iommu/arm-smmu-qcom: do not register driver in probe()

Commit 0b4eeee287 ("iommu/arm-smmu-qcom: Register the TBU driver in
qcom_smmu_impl_init") intended to also probe the TBU driver when
CONFIG_ARM_SMMU_QCOM_DEBUG is disabled, but also moved the corresponding
platform_driver_register() call into qcom_smmu_impl_init() which is
called from arm_smmu_device_probe().

However, it neither makes sense to register drivers from probe()
callbacks of other drivers, nor does the driver core allow registering
drivers with a device lock already being held.

The latter was revealed by commit dc23806a7c ("driver core: enforce
device_lock for driver_match_device()") leading to a deadlock condition
described in [1].

Additionally, it was noted by Robin that the current approach is
potentially racy with async probe [2].

Hence, fix this by registering the qcom_smmu_tbu_driver from
module_init(). Unfortunately, due to the vendoring of the driver, this
requires an indirection through arm-smmu-impl.c.

Reported-by: Mark Brown <broonie@kernel.org>
Closes: https://lore.kernel.org/lkml/7ae38e31-ef31-43ad-9106-7c76ea0e8596@sirena.org.uk/
Link: https://lore.kernel.org/lkml/DFU7CEPUSG9A.1KKGVW4HIPMSH@kernel.org/ [1]
Link: https://lore.kernel.org/lkml/0c0d3707-9ea5-44f9-88a1-a65c62e3df8d@arm.com/ [2]
Fixes: dc23806a7c ("driver core: enforce device_lock for driver_match_device()")
Fixes: 0b4eeee287 ("iommu/arm-smmu-qcom: Register the TBU driver in qcom_smmu_impl_init")
Acked-by: Robin Murphy <robin.murphy@arm.com>
Tested-by: Bjorn Andersson <andersson@kernel.org>
Reviewed-by: Bjorn Andersson <andersson@kernel.org>
Acked-by: Konrad Dybcio <konradybcio@kernel.org>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Tested-by: Ioana Ciornei <ioana.ciornei@nxp.com> #LX2160ARDB
Tested-by: Wang Jiayue <akaieurus@gmail.com>
Reviewed-by: Wang Jiayue <akaieurus@gmail.com>
Tested-by: Mark Brown <broonie@kernel.org>
Acked-by: Joerg Roedel <joerg.roedel@amd.com>
Link: https://patch.msgid.link/20260121141215.29658-1-dakr@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>

drivers/iommu/arm/arm-smmu/arm-smmu-impl.c

@@ -228,3 +228,17 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu)
 
 	return smmu;
 }
+
+int __init arm_smmu_impl_module_init(void)
+{
+	if (IS_ENABLED(CONFIG_ARM_SMMU_QCOM))
+		return qcom_smmu_module_init();
+
+	return 0;
+}
+
+void __exit arm_smmu_impl_module_exit(void)
+{
+	if (IS_ENABLED(CONFIG_ARM_SMMU_QCOM))
+		qcom_smmu_module_exit();
+}

drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c

@@ -774,10 +774,6 @@ struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu)
 {
 	const struct device_node *np = smmu->dev->of_node;
 	const struct of_device_id *match;
-	static u8 tbu_registered;
-
-	if (!tbu_registered++)
-		platform_driver_register(&qcom_smmu_tbu_driver);
 
 #ifdef CONFIG_ACPI
 	if (np == NULL) {
@@ -802,3 +798,13 @@ struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu)
 
 	return smmu;
 }
+
+int __init qcom_smmu_module_init(void)
+{
+	return platform_driver_register(&qcom_smmu_tbu_driver);
+}
+
+void __exit qcom_smmu_module_exit(void)
+{
+	platform_driver_unregister(&qcom_smmu_tbu_driver);
+}

drivers/iommu/arm/arm-smmu/arm-smmu.c

@@ -2365,7 +2365,29 @@ static struct platform_driver arm_smmu_driver = {
 	.remove = arm_smmu_device_remove,
 	.shutdown = arm_smmu_device_shutdown,
 };
-module_platform_driver(arm_smmu_driver);
+
+static int __init arm_smmu_init(void)
+{
+	int ret;
+
+	ret = platform_driver_register(&arm_smmu_driver);
+	if (ret)
+		return ret;
+
+	ret = arm_smmu_impl_module_init();
+	if (ret)
+		platform_driver_unregister(&arm_smmu_driver);
+
+	return ret;
+}
+module_init(arm_smmu_init);
+
+static void __exit arm_smmu_exit(void)
+{
+	arm_smmu_impl_module_exit();
+	platform_driver_unregister(&arm_smmu_driver);
+}
+module_exit(arm_smmu_exit);
 
 MODULE_DESCRIPTION("IOMMU API for ARM architected SMMU implementations");
 MODULE_AUTHOR("Will Deacon <will@kernel.org>");

drivers/iommu/arm/arm-smmu/arm-smmu.h

@@ -540,6 +540,11 @@ 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 __init arm_smmu_impl_module_init(void);
+void __exit arm_smmu_impl_module_exit(void);
+int __init qcom_smmu_module_init(void);
+void __exit qcom_smmu_module_exit(void);
+
 void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx);
 int arm_mmu500_reset(struct arm_smmu_device *smmu);