iommufd: Fault-capable hwpt attach/detach/replace

Add iopf-capable hw page table attach/detach/replace helpers. The pointer
to iommufd_device is stored in the domain attachment handle, so that it
can be echo'ed back in the iopf_group.

The iopf-capable hw page tables can only be attached to devices that
support the IOMMU_DEV_FEAT_IOPF feature. On the first attachment of an
iopf-capable hw_pagetable to the device, the IOPF feature is enabled on
the device. Similarly, after the last iopf-capable hwpt is detached from
the device, the IOPF feature is disabled on the device.

The current implementation allows a replacement between iopf-capable and
non-iopf-capable hw page tables. This matches the nested translation use
case, where a parent domain is attached by default and can then be
replaced with a nested user domain with iopf support.

Link: https://lore.kernel.org/r/20240702063444.105814-8-baolu.lu@linux.intel.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

Author: LuBaolu

drivers/iommu/iommufd/device.c

@@ -215,6 +215,7 @@ struct iommufd_device *iommufd_device_bind(struct iommufd_ctx *ictx,
 	refcount_inc(&idev->obj.users);
 	/* igroup refcount moves into iommufd_device */
 	idev->igroup = igroup;
+	mutex_init(&idev->iopf_lock);
 
 	/*
 	 * If the caller fails after this success it must call
@@ -376,7 +377,7 @@ int iommufd_hw_pagetable_attach(struct iommufd_hw_pagetable *hwpt,
 	 * attachment.
 	 */
 	if (list_empty(&idev->igroup->device_list)) {
-		rc = iommu_attach_group(hwpt->domain, idev->igroup->group);
+		rc = iommufd_hwpt_attach_device(hwpt, idev);
 		if (rc)
 			goto err_unresv;
 		idev->igroup->hwpt = hwpt;
@@ -402,7 +403,7 @@ iommufd_hw_pagetable_detach(struct iommufd_device *idev)
 	mutex_lock(&idev->igroup->lock);
 	list_del(&idev->group_item);
 	if (list_empty(&idev->igroup->device_list)) {
-		iommu_detach_group(hwpt->domain, idev->igroup->group);
+		iommufd_hwpt_detach_device(hwpt, idev);
 		idev->igroup->hwpt = NULL;
 	}
 	if (hwpt_is_paging(hwpt))
@@ -497,7 +498,7 @@ iommufd_device_do_replace(struct iommufd_device *idev,
 			goto err_unlock;
 	}
 
-	rc = iommu_group_replace_domain(igroup->group, hwpt->domain);
+	rc = iommufd_hwpt_replace_device(idev, hwpt, old_hwpt);
 	if (rc)
 		goto err_unresv;
 

drivers/iommu/iommufd/fault.c

@@ -8,13 +8,203 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/iommufd.h>
+#include <linux/pci.h>
 #include <linux/poll.h>
 #include <linux/anon_inodes.h>
 #include <uapi/linux/iommufd.h>
 
 #include "../iommu-priv.h"
 #include "iommufd_private.h"
 
+static int iommufd_fault_iopf_enable(struct iommufd_device *idev)
+{
+	struct device *dev = idev->dev;
+	int ret;
+
+	/*
+	 * Once we turn on PCI/PRI support for VF, the response failure code
+	 * should not be forwarded to the hardware due to PRI being a shared
+	 * resource between PF and VFs. There is no coordination for this
+	 * shared capability. This waits for a vPRI reset to recover.
+	 */
+	if (dev_is_pci(dev) && to_pci_dev(dev)->is_virtfn)
+		return -EINVAL;
+
+	mutex_lock(&idev->iopf_lock);
+	/* Device iopf has already been on. */
+	if (++idev->iopf_enabled > 1) {
+		mutex_unlock(&idev->iopf_lock);
+		return 0;
+	}
+
+	ret = iommu_dev_enable_feature(dev, IOMMU_DEV_FEAT_IOPF);
+	if (ret)
+		--idev->iopf_enabled;
+	mutex_unlock(&idev->iopf_lock);
+
+	return ret;
+}
+
+static void iommufd_fault_iopf_disable(struct iommufd_device *idev)
+{
+	mutex_lock(&idev->iopf_lock);
+	if (!WARN_ON(idev->iopf_enabled == 0)) {
+		if (--idev->iopf_enabled == 0)
+			iommu_dev_disable_feature(idev->dev, IOMMU_DEV_FEAT_IOPF);
+	}
+	mutex_unlock(&idev->iopf_lock);
+}
+
+static int __fault_domain_attach_dev(struct iommufd_hw_pagetable *hwpt,
+				     struct iommufd_device *idev)
+{
+	struct iommufd_attach_handle *handle;
+	int ret;
+
+	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
+	if (!handle)
+		return -ENOMEM;
+
+	handle->idev = idev;
+	ret = iommu_attach_group_handle(hwpt->domain, idev->igroup->group,
+					&handle->handle);
+	if (ret)
+		kfree(handle);
+
+	return ret;
+}
+
+int iommufd_fault_domain_attach_dev(struct iommufd_hw_pagetable *hwpt,
+				    struct iommufd_device *idev)
+{
+	int ret;
+
+	if (!hwpt->fault)
+		return -EINVAL;
+
+	ret = iommufd_fault_iopf_enable(idev);
+	if (ret)
+		return ret;
+
+	ret = __fault_domain_attach_dev(hwpt, idev);
+	if (ret)
+		iommufd_fault_iopf_disable(idev);
+
+	return ret;
+}
+
+static void iommufd_auto_response_faults(struct iommufd_hw_pagetable *hwpt,
+					 struct iommufd_attach_handle *handle)
+{
+	struct iommufd_fault *fault = hwpt->fault;
+	struct iopf_group *group, *next;
+	unsigned long index;
+
+	if (!fault)
+		return;
+
+	mutex_lock(&fault->mutex);
+	list_for_each_entry_safe(group, next, &fault->deliver, node) {
+		if (group->attach_handle != &handle->handle)
+			continue;
+		list_del(&group->node);
+		iopf_group_response(group, IOMMU_PAGE_RESP_INVALID);
+		iopf_free_group(group);
+	}
+
+	xa_for_each(&fault->response, index, group) {
+		if (group->attach_handle != &handle->handle)
+			continue;
+		xa_erase(&fault->response, index);
+		iopf_group_response(group, IOMMU_PAGE_RESP_INVALID);
+		iopf_free_group(group);
+	}
+	mutex_unlock(&fault->mutex);
+}
+
+static struct iommufd_attach_handle *
+iommufd_device_get_attach_handle(struct iommufd_device *idev)
+{
+	struct iommu_attach_handle *handle;
+
+	handle = iommu_attach_handle_get(idev->igroup->group, IOMMU_NO_PASID, 0);
+	if (!handle)
+		return NULL;
+
+	return to_iommufd_handle(handle);
+}
+
+void iommufd_fault_domain_detach_dev(struct iommufd_hw_pagetable *hwpt,
+				     struct iommufd_device *idev)
+{
+	struct iommufd_attach_handle *handle;
+
+	handle = iommufd_device_get_attach_handle(idev);
+	iommu_detach_group_handle(hwpt->domain, idev->igroup->group);
+	iommufd_auto_response_faults(hwpt, handle);
+	iommufd_fault_iopf_disable(idev);
+	kfree(handle);
+}
+
+static int __fault_domain_replace_dev(struct iommufd_device *idev,
+				      struct iommufd_hw_pagetable *hwpt,
+				      struct iommufd_hw_pagetable *old)
+{
+	struct iommufd_attach_handle *handle, *curr = NULL;
+	int ret;
+
+	if (old->fault)
+		curr = iommufd_device_get_attach_handle(idev);
+
+	if (hwpt->fault) {
+		handle = kzalloc(sizeof(*handle), GFP_KERNEL);
+		if (!handle)
+			return -ENOMEM;
+
+		handle->handle.domain = hwpt->domain;
+		handle->idev = idev;
+		ret = iommu_replace_group_handle(idev->igroup->group,
+						 hwpt->domain, &handle->handle);
+	} else {
+		ret = iommu_replace_group_handle(idev->igroup->group,
+						 hwpt->domain, NULL);
+	}
+
+	if (!ret && curr) {
+		iommufd_auto_response_faults(old, curr);
+		kfree(curr);
+	}
+
+	return ret;
+}
+
+int iommufd_fault_domain_replace_dev(struct iommufd_device *idev,
+				     struct iommufd_hw_pagetable *hwpt,
+				     struct iommufd_hw_pagetable *old)
+{
+	bool iopf_off = !hwpt->fault && old->fault;
+	bool iopf_on = hwpt->fault && !old->fault;
+	int ret;
+
+	if (iopf_on) {
+		ret = iommufd_fault_iopf_enable(idev);
+		if (ret)
+			return ret;
+	}
+
+	ret = __fault_domain_replace_dev(idev, hwpt, old);
+	if (ret) {
+		if (iopf_on)
+			iommufd_fault_iopf_disable(idev);
+		return ret;
+	}
+
+	if (iopf_off)
+		iommufd_fault_iopf_disable(idev);
+
+	return 0;
+}
+
 void iommufd_fault_destroy(struct iommufd_object *obj)
 {
 	struct iommufd_fault *fault = container_of(obj, struct iommufd_fault, obj);

drivers/iommu/iommufd/iommufd_private.h

@@ -11,6 +11,7 @@
 #include <linux/iommu.h>
 #include <linux/iova_bitmap.h>
 #include <uapi/linux/iommufd.h>
+#include "../iommu-priv.h"
 
 struct iommu_domain;
 struct iommu_group;
@@ -293,6 +294,7 @@ int iommufd_check_iova_range(struct io_pagetable *iopt,
 struct iommufd_hw_pagetable {
 	struct iommufd_object obj;
 	struct iommu_domain *domain;
+	struct iommufd_fault *fault;
 };
 
 struct iommufd_hwpt_paging {
@@ -396,6 +398,9 @@ struct iommufd_device {
 	/* always the physical device */
 	struct device *dev;
 	bool enforce_cache_coherency;
+	/* protect iopf_enabled counter */
+	struct mutex iopf_lock;
+	unsigned int iopf_enabled;
 };
 
 static inline struct iommufd_device *
@@ -456,6 +461,42 @@ struct iommufd_attach_handle {
 int iommufd_fault_alloc(struct iommufd_ucmd *ucmd);
 void iommufd_fault_destroy(struct iommufd_object *obj);
 
+int iommufd_fault_domain_attach_dev(struct iommufd_hw_pagetable *hwpt,
+				    struct iommufd_device *idev);
+void iommufd_fault_domain_detach_dev(struct iommufd_hw_pagetable *hwpt,
+				     struct iommufd_device *idev);
+int iommufd_fault_domain_replace_dev(struct iommufd_device *idev,
+				     struct iommufd_hw_pagetable *hwpt,
+				     struct iommufd_hw_pagetable *old);
+
+static inline int iommufd_hwpt_attach_device(struct iommufd_hw_pagetable *hwpt,
+					     struct iommufd_device *idev)
+{
+	if (hwpt->fault)
+		return iommufd_fault_domain_attach_dev(hwpt, idev);
+
+	return iommu_attach_group(hwpt->domain, idev->igroup->group);
+}
+
+static inline void iommufd_hwpt_detach_device(struct iommufd_hw_pagetable *hwpt,
+					      struct iommufd_device *idev)
+{
+	if (hwpt->fault)
+		iommufd_fault_domain_detach_dev(hwpt, idev);
+
+	iommu_detach_group(hwpt->domain, idev->igroup->group);
+}
+
+static inline int iommufd_hwpt_replace_device(struct iommufd_device *idev,
+					      struct iommufd_hw_pagetable *hwpt,
+					      struct iommufd_hw_pagetable *old)
+{
+	if (old->fault || hwpt->fault)
+		return iommufd_fault_domain_replace_dev(idev, hwpt, old);
+
+	return iommu_group_replace_domain(idev->igroup->group, hwpt->domain);
+}
+
 #ifdef CONFIG_IOMMUFD_TEST
 int iommufd_test(struct iommufd_ucmd *ucmd);
 void iommufd_selftest_destroy(struct iommufd_object *obj);