iommu/iommufd: Fix IOPF group ownership UAF

iopf_group_alloc() links each last-page IOPF group into the generic IOPF
pending list before invoking the domain fault handler.
iommufd_fault_iopf_handler() also queued an accepted group in the
IOMMUFD deliver list without removing it from the generic pending list.

When detach or HWPT replacement drops the device's IOPF reference count
to zero, an IOMMU driver may call iopf_queue_remove_device(). That
function responds to and frees groups through the generic pending list
without removing the same groups from IOMMUFD's deliver list or response
xarray. A later read, response, or cleanup can then access the freed
group and cause a UAF.

Fix this by dequeuing an accepted group from the generic pending list
before IOMMUFD queues it for userspace response.
Make iopf_group_response() send a response regardless of pending-list
membership, so the dequeued group can still be completed by IOMMUFD.

Link: https://patch.msgid.link/r/3CFD314D0FE4D7EC+20260720085017.3998878-2-peiyang_he@smail.nju.edu.cn
Closes: https://lore.kernel.org/all/B4F28798E2E784CA+d29f723c-b2b5-4b67-8d1c-4f7b9b0b27cb@smail.nju.edu.cn/
Fixes: 34765cbc679c ("iommufd: Associate fault object with iommufd_hw_pgtable")
Cc: stable@vger.kernel.org
Tested-by: Peiyang He <peiyang_he@smail.nju.edu.cn>
Assisted-by: Codex:gpt-5.6-sol
Signed-off-by: Peiyang He <peiyang_he@smail.nju.edu.cn>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

diff --git a/drivers/iommu/io-pgfault.c b/drivers/iommu/io-pgfault.c
index cca52a34d0ed69273f23d9ce7793f7065388273f..c16ff1fc4b95b67857f64b28170ce858b9d0655b 100644 (file)
--- a/drivers/iommu/io-pgfault.c
+++ b/drivers/iommu/io-pgfault.c
@@ -332,16 +332,30 @@ void iopf_group_response(struct iopf_group *group,
                .code = status,
        };
 
-       /* Only send response if there is a fault report pending */
        mutex_lock(&fault_param->lock);
-       if (!list_empty(&group->pending_node)) {
-               ops->page_response(dev, &group->last_fault, &resp);
-               list_del_init(&group->pending_node);
-       }
+       ops->page_response(dev, &group->last_fault, &resp);
+       list_del_init(&group->pending_node);
        mutex_unlock(&fault_param->lock);
 }
 EXPORT_SYMBOL_GPL(iopf_group_response);
 
+/**
+ * iopf_group_dequeue - Dequeue a page fault group from the pending list
+ * @group: the group to dequeue
+ *
+ * The fault handler is responsible for responding to the group after
+ * this function returns.
+ */
+void iopf_group_dequeue(struct iopf_group *group)
+{
+       struct iommu_fault_param *fault_param = group->fault_param;
+
+       mutex_lock(&fault_param->lock);
+       list_del_init(&group->pending_node);
+       mutex_unlock(&fault_param->lock);
+}
+EXPORT_SYMBOL_GPL(iopf_group_dequeue);
+
 /**
  * iopf_queue_discard_partial - Remove all pending partial fault
  * @queue: the queue whose partial faults need to be discarded

diff --git a/drivers/iommu/iommufd/eventq.c b/drivers/iommu/iommufd/eventq.c
index 5129e3bf5461cb1ef85c550369c9d1b2aa771829..747dd5155121cbe82fdffc3560de09256fc43f6e 100644 (file)
--- a/drivers/iommu/iommufd/eventq.c
+++ b/drivers/iommu/iommufd/eventq.c
@@ -484,6 +484,8 @@ int iommufd_fault_iopf_handler(struct iopf_group *group)
        hwpt = group->attach_handle->domain->iommufd_hwpt;
        fault = hwpt->fault;
 
+       iopf_group_dequeue(group);
+
        spin_lock(&fault->common.lock);
        list_add_tail(&group->node, &fault->common.deliver);
        spin_unlock(&fault->common.lock);

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index d20aa6f6863ab35a5932911219705f2ffd0e3352..ac43b8b93f14aa4853e794eec5e6ca39d1eac0f1 100644 (file)
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -1704,6 +1704,7 @@ void iopf_free_group(struct iopf_group *group);
 int iommu_report_device_fault(struct device *dev, struct iopf_fault *evt);
 void iopf_group_response(struct iopf_group *group,
                         enum iommu_page_response_code status);
+void iopf_group_dequeue(struct iopf_group *group);
 #else
 static inline int
 iopf_queue_add_device(struct iopf_queue *queue, struct device *dev)
@@ -1749,5 +1750,9 @@ static inline void iopf_group_response(struct iopf_group *group,
                                       enum iommu_page_response_code status)
 {
 }
+
+static inline void iopf_group_dequeue(struct iopf_group *group)
+{
+}
 #endif /* CONFIG_IOMMU_IOPF */
 #endif /* __LINUX_IOMMU_H */