[PATCH v2 7/9] iommu/vt-d: Listen to IOASID notifications

[Jacob Pan]

On Intel Scalable I/O Virtualization (SIOV) enabled platforms, IOMMU
driver is one of the users of IOASIDs. In normal flow, callers will
perform IOASID allocation, bind, unbind, and free in order. However, for
guest SVA, IOASID free could come before unbind as guest is untrusted.
This patch registers IOASID notification handler such that IOMMU driver
can perform PASID teardown upon receiving an unexpected IOASID free
event.

Signed-off-by: Jacob Pan <jacob.jun.pan@xxxxxxxxxxxxxxx>
---
 drivers/iommu/intel/svm.c   | 74 ++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/intel-iommu.h |  2 ++
 2 files changed, 75 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 634e191ca2c3..600e3ae5b656 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -95,6 +95,72 @@ static inline bool intel_svm_capable(struct intel_iommu *iommu)
 	return iommu->flags & VTD_FLAG_SVM_CAPABLE;
 }
 
+#define pasid_lock_held() lock_is_held(&pasid_mutex.dep_map)
+static DEFINE_MUTEX(pasid_mutex);
+
+static void intel_svm_free_async_fn(struct work_struct *work)
+{
+	struct intel_svm *svm = container_of(work, struct intel_svm, work);
+	struct intel_svm_dev *sdev;
+
+	/*
+	 * Unbind all devices associated with this PASID which is
+	 * being freed by other users such as VFIO.
+	 */
+	mutex_lock(&pasid_mutex);
+	list_for_each_entry_rcu(sdev, &svm->devs, list, pasid_lock_held()) {
+		/* Does not poison forward pointer */
+		list_del_rcu(&sdev->list);
+		spin_lock(&svm->iommu->lock);
+		intel_pasid_tear_down_entry(svm->iommu, sdev->dev,
+					svm->pasid, true);
+		spin_unlock(&svm->iommu->lock);
+		kfree_rcu(sdev, rcu);
+		/*
+		 * Free before unbind only happens with guest usaged
+		 * host PASIDs. IOASID free will detach private data
+		 * and free the IOASID entry.
+		 */
+		ioasid_put(NULL, svm->pasid);
+		if (list_empty(&svm->devs))
+			kfree(svm);
+	}
+	mutex_unlock(&pasid_mutex);
+}
+
+
+static int pasid_status_change(struct notifier_block *nb,
+				unsigned long code, void *data)
+{
+	struct ioasid_nb_args *args = (struct ioasid_nb_args *)data;
+	struct intel_svm *svm = (struct intel_svm *)args->pdata;
+	int ret = NOTIFY_DONE;
+
+	if (code == IOASID_FREE) {
+		if (!svm)
+			goto done;
+		if (args->id != svm->pasid) {
+			pr_warn("Notify PASID does not match data %d : %d\n",
+				args->id, svm->pasid);
+			goto done;
+		}
+		schedule_work(&svm->work);
+		return NOTIFY_OK;
+	}
+done:
+	return ret;
+}
+
+static struct notifier_block pasid_nb = {
+	.notifier_call = pasid_status_change,
+};
+
+void intel_svm_add_pasid_notifier(void)
+{
+	/* Listen to all PASIDs, not specific to a set */
+	ioasid_register_notifier(NULL, &pasid_nb);
+}
+
 void intel_svm_check(struct intel_iommu *iommu)
 {
 	if (!pasid_supported(iommu))
@@ -221,7 +287,6 @@ static const struct mmu_notifier_ops intel_mmuops = {
 	.invalidate_range = intel_invalidate_range,
 };
 
-static DEFINE_MUTEX(pasid_mutex);
 static LIST_HEAD(global_svm_list);
 
 #define for_each_svm_dev(sdev, svm, d)			\
@@ -342,7 +407,14 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 			svm->gpasid = data->gpasid;
 			svm->flags |= SVM_FLAG_GUEST_PASID;
 		}
+		svm->iommu = iommu;
+		/*
+		 * Set up cleanup async work in case IOASID core notify us PASID
+		 * is freed before unbind.
+		 */
+		INIT_WORK(&svm->work, intel_svm_free_async_fn);
 		ioasid_attach_data(data->hpasid, svm);
+		ioasid_get(NULL, svm->pasid);
 		INIT_LIST_HEAD_RCU(&svm->devs);
 		mmput(svm->mm);
 	}
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index b1ed2f25f7c0..d36038e6ae0b 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -744,6 +744,7 @@ void intel_svm_unbind(struct iommu_sva *handle);
 int intel_svm_get_pasid(struct iommu_sva *handle);
 int intel_svm_page_response(struct device *dev, struct iommu_fault_event *evt,
 			    struct iommu_page_response *msg);
+void intel_svm_add_pasid_notifier(void);
 
 struct svm_dev_ops;
 
@@ -770,6 +771,7 @@ struct intel_svm {
 	int gpasid; /* In case that guest PASID is different from host PASID */
 	struct list_head devs;
 	struct list_head list;
+	struct work_struct work; /* For deferred clean up */
 };
 #else
 static inline void intel_svm_check(struct intel_iommu *iommu) {}
-- 
2.7.4