[RFC PATCHES 09/17] iommufd: Add iommufd hwpt iopf handler

[Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx>]

The IOPF handler is responsible for delivering I/O page faults to user
space. When an I/O page fault occurs, the fault is placed in the fault
pending list of the hardware page table (HWPT). The HWPT then generates
a fault event, which is used to notify user space of the fault. User
space can then fetch the fault information from the HWPT and handle the
fault accordingly.

Signed-off-by: Yi Liu <yi.l.liu@xxxxxxxxx>
Signed-off-by: Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx>
---
 drivers/iommu/iommufd/iommufd_private.h |  8 ++++
 drivers/iommu/iommufd/hw_pagetable.c    | 50 +++++++++++++++++++++++++
 2 files changed, 58 insertions(+)

diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index 5ff139acc5c0..8ff7721ea922 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -243,6 +243,14 @@ struct hw_pgtable_fault {
 	struct eventfd_ctx *trigger;
 };
 
+struct iommufd_fault {
+	struct device *dev;
+	ioasid_t pasid;
+	struct iommu_hwpt_pgfault fault;
+	/* List head at hw_pgtable_fault:deliver or response */
+	struct list_head item;
+};
+
 /*
  * A HW pagetable is called an iommu_domain inside the kernel. This user object
  * allows directly creating and inspecting the domains. Domains that have kernel
diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
index d6d550c3d0cc..4d07c7c0073e 100644
--- a/drivers/iommu/iommufd/hw_pagetable.c
+++ b/drivers/iommu/iommufd/hw_pagetable.c
@@ -12,6 +12,9 @@
 
 static struct hw_pgtable_fault *hw_pagetable_fault_alloc(int eventfd);
 static void hw_pagetable_fault_free(struct hw_pgtable_fault *fault);
+static enum iommu_page_response_code
+iommufd_hw_pagetable_iopf_handler(struct iommu_fault *fault,
+				  struct device *dev, void *data);
 
 void iommufd_hw_pagetable_destroy(struct iommufd_object *obj)
 {
@@ -300,6 +303,10 @@ int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd)
 			rc = PTR_ERR(hwpt->fault);
 			goto out_hwpt;
 		}
+
+		iommu_domain_set_iopf_handler(hwpt->domain,
+					      iommufd_hw_pagetable_iopf_handler,
+					      hwpt);
 	}
 
 	cmd->out_hwpt_id = hwpt->obj.id;
@@ -367,6 +374,49 @@ int iommufd_hwpt_invalidate(struct iommufd_ucmd *ucmd)
 	return rc;
 }
 
+static void iommufd_compose_fault_message(struct iommu_fault *fault,
+					  struct iommu_hwpt_pgfault *hwpt_fault,
+					  unsigned int dev_id)
+{
+	hwpt_fault->size = sizeof(*hwpt_fault);
+	hwpt_fault->flags = fault->prm.flags;
+	hwpt_fault->dev_id = dev_id;
+	hwpt_fault->pasid = fault->prm.pasid;
+	hwpt_fault->grpid = fault->prm.grpid;
+	hwpt_fault->perm = fault->prm.perm;
+	hwpt_fault->addr = fault->prm.addr;
+	hwpt_fault->private_data[0] = fault->prm.private_data[0];
+	hwpt_fault->private_data[1] = fault->prm.private_data[1];
+}
+
+static enum iommu_page_response_code
+iommufd_hw_pagetable_iopf_handler(struct iommu_fault *fault,
+				  struct device *dev, void *data)
+{
+	struct iommufd_hw_pagetable *hwpt = data;
+	struct iommufd_fault_cookie *cookie;
+	struct iommufd_fault *ifault;
+
+	ifault = kzalloc(sizeof(*ifault), GFP_KERNEL);
+	if (!ifault)
+		return IOMMU_PAGE_RESP_FAILURE;
+
+	cookie = iommu_get_device_fault_cookie(dev, fault->prm.pasid);
+	if (!cookie)
+		return IOMMU_PAGE_RESP_FAILURE;
+
+	iommufd_compose_fault_message(fault, &ifault->fault, cookie->idev->obj.id);
+	ifault->dev = dev;
+	ifault->pasid = fault->prm.pasid;
+
+	mutex_lock(&hwpt->fault->mutex);
+	list_add_tail(&ifault->item, &hwpt->fault->deliver);
+	eventfd_signal(hwpt->fault->trigger, 1);
+	mutex_unlock(&hwpt->fault->mutex);
+
+	return IOMMU_PAGE_RESP_ASYNC;
+}
+
 static struct hw_pgtable_fault *hw_pagetable_fault_alloc(int eventfd)
 {
 	struct hw_pgtable_fault *fault;
-- 
2.34.1