[PATCH v9 0/4] NVIDIA ARM SMMUv2 Implementation

[PATCH v9 0/4] NVIDIA ARM SMMUv2 Implementation

[Krishna Reddy]

Changes in v9:
Move TLB Timeout and spin count macros to arm-smmu.h header to share with implementation.
Set minItems and maxItems for reg property when compatible contains nvidia,tegra194-smmu.
Update commit message for NVIDIA implementation patch.
Fail single SMMU instance usage through NVIDIA implementation to limit the usage to two or three instances.
Fix checkpatch warnings with --strict checking.

v8 - https://lkml.org/lkml/2020/6/29/2385
v7 - https://lkml.org/lkml/2020/6/28/347
v6 - https://lkml.org/lkml/2020/6/4/1018
v5 - https://lkml.org/lkml/2020/5/21/1114
v4 - https://lkml.org/lkml/2019/10/30/1054
v3 - https://lkml.org/lkml/2019/10/18/1601
v2 - https://lkml.org/lkml/2019/9/2/980
v1 - https://lkml.org/lkml/2019/8/29/1588

Krishna Reddy (4):
  iommu/arm-smmu: move TLB timeout and spin count macros
  iommu/arm-smmu: add NVIDIA implementation for ARM MMU-500 usage
  dt-bindings: arm-smmu: add binding for Tegra194 SMMU
  iommu/arm-smmu: Add global/context fault implementation hooks

 .../devicetree/bindings/iommu/arm,smmu.yaml   |  18 ++
 MAINTAINERS                                   |   2 +
 drivers/iommu/Makefile                        |   2 +-
 drivers/iommu/arm-smmu-impl.c                 |   3 +
 drivers/iommu/arm-smmu-nvidia.c               | 304 ++++++++++++++++++
 drivers/iommu/arm-smmu.c                      |  20 +-
 drivers/iommu/arm-smmu.h                      |   6 +
 7 files changed, 349 insertions(+), 6 deletions(-)
 create mode 100644 drivers/iommu/arm-smmu-nvidia.c


base-commit: 48f0bcfb7aad2c6eb4c1e66476b58475aa14393e
-- 
2.26.2

[PATCH v9 0/4] NVIDIA ARM SMMUv2 Implementation

[Krishna Reddy]

Changes in v9:
Move TLB Timeout and spin count macros to arm-smmu.h header to share with implementation.
Set minItems and maxItems for reg property when compatible contains nvidia,tegra194-smmu.
Update commit message for NVIDIA implementation patch.
Fail single SMMU instance usage through NVIDIA implementation to limit the usage to two or three instances.
Fix checkpatch warnings with --strict checking.

v8 - https://lkml.org/lkml/2020/6/29/2385
v7 - https://lkml.org/lkml/2020/6/28/347
v6 - https://lkml.org/lkml/2020/6/4/1018
v5 - https://lkml.org/lkml/2020/5/21/1114
v4 - https://lkml.org/lkml/2019/10/30/1054
v3 - https://lkml.org/lkml/2019/10/18/1601
v2 - https://lkml.org/lkml/2019/9/2/980
v1 - https://lkml.org/lkml/2019/8/29/1588

Krishna Reddy (4):
  iommu/arm-smmu: move TLB timeout and spin count macros
  iommu/arm-smmu: add NVIDIA implementation for ARM MMU-500 usage
  dt-bindings: arm-smmu: add binding for Tegra194 SMMU
  iommu/arm-smmu: Add global/context fault implementation hooks

 .../devicetree/bindings/iommu/arm,smmu.yaml   |  18 ++
 MAINTAINERS                                   |   2 +
 drivers/iommu/Makefile                        |   2 +-
 drivers/iommu/arm-smmu-impl.c                 |   3 +
 drivers/iommu/arm-smmu-nvidia.c               | 304 ++++++++++++++++++
 drivers/iommu/arm-smmu.c                      |  20 +-
 drivers/iommu/arm-smmu.h                      |   6 +
 7 files changed, 349 insertions(+), 6 deletions(-)
 create mode 100644 drivers/iommu/arm-smmu-nvidia.c


base-commit: 48f0bcfb7aad2c6eb4c1e66476b58475aa14393e
-- 
2.26.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v9 0/4] NVIDIA ARM SMMUv2 Implementation

[Krishna Reddy]

Changes in v9:
Move TLB Timeout and spin count macros to arm-smmu.h header to share with implementation.
Set minItems and maxItems for reg property when compatible contains nvidia,tegra194-smmu.
Update commit message for NVIDIA implementation patch.
Fail single SMMU instance usage through NVIDIA implementation to limit the usage to two or three instances.
Fix checkpatch warnings with --strict checking.

v8 - https://lkml.org/lkml/2020/6/29/2385
v7 - https://lkml.org/lkml/2020/6/28/347
v6 - https://lkml.org/lkml/2020/6/4/1018
v5 - https://lkml.org/lkml/2020/5/21/1114
v4 - https://lkml.org/lkml/2019/10/30/1054
v3 - https://lkml.org/lkml/2019/10/18/1601
v2 - https://lkml.org/lkml/2019/9/2/980
v1 - https://lkml.org/lkml/2019/8/29/1588

Krishna Reddy (4):
  iommu/arm-smmu: move TLB timeout and spin count macros
  iommu/arm-smmu: add NVIDIA implementation for ARM MMU-500 usage
  dt-bindings: arm-smmu: add binding for Tegra194 SMMU
  iommu/arm-smmu: Add global/context fault implementation hooks

 .../devicetree/bindings/iommu/arm,smmu.yaml   |  18 ++
 MAINTAINERS                                   |   2 +
 drivers/iommu/Makefile                        |   2 +-
 drivers/iommu/arm-smmu-impl.c                 |   3 +
 drivers/iommu/arm-smmu-nvidia.c               | 304 ++++++++++++++++++
 drivers/iommu/arm-smmu.c                      |  20 +-
 drivers/iommu/arm-smmu.h                      |   6 +
 7 files changed, 349 insertions(+), 6 deletions(-)
 create mode 100644 drivers/iommu/arm-smmu-nvidia.c


base-commit: 48f0bcfb7aad2c6eb4c1e66476b58475aa14393e
-- 
2.26.2

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH v9 0/4] NVIDIA ARM SMMUv2 Implementation

[Krishna Reddy]

Changes in v9:
Move TLB Timeout and spin count macros to arm-smmu.h header to share with implementation.
Set minItems and maxItems for reg property when compatible contains nvidia,tegra194-smmu.
Update commit message for NVIDIA implementation patch.
Fail single SMMU instance usage through NVIDIA implementation to limit the usage to two or three instances.
Fix checkpatch warnings with --strict checking.

v8 - https://lkml.org/lkml/2020/6/29/2385
v7 - https://lkml.org/lkml/2020/6/28/347
v6 - https://lkml.org/lkml/2020/6/4/1018
v5 - https://lkml.org/lkml/2020/5/21/1114
v4 - https://lkml.org/lkml/2019/10/30/1054
v3 - https://lkml.org/lkml/2019/10/18/1601
v2 - https://lkml.org/lkml/2019/9/2/980
v1 - https://lkml.org/lkml/2019/8/29/1588

Krishna Reddy (4):
  iommu/arm-smmu: move TLB timeout and spin count macros
  iommu/arm-smmu: add NVIDIA implementation for ARM MMU-500 usage
  dt-bindings: arm-smmu: add binding for Tegra194 SMMU
  iommu/arm-smmu: Add global/context fault implementation hooks

 .../devicetree/bindings/iommu/arm,smmu.yaml   |  18 ++
 MAINTAINERS                                   |   2 +
 drivers/iommu/Makefile                        |   2 +-
 drivers/iommu/arm-smmu-impl.c                 |   3 +
 drivers/iommu/arm-smmu-nvidia.c               | 304 ++++++++++++++++++
 drivers/iommu/arm-smmu.c                      |  20 +-
 drivers/iommu/arm-smmu.h                      |   6 +
 7 files changed, 349 insertions(+), 6 deletions(-)
 create mode 100644 drivers/iommu/arm-smmu-nvidia.c


base-commit: 48f0bcfb7aad2c6eb4c1e66476b58475aa14393e
-- 
2.26.2

[PATCH v9 1/4] iommu/arm-smmu: move TLB timeout and spin count macros

[Krishna Reddy]

Move TLB timeout and spin count macros to header file to
allow using the same values from vendor specific implementations.

Signed-off-by: Krishna Reddy <vdumpa-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
---
 drivers/iommu/arm-smmu.c | 3 ---
 drivers/iommu/arm-smmu.h | 2 ++
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 243bc4cb2705b..d2054178df357 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
 
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index d172c024be618..c7d0122a7c6ca 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -236,6 +236,8 @@ 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 {
-- 
2.26.2

[PATCH v9 1/4] iommu/arm-smmu: move TLB timeout and spin count macros

[Krishna Reddy]

Move TLB timeout and spin count macros to header file to
allow using the same values from vendor specific implementations.

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

diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 243bc4cb2705b..d2054178df357 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
 
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index d172c024be618..c7d0122a7c6ca 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -236,6 +236,8 @@ 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 {
-- 
2.26.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v9 1/4] iommu/arm-smmu: move TLB timeout and spin count macros

[Krishna Reddy]

Move TLB timeout and spin count macros to header file to
allow using the same values from vendor specific implementations.

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

diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 243bc4cb2705b..d2054178df357 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
 
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index d172c024be618..c7d0122a7c6ca 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -236,6 +236,8 @@ 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 {
-- 
2.26.2

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH v9 1/4] iommu/arm-smmu: move TLB timeout and spin count macros

[Krishna Reddy]

Move TLB timeout and spin count macros to header file to
allow using the same values from vendor specific implementations.

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

diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 243bc4cb2705b..d2054178df357 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
 
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index d172c024be618..c7d0122a7c6ca 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -236,6 +236,8 @@ 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 {
-- 
2.26.2

[PATCH v9 2/4] iommu/arm-smmu: add NVIDIA implementation for ARM MMU-500 usage

[Krishna Reddy]

NVIDIA's Tegra194 SoC has three ARM MMU-500 instances.
It uses two of ARM MMU-500s together to interleave IOVA accesses
across them and must be programmed identically.
The third SMMU instance is used as a regular ARM MMU-500 and it
can either be programmed independently or identical to other
two ARM MMU-500s.

This implementation supports programming two or three ARM MMU-500s
identically as per DT config.

Signed-off-by: Krishna Reddy <vdumpa-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
---
 MAINTAINERS                     |   2 +
 drivers/iommu/Makefile          |   2 +-
 drivers/iommu/arm-smmu-impl.c   |   3 +
 drivers/iommu/arm-smmu-nvidia.c | 206 ++++++++++++++++++++++++++++++++
 drivers/iommu/arm-smmu.h        |   1 +
 5 files changed, 213 insertions(+), 1 deletion(-)
 create mode 100644 drivers/iommu/arm-smmu-nvidia.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 7b5ffd646c6b9..64c37dbdd4426 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16808,8 +16808,10 @@ F:	drivers/i2c/busses/i2c-tegra.c
 
 TEGRA IOMMU DRIVERS
 M:	Thierry Reding <thierry.reding-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
+R:	Krishna Reddy <vdumpa-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
 L:	linux-tegra-u79uwXL29TY76Z2rM5mHXA@public.gmane.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 342190196dfb0..2b8203db73ec3 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 c75b9d957b702..f15571d05474e 100644
--- a/drivers/iommu/arm-smmu-impl.c
+++ b/drivers/iommu/arm-smmu-impl.c
@@ -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(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"))
 		return qcom_smmu_impl_init(smmu);
diff --git a/drivers/iommu/arm-smmu-nvidia.c b/drivers/iommu/arm-smmu-nvidia.c
new file mode 100644
index 0000000000000..5c874912e1c1a
--- /dev/null
+++ b/drivers/iommu/arm-smmu-nvidia.c
@@ -0,0 +1,206 @@
+// 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
+
+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;
+	struct nvidia_smmu *nvidia_smmu = to_nvidia_smmu(smmu);
+
+	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 < 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)
+{
+	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 arm_smmu_device struct allocated in arm-smmu.c.
+	 * The memory for the arm_smmu_device struct from arm-smmu.c is freed
+	 * subsequently.
+	 */
+	nvidia_smmu->smmu = *smmu;
+	/* Instance 0 is ioremapped by arm-smmu.c after this function returns */
+	nvidia_smmu->num_inst = 1;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	/* Minimum two SMMU instances are expected. */
+	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->num_inst++;
+
+	/* 3rd SMMU instance is Optional. */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 2);
+	if (res) {
+		nvidia_smmu->bases[2] = devm_ioremap_resource(dev, res);
+		if (IS_ERR(nvidia_smmu->bases[2]))
+			return ERR_CAST(nvidia_smmu->bases[2]);
+
+		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(dev, smmu);
+
+	return &nvidia_smmu->smmu;
+}
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index c7d0122a7c6ca..fad63efa1a72d 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -452,6 +452,7 @@ 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);
-- 
2.26.2

[PATCH v9 2/4] iommu/arm-smmu: add NVIDIA implementation for ARM MMU-500 usage

[Krishna Reddy]

NVIDIA's Tegra194 SoC has three ARM MMU-500 instances.
It uses two of ARM MMU-500s together to interleave IOVA accesses
across them and must be programmed identically.
The third SMMU instance is used as a regular ARM MMU-500 and it
can either be programmed independently or identical to other
two ARM MMU-500s.

This implementation supports programming two or three ARM MMU-500s
identically as per DT config.

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 | 206 ++++++++++++++++++++++++++++++++
 drivers/iommu/arm-smmu.h        |   1 +
 5 files changed, 213 insertions(+), 1 deletion(-)
 create mode 100644 drivers/iommu/arm-smmu-nvidia.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 7b5ffd646c6b9..64c37dbdd4426 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -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
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index 342190196dfb0..2b8203db73ec3 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 c75b9d957b702..f15571d05474e 100644
--- a/drivers/iommu/arm-smmu-impl.c
+++ b/drivers/iommu/arm-smmu-impl.c
@@ -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(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"))
 		return qcom_smmu_impl_init(smmu);
diff --git a/drivers/iommu/arm-smmu-nvidia.c b/drivers/iommu/arm-smmu-nvidia.c
new file mode 100644
index 0000000000000..5c874912e1c1a
--- /dev/null
+++ b/drivers/iommu/arm-smmu-nvidia.c
@@ -0,0 +1,206 @@
+// 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
+
+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;
+	struct nvidia_smmu *nvidia_smmu = to_nvidia_smmu(smmu);
+
+	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 < 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)
+{
+	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 arm_smmu_device struct allocated in arm-smmu.c.
+	 * The memory for the arm_smmu_device struct from arm-smmu.c is freed
+	 * subsequently.
+	 */
+	nvidia_smmu->smmu = *smmu;
+	/* Instance 0 is ioremapped by arm-smmu.c after this function returns */
+	nvidia_smmu->num_inst = 1;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	/* Minimum two SMMU instances are expected. */
+	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->num_inst++;
+
+	/* 3rd SMMU instance is Optional. */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 2);
+	if (res) {
+		nvidia_smmu->bases[2] = devm_ioremap_resource(dev, res);
+		if (IS_ERR(nvidia_smmu->bases[2]))
+			return ERR_CAST(nvidia_smmu->bases[2]);
+
+		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(dev, smmu);
+
+	return &nvidia_smmu->smmu;
+}
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index c7d0122a7c6ca..fad63efa1a72d 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -452,6 +452,7 @@ 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);
-- 
2.26.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v9 2/4] iommu/arm-smmu: add NVIDIA implementation for ARM MMU-500 usage

[Krishna Reddy]

NVIDIA's Tegra194 SoC has three ARM MMU-500 instances.
It uses two of ARM MMU-500s together to interleave IOVA accesses
across them and must be programmed identically.
The third SMMU instance is used as a regular ARM MMU-500 and it
can either be programmed independently or identical to other
two ARM MMU-500s.

This implementation supports programming two or three ARM MMU-500s
identically as per DT config.

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 | 206 ++++++++++++++++++++++++++++++++
 drivers/iommu/arm-smmu.h        |   1 +
 5 files changed, 213 insertions(+), 1 deletion(-)
 create mode 100644 drivers/iommu/arm-smmu-nvidia.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 7b5ffd646c6b9..64c37dbdd4426 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -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
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index 342190196dfb0..2b8203db73ec3 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 c75b9d957b702..f15571d05474e 100644
--- a/drivers/iommu/arm-smmu-impl.c
+++ b/drivers/iommu/arm-smmu-impl.c
@@ -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(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"))
 		return qcom_smmu_impl_init(smmu);
diff --git a/drivers/iommu/arm-smmu-nvidia.c b/drivers/iommu/arm-smmu-nvidia.c
new file mode 100644
index 0000000000000..5c874912e1c1a
--- /dev/null
+++ b/drivers/iommu/arm-smmu-nvidia.c
@@ -0,0 +1,206 @@
+// 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
+
+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;
+	struct nvidia_smmu *nvidia_smmu = to_nvidia_smmu(smmu);
+
+	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 < 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)
+{
+	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 arm_smmu_device struct allocated in arm-smmu.c.
+	 * The memory for the arm_smmu_device struct from arm-smmu.c is freed
+	 * subsequently.
+	 */
+	nvidia_smmu->smmu = *smmu;
+	/* Instance 0 is ioremapped by arm-smmu.c after this function returns */
+	nvidia_smmu->num_inst = 1;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	/* Minimum two SMMU instances are expected. */
+	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->num_inst++;
+
+	/* 3rd SMMU instance is Optional. */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 2);
+	if (res) {
+		nvidia_smmu->bases[2] = devm_ioremap_resource(dev, res);
+		if (IS_ERR(nvidia_smmu->bases[2]))
+			return ERR_CAST(nvidia_smmu->bases[2]);
+
+		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(dev, smmu);
+
+	return &nvidia_smmu->smmu;
+}
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index c7d0122a7c6ca..fad63efa1a72d 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -452,6 +452,7 @@ 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);
-- 
2.26.2

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH v9 2/4] iommu/arm-smmu: add NVIDIA implementation for ARM MMU-500 usage

[Krishna Reddy]

NVIDIA's Tegra194 SoC has three ARM MMU-500 instances.
It uses two of ARM MMU-500s together to interleave IOVA accesses
across them and must be programmed identically.
The third SMMU instance is used as a regular ARM MMU-500 and it
can either be programmed independently or identical to other
two ARM MMU-500s.

This implementation supports programming two or three ARM MMU-500s
identically as per DT config.

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 | 206 ++++++++++++++++++++++++++++++++
 drivers/iommu/arm-smmu.h        |   1 +
 5 files changed, 213 insertions(+), 1 deletion(-)
 create mode 100644 drivers/iommu/arm-smmu-nvidia.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 7b5ffd646c6b9..64c37dbdd4426 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -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
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index 342190196dfb0..2b8203db73ec3 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 c75b9d957b702..f15571d05474e 100644
--- a/drivers/iommu/arm-smmu-impl.c
+++ b/drivers/iommu/arm-smmu-impl.c
@@ -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(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"))
 		return qcom_smmu_impl_init(smmu);
diff --git a/drivers/iommu/arm-smmu-nvidia.c b/drivers/iommu/arm-smmu-nvidia.c
new file mode 100644
index 0000000000000..5c874912e1c1a
--- /dev/null
+++ b/drivers/iommu/arm-smmu-nvidia.c
@@ -0,0 +1,206 @@
+// 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
+
+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;
+	struct nvidia_smmu *nvidia_smmu = to_nvidia_smmu(smmu);
+
+	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 < 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)
+{
+	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 arm_smmu_device struct allocated in arm-smmu.c.
+	 * The memory for the arm_smmu_device struct from arm-smmu.c is freed
+	 * subsequently.
+	 */
+	nvidia_smmu->smmu = *smmu;
+	/* Instance 0 is ioremapped by arm-smmu.c after this function returns */
+	nvidia_smmu->num_inst = 1;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	/* Minimum two SMMU instances are expected. */
+	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->num_inst++;
+
+	/* 3rd SMMU instance is Optional. */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 2);
+	if (res) {
+		nvidia_smmu->bases[2] = devm_ioremap_resource(dev, res);
+		if (IS_ERR(nvidia_smmu->bases[2]))
+			return ERR_CAST(nvidia_smmu->bases[2]);
+
+		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(dev, smmu);
+
+	return &nvidia_smmu->smmu;
+}
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index c7d0122a7c6ca..fad63efa1a72d 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -452,6 +452,7 @@ 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);
-- 
2.26.2

Re: [PATCH v9 2/4] iommu/arm-smmu: add NVIDIA implementation for ARM MMU-500 usage

[Jon Hunter]

On 01/07/2020 00:57, Krishna Reddy wrote:
> NVIDIA's Tegra194 SoC has three ARM MMU-500 instances.
> It uses two of ARM MMU-500s together to interleave IOVA accesses
> across them and must be programmed identically.
> The third SMMU instance is used as a regular ARM MMU-500 and it
> can either be programmed independently or identical to other
> two ARM MMU-500s.
> 
> This implementation supports programming two or three ARM MMU-500s
> identically as per DT config.
> 
> Signed-off-by: Krishna Reddy <vdumpa-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
> ---
>  MAINTAINERS                     |   2 +
>  drivers/iommu/Makefile          |   2 +-
>  drivers/iommu/arm-smmu-impl.c   |   3 +
>  drivers/iommu/arm-smmu-nvidia.c | 206 ++++++++++++++++++++++++++++++++
>  drivers/iommu/arm-smmu.h        |   1 +
>  5 files changed, 213 insertions(+), 1 deletion(-)
>  create mode 100644 drivers/iommu/arm-smmu-nvidia.c
> 
> diff --git a/MAINTAINERS b/MAINTAINERS
> index 7b5ffd646c6b9..64c37dbdd4426 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -16808,8 +16808,10 @@ F:	drivers/i2c/busses/i2c-tegra.c
>  
>  TEGRA IOMMU DRIVERS
>  M:	Thierry Reding <thierry.reding-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
> +R:	Krishna Reddy <vdumpa-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
>  L:	linux-tegra-u79uwXL29TY76Z2rM5mHXA@public.gmane.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 342190196dfb0..2b8203db73ec3 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 c75b9d957b702..f15571d05474e 100644
> --- a/drivers/iommu/arm-smmu-impl.c
> +++ b/drivers/iommu/arm-smmu-impl.c
> @@ -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(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"))
>  		return qcom_smmu_impl_init(smmu);
> diff --git a/drivers/iommu/arm-smmu-nvidia.c b/drivers/iommu/arm-smmu-nvidia.c
> new file mode 100644
> index 0000000000000..5c874912e1c1a
> --- /dev/null
> +++ b/drivers/iommu/arm-smmu-nvidia.c
> @@ -0,0 +1,206 @@
> +// 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.
> + */

We should address Robin's comment about the 'When' above.

> +#define MAX_SMMU_INSTANCES 3
> +
> +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;


Robin said that he would accept a patch to move the
devm_ioremap_resource() call in arm_smmu_device_probe() so that we do
not need to do this. See the V7 series. I think that this would be a
good improvement so that we could avoid doing the above.

Cheers
Jon

-- 
nvpublic

Re: [PATCH v9 2/4] iommu/arm-smmu: add NVIDIA implementation for ARM MMU-500 usage

[Jon Hunter]

On 01/07/2020 00:57, Krishna Reddy wrote:
> NVIDIA's Tegra194 SoC has three ARM MMU-500 instances.
> It uses two of ARM MMU-500s together to interleave IOVA accesses
> across them and must be programmed identically.
> The third SMMU instance is used as a regular ARM MMU-500 and it
> can either be programmed independently or identical to other
> two ARM MMU-500s.
> 
> This implementation supports programming two or three ARM MMU-500s
> identically as per DT config.
> 
> 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 | 206 ++++++++++++++++++++++++++++++++
>  drivers/iommu/arm-smmu.h        |   1 +
>  5 files changed, 213 insertions(+), 1 deletion(-)
>  create mode 100644 drivers/iommu/arm-smmu-nvidia.c
> 
> diff --git a/MAINTAINERS b/MAINTAINERS
> index 7b5ffd646c6b9..64c37dbdd4426 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -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
> diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
> index 342190196dfb0..2b8203db73ec3 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 c75b9d957b702..f15571d05474e 100644
> --- a/drivers/iommu/arm-smmu-impl.c
> +++ b/drivers/iommu/arm-smmu-impl.c
> @@ -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(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"))
>  		return qcom_smmu_impl_init(smmu);
> diff --git a/drivers/iommu/arm-smmu-nvidia.c b/drivers/iommu/arm-smmu-nvidia.c
> new file mode 100644
> index 0000000000000..5c874912e1c1a
> --- /dev/null
> +++ b/drivers/iommu/arm-smmu-nvidia.c
> @@ -0,0 +1,206 @@
> +// 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.
> + */

We should address Robin's comment about the 'When' above.

> +#define MAX_SMMU_INSTANCES 3
> +
> +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;


Robin said that he would accept a patch to move the
devm_ioremap_resource() call in arm_smmu_device_probe() so that we do
not need to do this. See the V7 series. I think that this would be a
good improvement so that we could avoid doing the above.

Cheers
Jon

-- 
nvpublic

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH v9 2/4] iommu/arm-smmu: add NVIDIA implementation for ARM MMU-500 usage

[Jon Hunter]

On 01/07/2020 00:57, Krishna Reddy wrote:
> NVIDIA's Tegra194 SoC has three ARM MMU-500 instances.
> It uses two of ARM MMU-500s together to interleave IOVA accesses
> across them and must be programmed identically.
> The third SMMU instance is used as a regular ARM MMU-500 and it
> can either be programmed independently or identical to other
> two ARM MMU-500s.
> 
> This implementation supports programming two or three ARM MMU-500s
> identically as per DT config.
> 
> 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 | 206 ++++++++++++++++++++++++++++++++
>  drivers/iommu/arm-smmu.h        |   1 +
>  5 files changed, 213 insertions(+), 1 deletion(-)
>  create mode 100644 drivers/iommu/arm-smmu-nvidia.c
> 
> diff --git a/MAINTAINERS b/MAINTAINERS
> index 7b5ffd646c6b9..64c37dbdd4426 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -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
> diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
> index 342190196dfb0..2b8203db73ec3 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 c75b9d957b702..f15571d05474e 100644
> --- a/drivers/iommu/arm-smmu-impl.c
> +++ b/drivers/iommu/arm-smmu-impl.c
> @@ -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(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"))
>  		return qcom_smmu_impl_init(smmu);
> diff --git a/drivers/iommu/arm-smmu-nvidia.c b/drivers/iommu/arm-smmu-nvidia.c
> new file mode 100644
> index 0000000000000..5c874912e1c1a
> --- /dev/null
> +++ b/drivers/iommu/arm-smmu-nvidia.c
> @@ -0,0 +1,206 @@
> +// 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.
> + */

We should address Robin's comment about the 'When' above.

> +#define MAX_SMMU_INSTANCES 3
> +
> +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;


Robin said that he would accept a patch to move the
devm_ioremap_resource() call in arm_smmu_device_probe() so that we do
not need to do this. See the V7 series. I think that this would be a
good improvement so that we could avoid doing the above.

Cheers
Jon

-- 
nvpublic
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: [PATCH v9 2/4] iommu/arm-smmu: add NVIDIA implementation for ARM MMU-500 usage

[Jon Hunter]

On 01/07/2020 00:57, Krishna Reddy wrote:
> NVIDIA's Tegra194 SoC has three ARM MMU-500 instances.
> It uses two of ARM MMU-500s together to interleave IOVA accesses
> across them and must be programmed identically.
> The third SMMU instance is used as a regular ARM MMU-500 and it
> can either be programmed independently or identical to other
> two ARM MMU-500s.
> 
> This implementation supports programming two or three ARM MMU-500s
> identically as per DT config.
> 
> 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 | 206 ++++++++++++++++++++++++++++++++
>  drivers/iommu/arm-smmu.h        |   1 +
>  5 files changed, 213 insertions(+), 1 deletion(-)
>  create mode 100644 drivers/iommu/arm-smmu-nvidia.c
> 
> diff --git a/MAINTAINERS b/MAINTAINERS
> index 7b5ffd646c6b9..64c37dbdd4426 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -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
> diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
> index 342190196dfb0..2b8203db73ec3 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 c75b9d957b702..f15571d05474e 100644
> --- a/drivers/iommu/arm-smmu-impl.c
> +++ b/drivers/iommu/arm-smmu-impl.c
> @@ -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(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"))
>  		return qcom_smmu_impl_init(smmu);
> diff --git a/drivers/iommu/arm-smmu-nvidia.c b/drivers/iommu/arm-smmu-nvidia.c
> new file mode 100644
> index 0000000000000..5c874912e1c1a
> --- /dev/null
> +++ b/drivers/iommu/arm-smmu-nvidia.c
> @@ -0,0 +1,206 @@
> +// 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.
> + */

We should address Robin's comment about the 'When' above.

> +#define MAX_SMMU_INSTANCES 3
> +
> +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;


Robin said that he would accept a patch to move the
devm_ioremap_resource() call in arm_smmu_device_probe() so that we do
not need to do this. See the V7 series. I think that this would be a
good improvement so that we could avoid doing the above.

Cheers
Jon

-- 
nvpublic

[PATCH v9 3/4] dt-bindings: arm-smmu: add binding for Tegra194 SMMU

[Krishna Reddy]

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

Signed-off-by: Krishna Reddy <vdumpa-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
---
 .../devicetree/bindings/iommu/arm,smmu.yaml    | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
index d7ceb4c34423b..662c46e16f07d 100644
--- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
@@ -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:
+              - nvidia,tegra194-smmu
+          - const: arm,mmu-500
       - items:
           - const: arm,mmu-500
           - const: arm,smmu-v2
@@ -138,6 +143,19 @@ required:
 
 additionalProperties: false
 
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - nvidia,tegra194-smmu
+    then:
+      properties:
+        reg:
+          minItems: 2
+          maxItems: 3
+
 examples:
   - |+
     /* SMMU with stream matching or stream indexing */
-- 
2.26.2

[PATCH v9 3/4] dt-bindings: arm-smmu: add binding for Tegra194 SMMU

[Krishna Reddy]

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

Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
---
 .../devicetree/bindings/iommu/arm,smmu.yaml    | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
index d7ceb4c34423b..662c46e16f07d 100644
--- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
@@ -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:
+              - nvidia,tegra194-smmu
+          - const: arm,mmu-500
       - items:
           - const: arm,mmu-500
           - const: arm,smmu-v2
@@ -138,6 +143,19 @@ required:
 
 additionalProperties: false
 
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - nvidia,tegra194-smmu
+    then:
+      properties:
+        reg:
+          minItems: 2
+          maxItems: 3
+
 examples:
   - |+
     /* SMMU with stream matching or stream indexing */
-- 
2.26.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v9 3/4] dt-bindings: arm-smmu: add binding for Tegra194 SMMU

[Krishna Reddy]

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

Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
---
 .../devicetree/bindings/iommu/arm,smmu.yaml    | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
index d7ceb4c34423b..662c46e16f07d 100644
--- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
@@ -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:
+              - nvidia,tegra194-smmu
+          - const: arm,mmu-500
       - items:
           - const: arm,mmu-500
           - const: arm,smmu-v2
@@ -138,6 +143,19 @@ required:
 
 additionalProperties: false
 
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - nvidia,tegra194-smmu
+    then:
+      properties:
+        reg:
+          minItems: 2
+          maxItems: 3
+
 examples:
   - |+
     /* SMMU with stream matching or stream indexing */
-- 
2.26.2

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH v9 3/4] dt-bindings: arm-smmu: add binding for Tegra194 SMMU

[Krishna Reddy]

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

Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
---
 .../devicetree/bindings/iommu/arm,smmu.yaml    | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
index d7ceb4c34423b..662c46e16f07d 100644
--- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
@@ -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:
+              - nvidia,tegra194-smmu
+          - const: arm,mmu-500
       - items:
           - const: arm,mmu-500
           - const: arm,smmu-v2
@@ -138,6 +143,19 @@ required:
 
 additionalProperties: false
 
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - nvidia,tegra194-smmu
+    then:
+      properties:
+        reg:
+          minItems: 2
+          maxItems: 3
+
 examples:
   - |+
     /* SMMU with stream matching or stream indexing */
-- 
2.26.2

Re: [PATCH v9 3/4] dt-bindings: arm-smmu: add binding for Tegra194 SMMU

[Jon Hunter]

On 01/07/2020 00:57, Krishna Reddy wrote:
> Add binding for NVIDIA's Tegra194 SoC SMMU topology that is based
> on ARM MMU-500.
> 
> Signed-off-by: Krishna Reddy <vdumpa-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
> ---
>  .../devicetree/bindings/iommu/arm,smmu.yaml    | 18 ++++++++++++++++++
>  1 file changed, 18 insertions(+)
> 
> diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
> index d7ceb4c34423b..662c46e16f07d 100644
> --- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
> +++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
> @@ -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:
> +              - nvidia,tegra194-smmu
> +          - const: arm,mmu-500

We should also address Robin's comments here. I don't think that we ever
want to fail back to just the regular 'arm,mmu-500' and should be should
probably just drop this part.

Jon

-- 
nvpublic

Re: [PATCH v9 3/4] dt-bindings: arm-smmu: add binding for Tegra194 SMMU

[Jon Hunter]

On 01/07/2020 00:57, Krishna Reddy wrote:
> Add binding for NVIDIA's Tegra194 SoC SMMU topology that is based
> on ARM MMU-500.
> 
> Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
> ---
>  .../devicetree/bindings/iommu/arm,smmu.yaml    | 18 ++++++++++++++++++
>  1 file changed, 18 insertions(+)
> 
> diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
> index d7ceb4c34423b..662c46e16f07d 100644
> --- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
> +++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
> @@ -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:
> +              - nvidia,tegra194-smmu
> +          - const: arm,mmu-500

We should also address Robin's comments here. I don't think that we ever
want to fail back to just the regular 'arm,mmu-500' and should be should
probably just drop this part.

Jon

-- 
nvpublic

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH v9 3/4] dt-bindings: arm-smmu: add binding for Tegra194 SMMU

[Jon Hunter]

On 01/07/2020 00:57, Krishna Reddy wrote:
> Add binding for NVIDIA's Tegra194 SoC SMMU topology that is based
> on ARM MMU-500.
> 
> Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
> ---
>  .../devicetree/bindings/iommu/arm,smmu.yaml    | 18 ++++++++++++++++++
>  1 file changed, 18 insertions(+)
> 
> diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
> index d7ceb4c34423b..662c46e16f07d 100644
> --- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
> +++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
> @@ -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:
> +              - nvidia,tegra194-smmu
> +          - const: arm,mmu-500

We should also address Robin's comments here. I don't think that we ever
want to fail back to just the regular 'arm,mmu-500' and should be should
probably just drop this part.

Jon

-- 
nvpublic
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: [PATCH v9 3/4] dt-bindings: arm-smmu: add binding for Tegra194 SMMU

[Jon Hunter]

On 01/07/2020 00:57, Krishna Reddy wrote:
> Add binding for NVIDIA's Tegra194 SoC SMMU topology that is based
> on ARM MMU-500.
> 
> Signed-off-by: Krishna Reddy <vdumpa@nvidia.com>
> ---
>  .../devicetree/bindings/iommu/arm,smmu.yaml    | 18 ++++++++++++++++++
>  1 file changed, 18 insertions(+)
> 
> diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
> index d7ceb4c34423b..662c46e16f07d 100644
> --- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
> +++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml
> @@ -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:
> +              - nvidia,tegra194-smmu
> +          - const: arm,mmu-500

We should also address Robin's comments here. I don't think that we ever
want to fail back to just the regular 'arm,mmu-500' and should be should
probably just drop this part.

Jon

-- 
nvpublic

[PATCH v9 4/4] 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-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
---
 drivers/iommu/arm-smmu-nvidia.c | 98 +++++++++++++++++++++++++++++++++
 drivers/iommu/arm-smmu.c        | 17 +++++-
 drivers/iommu/arm-smmu.h        |  3 +
 3 files changed, 116 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/arm-smmu-nvidia.c b/drivers/iommu/arm-smmu-nvidia.c
index 5c874912e1c1a..d279788eab954 100644
--- a/drivers/iommu/arm-smmu-nvidia.c
+++ b/drivers/iommu/arm-smmu-nvidia.c
@@ -144,6 +144,102 @@ 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);
+	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)
+{
+	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 = 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 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 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)
+				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,
@@ -151,6 +247,8 @@ 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)
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index d2054178df357..161d68c8208a4 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -670,6 +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)
@@ -832,7 +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",
@@ -2104,6 +2111,7 @@ 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) {
@@ -2190,9 +2198,14 @@ 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 fad63efa1a72d..d890a4a968e8c 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>
@@ -389,6 +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)
-- 
2.26.2

[PATCH v9 4/4] 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 | 98 +++++++++++++++++++++++++++++++++
 drivers/iommu/arm-smmu.c        | 17 +++++-
 drivers/iommu/arm-smmu.h        |  3 +
 3 files changed, 116 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/arm-smmu-nvidia.c b/drivers/iommu/arm-smmu-nvidia.c
index 5c874912e1c1a..d279788eab954 100644
--- a/drivers/iommu/arm-smmu-nvidia.c
+++ b/drivers/iommu/arm-smmu-nvidia.c
@@ -144,6 +144,102 @@ 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);
+	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)
+{
+	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 = 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 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 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)
+				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,
@@ -151,6 +247,8 @@ 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)
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index d2054178df357..161d68c8208a4 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -670,6 +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)
@@ -832,7 +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",
@@ -2104,6 +2111,7 @@ 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) {
@@ -2190,9 +2198,14 @@ 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 fad63efa1a72d..d890a4a968e8c 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>
@@ -389,6 +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)
-- 
2.26.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v9 4/4] 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 | 98 +++++++++++++++++++++++++++++++++
 drivers/iommu/arm-smmu.c        | 17 +++++-
 drivers/iommu/arm-smmu.h        |  3 +
 3 files changed, 116 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/arm-smmu-nvidia.c b/drivers/iommu/arm-smmu-nvidia.c
index 5c874912e1c1a..d279788eab954 100644
--- a/drivers/iommu/arm-smmu-nvidia.c
+++ b/drivers/iommu/arm-smmu-nvidia.c
@@ -144,6 +144,102 @@ 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);
+	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)
+{
+	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 = 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 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 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)
+				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,
@@ -151,6 +247,8 @@ 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)
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index d2054178df357..161d68c8208a4 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -670,6 +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)
@@ -832,7 +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",
@@ -2104,6 +2111,7 @@ 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) {
@@ -2190,9 +2198,14 @@ 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 fad63efa1a72d..d890a4a968e8c 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>
@@ -389,6 +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)
-- 
2.26.2

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH v9 4/4] 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 | 98 +++++++++++++++++++++++++++++++++
 drivers/iommu/arm-smmu.c        | 17 +++++-
 drivers/iommu/arm-smmu.h        |  3 +
 3 files changed, 116 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/arm-smmu-nvidia.c b/drivers/iommu/arm-smmu-nvidia.c
index 5c874912e1c1a..d279788eab954 100644
--- a/drivers/iommu/arm-smmu-nvidia.c
+++ b/drivers/iommu/arm-smmu-nvidia.c
@@ -144,6 +144,102 @@ 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);
+	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)
+{
+	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 = 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 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 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)
+				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,
@@ -151,6 +247,8 @@ 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)
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index d2054178df357..161d68c8208a4 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -670,6 +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)
@@ -832,7 +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",
@@ -2104,6 +2111,7 @@ 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) {
@@ -2190,9 +2198,14 @@ 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 fad63efa1a72d..d890a4a968e8c 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>
@@ -389,6 +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)
-- 
2.26.2