From: Krishna Reddy <vdumpa-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
To: joro-zLv9SwRftAIdnm+yROfE0A@public.gmane.org,
will-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org,
robin.murphy-5wv7dgnIgG8@public.gmane.org,
robh+dt-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org,
treding-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org,
jonathanh-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org
Cc: devicetree-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org,
iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-tegra-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
yhsu-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org,
snikam-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org,
praithatha-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org,
talho-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org,
bbiswas-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org,
mperttunen-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org,
nicolinc-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org,
bhuntsman-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org,
nicoleotsuka-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org,
Krishna Reddy <vdumpa-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
Subject: [PATCH v10 3/5] iommu/arm-smmu: add NVIDIA implementation for ARM MMU-500 usage
Date: Tue, 7 Jul 2020 22:00:15 -0700 [thread overview]
Message-ID: <20200708050017.31563-4-vdumpa@nvidia.com> (raw)
In-Reply-To: <20200708050017.31563-1-vdumpa-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
NVIDIA's Tegra194 SoC has three ARM MMU-500 instances.
It uses two of the ARM MMU-500s together to interleave IOVA
accesses across them and must be programmed identically.
This implementation supports programming the two ARM MMU-500s
that must be programmed identically.
The third ARM MMU-500 instance is supported by standard
arm-smmu.c driver itself.
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 | 179 ++++++++++++++++++++++++++++++++
drivers/iommu/arm-smmu.c | 1 +
drivers/iommu/arm-smmu.h | 1 +
6 files changed, 187 insertions(+), 1 deletion(-)
create mode 100644 drivers/iommu/arm-smmu-nvidia.c
diff --git a/MAINTAINERS b/MAINTAINERS
index c23352059a6b..534cedaf8e55 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16811,8 +16811,10 @@ 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 342190196dfb..2b8203db73ec 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -15,7 +15,7 @@ obj-$(CONFIG_AMD_IOMMU) += amd/iommu.o amd/init.o amd/quirks.o
obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += amd/debugfs.o
obj-$(CONFIG_AMD_IOMMU_V2) += amd/iommu_v2.o
obj-$(CONFIG_ARM_SMMU) += arm_smmu.o
-arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-qcom.o
+arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-nvidia.o arm-smmu-qcom.o
obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o
obj-$(CONFIG_DMAR_TABLE) += intel/dmar.o
obj-$(CONFIG_INTEL_IOMMU) += intel/iommu.o intel/pasid.o
diff --git a/drivers/iommu/arm-smmu-impl.c b/drivers/iommu/arm-smmu-impl.c
index c75b9d957b70..f15571d05474 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 000000000000..2f55e5793d34
--- /dev/null
+++ b/drivers/iommu/arm-smmu-nvidia.c
@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2019-2020 NVIDIA CORPORATION. All rights reserved.
+
+#include <linux/bitfield.h>
+#include <linux/delay.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include "arm-smmu.h"
+
+/*
+ * Tegra194 has three ARM MMU-500 Instances.
+ * Two of them are used together and must be programmed identically for
+ * interleaved IOVA accesses across them and translates accesses from
+ * non-isochronous HW devices.
+ * Third one is used for translating accesses from isochronous HW devices.
+ * This implementation supports programming of the two instances that must
+ * be programmed identically.
+ * The third instance usage is through standard arm-smmu driver itself and
+ * is out of scope of this implementation.
+ */
+#define NUM_SMMU_INSTANCES 2
+
+struct nvidia_smmu {
+ struct arm_smmu_device smmu;
+ void __iomem *bases[NUM_SMMU_INSTANCES];
+};
+
+static inline void __iomem *nvidia_smmu_page(struct arm_smmu_device *smmu,
+ unsigned int inst, int page)
+{
+ struct nvidia_smmu *nvidia_smmu;
+
+ nvidia_smmu = container_of(smmu, struct nvidia_smmu, smmu);
+ return nvidia_smmu->bases[inst] + (page << smmu->pgshift);
+}
+
+static u32 nvidia_smmu_read_reg(struct arm_smmu_device *smmu,
+ int page, int offset)
+{
+ void __iomem *reg = nvidia_smmu_page(smmu, 0, page) + offset;
+
+ return readl_relaxed(reg);
+}
+
+static void nvidia_smmu_write_reg(struct arm_smmu_device *smmu,
+ int page, int offset, u32 val)
+{
+ unsigned int i;
+
+ for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+ void __iomem *reg = nvidia_smmu_page(smmu, i, page) + offset;
+
+ writel_relaxed(val, reg);
+ }
+}
+
+static u64 nvidia_smmu_read_reg64(struct arm_smmu_device *smmu,
+ int page, int offset)
+{
+ void __iomem *reg = nvidia_smmu_page(smmu, 0, page) + offset;
+
+ return readq_relaxed(reg);
+}
+
+static void nvidia_smmu_write_reg64(struct arm_smmu_device *smmu,
+ int page, int offset, u64 val)
+{
+ unsigned int i;
+
+ for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+ void __iomem *reg = nvidia_smmu_page(smmu, i, page) + offset;
+
+ writeq_relaxed(val, reg);
+ }
+}
+
+static void nvidia_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
+ int sync, int status)
+{
+ unsigned int delay;
+
+ arm_smmu_writel(smmu, page, sync, 0);
+
+ for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) {
+ unsigned int spin_cnt;
+
+ for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) {
+ u32 val = 0;
+ unsigned int i;
+
+ for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+ void __iomem *reg;
+
+ reg = nvidia_smmu_page(smmu, i, page) + status;
+ val |= readl_relaxed(reg);
+ }
+
+ if (!(val & ARM_SMMU_sTLBGSTATUS_GSACTIVE))
+ return;
+
+ cpu_relax();
+ }
+
+ udelay(delay);
+ }
+
+ dev_err_ratelimited(smmu->dev,
+ "TLB sync timed out -- SMMU may be deadlocked\n");
+}
+
+static int nvidia_smmu_reset(struct arm_smmu_device *smmu)
+{
+ unsigned int i;
+
+ for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+ u32 val;
+ void __iomem *reg = nvidia_smmu_page(smmu, i, ARM_SMMU_GR0) +
+ ARM_SMMU_GR0_sGFSR;
+
+ /* clear global FSR */
+ val = readl_relaxed(reg);
+ writel_relaxed(val, reg);
+ }
+
+ return 0;
+}
+
+static 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 struct arm_smmu_device *smmu allocated in
+ * arm-smmu.c. The smmu from struct nvidia_smmu replaces the smmu
+ * pointer used in arm-smmu.c once this function returns.
+ * This is necessary to derive nvidia_smmu from smmu pointer passed
+ * through arm_smmu_impl function calls subsequently.
+ */
+ nvidia_smmu->smmu = *smmu;
+ /* Instance 0 is ioremapped by arm-smmu.c. */
+ nvidia_smmu->bases[0] = smmu->base;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+ if (!res)
+ return ERR_PTR(-ENODEV);
+
+ nvidia_smmu->bases[1] = devm_ioremap_resource(dev, res);
+ if (IS_ERR(nvidia_smmu->bases[1]))
+ return ERR_CAST(nvidia_smmu->bases[1]);
+
+ nvidia_smmu->smmu.impl = &nvidia_smmu_impl;
+
+ /*
+ * Free the struct arm_smmu_device *smmu allocated in arm-smmu.c.
+ * Once this function returns, arm-smmu.c would use arm_smmu_device
+ * allocated as part of struct nvidia_smmu.
+ */
+ devm_kfree(dev, smmu);
+
+ return &nvidia_smmu->smmu;
+}
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index e03e873d3bca..c123a5814f70 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -1943,6 +1943,7 @@ static const struct of_device_id arm_smmu_of_match[] = {
{ .compatible = "arm,mmu-401", .data = &arm_mmu401 },
{ .compatible = "arm,mmu-500", .data = &arm_mmu500 },
{ .compatible = "cavium,smmu-v2", .data = &cavium_smmuv2 },
+ { .compatible = "nvidia,smmu-500", .data = &arm_mmu500 },
{ .compatible = "qcom,smmu-v2", .data = &qcom_smmuv2 },
{ },
};
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index c7d0122a7c6c..fad63efa1a72 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
WARNING: multiple messages have this Message-ID (diff)
From: Krishna Reddy <vdumpa@nvidia.com>
To: <joro@8bytes.org>, <will@kernel.org>, <robin.murphy@arm.com>,
<robh+dt@kernel.org>, <treding@nvidia.com>,
<jonathanh@nvidia.com>
Cc: <devicetree@vger.kernel.org>,
<linux-arm-kernel@lists.infradead.org>,
<iommu@lists.linux-foundation.org>,
<linux-kernel@vger.kernel.org>, <linux-tegra@vger.kernel.org>,
<yhsu@nvidia.com>, <snikam@nvidia.com>, <praithatha@nvidia.com>,
<talho@nvidia.com>, <bbiswas@nvidia.com>, <mperttunen@nvidia.com>,
<nicolinc@nvidia.com>, <bhuntsman@nvidia.com>,
<nicoleotsuka@gmail.com>, Krishna Reddy <vdumpa@nvidia.com>
Subject: [PATCH v10 3/5] iommu/arm-smmu: add NVIDIA implementation for ARM MMU-500 usage
Date: Tue, 7 Jul 2020 22:00:15 -0700 [thread overview]
Message-ID: <20200708050017.31563-4-vdumpa@nvidia.com> (raw)
In-Reply-To: <20200708050017.31563-1-vdumpa@nvidia.com>
NVIDIA's Tegra194 SoC has three ARM MMU-500 instances.
It uses two of the ARM MMU-500s together to interleave IOVA
accesses across them and must be programmed identically.
This implementation supports programming the two ARM MMU-500s
that must be programmed identically.
The third ARM MMU-500 instance is supported by standard
arm-smmu.c driver itself.
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 | 179 ++++++++++++++++++++++++++++++++
drivers/iommu/arm-smmu.c | 1 +
drivers/iommu/arm-smmu.h | 1 +
6 files changed, 187 insertions(+), 1 deletion(-)
create mode 100644 drivers/iommu/arm-smmu-nvidia.c
diff --git a/MAINTAINERS b/MAINTAINERS
index c23352059a6b..534cedaf8e55 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16811,8 +16811,10 @@ F: drivers/i2c/busses/i2c-tegra.c
TEGRA IOMMU DRIVERS
M: Thierry Reding <thierry.reding@gmail.com>
+R: Krishna Reddy <vdumpa@nvidia.com>
L: linux-tegra@vger.kernel.org
S: Supported
+F: drivers/iommu/arm-smmu-nvidia.c
F: drivers/iommu/tegra*
TEGRA KBC DRIVER
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index 342190196dfb..2b8203db73ec 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -15,7 +15,7 @@ obj-$(CONFIG_AMD_IOMMU) += amd/iommu.o amd/init.o amd/quirks.o
obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += amd/debugfs.o
obj-$(CONFIG_AMD_IOMMU_V2) += amd/iommu_v2.o
obj-$(CONFIG_ARM_SMMU) += arm_smmu.o
-arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-qcom.o
+arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-nvidia.o arm-smmu-qcom.o
obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o
obj-$(CONFIG_DMAR_TABLE) += intel/dmar.o
obj-$(CONFIG_INTEL_IOMMU) += intel/iommu.o intel/pasid.o
diff --git a/drivers/iommu/arm-smmu-impl.c b/drivers/iommu/arm-smmu-impl.c
index c75b9d957b70..f15571d05474 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 000000000000..2f55e5793d34
--- /dev/null
+++ b/drivers/iommu/arm-smmu-nvidia.c
@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2019-2020 NVIDIA CORPORATION. All rights reserved.
+
+#include <linux/bitfield.h>
+#include <linux/delay.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include "arm-smmu.h"
+
+/*
+ * Tegra194 has three ARM MMU-500 Instances.
+ * Two of them are used together and must be programmed identically for
+ * interleaved IOVA accesses across them and translates accesses from
+ * non-isochronous HW devices.
+ * Third one is used for translating accesses from isochronous HW devices.
+ * This implementation supports programming of the two instances that must
+ * be programmed identically.
+ * The third instance usage is through standard arm-smmu driver itself and
+ * is out of scope of this implementation.
+ */
+#define NUM_SMMU_INSTANCES 2
+
+struct nvidia_smmu {
+ struct arm_smmu_device smmu;
+ void __iomem *bases[NUM_SMMU_INSTANCES];
+};
+
+static inline void __iomem *nvidia_smmu_page(struct arm_smmu_device *smmu,
+ unsigned int inst, int page)
+{
+ struct nvidia_smmu *nvidia_smmu;
+
+ nvidia_smmu = container_of(smmu, struct nvidia_smmu, smmu);
+ return nvidia_smmu->bases[inst] + (page << smmu->pgshift);
+}
+
+static u32 nvidia_smmu_read_reg(struct arm_smmu_device *smmu,
+ int page, int offset)
+{
+ void __iomem *reg = nvidia_smmu_page(smmu, 0, page) + offset;
+
+ return readl_relaxed(reg);
+}
+
+static void nvidia_smmu_write_reg(struct arm_smmu_device *smmu,
+ int page, int offset, u32 val)
+{
+ unsigned int i;
+
+ for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+ void __iomem *reg = nvidia_smmu_page(smmu, i, page) + offset;
+
+ writel_relaxed(val, reg);
+ }
+}
+
+static u64 nvidia_smmu_read_reg64(struct arm_smmu_device *smmu,
+ int page, int offset)
+{
+ void __iomem *reg = nvidia_smmu_page(smmu, 0, page) + offset;
+
+ return readq_relaxed(reg);
+}
+
+static void nvidia_smmu_write_reg64(struct arm_smmu_device *smmu,
+ int page, int offset, u64 val)
+{
+ unsigned int i;
+
+ for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+ void __iomem *reg = nvidia_smmu_page(smmu, i, page) + offset;
+
+ writeq_relaxed(val, reg);
+ }
+}
+
+static void nvidia_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
+ int sync, int status)
+{
+ unsigned int delay;
+
+ arm_smmu_writel(smmu, page, sync, 0);
+
+ for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) {
+ unsigned int spin_cnt;
+
+ for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) {
+ u32 val = 0;
+ unsigned int i;
+
+ for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+ void __iomem *reg;
+
+ reg = nvidia_smmu_page(smmu, i, page) + status;
+ val |= readl_relaxed(reg);
+ }
+
+ if (!(val & ARM_SMMU_sTLBGSTATUS_GSACTIVE))
+ return;
+
+ cpu_relax();
+ }
+
+ udelay(delay);
+ }
+
+ dev_err_ratelimited(smmu->dev,
+ "TLB sync timed out -- SMMU may be deadlocked\n");
+}
+
+static int nvidia_smmu_reset(struct arm_smmu_device *smmu)
+{
+ unsigned int i;
+
+ for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+ u32 val;
+ void __iomem *reg = nvidia_smmu_page(smmu, i, ARM_SMMU_GR0) +
+ ARM_SMMU_GR0_sGFSR;
+
+ /* clear global FSR */
+ val = readl_relaxed(reg);
+ writel_relaxed(val, reg);
+ }
+
+ return 0;
+}
+
+static 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 struct arm_smmu_device *smmu allocated in
+ * arm-smmu.c. The smmu from struct nvidia_smmu replaces the smmu
+ * pointer used in arm-smmu.c once this function returns.
+ * This is necessary to derive nvidia_smmu from smmu pointer passed
+ * through arm_smmu_impl function calls subsequently.
+ */
+ nvidia_smmu->smmu = *smmu;
+ /* Instance 0 is ioremapped by arm-smmu.c. */
+ nvidia_smmu->bases[0] = smmu->base;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+ if (!res)
+ return ERR_PTR(-ENODEV);
+
+ nvidia_smmu->bases[1] = devm_ioremap_resource(dev, res);
+ if (IS_ERR(nvidia_smmu->bases[1]))
+ return ERR_CAST(nvidia_smmu->bases[1]);
+
+ nvidia_smmu->smmu.impl = &nvidia_smmu_impl;
+
+ /*
+ * Free the struct arm_smmu_device *smmu allocated in arm-smmu.c.
+ * Once this function returns, arm-smmu.c would use arm_smmu_device
+ * allocated as part of struct nvidia_smmu.
+ */
+ devm_kfree(dev, smmu);
+
+ return &nvidia_smmu->smmu;
+}
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index e03e873d3bca..c123a5814f70 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -1943,6 +1943,7 @@ static const struct of_device_id arm_smmu_of_match[] = {
{ .compatible = "arm,mmu-401", .data = &arm_mmu401 },
{ .compatible = "arm,mmu-500", .data = &arm_mmu500 },
{ .compatible = "cavium,smmu-v2", .data = &cavium_smmuv2 },
+ { .compatible = "nvidia,smmu-500", .data = &arm_mmu500 },
{ .compatible = "qcom,smmu-v2", .data = &qcom_smmuv2 },
{ },
};
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index c7d0122a7c6c..fad63efa1a72 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
WARNING: multiple messages have this Message-ID (diff)
From: Krishna Reddy <vdumpa@nvidia.com>
To: <joro@8bytes.org>, <will@kernel.org>, <robin.murphy@arm.com>,
<robh+dt@kernel.org>, <treding@nvidia.com>,
<jonathanh@nvidia.com>
Cc: snikam@nvidia.com, devicetree@vger.kernel.org,
nicoleotsuka@gmail.com, mperttunen@nvidia.com,
bhuntsman@nvidia.com, yhsu@nvidia.com,
linux-kernel@vger.kernel.org, talho@nvidia.com,
iommu@lists.linux-foundation.org, nicolinc@nvidia.com,
linux-tegra@vger.kernel.org, praithatha@nvidia.com,
linux-arm-kernel@lists.infradead.org, bbiswas@nvidia.com
Subject: [PATCH v10 3/5] iommu/arm-smmu: add NVIDIA implementation for ARM MMU-500 usage
Date: Tue, 7 Jul 2020 22:00:15 -0700 [thread overview]
Message-ID: <20200708050017.31563-4-vdumpa@nvidia.com> (raw)
In-Reply-To: <20200708050017.31563-1-vdumpa@nvidia.com>
NVIDIA's Tegra194 SoC has three ARM MMU-500 instances.
It uses two of the ARM MMU-500s together to interleave IOVA
accesses across them and must be programmed identically.
This implementation supports programming the two ARM MMU-500s
that must be programmed identically.
The third ARM MMU-500 instance is supported by standard
arm-smmu.c driver itself.
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 | 179 ++++++++++++++++++++++++++++++++
drivers/iommu/arm-smmu.c | 1 +
drivers/iommu/arm-smmu.h | 1 +
6 files changed, 187 insertions(+), 1 deletion(-)
create mode 100644 drivers/iommu/arm-smmu-nvidia.c
diff --git a/MAINTAINERS b/MAINTAINERS
index c23352059a6b..534cedaf8e55 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16811,8 +16811,10 @@ F: drivers/i2c/busses/i2c-tegra.c
TEGRA IOMMU DRIVERS
M: Thierry Reding <thierry.reding@gmail.com>
+R: Krishna Reddy <vdumpa@nvidia.com>
L: linux-tegra@vger.kernel.org
S: Supported
+F: drivers/iommu/arm-smmu-nvidia.c
F: drivers/iommu/tegra*
TEGRA KBC DRIVER
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index 342190196dfb..2b8203db73ec 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -15,7 +15,7 @@ obj-$(CONFIG_AMD_IOMMU) += amd/iommu.o amd/init.o amd/quirks.o
obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += amd/debugfs.o
obj-$(CONFIG_AMD_IOMMU_V2) += amd/iommu_v2.o
obj-$(CONFIG_ARM_SMMU) += arm_smmu.o
-arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-qcom.o
+arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-nvidia.o arm-smmu-qcom.o
obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o
obj-$(CONFIG_DMAR_TABLE) += intel/dmar.o
obj-$(CONFIG_INTEL_IOMMU) += intel/iommu.o intel/pasid.o
diff --git a/drivers/iommu/arm-smmu-impl.c b/drivers/iommu/arm-smmu-impl.c
index c75b9d957b70..f15571d05474 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 000000000000..2f55e5793d34
--- /dev/null
+++ b/drivers/iommu/arm-smmu-nvidia.c
@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2019-2020 NVIDIA CORPORATION. All rights reserved.
+
+#include <linux/bitfield.h>
+#include <linux/delay.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include "arm-smmu.h"
+
+/*
+ * Tegra194 has three ARM MMU-500 Instances.
+ * Two of them are used together and must be programmed identically for
+ * interleaved IOVA accesses across them and translates accesses from
+ * non-isochronous HW devices.
+ * Third one is used for translating accesses from isochronous HW devices.
+ * This implementation supports programming of the two instances that must
+ * be programmed identically.
+ * The third instance usage is through standard arm-smmu driver itself and
+ * is out of scope of this implementation.
+ */
+#define NUM_SMMU_INSTANCES 2
+
+struct nvidia_smmu {
+ struct arm_smmu_device smmu;
+ void __iomem *bases[NUM_SMMU_INSTANCES];
+};
+
+static inline void __iomem *nvidia_smmu_page(struct arm_smmu_device *smmu,
+ unsigned int inst, int page)
+{
+ struct nvidia_smmu *nvidia_smmu;
+
+ nvidia_smmu = container_of(smmu, struct nvidia_smmu, smmu);
+ return nvidia_smmu->bases[inst] + (page << smmu->pgshift);
+}
+
+static u32 nvidia_smmu_read_reg(struct arm_smmu_device *smmu,
+ int page, int offset)
+{
+ void __iomem *reg = nvidia_smmu_page(smmu, 0, page) + offset;
+
+ return readl_relaxed(reg);
+}
+
+static void nvidia_smmu_write_reg(struct arm_smmu_device *smmu,
+ int page, int offset, u32 val)
+{
+ unsigned int i;
+
+ for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+ void __iomem *reg = nvidia_smmu_page(smmu, i, page) + offset;
+
+ writel_relaxed(val, reg);
+ }
+}
+
+static u64 nvidia_smmu_read_reg64(struct arm_smmu_device *smmu,
+ int page, int offset)
+{
+ void __iomem *reg = nvidia_smmu_page(smmu, 0, page) + offset;
+
+ return readq_relaxed(reg);
+}
+
+static void nvidia_smmu_write_reg64(struct arm_smmu_device *smmu,
+ int page, int offset, u64 val)
+{
+ unsigned int i;
+
+ for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+ void __iomem *reg = nvidia_smmu_page(smmu, i, page) + offset;
+
+ writeq_relaxed(val, reg);
+ }
+}
+
+static void nvidia_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
+ int sync, int status)
+{
+ unsigned int delay;
+
+ arm_smmu_writel(smmu, page, sync, 0);
+
+ for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) {
+ unsigned int spin_cnt;
+
+ for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) {
+ u32 val = 0;
+ unsigned int i;
+
+ for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+ void __iomem *reg;
+
+ reg = nvidia_smmu_page(smmu, i, page) + status;
+ val |= readl_relaxed(reg);
+ }
+
+ if (!(val & ARM_SMMU_sTLBGSTATUS_GSACTIVE))
+ return;
+
+ cpu_relax();
+ }
+
+ udelay(delay);
+ }
+
+ dev_err_ratelimited(smmu->dev,
+ "TLB sync timed out -- SMMU may be deadlocked\n");
+}
+
+static int nvidia_smmu_reset(struct arm_smmu_device *smmu)
+{
+ unsigned int i;
+
+ for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+ u32 val;
+ void __iomem *reg = nvidia_smmu_page(smmu, i, ARM_SMMU_GR0) +
+ ARM_SMMU_GR0_sGFSR;
+
+ /* clear global FSR */
+ val = readl_relaxed(reg);
+ writel_relaxed(val, reg);
+ }
+
+ return 0;
+}
+
+static 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 struct arm_smmu_device *smmu allocated in
+ * arm-smmu.c. The smmu from struct nvidia_smmu replaces the smmu
+ * pointer used in arm-smmu.c once this function returns.
+ * This is necessary to derive nvidia_smmu from smmu pointer passed
+ * through arm_smmu_impl function calls subsequently.
+ */
+ nvidia_smmu->smmu = *smmu;
+ /* Instance 0 is ioremapped by arm-smmu.c. */
+ nvidia_smmu->bases[0] = smmu->base;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+ if (!res)
+ return ERR_PTR(-ENODEV);
+
+ nvidia_smmu->bases[1] = devm_ioremap_resource(dev, res);
+ if (IS_ERR(nvidia_smmu->bases[1]))
+ return ERR_CAST(nvidia_smmu->bases[1]);
+
+ nvidia_smmu->smmu.impl = &nvidia_smmu_impl;
+
+ /*
+ * Free the struct arm_smmu_device *smmu allocated in arm-smmu.c.
+ * Once this function returns, arm-smmu.c would use arm_smmu_device
+ * allocated as part of struct nvidia_smmu.
+ */
+ devm_kfree(dev, smmu);
+
+ return &nvidia_smmu->smmu;
+}
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index e03e873d3bca..c123a5814f70 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -1943,6 +1943,7 @@ static const struct of_device_id arm_smmu_of_match[] = {
{ .compatible = "arm,mmu-401", .data = &arm_mmu401 },
{ .compatible = "arm,mmu-500", .data = &arm_mmu500 },
{ .compatible = "cavium,smmu-v2", .data = &cavium_smmuv2 },
+ { .compatible = "nvidia,smmu-500", .data = &arm_mmu500 },
{ .compatible = "qcom,smmu-v2", .data = &qcom_smmuv2 },
{ },
};
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index c7d0122a7c6c..fad63efa1a72 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
WARNING: multiple messages have this Message-ID (diff)
From: Krishna Reddy <vdumpa@nvidia.com>
To: <joro@8bytes.org>, <will@kernel.org>, <robin.murphy@arm.com>,
<robh+dt@kernel.org>, <treding@nvidia.com>,
<jonathanh@nvidia.com>
Cc: snikam@nvidia.com, devicetree@vger.kernel.org,
nicoleotsuka@gmail.com, mperttunen@nvidia.com,
bhuntsman@nvidia.com, yhsu@nvidia.com,
linux-kernel@vger.kernel.org, talho@nvidia.com,
iommu@lists.linux-foundation.org, nicolinc@nvidia.com,
linux-tegra@vger.kernel.org, praithatha@nvidia.com,
linux-arm-kernel@lists.infradead.org, bbiswas@nvidia.com
Subject: [PATCH v10 3/5] iommu/arm-smmu: add NVIDIA implementation for ARM MMU-500 usage
Date: Tue, 7 Jul 2020 22:00:15 -0700 [thread overview]
Message-ID: <20200708050017.31563-4-vdumpa@nvidia.com> (raw)
In-Reply-To: <20200708050017.31563-1-vdumpa@nvidia.com>
NVIDIA's Tegra194 SoC has three ARM MMU-500 instances.
It uses two of the ARM MMU-500s together to interleave IOVA
accesses across them and must be programmed identically.
This implementation supports programming the two ARM MMU-500s
that must be programmed identically.
The third ARM MMU-500 instance is supported by standard
arm-smmu.c driver itself.
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 | 179 ++++++++++++++++++++++++++++++++
drivers/iommu/arm-smmu.c | 1 +
drivers/iommu/arm-smmu.h | 1 +
6 files changed, 187 insertions(+), 1 deletion(-)
create mode 100644 drivers/iommu/arm-smmu-nvidia.c
diff --git a/MAINTAINERS b/MAINTAINERS
index c23352059a6b..534cedaf8e55 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16811,8 +16811,10 @@ F: drivers/i2c/busses/i2c-tegra.c
TEGRA IOMMU DRIVERS
M: Thierry Reding <thierry.reding@gmail.com>
+R: Krishna Reddy <vdumpa@nvidia.com>
L: linux-tegra@vger.kernel.org
S: Supported
+F: drivers/iommu/arm-smmu-nvidia.c
F: drivers/iommu/tegra*
TEGRA KBC DRIVER
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index 342190196dfb..2b8203db73ec 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -15,7 +15,7 @@ obj-$(CONFIG_AMD_IOMMU) += amd/iommu.o amd/init.o amd/quirks.o
obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += amd/debugfs.o
obj-$(CONFIG_AMD_IOMMU_V2) += amd/iommu_v2.o
obj-$(CONFIG_ARM_SMMU) += arm_smmu.o
-arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-qcom.o
+arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-nvidia.o arm-smmu-qcom.o
obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o
obj-$(CONFIG_DMAR_TABLE) += intel/dmar.o
obj-$(CONFIG_INTEL_IOMMU) += intel/iommu.o intel/pasid.o
diff --git a/drivers/iommu/arm-smmu-impl.c b/drivers/iommu/arm-smmu-impl.c
index c75b9d957b70..f15571d05474 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 000000000000..2f55e5793d34
--- /dev/null
+++ b/drivers/iommu/arm-smmu-nvidia.c
@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2019-2020 NVIDIA CORPORATION. All rights reserved.
+
+#include <linux/bitfield.h>
+#include <linux/delay.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include "arm-smmu.h"
+
+/*
+ * Tegra194 has three ARM MMU-500 Instances.
+ * Two of them are used together and must be programmed identically for
+ * interleaved IOVA accesses across them and translates accesses from
+ * non-isochronous HW devices.
+ * Third one is used for translating accesses from isochronous HW devices.
+ * This implementation supports programming of the two instances that must
+ * be programmed identically.
+ * The third instance usage is through standard arm-smmu driver itself and
+ * is out of scope of this implementation.
+ */
+#define NUM_SMMU_INSTANCES 2
+
+struct nvidia_smmu {
+ struct arm_smmu_device smmu;
+ void __iomem *bases[NUM_SMMU_INSTANCES];
+};
+
+static inline void __iomem *nvidia_smmu_page(struct arm_smmu_device *smmu,
+ unsigned int inst, int page)
+{
+ struct nvidia_smmu *nvidia_smmu;
+
+ nvidia_smmu = container_of(smmu, struct nvidia_smmu, smmu);
+ return nvidia_smmu->bases[inst] + (page << smmu->pgshift);
+}
+
+static u32 nvidia_smmu_read_reg(struct arm_smmu_device *smmu,
+ int page, int offset)
+{
+ void __iomem *reg = nvidia_smmu_page(smmu, 0, page) + offset;
+
+ return readl_relaxed(reg);
+}
+
+static void nvidia_smmu_write_reg(struct arm_smmu_device *smmu,
+ int page, int offset, u32 val)
+{
+ unsigned int i;
+
+ for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+ void __iomem *reg = nvidia_smmu_page(smmu, i, page) + offset;
+
+ writel_relaxed(val, reg);
+ }
+}
+
+static u64 nvidia_smmu_read_reg64(struct arm_smmu_device *smmu,
+ int page, int offset)
+{
+ void __iomem *reg = nvidia_smmu_page(smmu, 0, page) + offset;
+
+ return readq_relaxed(reg);
+}
+
+static void nvidia_smmu_write_reg64(struct arm_smmu_device *smmu,
+ int page, int offset, u64 val)
+{
+ unsigned int i;
+
+ for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+ void __iomem *reg = nvidia_smmu_page(smmu, i, page) + offset;
+
+ writeq_relaxed(val, reg);
+ }
+}
+
+static void nvidia_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
+ int sync, int status)
+{
+ unsigned int delay;
+
+ arm_smmu_writel(smmu, page, sync, 0);
+
+ for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) {
+ unsigned int spin_cnt;
+
+ for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) {
+ u32 val = 0;
+ unsigned int i;
+
+ for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+ void __iomem *reg;
+
+ reg = nvidia_smmu_page(smmu, i, page) + status;
+ val |= readl_relaxed(reg);
+ }
+
+ if (!(val & ARM_SMMU_sTLBGSTATUS_GSACTIVE))
+ return;
+
+ cpu_relax();
+ }
+
+ udelay(delay);
+ }
+
+ dev_err_ratelimited(smmu->dev,
+ "TLB sync timed out -- SMMU may be deadlocked\n");
+}
+
+static int nvidia_smmu_reset(struct arm_smmu_device *smmu)
+{
+ unsigned int i;
+
+ for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+ u32 val;
+ void __iomem *reg = nvidia_smmu_page(smmu, i, ARM_SMMU_GR0) +
+ ARM_SMMU_GR0_sGFSR;
+
+ /* clear global FSR */
+ val = readl_relaxed(reg);
+ writel_relaxed(val, reg);
+ }
+
+ return 0;
+}
+
+static 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 struct arm_smmu_device *smmu allocated in
+ * arm-smmu.c. The smmu from struct nvidia_smmu replaces the smmu
+ * pointer used in arm-smmu.c once this function returns.
+ * This is necessary to derive nvidia_smmu from smmu pointer passed
+ * through arm_smmu_impl function calls subsequently.
+ */
+ nvidia_smmu->smmu = *smmu;
+ /* Instance 0 is ioremapped by arm-smmu.c. */
+ nvidia_smmu->bases[0] = smmu->base;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+ if (!res)
+ return ERR_PTR(-ENODEV);
+
+ nvidia_smmu->bases[1] = devm_ioremap_resource(dev, res);
+ if (IS_ERR(nvidia_smmu->bases[1]))
+ return ERR_CAST(nvidia_smmu->bases[1]);
+
+ nvidia_smmu->smmu.impl = &nvidia_smmu_impl;
+
+ /*
+ * Free the struct arm_smmu_device *smmu allocated in arm-smmu.c.
+ * Once this function returns, arm-smmu.c would use arm_smmu_device
+ * allocated as part of struct nvidia_smmu.
+ */
+ devm_kfree(dev, smmu);
+
+ return &nvidia_smmu->smmu;
+}
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index e03e873d3bca..c123a5814f70 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -1943,6 +1943,7 @@ static const struct of_device_id arm_smmu_of_match[] = {
{ .compatible = "arm,mmu-401", .data = &arm_mmu401 },
{ .compatible = "arm,mmu-500", .data = &arm_mmu500 },
{ .compatible = "cavium,smmu-v2", .data = &cavium_smmuv2 },
+ { .compatible = "nvidia,smmu-500", .data = &arm_mmu500 },
{ .compatible = "qcom,smmu-v2", .data = &qcom_smmuv2 },
{ },
};
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index c7d0122a7c6c..fad63efa1a72 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
next prev parent reply other threads:[~2020-07-08 5:00 UTC|newest]
Thread overview: 100+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-07-08 5:00 [PATCH v10 0/5] NVIDIA ARM SMMU Implementation Krishna Reddy
2020-07-08 5:00 ` Krishna Reddy
2020-07-08 5:00 ` Krishna Reddy
2020-07-08 5:00 ` Krishna Reddy
2020-07-08 5:00 ` [PATCH v10 1/5] iommu/arm-smmu: move TLB timeout and spin count macros Krishna Reddy
2020-07-08 5:00 ` Krishna Reddy
2020-07-08 5:00 ` Krishna Reddy
2020-07-08 5:00 ` Krishna Reddy
[not found] ` <20200708050017.31563-2-vdumpa-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
2020-07-08 12:05 ` Jon Hunter
2020-07-08 12:05 ` Jon Hunter
2020-07-08 12:05 ` Jon Hunter
2020-07-08 12:05 ` Jon Hunter
2020-07-08 20:37 ` Nicolin Chen
2020-07-08 20:37 ` Nicolin Chen
2020-07-08 20:37 ` Nicolin Chen
2020-07-08 20:37 ` Nicolin Chen
[not found] ` <20200708050017.31563-1-vdumpa-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
2020-07-08 5:00 ` [PATCH v10 2/5] iommu/arm-smmu: ioremap smmu mmio region before implementation init Krishna Reddy
2020-07-08 5:00 ` Krishna Reddy
2020-07-08 5:00 ` Krishna Reddy
2020-07-08 5:00 ` Krishna Reddy
[not found] ` <20200708050017.31563-3-vdumpa-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
2020-07-08 12:05 ` Jon Hunter
2020-07-08 12:05 ` Jon Hunter
2020-07-08 12:05 ` Jon Hunter
2020-07-08 12:05 ` Jon Hunter
2020-07-08 20:37 ` Nicolin Chen
2020-07-08 20:37 ` Nicolin Chen
2020-07-08 20:37 ` Nicolin Chen
2020-07-08 20:37 ` Nicolin Chen
2020-07-13 14:02 ` Robin Murphy
2020-07-13 14:02 ` Robin Murphy
2020-07-13 14:02 ` Robin Murphy
2020-07-13 14:02 ` Robin Murphy
2020-07-08 5:00 ` Krishna Reddy [this message]
2020-07-08 5:00 ` [PATCH v10 3/5] iommu/arm-smmu: add NVIDIA implementation for ARM MMU-500 usage Krishna Reddy
2020-07-08 5:00 ` Krishna Reddy
2020-07-08 5:00 ` Krishna Reddy
[not found] ` <20200708050017.31563-4-vdumpa-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
2020-07-08 12:24 ` Jon Hunter
2020-07-08 12:24 ` Jon Hunter
2020-07-08 12:24 ` Jon Hunter
2020-07-08 12:24 ` Jon Hunter
2020-07-08 20:36 ` Nicolin Chen
2020-07-08 20:36 ` Nicolin Chen
2020-07-08 20:36 ` Nicolin Chen
2020-07-08 20:36 ` Nicolin Chen
2020-07-08 5:00 ` [PATCH v10 4/5] dt-bindings: arm-smmu: add binding for Tegra194 SMMU Krishna Reddy
2020-07-08 5:00 ` Krishna Reddy
2020-07-08 5:00 ` Krishna Reddy
2020-07-08 5:00 ` Krishna Reddy
[not found] ` <20200708050017.31563-5-vdumpa-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
2020-07-08 12:25 ` Jon Hunter
2020-07-08 12:25 ` Jon Hunter
2020-07-08 12:25 ` Jon Hunter
2020-07-08 12:25 ` Jon Hunter
2020-07-09 20:13 ` Rob Herring
2020-07-09 20:13 ` Rob Herring
2020-07-09 20:13 ` Rob Herring
2020-07-09 20:13 ` Rob Herring
2020-07-10 20:29 ` Krishna Reddy
2020-07-10 20:29 ` Krishna Reddy
2020-07-10 20:29 ` Krishna Reddy
2020-07-10 20:29 ` Krishna Reddy
[not found] ` <BYAPR12MB2822514F93F831507A811EE9B3650-ZGDeBxoHBPlXmIuPQoPGkAdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
2020-07-13 14:10 ` Robin Murphy
2020-07-13 14:10 ` Robin Murphy
2020-07-13 14:10 ` Robin Murphy
2020-07-13 14:10 ` Robin Murphy
[not found] ` <c2ab2a0d-419d-555f-c124-2cfa1ecb2a81-5wv7dgnIgG8@public.gmane.org>
2020-07-14 14:22 ` Rob Herring
2020-07-14 14:22 ` Rob Herring
2020-07-14 14:22 ` Rob Herring
2020-07-14 14:22 ` Rob Herring
2020-07-08 5:00 ` [PATCH v10 5/5] iommu/arm-smmu: Add global/context fault implementation hooks Krishna Reddy
2020-07-08 5:00 ` Krishna Reddy
2020-07-08 5:00 ` Krishna Reddy
2020-07-08 5:00 ` Krishna Reddy
[not found] ` <20200708050017.31563-6-vdumpa-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
2020-07-08 12:28 ` Jon Hunter
2020-07-08 12:28 ` Jon Hunter
2020-07-08 12:28 ` Jon Hunter
2020-07-08 12:28 ` Jon Hunter
2020-07-08 20:36 ` Nicolin Chen
2020-07-08 20:36 ` Nicolin Chen
2020-07-08 20:36 ` Nicolin Chen
2020-07-08 20:36 ` Nicolin Chen
2020-07-13 13:44 ` Will Deacon
2020-07-13 13:44 ` Will Deacon
2020-07-13 13:44 ` Will Deacon
2020-07-13 13:44 ` Will Deacon
2020-07-17 11:58 ` Robin Murphy
2020-07-17 11:58 ` Robin Murphy
2020-07-17 11:58 ` Robin Murphy
2020-07-17 11:58 ` Robin Murphy
2020-07-13 13:50 ` [PATCH v10 0/5] NVIDIA ARM SMMU Implementation Will Deacon
2020-07-13 13:50 ` Will Deacon
2020-07-13 13:50 ` Will Deacon
2020-07-13 13:50 ` Will Deacon
2020-07-17 10:03 ` Will Deacon
2020-07-17 10:03 ` Will Deacon
2020-07-17 10:03 ` Will Deacon
2020-07-17 10:03 ` Will Deacon
2020-07-17 22:36 ` Krishna Reddy
2020-07-17 22:36 ` Krishna Reddy
2020-07-17 22:36 ` Krishna Reddy
2020-07-17 22:36 ` Krishna Reddy
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200708050017.31563-4-vdumpa@nvidia.com \
--to=vdumpa-ddmlm1+adcrqt0dzr+alfa@public.gmane.org \
--cc=bbiswas-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org \
--cc=bhuntsman-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org \
--cc=devicetree-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org \
--cc=jonathanh-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org \
--cc=joro-zLv9SwRftAIdnm+yROfE0A@public.gmane.org \
--cc=linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org \
--cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=linux-tegra-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=mperttunen-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org \
--cc=nicoleotsuka-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org \
--cc=nicolinc-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org \
--cc=praithatha-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org \
--cc=robh+dt-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org \
--cc=robin.murphy-5wv7dgnIgG8@public.gmane.org \
--cc=snikam-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org \
--cc=talho-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org \
--cc=treding-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org \
--cc=will-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org \
--cc=yhsu-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.