intel_flush_svm_range_dev(svm, sdev, 0, -1, 0);
}
rcu_read_unlock();
@@ -403,12 +405,8 @@ int intel_svm_unbind_gpasid(struct device *dev, int
pasid)
if (!sdev->users) {
list_del_rcu(&sdev->list);
intel_pasid_tear_down_entry(iommu, dev, svm-
pasid);
+ intel_svm_drain_prq(dev, svm->pasid);
intel_flush_svm_range_dev(svm, sdev, 0, -1, 0);
- /* TODO: Drain in flight PRQ for the PASID since it
- * may get reused soon, we don't want to
- * confuse with its previous life.
- * intel_svm_drain_prq(dev, pasid);
- */
kfree_rcu(sdev, rcu);
if (list_empty(&svm->devs)) {
@@ -646,6 +644,7 @@ int intel_svm_unbind_mm(struct device *dev, int
pasid)
* large and has to be physically contiguous. So it's
* hard to be as defensive as we might like. */
intel_pasid_tear_down_entry(iommu, dev, svm-
pasid);
+ intel_svm_drain_prq(dev, svm->pasid);
intel_flush_svm_range_dev(svm, sdev, 0, -1, 0);
kfree_rcu(sdev, rcu);
@@ -703,6 +702,7 @@ struct page_req_dsc {
struct page_req {
struct list_head list;
struct page_req_dsc desc;
+ struct completion complete;
unsigned int processing:1;
unsigned int drained:1;
unsigned int completed:1;
@@ -732,9 +732,83 @@ static bool is_canonical_address(u64 addr)
return (((saddr << shift) >> shift) == saddr);
}
+/**
+ * intel_svm_drain_prq:
+ *
+ * Drain all pending page requests related to a specific pasid in both
+ * software and hardware. The caller must guarantee that no more page
+ * requests related to this pasid coming.
+ */
+static void intel_svm_drain_prq(struct device *dev, int pasid)
+{
+ struct device_domain_info *info;
+ struct dmar_domain *domain;
+ struct intel_iommu *iommu;
+ struct qi_desc desc[3];
+ struct pci_dev *pdev;
+ struct page_req *req;
+ unsigned long flags;
+ u16 sid, did;
+ int qdep;
+
+ info = get_domain_info(dev);
+ if (WARN_ON(!info || !dev_is_pci(dev)))
+ return;
+
+ iommu = info->iommu;
+ domain = info->domain;
+ pdev = to_pci_dev(dev);
+
+ /* Mark all related pending requests drained. */
+ spin_lock_irqsave(&iommu->prq_lock, flags);
+ list_for_each_entry(req, &iommu->prq_list, list)
+ if (req->desc.pasid_present && req->desc.pasid == pasid)
+ req->drained = true;
+ spin_unlock_irqrestore(&iommu->prq_lock, flags);
+
+ /* Wait until all related pending requests complete. */
+retry:
+ spin_lock_irqsave(&iommu->prq_lock, flags);
+ list_for_each_entry(req, &iommu->prq_list, list) {
+ if (req->desc.pasid_present &&
+ req->desc.pasid == pasid &&
+ !req->completed) {
+ spin_unlock_irqrestore(&iommu->prq_lock, flags);
+ wait_for_completion_timeout(&req->complete, 5 *
HZ);
+ goto retry;
+ }
+ }
+ spin_unlock_irqrestore(&iommu->prq_lock, flags);
+
+ /*
+ * Perform steps described in VT-d spec CH7.10 to drain page
+ * request and responses in hardware.
+ */
+ sid = PCI_DEVID(info->bus, info->devfn);
+ did = domain->iommu_did[iommu->seq_id];
+ qdep = pci_ats_queue_depth(pdev);
+
+ memset(desc, 0, sizeof(desc));
+ desc[0].qw0 = QI_IWD_STATUS_DATA(QI_DONE) |
+ QI_IWD_FENCE |
+ QI_IWD_TYPE;
+ desc[1].qw0 = QI_EIOTLB_PASID(pasid) |
+ QI_EIOTLB_DID(did) |
+ QI_EIOTLB_GRAN(QI_GRAN_NONG_PASID) |
+ QI_EIOTLB_TYPE;
+ desc[2].qw0 = QI_DEV_EIOTLB_PASID(pasid) |
+ QI_DEV_EIOTLB_SID(sid) |
+ QI_DEV_EIOTLB_QDEP(qdep) |
+ QI_DEIOTLB_TYPE |
+ QI_DEV_IOTLB_PFSID(info->pfsid);
+
+ qi_submit_sync(iommu, desc, 3, QI_OPT_WAIT_DRAIN);
