Received-SPF: pass (google.com: domain of linux-kernel+bounces-164217-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
From: Lu Baolu <baolu.lu@linux.intel.com>
To: Jason Gunthorpe <jgg@ziepe.ca>,
	Kevin Tian <kevin.tian@intel.com>,
	Joerg Roedel <joro@8bytes.org>,
	Will Deacon <will@kernel.org>,
	Robin Murphy <robin.murphy@arm.com>,
	Jean-Philippe Brucker <jean-philippe@linaro.org>,
	Nicolin Chen <nicolinc@nvidia.com>,
	Yi Liu <yi.l.liu@intel.com>,
	Jacob Pan <jacob.jun.pan@linux.intel.com>,
	Joel Granados <j.granados@samsung.com>
Cc: iommu@lists.linux.dev,
	virtualization@lists.linux-foundation.org,
	linux-kernel@vger.kernel.org,
	Lu Baolu <baolu.lu@linux.intel.com>
Subject: [PATCH v5 7/9] iommufd: Associate fault object with iommufd_hw_pgtable
Date: Tue, 30 Apr 2024 22:57:08 +0800
Message-Id: <20240430145710.68112-8-baolu.lu@linux.intel.com>
In-Reply-To: <20240430145710.68112-1-baolu.lu@linux.intel.com>
References: <20240430145710.68112-1-baolu.lu@linux.intel.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

When allocating a user iommufd_hw_pagetable, the user space is allowed to
associate a fault object with the hw_pagetable by specifying the fault
object ID in the page table allocation data and setting the
IOMMU_HWPT_FAULT_ID_VALID flag bit.

On a successful return of hwpt allocation, the user can retrieve and
respond to page faults by reading and writing the file interface of the
fault object.

Once a fault object has been associated with a hwpt, the hwpt is
iopf-capable, indicated by fault_capable set to true. Attaching,
detaching, or replacing an iopf-capable hwpt to an RID or PASID will
differ from those that are not iopf-capable.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
---
 drivers/iommu/iommufd/iommufd_private.h |  9 +++++++
 include/uapi/linux/iommufd.h            |  8 ++++++
 drivers/iommu/iommufd/fault.c           | 17 ++++++++++++
 drivers/iommu/iommufd/hw_pagetable.c    | 35 +++++++++++++++++++------
 drivers/iommu/iommufd/main.c            |  2 +-
 5 files changed, 62 insertions(+), 9 deletions(-)

diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index 18c8d7d38dcd..100c7b585e7e 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -449,8 +449,17 @@ struct iommufd_fault {
 	struct wait_queue_head wait_queue;
 };
 
+static inline struct iommufd_fault *
+iommufd_get_fault(struct iommufd_ucmd *ucmd, u32 id)
+{
+	return container_of(iommufd_get_object(ucmd->ictx, id,
+					       IOMMUFD_OBJ_FAULT),
+			    struct iommufd_fault, obj);
+}
+
 int iommufd_fault_alloc(struct iommufd_ucmd *ucmd);
 void iommufd_fault_destroy(struct iommufd_object *obj);
+int iommufd_fault_iopf_handler(struct iopf_group *group);
 
 int iommufd_fault_domain_attach_dev(struct iommufd_hw_pagetable *hwpt,
 				    struct iommufd_device *idev);
diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h
index 1819b28e9e6b..3d566c1ffcc6 100644
--- a/include/uapi/linux/iommufd.h
+++ b/include/uapi/linux/iommufd.h
@@ -357,10 +357,13 @@ struct iommu_vfio_ioas {
  *                                the parent HWPT in a nesting configuration.
  * @IOMMU_HWPT_ALLOC_DIRTY_TRACKING: Dirty tracking support for device IOMMU is
  *                                   enforced on device attachment
+ * @IOMMU_HWPT_FAULT_ID_VALID: The fault_id field of hwpt allocation data is
+ *                             valid.
  */
 enum iommufd_hwpt_alloc_flags {
 	IOMMU_HWPT_ALLOC_NEST_PARENT = 1 << 0,
 	IOMMU_HWPT_ALLOC_DIRTY_TRACKING = 1 << 1,
+	IOMMU_HWPT_FAULT_ID_VALID = 1 << 2,
 };
 
 /**
@@ -412,6 +415,9 @@ enum iommu_hwpt_data_type {
  * @data_type: One of enum iommu_hwpt_data_type
  * @data_len: Length of the type specific data
  * @data_uptr: User pointer to the type specific data
+ * @fault_id: The ID of IOMMUFD_FAULT object. Valid only if flags field of
+ *            IOMMU_HWPT_FAULT_ID_VALID is set.
+ * @__reserved2: Padding to 64-bit alignment. Must be 0.
  *
  * Explicitly allocate a hardware page table object. This is the same object
  * type that is returned by iommufd_device_attach() and represents the
@@ -442,6 +448,8 @@ struct iommu_hwpt_alloc {
 	__u32 data_type;
 	__u32 data_len;
 	__aligned_u64 data_uptr;
+	__u32 fault_id;
+	__u32 __reserved2;
 };
 #define IOMMU_HWPT_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_ALLOC)
 
diff --git a/drivers/iommu/iommufd/fault.c b/drivers/iommu/iommufd/fault.c
index 6357229bf3b4..802d0f819b22 100644
--- a/drivers/iommu/iommufd/fault.c
+++ b/drivers/iommu/iommufd/fault.c
@@ -354,3 +354,20 @@ int iommufd_fault_alloc(struct iommufd_ucmd *ucmd)
 
 	return rc;
 }
+
+int iommufd_fault_iopf_handler(struct iopf_group *group)
+{
+	struct iommufd_hw_pagetable *hwpt;
+	struct iommufd_fault *fault;
+
+	hwpt = group->domain->fault_data;
+	fault = hwpt->fault;
+
+	mutex_lock(&fault->mutex);
+	list_add_tail(&group->node, &fault->deliver);
+	mutex_unlock(&fault->mutex);
+
+	wake_up_interruptible(&fault->wait_queue);
+
+	return 0;
+}
diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
index 33d142f8057d..f7d05e12dea1 100644
--- a/drivers/iommu/iommufd/hw_pagetable.c
+++ b/drivers/iommu/iommufd/hw_pagetable.c
@@ -8,6 +8,15 @@
 #include "../iommu-priv.h"
 #include "iommufd_private.h"
 
+static void __iommufd_hwpt_destroy(struct iommufd_hw_pagetable *hwpt)
+{
+	if (hwpt->domain)
+		iommu_domain_free(hwpt->domain);
+
+	if (hwpt->fault)
+		iommufd_put_object(hwpt->fault->ictx, &hwpt->fault->obj);
+}
+
 void iommufd_hwpt_paging_destroy(struct iommufd_object *obj)
 {
 	struct iommufd_hwpt_paging *hwpt_paging =
@@ -22,9 +31,7 @@ void iommufd_hwpt_paging_destroy(struct iommufd_object *obj)
 					 hwpt_paging->common.domain);
 	}
 
-	if (hwpt_paging->common.domain)
-		iommu_domain_free(hwpt_paging->common.domain);
-
+	__iommufd_hwpt_destroy(&hwpt_paging->common);
 	refcount_dec(&hwpt_paging->ioas->obj.users);
 }
 
@@ -49,9 +56,7 @@ void iommufd_hwpt_nested_destroy(struct iommufd_object *obj)
 	struct iommufd_hwpt_nested *hwpt_nested =
 		container_of(obj, struct iommufd_hwpt_nested, common.obj);
 
-	if (hwpt_nested->common.domain)
-		iommu_domain_free(hwpt_nested->common.domain);
-
+	__iommufd_hwpt_destroy(&hwpt_nested->common);
 	refcount_dec(&hwpt_nested->parent->common.obj.users);
 }
 
@@ -213,7 +218,8 @@ iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx,
 	struct iommufd_hw_pagetable *hwpt;
 	int rc;
 
-	if (flags || !user_data->len || !ops->domain_alloc_user)
+	if ((flags & ~IOMMU_HWPT_FAULT_ID_VALID) ||
+	    !user_data->len || !ops->domain_alloc_user)
 		return ERR_PTR(-EOPNOTSUPP);
 	if (parent->auto_domain || !parent->nest_parent)
 		return ERR_PTR(-EINVAL);
@@ -227,7 +233,7 @@ iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx,
 	refcount_inc(&parent->common.obj.users);
 	hwpt_nested->parent = parent;
 
-	hwpt->domain = ops->domain_alloc_user(idev->dev, flags,
+	hwpt->domain = ops->domain_alloc_user(idev->dev, 0,
 					      parent->common.domain, user_data);
 	if (IS_ERR(hwpt->domain)) {
 		rc = PTR_ERR(hwpt->domain);
@@ -308,6 +314,19 @@ int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd)
 		goto out_put_pt;
 	}
 
+	if (cmd->flags & IOMMU_HWPT_FAULT_ID_VALID) {
+		struct iommufd_fault *fault;
+
+		fault = iommufd_get_fault(ucmd, cmd->fault_id);
+		if (IS_ERR(fault)) {
+			rc = PTR_ERR(fault);
+			goto out_hwpt;
+		}
+		hwpt->fault = fault;
+		hwpt->domain->iopf_handler = iommufd_fault_iopf_handler;
+		hwpt->domain->fault_data = hwpt;
+	}
+
 	cmd->out_hwpt_id = hwpt->obj.id;
 	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 	if (rc)
diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
index 792db077d33e..d8414ee9feae 100644
--- a/drivers/iommu/iommufd/main.c
+++ b/drivers/iommu/iommufd/main.c
@@ -359,7 +359,7 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = {
 	IOCTL_OP(IOMMU_GET_HW_INFO, iommufd_get_hw_info, struct iommu_hw_info,
 		 __reserved),
 	IOCTL_OP(IOMMU_HWPT_ALLOC, iommufd_hwpt_alloc, struct iommu_hwpt_alloc,
-		 __reserved),
+		 __reserved2),
 	IOCTL_OP(IOMMU_HWPT_GET_DIRTY_BITMAP, iommufd_hwpt_get_dirty_bitmap,
 		 struct iommu_hwpt_get_dirty_bitmap, data),
 	IOCTL_OP(IOMMU_HWPT_INVALIDATE, iommufd_hwpt_invalidate,
-- 
2.34.1