1 files changed, 258 insertions, 80 deletions

diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 6c87c807a0ab..95c3164a2302 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -20,7 +20,7 @@
 #include <linux/ioasid.h>
 #include <asm/page.h>
 
-#include "intel-pasid.h"
+#include "pasid.h"
 
 static irqreturn_t prq_event_thread(int irq, void *d);
 static void intel_svm_drain_prq(struct device *dev, int pasid);
@@ -228,13 +228,57 @@ static LIST_HEAD(global_svm_list);
 	list_for_each_entry((sdev), &(svm)->devs, list)	\
 		if ((d) != (sdev)->dev) {} else
 
+static int pasid_to_svm_sdev(struct device *dev, unsigned int pasid,
+			     struct intel_svm **rsvm,
+			     struct intel_svm_dev **rsdev)
+{
+	struct intel_svm_dev *d, *sdev = NULL;
+	struct intel_svm *svm;
+
+	/* The caller should hold the pasid_mutex lock */
+	if (WARN_ON(!mutex_is_locked(&pasid_mutex)))
+		return -EINVAL;
+
+	if (pasid == INVALID_IOASID || pasid >= PASID_MAX)
+		return -EINVAL;
+
+	svm = ioasid_find(NULL, pasid, NULL);
+	if (IS_ERR(svm))
+		return PTR_ERR(svm);
+
+	if (!svm)
+		goto out;
+
+	/*
+	 * If we found svm for the PASID, there must be at least one device
+	 * bond.
+	 */
+	if (WARN_ON(list_empty(&svm->devs)))
+		return -EINVAL;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(d, &svm->devs, list) {
+		if (d->dev == dev) {
+			sdev = d;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+out:
+	*rsvm = svm;
+	*rsdev = sdev;
+
+	return 0;
+}
+
 int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 			  struct iommu_gpasid_bind_data *data)
 {
-	struct intel_iommu *iommu = intel_svm_device_to_iommu(dev);
+	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
+	struct intel_svm_dev *sdev = NULL;
 	struct dmar_domain *dmar_domain;
-	struct intel_svm_dev *sdev;
-	struct intel_svm *svm;
+	struct intel_svm *svm = NULL;
 	int ret = 0;
 
 	if (WARN_ON(!iommu) || !data)
@@ -261,39 +305,23 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 	dmar_domain = to_dmar_domain(domain);
 
 	mutex_lock(&pasid_mutex);
-	svm = ioasid_find(NULL, data->hpasid, NULL);
-	if (IS_ERR(svm)) {
-		ret = PTR_ERR(svm);
+	ret = pasid_to_svm_sdev(dev, data->hpasid, &svm, &sdev);
+	if (ret)
 		goto out;
-	}
 
-	if (svm) {
+	if (sdev) {
 		/*
-		 * If we found svm for the PASID, there must be at
-		 * least one device bond, otherwise svm should be freed.
+		 * Do not allow multiple bindings of the same device-PASID since
+		 * there is only one SL page tables per PASID. We may revisit
+		 * once sharing PGD across domains are supported.
 		 */
-		if (WARN_ON(list_empty(&svm->devs))) {
-			ret = -EINVAL;
-			goto out;
-		}
+		dev_warn_ratelimited(dev, "Already bound with PASID %u\n",
+				     svm->pasid);
+		ret = -EBUSY;
+		goto out;
+	}
 
-		for_each_svm_dev(sdev, svm, dev) {
-			/*
-			 * For devices with aux domains, we should allow
-			 * multiple bind calls with the same PASID and pdev.
-			 */
-			if (iommu_dev_feature_enabled(dev,
-						      IOMMU_DEV_FEAT_AUX)) {
-				sdev->users++;
-			} else {
-				dev_warn_ratelimited(dev,
-						     "Already bound with PASID %u\n",
-						     svm->pasid);
-				ret = -EBUSY;
-			}
-			goto out;
-		}
-	} else {
+	if (!svm) {
 		/* We come here when PASID has never been bond to a device. */
 		svm = kzalloc(sizeof(*svm), GFP_KERNEL);
 		if (!svm) {
@@ -373,28 +401,20 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 
 int intel_svm_unbind_gpasid(struct device *dev, int pasid)
 {
-	struct intel_iommu *iommu = intel_svm_device_to_iommu(dev);
+	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
 	struct intel_svm_dev *sdev;
 	struct intel_svm *svm;
-	int ret = -EINVAL;
+	int ret;
 
 	if (WARN_ON(!iommu))
 		return -EINVAL;
 
 	mutex_lock(&pasid_mutex);
-	svm = ioasid_find(NULL, pasid, NULL);
-	if (!svm) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (IS_ERR(svm)) {
-		ret = PTR_ERR(svm);
+	ret = pasid_to_svm_sdev(dev, pasid, &svm, &sdev);
+	if (ret)
 		goto out;
-	}
 
-	for_each_svm_dev(sdev, svm, dev) {
-		ret = 0;
+	if (sdev) {
 		if (iommu_dev_feature_enabled(dev, IOMMU_DEV_FEAT_AUX))
 			sdev->users--;
 		if (!sdev->users) {
@@ -418,7 +438,6 @@ int intel_svm_unbind_gpasid(struct device *dev, int pasid)
 				kfree(svm);
 			}
 		}
-		break;
 	}
 out:
 	mutex_unlock(&pasid_mutex);
@@ -430,7 +449,7 @@ static int
 intel_svm_bind_mm(struct device *dev, int flags, struct svm_dev_ops *ops,
 		  struct mm_struct *mm, struct intel_svm_dev **sd)
 {
-	struct intel_iommu *iommu = intel_svm_device_to_iommu(dev);
+	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
 	struct device_domain_info *info;
 	struct intel_svm_dev *sdev;
 	struct intel_svm *svm = NULL;
@@ -596,7 +615,7 @@ success:
 	if (sd)
 		*sd = sdev;
 	ret = 0;
- out:
+out:
 	return ret;
 }
 
@@ -608,21 +627,15 @@ static int intel_svm_unbind_mm(struct device *dev, int pasid)
 	struct intel_svm *svm;
 	int ret = -EINVAL;
 
-	iommu = intel_svm_device_to_iommu(dev);
+	iommu = device_to_iommu(dev, NULL, NULL);
 	if (!iommu)
 		goto out;
 
-	svm = ioasid_find(NULL, pasid, NULL);
-	if (!svm)
-		goto out;
-
-	if (IS_ERR(svm)) {
-		ret = PTR_ERR(svm);
+	ret = pasid_to_svm_sdev(dev, pasid, &svm, &sdev);
+	if (ret)
 		goto out;
-	}
 
-	for_each_svm_dev(sdev, svm, dev) {
-		ret = 0;
+	if (sdev) {
 		sdev->users--;
 		if (!sdev->users) {
 			list_del_rcu(&sdev->list);
@@ -651,10 +664,8 @@ static int intel_svm_unbind_mm(struct device *dev, int pasid)
 				kfree(svm);
 			}
 		}
-		break;
 	}
- out:
-
+out:
 	return ret;
 }
 
@@ -800,8 +811,63 @@ qi_retry:
 	}
 }
 
+static int prq_to_iommu_prot(struct page_req_dsc *req)
+{
+	int prot = 0;
+
+	if (req->rd_req)
+		prot |= IOMMU_FAULT_PERM_READ;
+	if (req->wr_req)
+		prot |= IOMMU_FAULT_PERM_WRITE;
+	if (req->exe_req)
+		prot |= IOMMU_FAULT_PERM_EXEC;
+	if (req->pm_req)
+		prot |= IOMMU_FAULT_PERM_PRIV;
+
+	return prot;
+}
+
+static int
+intel_svm_prq_report(struct device *dev, struct page_req_dsc *desc)
+{
+	struct iommu_fault_event event;
+
+	if (!dev || !dev_is_pci(dev))
+		return -ENODEV;
+
+	/* Fill in event data for device specific processing */
+	memset(&event, 0, sizeof(struct iommu_fault_event));
+	event.fault.type = IOMMU_FAULT_PAGE_REQ;
+	event.fault.prm.addr = desc->addr;
+	event.fault.prm.pasid = desc->pasid;
+	event.fault.prm.grpid = desc->prg_index;
+	event.fault.prm.perm = prq_to_iommu_prot(desc);
+
+	if (desc->lpig)
+		event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE;
+	if (desc->pasid_present) {
+		event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
+		event.fault.prm.flags |= IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID;
+	}
+	if (desc->priv_data_present) {
+		/*
+		 * Set last page in group bit if private data is present,
+		 * page response is required as it does for LPIG.
+		 * iommu_report_device_fault() doesn't understand this vendor
+		 * specific requirement thus we set last_page as a workaround.
+		 */
+		event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE;
+		event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA;
+		memcpy(event.fault.prm.private_data, desc->priv_data,
+		       sizeof(desc->priv_data));
+	}
+
+	return iommu_report_device_fault(dev, &event);
+}
+
 static irqreturn_t prq_event_thread(int irq, void *d)
 {
+	struct intel_svm_dev *sdev = NULL;
 	struct intel_iommu *iommu = d;
 	struct intel_svm *svm = NULL;
 	int head, tail, handled = 0;
@@ -813,7 +879,6 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 	tail = dmar_readq(iommu->reg + DMAR_PQT_REG) & PRQ_RING_MASK;
 	head = dmar_readq(iommu->reg + DMAR_PQH_REG) & PRQ_RING_MASK;
 	while (head != tail) {
-		struct intel_svm_dev *sdev;
 		struct vm_area_struct *vma;
 		struct page_req_dsc *req;
 		struct qi_desc resp;
@@ -849,6 +914,20 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 			}
 		}
 
+		if (!sdev || sdev->sid != req->rid) {
+			struct intel_svm_dev *t;
+
+			sdev = NULL;
+			rcu_read_lock();
+			list_for_each_entry_rcu(t, &svm->devs, list) {
+				if (t->sid == req->rid) {
+					sdev = t;
+					break;
+				}
+			}
+			rcu_read_unlock();
+		}
+
 		result = QI_RESP_INVALID;
 		/* Since we're using init_mm.pgd directly, we should never take
 		 * any faults on kernel addresses. */
@@ -859,6 +938,17 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 		if (!is_canonical_address(address))
 			goto bad_req;
 
+		/*
+		 * If prq is to be handled outside iommu driver via receiver of
+		 * the fault notifiers, we skip the page response here.
+		 */
+		if (svm->flags & SVM_FLAG_GUEST_MODE) {
+			if (sdev && !intel_svm_prq_report(sdev->dev, req))
+				goto prq_advance;
+			else
+				goto bad_req;
+		}
+
 		/* If the mm is already defunct, don't handle faults. */
 		if (!mmget_not_zero(svm->mm))
 			goto bad_req;
@@ -872,29 +962,17 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 			goto invalid;
 
 		ret = handle_mm_fault(vma, address,
-				      req->wr_req ? FAULT_FLAG_WRITE : 0);
+				      req->wr_req ? FAULT_FLAG_WRITE : 0,
+				      NULL);
 		if (ret & VM_FAULT_ERROR)
 			goto invalid;
 
 		result = QI_RESP_SUCCESS;
-	invalid:
+invalid:
 		mmap_read_unlock(svm->mm);
 		mmput(svm->mm);
-	bad_req:
-		/* Accounting for major/minor faults? */
-		rcu_read_lock();
-		list_for_each_entry_rcu(sdev, &svm->devs, list) {
-			if (sdev->sid == req->rid)
-				break;
-		}
-		/* Other devices can go away, but the drivers are not permitted
-		 * to unbind while any page faults might be in flight. So it's
-		 * OK to drop the 'lock' here now we have it. */
-		rcu_read_unlock();
-
-		if (WARN_ON(&sdev->list == &svm->devs))
-			sdev = NULL;
-
+bad_req:
+		WARN_ON(!sdev);
 		if (sdev && sdev->ops && sdev->ops->fault_cb) {
 			int rwxp = (req->rd_req << 3) | (req->wr_req << 2) |
 				(req->exe_req << 1) | (req->pm_req);
@@ -905,7 +983,7 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 		   and these can be NULL. Do not use them below this point! */
 		sdev = NULL;
 		svm = NULL;
-	no_pasid:
+no_pasid:
 		if (req->lpig || req->priv_data_present) {
 			/*
 			 * Per VT-d spec. v3.0 ch7.7, system software must
@@ -930,6 +1008,7 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 			resp.qw3 = 0;
 			qi_submit_sync(iommu, &resp, 1, 0);
 		}
+prq_advance:
 		head = (head + sizeof(*req)) & PRQ_RING_MASK;
 	}
 
@@ -1000,3 +1079,102 @@ int intel_svm_get_pasid(struct iommu_sva *sva)
 
 	return pasid;
 }
+
+int intel_svm_page_response(struct device *dev,
+			    struct iommu_fault_event *evt,
+			    struct iommu_page_response *msg)
+{
+	struct iommu_fault_page_request *prm;
+	struct intel_svm_dev *sdev = NULL;
+	struct intel_svm *svm = NULL;
+	struct intel_iommu *iommu;
+	bool private_present;
+	bool pasid_present;
+	bool last_page;
+	u8 bus, devfn;
+	int ret = 0;
+	u16 sid;
+
+	if (!dev || !dev_is_pci(dev))
+		return -ENODEV;
+
+	iommu = device_to_iommu(dev, &bus, &devfn);
+	if (!iommu)
+		return -ENODEV;
+
+	if (!msg || !evt)
+		return -EINVAL;
+
+	mutex_lock(&pasid_mutex);
+
+	prm = &evt->fault.prm;
+	sid = PCI_DEVID(bus, devfn);
+	pasid_present = prm->flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
+	private_present = prm->flags & IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA;
+	last_page = prm->flags & IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE;
+
+	if (!pasid_present) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (prm->pasid == 0 || prm->pasid >= PASID_MAX) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = pasid_to_svm_sdev(dev, prm->pasid, &svm, &sdev);
+	if (ret || !sdev) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	/*
+	 * For responses from userspace, need to make sure that the
+	 * pasid has been bound to its mm.
+	 */
+	if (svm->flags & SVM_FLAG_GUEST_MODE) {
+		struct mm_struct *mm;
+
+		mm = get_task_mm(current);
+		if (!mm) {
+			ret = -EINVAL;
+			goto out;
+		}
+
+		if (mm != svm->mm) {
+			ret = -ENODEV;
+			mmput(mm);
+			goto out;
+		}
+
+		mmput(mm);
+	}
+
+	/*
+	 * Per VT-d spec. v3.0 ch7.7, system software must respond
+	 * with page group response if private data is present (PDP)
+	 * or last page in group (LPIG) bit is set. This is an
+	 * additional VT-d requirement beyond PCI ATS spec.
+	 */
+	if (last_page || private_present) {
+		struct qi_desc desc;
+
+		desc.qw0 = QI_PGRP_PASID(prm->pasid) | QI_PGRP_DID(sid) |
+				QI_PGRP_PASID_P(pasid_present) |
+				QI_PGRP_PDP(private_present) |
+				QI_PGRP_RESP_CODE(msg->code) |
+				QI_PGRP_RESP_TYPE;
+		desc.qw1 = QI_PGRP_IDX(prm->grpid) | QI_PGRP_LPIG(last_page);
+		desc.qw2 = 0;
+		desc.qw3 = 0;
+		if (private_present)
+			memcpy(&desc.qw2, prm->private_data,
+			       sizeof(prm->private_data));
+
+		qi_submit_sync(iommu, &desc, 1, 0);
+	}
+out:
+	mutex_unlock(&pasid_mutex);
+	return ret;
+}