
 									<0x07>;
 			nvidia,pad-autocal-pull-down-offset-3v3-timeout =
@@ -435,6 +438,7 @@
 			clock-names = "sdhci";
 			resets = <&bpmp TEGRA194_RESET_SDMMC3>;
 			reset-names = "sdhci";
+			iommus = <&smmu TEGRA186_SID_SDMMC3>;
 			nvidia,pad-autocal-pull-up-offset-1v8 = <0x00>;
 			nvidia,pad-autocal-pull-down-offset-1v8 = <0x7a>;
 			nvidia,pad-autocal-pull-up-offset-3v3-timeout = <0x07>;
@@ -462,6 +466,7 @@
 					  <&bpmp TEGRA194_CLK_PLLC4>;
 			resets = <&bpmp TEGRA194_RESET_SDMMC4>;
 			reset-names = "sdhci";
+			iommus = <&smmu TEGRA186_SID_SDMMC4>;
 			nvidia,pad-autocal-pull-up-offset-hs400 = <0x00>;
 			nvidia,pad-autocal-pull-down-offset-hs400 = <0x00>;
 			nvidia,pad-autocal-pull-up-offset-1v8-timeout = <0x0a>;
-- 
2.7.4

Re: [PATCH v3 0/7] Nvidia Arm SMMUv2 Implementation

[Robin Murphy]

Hi Krishna,

On 19/10/2019 00:31, Krishna Reddy wrote:
> Changes in v3:
> Rebased on top of https://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git/ next.
> Resolved compile error seen with tegra194.dtsi changes after rebase.

Apologies for crossed wires, but I had a series getting rid of 
arm_smmu_flush_ops which was also meant to end up making things a bit 
easier for you:

https://lore.kernel.org/linux-iommu/cover.1568820087.git.robin.murphy@arm.com/

Will, did you have any plans to push out an updates or iommu/devel 
branch for Krishna to base on?

Robin.

> 
> v2 - https://lkml.org/lkml/2019/9/2/980
> v1 - https://lkml.org/lkml/2019/8/29/1588
> 
> Krishna Reddy (7):
>    iommu/arm-smmu: prepare arm_smmu_flush_ops for override
>    iommu/arm-smmu: add NVIDIA implementation for dual ARM MMU-500 usage
>    dt-bindings: arm-smmu: Add binding for Tegra194 SMMU
>    iommu/arm-smmu: Add global/context fault implementation hooks
>    arm64: tegra: Add Memory controller DT node on T194
>    arm64: tegra: Add DT node for T194 SMMU
>    arm64: tegra: enable SMMU for SDHCI and EQOS on T194
> 
>   .../devicetree/bindings/iommu/arm,smmu.txt         |   4 +
>   MAINTAINERS                                        |   2 +
>   arch/arm64/boot/dts/nvidia/tegra194-p2888.dtsi     |   4 +
>   arch/arm64/boot/dts/nvidia/tegra194.dtsi           |  88 +++++++
>   drivers/iommu/Makefile                             |   2 +-
>   drivers/iommu/arm-smmu-impl.c                      |   3 +
>   drivers/iommu/arm-smmu-nvidia.c                    | 287 +++++++++++++++++++++
>   drivers/iommu/arm-smmu.c                           |  27 +-
>   drivers/iommu/arm-smmu.h                           |   8 +-
>   9 files changed, 413 insertions(+), 12 deletions(-)
>   create mode 100644 drivers/iommu/arm-smmu-nvidia.c
> 

Re: [PATCH v3 3/7] dt-bindings: arm-smmu: Add binding for Tegra194 SMMU

[Robin Murphy]

On 19/10/2019 00:31, Krishna Reddy wrote:
> Add binding for NVIDIA's Tegra194 Soc SMMU that is based
> on ARM MMU-500.
> 
> Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
> ---
>   Documentation/devicetree/bindings/iommu/arm,smmu.txt | 4 ++++

Rob (+cc) is in the process of converting the SMMU bindings to schema, 
so we might need a bit of coordination here...

Robin.

>   1 file changed, 4 insertions(+)
> 
> diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.txt b/Documentation/devicetree/bindings/iommu/arm,smmu.txt
> index 3133f3b..1d72fac 100644
> --- a/Documentation/devicetree/bindings/iommu/arm,smmu.txt
> +++ b/Documentation/devicetree/bindings/iommu/arm,smmu.txt
> @@ -31,6 +31,10 @@ conditions.
>                     as below, SoC-specific compatibles:
>                     "qcom,sdm845-smmu-500", "arm,mmu-500"
>   
> +                  NVIDIA SoCs that use more than one ARM MMU-500 together
> +                  needs following SoC-specific compatibles along with "arm,mmu-500":
> +                  "nvidia,tegra194-smmu"
> +
>   - reg           : Base address and size of the SMMU.
>   
>   - #global-interrupts : The number of global interrupts exposed by the
> 

RE: [PATCH v3 0/7] Nvidia Arm SMMUv2 Implementation

[Krishna Reddy]

Hi Robin,
>>Apologies for crossed wires, but I had a series getting rid of arm_smmu_flush_ops which was also meant to end up making things a bit easier for you:

I was looking to rebase on top of your changes first.  Then I read Will's reply that said your work is queued for 5.5. 
Let me know if these patches need to rebased on top of iommu/devel or a different branch. I can resend the patch set on top of necessary branch.

-KR

Re: [PATCH v3 0/7] Nvidia Arm SMMUv2 Implementation

[Will Deacon]

On Tue, Oct 22, 2019 at 11:48:55PM +0000, Krishna Reddy wrote:
> >>Apologies for crossed wires, but I had a series getting rid of
> >>arm_smmu_flush_ops which was also meant to end up making things a bit
> >>easier for you:
> 
> I was looking to rebase on top of your changes first.  Then I read Will's
> reply that said your work is queued for 5.5.

D'oh, sorry, I completely forgot to push that branch out. Now done:

https://git.kernel.org/pub/scm/linux/kernel/git/will/linux.git/log/?h=for-joerg/arm-smmu/updates

Will

RE: [PATCH v3 0/7] Nvidia Arm SMMUv2 Implementation

[Krishna Reddy]

>>https://git.kernel.org/pub/scm/linux/kernel/git/will/linux.git/log/?h=for-joerg/arm-smmu/updates

Thanks Will! Let me rebase my patches on top of this branch and send it out.

-KR