[PATCH v4 4/9] iommufd: Fault-capable hw page table attach/detach/replace

[Lu Baolu]

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.

Signed-off-by: Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx>
---
 drivers/iommu/iommufd/iommufd_private.h |   9 ++
 drivers/iommu/iommufd/device.c          |  15 +++-
 drivers/iommu/iommufd/fault.c           | 113 ++++++++++++++++++++++++
 drivers/iommu/iommufd/Makefile          |   1 +
 4 files changed, 135 insertions(+), 3 deletions(-)
 create mode 100644 drivers/iommu/iommufd/fault.c

diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index 991f864d1f9b..047cfb47112a 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -292,6 +292,7 @@ int iommufd_check_iova_range(struct io_pagetable *iopt,
 struct iommufd_hw_pagetable {
 	struct iommufd_object obj;
 	struct iommu_domain *domain;
+	bool fault_capable;
 };
 
 struct iommufd_hwpt_paging {
@@ -395,6 +396,7 @@ struct iommufd_device {
 	/* always the physical device */
 	struct device *dev;
 	bool enforce_cache_coherency;
+	bool iopf_enabled;
 };
 
 static inline struct iommufd_device *
@@ -426,6 +428,13 @@ void iopt_remove_access(struct io_pagetable *iopt,
 			u32 iopt_access_list_id);
 void iommufd_access_destroy_object(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_hw_pagetable *hwpt,
+				     struct iommufd_device *idev);
+
 #ifdef CONFIG_IOMMUFD_TEST
 int iommufd_test(struct iommufd_ucmd *ucmd);
 void iommufd_selftest_destroy(struct iommufd_object *obj);
diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c
index 873630c111c1..4fc183a83925 100644
--- a/drivers/iommu/iommufd/device.c
+++ b/drivers/iommu/iommufd/device.c
@@ -376,7 +376,10 @@ 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);
+		if (hwpt->fault_capable)
+			rc = iommufd_fault_domain_attach_dev(hwpt, idev);
+		else
+			rc = iommu_attach_group(hwpt->domain, idev->igroup->group);
 		if (rc)
 			goto err_unresv;
 		idev->igroup->hwpt = hwpt;
@@ -402,7 +405,10 @@ 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);
+		if (hwpt->fault_capable)
+			iommufd_fault_domain_detach_dev(hwpt, idev);
+		else
+			iommu_detach_group(hwpt->domain, idev->igroup->group);
 		idev->igroup->hwpt = NULL;
 	}
 	if (hwpt_is_paging(hwpt))
@@ -497,7 +503,10 @@ iommufd_device_do_replace(struct iommufd_device *idev,
 			goto err_unlock;
 	}
 
-	rc = iommu_group_replace_domain(igroup->group, hwpt->domain);
+	if (old_hwpt->fault_capable || hwpt->fault_capable)
+		rc = iommufd_fault_domain_replace_dev(hwpt, idev);
+	else
+		rc = iommu_group_replace_domain(igroup->group, hwpt->domain);
 	if (rc)
 		goto err_unresv;
 
diff --git a/drivers/iommu/iommufd/fault.c b/drivers/iommu/iommufd/fault.c
new file mode 100644
index 000000000000..47d7c106d839
--- /dev/null
+++ b/drivers/iommu/iommufd/fault.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2024 Intel Corporation
+ */
+#define pr_fmt(fmt) "iommufd: " fmt
+
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/iommufd.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)
+{
+	int ret;
+
+	if (idev->iopf_enabled)
+		return 0;
+
+	ret = iommu_dev_enable_feature(idev->dev, IOMMU_DEV_FEAT_IOPF);
+	if (ret)
+		return ret;
+
+	idev->iopf_enabled = true;
+
+	return 0;
+}
+
+static void iommufd_fault_iopf_disable(struct iommufd_device *idev)
+{
+	if (!idev->iopf_enabled)
+		return;
+
+	iommu_dev_disable_feature(idev->dev, IOMMU_DEV_FEAT_IOPF);
+	idev->iopf_enabled = false;
+}
+
+int iommufd_fault_domain_attach_dev(struct iommufd_hw_pagetable *hwpt,
+				    struct iommufd_device *idev)
+{
+	struct iommu_attach_handle *handle;
+	int ret;
+
+	if (!hwpt->fault_capable)
+		return -EINVAL;
+
+	if (!idev->iopf_enabled) {
+		ret = iommufd_fault_iopf_enable(idev);
+		if (ret)
+			return ret;
+	}
+
+	ret = iommu_attach_group(hwpt->domain, idev->igroup->group);
+	if (ret) {
+		iommufd_fault_iopf_disable(idev);
+		return ret;
+	}
+
+	handle = iommu_attach_handle_get(idev->igroup->group, IOMMU_NO_PASID);
+	handle->priv = idev;
+	iommu_attach_handle_put(handle);
+
+	return 0;
+}
+
+void iommufd_fault_domain_detach_dev(struct iommufd_hw_pagetable *hwpt,
+				     struct iommufd_device *idev)
+{
+	if (WARN_ON(!hwpt->fault_capable))
+		return;
+
+	iommu_detach_group(hwpt->domain, idev->igroup->group);
+	iommufd_fault_iopf_disable(idev);
+}
+
+int iommufd_fault_domain_replace_dev(struct iommufd_hw_pagetable *hwpt,
+				     struct iommufd_device *idev)
+{
+	bool iopf_enabled_originally = idev->iopf_enabled;
+	struct iommu_attach_handle *handle;
+	int ret;
+
+	if (hwpt->fault_capable) {
+		ret = iommufd_fault_iopf_enable(idev);
+		if (ret)
+			return ret;
+	}
+
+	ret = iommu_group_replace_domain(idev->igroup->group, hwpt->domain);
+	if (ret)
+		goto out_cleanup;
+
+	if (!hwpt->fault_capable)
+		iommufd_fault_iopf_disable(idev);
+
+	handle = iommu_attach_handle_get(idev->igroup->group, IOMMU_NO_PASID);
+	handle->priv = idev;
+	iommu_attach_handle_put(handle);
+
+	return 0;
+out_cleanup:
+	if (iopf_enabled_originally)
+		iommufd_fault_iopf_enable(idev);
+	else
+		iommufd_fault_iopf_disable(idev);
+
+	return ret;
+}
diff --git a/drivers/iommu/iommufd/Makefile b/drivers/iommu/iommufd/Makefile
index 34b446146961..b94a74366eed 100644
--- a/drivers/iommu/iommufd/Makefile
+++ b/drivers/iommu/iommufd/Makefile
@@ -6,6 +6,7 @@ iommufd-y := \
 	ioas.o \
 	main.o \
 	pages.o \
+	fault.o \
 	vfio_compat.o
 
 iommufd-$(CONFIG_IOMMUFD_TEST) += selftest.o
-- 
2.34.1