[PATCH v8 3/3] iommu/arm-smmu-v3: Enable CFGI/TLBI-repeat workaround on Tegra264

Nvidia Tegra264 SMMU is affected by an erratum where a TLB entry can
survive an invalidation that races with concurrent traffic targeting
the same entry. The hardware-recommended software workaround is to
issue every CFGI/TLBI command (each followed by CMD_SYNC) twice, and
that infrastructure is already in place behind
arm_smmu_erratum_repeat_tlbi_cfgi_key.

Neither IDR nor IIDR flags this Tegra264-specific bug, so hardware
detection is not possible. Tegra264 is device-tree-only (no ACPI/IORT
support) and already has a dedicated "nvidia,tegra264-smmu" compatible,
so DT-probe is the only viable detection path.

Enable the workaround on instances matching the existing
"nvidia,tegra264-smmu" compatible by calling static_branch_enable() on
arm_smmu_erratum_repeat_tlbi_cfgi_key. Document the erratum in
Documentation/arch/arm64/silicon-errata.rst.

The host repeats only the invalidations it issues itself. On a nesting
setup the guest submits its own invalidations, either directly through
VCMDQ or via the iommufd user-invalidation path, so the guest is the one
that has to apply the workaround there. Report the erratum to user space
through the new IOMMU_HW_INFO_ARM_SMMUV3_ERRATA_REPEAT_TLBI_CFGI hw_info
flag so a VMM can confirm the guest runs a matching "nvidia,tegra264-smmu"
(or otherwise double the commands itself). The host therefore does not
repeat the guest's user-issued invalidations, which would otherwise be
doubled a second time.

Signed-off-by: Ashish Mhetre <[email protected]>
---
 Documentation/arch/arm64/silicon-errata.rst         |  2 ++
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c |  3 +++
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c         | 11 +++++++++--
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h         |  1 +
 include/uapi/linux/iommufd.h                        | 12 +++++++++++-
 5 files changed, 26 insertions(+), 3 deletions(-)

diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst
index b0c68b64f5ac..744591598dfc 100644
--- a/Documentation/arch/arm64/silicon-errata.rst
+++ b/Documentation/arch/arm64/silicon-errata.rst
@@ -312,6 +312,8 @@ stable kernels.
 |                |                 | T241-MPAM-4,    |                             |
 |                |                 | T241-MPAM-6     |                             |
 +----------------+-----------------+-----------------+-----------------------------+
+| NVIDIA         | T264 SMMU       | T264-SMMU-3     | N/A                         |
++----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+
 | Freescale/NXP  | LS2080A/LS1043A | A-008585        | FSL_ERRATUM_A008585         |
 +----------------+-----------------+-----------------+-----------------------------+
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c
index 032d0c272f3f..25982bdbcbd9 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c
@@ -33,6 +33,9 @@ void *arm_smmu_hw_info(struct device *dev, u32 *length,
 	info->iidr = readl_relaxed(master->smmu->base + ARM_SMMU_IIDR);
 	info->aidr = readl_relaxed(master->smmu->base + ARM_SMMU_AIDR);
 
+	if (arm_smmu_erratum_repeat_tlbi_cfgi())
+		info->flags |= IOMMU_HW_INFO_ARM_SMMUV3_ERRATA_REPEAT_TLBI_CFGI;
+
 	*length = sizeof(*info);
 	*type = IOMMU_HW_INFO_TYPE_ARM_SMMUV3;
 
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index f0f8b2daf8d5..67e19c240ea5 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -829,11 +829,16 @@ int __arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu,
 	return ret;
 }
 
+bool arm_smmu_erratum_repeat_tlbi_cfgi(void)
+{
+	return static_branch_unlikely(&arm_smmu_erratum_repeat_tlbi_cfgi_key);
+}
+
 bool arm_smmu_erratum_cmd_needs_repeating(struct arm_smmu_cmd *cmd)
 {
 	u8 opcode;
 
-	if (!static_branch_unlikely(&arm_smmu_erratum_repeat_tlbi_cfgi_key))
+	if (!arm_smmu_erratum_repeat_tlbi_cfgi())
 		return false;
 
 	opcode = FIELD_GET(CMDQ_0_OP, cmd->data[0]);
@@ -5357,8 +5362,10 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev,
 	if (of_dma_is_coherent(dev->of_node))
 		smmu->features |= ARM_SMMU_FEAT_COHERENCY;
 
-	if (of_device_is_compatible(dev->of_node, "nvidia,tegra264-smmu"))
+	if (of_device_is_compatible(dev->of_node, "nvidia,tegra264-smmu")) {
 		tegra_cmdqv_dt_probe(dev->of_node, smmu);
+		static_branch_enable(&arm_smmu_erratum_repeat_tlbi_cfgi_key);
+	}
 
 	return ret;
 }
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index 9508bf50d14c..6465c0357fb5 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -1216,6 +1216,7 @@ int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu,
 				struct arm_smmu_cmd *cmds, int n,
 				bool sync);
 bool arm_smmu_erratum_cmd_needs_repeating(struct arm_smmu_cmd *cmd);
+bool arm_smmu_erratum_repeat_tlbi_cfgi(void);
 
 #ifdef CONFIG_ARM_SMMU_V3_SVA
 bool arm_smmu_sva_supported(struct arm_smmu_device *smmu);
diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h
index fddaf14cfdd2..be23922b053a 100644
--- a/include/uapi/linux/iommufd.h
+++ b/include/uapi/linux/iommufd.h
@@ -602,11 +602,21 @@ struct iommu_hw_info_vtd {
 	__aligned_u64 ecap_reg;
 };
 
+/**
+ * enum iommu_hw_info_arm_smmuv3_flags - Flags for ARM SMMUv3 hw_info
+ * @IOMMU_HW_INFO_ARM_SMMUV3_ERRATA_REPEAT_TLBI_CFGI: If set, user space must
+ *	issue TLBI/CFGI+SYNC commands twice due to a hardware erratum T264-SMMU-3.
+ *	See the description at arm_smmu_erratum_repeat_tlbi_cfgi_key.
+ */
+enum iommu_hw_info_arm_smmuv3_flags {
+	IOMMU_HW_INFO_ARM_SMMUV3_ERRATA_REPEAT_TLBI_CFGI = 1 << 0,
+};
+
 /**
  * struct iommu_hw_info_arm_smmuv3 - ARM SMMUv3 hardware information
  *                                   (IOMMU_HW_INFO_TYPE_ARM_SMMUV3)
  *
- * @flags: Must be set to 0
+ * @flags: Combination of enum iommu_hw_info_arm_smmuv3_flags
  * @__reserved: Must be 0
  * @idr: Implemented features for ARM SMMU Non-secure programming interface
  * @iidr: Information about the implementation and implementer of ARM SMMU,
-- 
2.50.1