sync: rvck #144: 【bugfix】修复iommu的几个严重bug

drivers/acpi/arm64/dma.c

@@ -26,6 +26,11 @@ void acpi_arch_dma_setup(struct device *dev)
 	else
 		end = (1ULL << 32) - 1;
 
+	if (dev->dma_range_map) {
+		dev_dbg(dev, "dma_range_map already set\n");
+		return;
+	}
+
 	ret = acpi_dma_get_range(dev, &map);
 	if (!ret && map) {
 		end = dma_range_map_max(map);

drivers/acpi/arm64/iort.c

@@ -1318,30 +1318,21 @@ static bool iort_pci_rc_supports_canwbs(struct acpi_iort_node *node)
 static int iort_iommu_xlate(struct device *dev, struct acpi_iort_node *node,
 			    u32 streamid)
 {
-	const struct iommu_ops *ops;
 	struct fwnode_handle *iort_fwnode;
 
-	if (!node)
+	/* If there's no SMMU driver at all, give up now */
+	if (!node || !iort_iommu_driver_enabled(node->type))
 		return -ENODEV;
 
 	iort_fwnode = iort_get_fwnode(node);
 	if (!iort_fwnode)
 		return -ENODEV;
 
 	/*
-	 * If the ops look-up fails, this means that either
-	 * the SMMU drivers have not been probed yet or that
-	 * the SMMU drivers are not built in the kernel;
-	 * Depending on whether the SMMU drivers are built-in
-	 * in the kernel or not, defer the IOMMU configuration
-	 * or just abort it.
+	 * If the SMMU drivers are enabled but not loaded/probed
+	 * yet, this will defer.
 	 */
-	ops = iommu_ops_from_fwnode(iort_fwnode);
-	if (!ops)
-		return iort_iommu_driver_enabled(node->type) ?
-		       -EPROBE_DEFER : -ENODEV;
-
-	return acpi_iommu_fwspec_init(dev, streamid, iort_fwnode, ops);
+	return acpi_iommu_fwspec_init(dev, streamid, iort_fwnode);
 }
 
 struct iort_pci_alias_info {

drivers/acpi/scan.c

@@ -1619,37 +1619,24 @@ int acpi_dma_get_range(struct device *dev, const struct bus_dma_region **map)
 
 #ifdef CONFIG_IOMMU_API
 int acpi_iommu_fwspec_init(struct device *dev, u32 id,
-			   struct fwnode_handle *fwnode,
-			   const struct iommu_ops *ops)
+			   struct fwnode_handle *fwnode)
 {
-	int ret = iommu_fwspec_init(dev, fwnode, ops);
+	int ret = iommu_fwspec_init(dev, fwnode);
 
 	if (!ret)
 		ret = iommu_fwspec_add_ids(dev, &id, 1);
 
 	return ret;
 }
 
-static inline const struct iommu_ops *acpi_iommu_fwspec_ops(struct device *dev)
-{
-	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
-
-	return fwspec ? fwspec->ops : NULL;
-}
-
 static int acpi_iommu_configure_id(struct device *dev, const u32 *id_in)
 {
 	int err;
-	const struct iommu_ops *ops;
 
 	/* Serialise to make dev->iommu stable under our potential fwspec */
 	mutex_lock(&iommu_probe_device_lock);
-	/*
-	 * If we already translated the fwspec there is nothing left to do,
-	 * return the iommu_ops.
-	 */
-	ops = acpi_iommu_fwspec_ops(dev);
-	if (ops) {
+	/* If we already translated the fwspec there is nothing left to do */
+	if (dev_iommu_fwspec_get(dev)) {
 		mutex_unlock(&iommu_probe_device_lock);
 		return 0;
 	}
@@ -1659,30 +1646,13 @@ static int acpi_iommu_configure_id(struct device *dev, const u32 *id_in)
 		err = viot_iommu_configure(dev);
 	mutex_unlock(&iommu_probe_device_lock);
 
-	/*
-	 * If we have reason to believe the IOMMU driver missed the initial
-	 * iommu_probe_device() call for dev, replay it to get things in order.
-	 */
-	if (!err && dev->bus)
-		err = iommu_probe_device(dev);
-
-	/* Ignore all other errors apart from EPROBE_DEFER */
-	if (err == -EPROBE_DEFER) {
-		return err;
-	} else if (err) {
-		dev_dbg(dev, "Adding to IOMMU failed: %d\n", err);
-		return -ENODEV;
-	}
-	if (!acpi_iommu_fwspec_ops(dev))
-		return -ENODEV;
-	return 0;
+	return err;
 }
 
 #else /* !CONFIG_IOMMU_API */
 
 int acpi_iommu_fwspec_init(struct device *dev, u32 id,
-			   struct fwnode_handle *fwnode,
-			   const struct iommu_ops *ops)
+			   struct fwnode_handle *fwnode)
 {
 	return -ENODEV;
 }
@@ -1715,6 +1685,8 @@ int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr,
 	ret = acpi_iommu_configure_id(dev, input_id);
 	if (ret == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
+	if (ret)
+		dev_dbg(dev, "Adding to IOMMU failed: %d\n", ret);
 
 	/*
 	 * Historically this routine doesn't fail driver probing due to errors

drivers/acpi/viot.c

@@ -307,21 +307,14 @@ void __init acpi_viot_init(void)
 static int viot_dev_iommu_init(struct device *dev, struct viot_iommu *viommu,
 			       u32 epid)
 {
-	const struct iommu_ops *ops;
-
-	if (!viommu)
+	if (!viommu || !IS_ENABLED(CONFIG_VIRTIO_IOMMU))
 		return -ENODEV;
 
 	/* We're not translating ourself */
 	if (device_match_fwnode(dev, viommu->fwnode))
 		return -EINVAL;
 
-	ops = iommu_ops_from_fwnode(viommu->fwnode);
-	if (!ops)
-		return IS_ENABLED(CONFIG_VIRTIO_IOMMU) ?
-			-EPROBE_DEFER : -ENODEV;
-
-	return acpi_iommu_fwspec_init(dev, epid, viommu->fwnode, ops);
+	return acpi_iommu_fwspec_init(dev, epid, viommu->fwnode);
 }
 
 static int viot_pci_dev_iommu_init(struct pci_dev *pdev, u16 dev_id, void *data)

drivers/amba/bus.c

@@ -363,7 +363,8 @@ static int amba_dma_configure(struct device *dev)
 		ret = acpi_dma_configure(dev, attr);
 	}
 
-	if (!ret && !drv->driver_managed_dma) {
+	/* @drv may not be valid when we're called from the IOMMU layer */
+	if (!ret && dev->driver && !drv->driver_managed_dma) {
 		ret = iommu_device_use_default_domain(dev);
 		if (ret)
 			arch_teardown_dma_ops(dev);

drivers/base/platform.c

@@ -1457,7 +1457,8 @@ static int platform_dma_configure(struct device *dev)
 		ret = acpi_dma_configure(dev, attr);
 	}
 
-	if (!ret && !drv->driver_managed_dma) {
+	/* @drv may not be valid when we're called from the IOMMU layer */
+	if (!ret && dev->driver && !drv->driver_managed_dma) {
 		ret = iommu_device_use_default_domain(dev);
 		if (ret)
 			arch_teardown_dma_ops(dev);

drivers/bus/fsl-mc/fsl-mc-bus.c

@@ -153,7 +153,8 @@ static int fsl_mc_dma_configure(struct device *dev)
 	else
 		ret = acpi_dma_configure_id(dev, DEV_DMA_COHERENT, &input_id);
 
-	if (!ret && !mc_drv->driver_managed_dma) {
+	/* @mc_drv may not be valid when we're called from the IOMMU layer */
+	if (!ret && dev->driver && !mc_drv->driver_managed_dma) {
 		ret = iommu_device_use_default_domain(dev);
 		if (ret)
 			arch_teardown_dma_ops(dev);

drivers/cdx/cdx.c

@@ -270,7 +270,8 @@ static int cdx_dma_configure(struct device *dev)
 		return ret;
 	}
 
-	if (!ret && !cdx_drv->driver_managed_dma) {
+	/* @cdx_drv may not be valid when we're called from the IOMMU layer */
+	if (!ret && dev->driver && !cdx_drv->driver_managed_dma) {
 		ret = iommu_device_use_default_domain(dev);
 		if (ret)
 			arch_teardown_dma_ops(dev);

drivers/gpu/drm/msm/msm_iommu.c

@@ -407,10 +407,13 @@ struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks)
 	struct msm_iommu *iommu;
 	int ret;
 
-	domain = iommu_domain_alloc(dev->bus);
-	if (!domain)
+	if (!device_iommu_mapped(dev))
 		return NULL;
 
+	domain = iommu_paging_domain_alloc(dev);
+	if (IS_ERR(domain))
+		return ERR_CAST(domain);
+
 	iommu_set_pgtable_quirks(domain, quirks);
 
 	iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);

drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c

@@ -120,8 +120,8 @@ nvkm_device_tegra_probe_iommu(struct nvkm_device_tegra *tdev)
 	mutex_init(&tdev->iommu.mutex);
 
 	if (device_iommu_mapped(dev)) {
-		tdev->iommu.domain = iommu_domain_alloc(&platform_bus_type);
-		if (!tdev->iommu.domain)
+		tdev->iommu.domain = iommu_paging_domain_alloc(dev);
+		if (IS_ERR(tdev->iommu.domain))
 			goto error;
 
 		/*

drivers/gpu/drm/rockchip/rockchip_drm_drv.c

@@ -103,13 +103,17 @@ static int rockchip_drm_init_iommu(struct drm_device *drm_dev)
 	struct rockchip_drm_private *private = drm_dev->dev_private;
 	struct iommu_domain_geometry *geometry;
 	u64 start, end;
+	int ret;
 
 	if (IS_ERR_OR_NULL(private->iommu_dev))
 		return 0;
 
-	private->domain = iommu_domain_alloc(private->iommu_dev->bus);
-	if (!private->domain)
-		return -ENOMEM;
+	private->domain = iommu_paging_domain_alloc(private->iommu_dev);
+	if (IS_ERR(private->domain)) {
+		ret = PTR_ERR(private->domain);
+		private->domain = NULL;
+		return ret;
+	}
 
 	geometry = &private->domain->geometry;
 	start = geometry->aperture_start;

drivers/gpu/drm/tegra/drm.c

@@ -1134,6 +1134,7 @@ static bool host1x_drm_wants_iommu(struct host1x_device *dev)
 
 static int host1x_drm_probe(struct host1x_device *dev)
 {
+	struct device *dma_dev = dev->dev.parent;
 	struct tegra_drm *tegra;
 	struct drm_device *drm;
 	int err;
@@ -1148,8 +1149,8 @@ static int host1x_drm_probe(struct host1x_device *dev)
 		goto put;
 	}
 
-	if (host1x_drm_wants_iommu(dev) && iommu_present(&platform_bus_type)) {
-		tegra->domain = iommu_domain_alloc(&platform_bus_type);
+	if (host1x_drm_wants_iommu(dev) && device_iommu_mapped(dma_dev)) {
+		tegra->domain = iommu_paging_domain_alloc(dma_dev);
 		if (!tegra->domain) {
 			err = -ENOMEM;
 			goto free;

drivers/gpu/host1x/dev.c

@@ -379,9 +379,10 @@ static struct iommu_domain *host1x_iommu_attach(struct host1x *host)
 		if (err < 0)
 			goto put_group;
 
-		host->domain = iommu_domain_alloc(&platform_bus_type);
-		if (!host->domain) {
-			err = -ENOMEM;
+		host->domain = iommu_paging_domain_alloc(host->dev);
+		if (IS_ERR(host->domain)) {
+			err = PTR_ERR(host->domain);
+			host->domain = NULL;
 			goto put_cache;
 		}
 

drivers/infiniband/hw/usnic/usnic_uiom.c

@@ -443,11 +443,11 @@ struct usnic_uiom_pd *usnic_uiom_alloc_pd(struct device *dev)
 	if (!pd)
 		return ERR_PTR(-ENOMEM);
 
-	pd->domain = domain = iommu_domain_alloc(dev->bus);
-	if (!domain) {
+	pd->domain = domain = iommu_paging_domain_alloc(dev);
+	if (IS_ERR(domain)) {
 		usnic_err("Failed to allocate IOMMU domain");
 		kfree(pd);
-		return ERR_PTR(-ENOMEM);
+		return ERR_CAST(domain);
 	}
 
 	iommu_set_fault_handler(pd->domain, usnic_uiom_dma_fault, NULL);

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

@@ -183,8 +183,7 @@ static int arm_smmu_register_legacy_master(struct device *dev,
 		it.cur_count = 1;
 	}
 
-	err = iommu_fwspec_init(dev, &smmu_dev->of_node->fwnode,
-				&arm_smmu_ops);
+	err = iommu_fwspec_init(dev, NULL);
 	if (err)
 		return err;
 
@@ -1471,7 +1470,6 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 out_cfg_free:
 	kfree(cfg);
 out_free:
-	iommu_fwspec_free(dev);
 	return ERR_PTR(ret);
 }
 

drivers/iommu/iommu-priv.h

@@ -17,9 +17,20 @@ static inline const struct iommu_ops *dev_iommu_ops(struct device *dev)
 	return dev->iommu->iommu_dev->ops;
 }
 
+void dev_iommu_free(struct device *dev);
+
+const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode);
+
+static inline const struct iommu_ops *iommu_fwspec_ops(struct iommu_fwspec *fwspec)
+{
+	return iommu_ops_from_fwnode(fwspec ? fwspec->iommu_fwnode : NULL);
+}
+
 int iommu_group_replace_domain(struct iommu_group *group,
 			       struct iommu_domain *new_domain);
 
+void iommu_fwspec_free(struct device *dev);
+
 int iommu_device_register_bus(struct iommu_device *iommu,
 			      const struct iommu_ops *ops, struct bus_type *bus,
 			      struct notifier_block *nb);