Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Stanimir Varbanov <svarbanov@suse.de>
To:     linux-tegra@vger.kernel.org, linux-arm-kernel@lists.infradead.org,
        iommu@lists.linux.dev, linux-kernel@vger.kernel.org
Cc:     Thierry Reding <thierry.reding@gmail.com>,
        Krishna Reddy <vdumpa@nvidia.com>,
        Will Deacon <will@kernel.org>,
        Robin Murphy <robin.murphy@arm.com>,
        Joerg Roedel <joro@8bytes.org>,
        Stanimir Varbanov <svarbanov@suse.de>
Subject: [RFC PATCH] iommu: arm-smmu-nvidia: Add default domain type implementation op
Date:   Mon, 10 Jul 2023 11:22:52 +0300
Message-ID: <20230710082252.9702-1-svarbanov@suse.de>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Add def_domain_type implementation op and override default IOMMU
domain Kconfig option (CONFIG_IOMMU_DEFAULT_PASSTHROUGH=y), which
could be enabled on some distros. The current quirk has been done
for Tegra234 machine, because I found the issue on it. The issue
itself appears on USB host controller which cannot be initialized
without IOMMU translation. Something more, we proved that IOMMU
translation is needed for display and GPU drivers as well.

I evaluated few possible options to solve that:

 a) select default IOMMU domain from .def_domain_type op
 b) Unset CONFIG_IOMMU_DEFAULT_PASSTHROUGH=n
 c) add iommu.passthrough=0 on the kernel cmdline
 d) firmware - ACPI / DT

a) This option is implemented in the proposed patch.

b) Since that the community has agreed that pass-through is preferred
as a default IOMMU domain option because this will avoid performance
impacts on some of the platforms [1]. On the other side we have examples
where you cannot even install Linux distribution on a machine where the
storage media cannot be detected and the system just hangs.

c) - This option involves installer's knowledge of platforms/devices
which needs IOMMU translations.

d) - IORT ACPI table / DT - I'm not sure is that option even possible
but firmware looks like a good place for such.

Please, treat this as an RFC and a call for proper solution.

[1] https://marc.info/?l=linux-arm-kernel&m=148864682514762

Signed-off-by: Stanimir Varbanov <svarbanov@suse.de>
---
 drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c b/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c
index 87bf522b9d2e..691b57d1e699 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c
@@ -286,6 +286,22 @@ static int nvidia_smmu_init_context(struct arm_smmu_domain *smmu_domain,
 	return 0;
 }
 
+static int nvidia_smmu_def_domain_type(struct device *dev)
+{
+	if (of_machine_is_compatible("nvidia,tegra234"))
+		return IOMMU_DOMAIN_DMA;
+
+	return 0;
+}
+
+static int nvidia_smmu_single_def_domain_type(struct device *dev)
+{
+	if (of_machine_is_compatible("nvidia,tegra234"))
+		return IOMMU_DOMAIN_DMA;
+
+	return 0;
+}
+
 static const struct arm_smmu_impl nvidia_smmu_impl = {
 	.read_reg = nvidia_smmu_read_reg,
 	.write_reg = nvidia_smmu_write_reg,
@@ -297,11 +313,13 @@ static const struct arm_smmu_impl nvidia_smmu_impl = {
 	.context_fault = nvidia_smmu_context_fault,
 	.probe_finalize = nvidia_smmu_probe_finalize,
 	.init_context = nvidia_smmu_init_context,
+	.def_domain_type = nvidia_smmu_def_domain_type,
 };
 
 static const struct arm_smmu_impl nvidia_smmu_single_impl = {
 	.probe_finalize = nvidia_smmu_probe_finalize,
 	.init_context = nvidia_smmu_init_context,
+	.def_domain_type = nvidia_smmu_single_def_domain_type,
 };
 
 struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu)
-- 
2.41.0