1 files changed, 317 insertions, 326 deletions

diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 5165cea90421..9b0f22bc0514 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -17,19 +17,76 @@
 #include <linux/dmar.h>
 #include <linux/interrupt.h>
 #include <linux/mm_types.h>
+#include <linux/xarray.h>
 #include <linux/ioasid.h>
 #include <asm/page.h>
 #include <asm/fpu/api.h>
+#include <trace/events/intel_iommu.h>
 
 #include "pasid.h"
+#include "perf.h"
+#include "../iommu-sva-lib.h"
 
 static irqreturn_t prq_event_thread(int irq, void *d);
 static void intel_svm_drain_prq(struct device *dev, u32 pasid);
+#define to_intel_svm_dev(handle) container_of(handle, struct intel_svm_dev, sva)
 
 #define PRQ_ORDER 0
 
+static DEFINE_XARRAY_ALLOC(pasid_private_array);
+static int pasid_private_add(ioasid_t pasid, void *priv)
+{
+	return xa_alloc(&pasid_private_array, &pasid, priv,
+			XA_LIMIT(pasid, pasid), GFP_ATOMIC);
+}
+
+static void pasid_private_remove(ioasid_t pasid)
+{
+	xa_erase(&pasid_private_array, pasid);
+}
+
+static void *pasid_private_find(ioasid_t pasid)
+{
+	return xa_load(&pasid_private_array, pasid);
+}
+
+static struct intel_svm_dev *
+svm_lookup_device_by_sid(struct intel_svm *svm, u16 sid)
+{
+	struct intel_svm_dev *sdev = NULL, *t;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(t, &svm->devs, list) {
+		if (t->sid == sid) {
+			sdev = t;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return sdev;
+}
+
+static struct intel_svm_dev *
+svm_lookup_device_by_dev(struct intel_svm *svm, struct device *dev)
+{
+	struct intel_svm_dev *sdev = NULL, *t;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(t, &svm->devs, list) {
+		if (t->dev == dev) {
+			sdev = t;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return sdev;
+}
+
 int intel_svm_enable_prq(struct intel_iommu *iommu)
 {
+	struct iopf_queue *iopfq;
 	struct page *pages;
 	int irq, ret;
 
@@ -46,13 +103,20 @@ int intel_svm_enable_prq(struct intel_iommu *iommu)
 		pr_err("IOMMU: %s: Failed to create IRQ vector for page request queue\n",
 		       iommu->name);
 		ret = -EINVAL;
-	err:
-		free_pages((unsigned long)iommu->prq, PRQ_ORDER);
-		iommu->prq = NULL;
-		return ret;
+		goto free_prq;
 	}
 	iommu->pr_irq = irq;
 
+	snprintf(iommu->iopfq_name, sizeof(iommu->iopfq_name),
+		 "dmar%d-iopfq", iommu->seq_id);
+	iopfq = iopf_queue_alloc(iommu->iopfq_name);
+	if (!iopfq) {
+		pr_err("IOMMU: %s: Failed to allocate iopf queue\n", iommu->name);
+		ret = -ENOMEM;
+		goto free_hwirq;
+	}
+	iommu->iopf_queue = iopfq;
+
 	snprintf(iommu->prq_name, sizeof(iommu->prq_name), "dmar%d-prq", iommu->seq_id);
 
 	ret = request_threaded_irq(irq, NULL, prq_event_thread, IRQF_ONESHOT,
@@ -60,9 +124,7 @@ int intel_svm_enable_prq(struct intel_iommu *iommu)
 	if (ret) {
 		pr_err("IOMMU: %s: Failed to request IRQ for page request queue\n",
 		       iommu->name);
-		dmar_free_hwirq(irq);
-		iommu->pr_irq = 0;
-		goto err;
+		goto free_iopfq;
 	}
 	dmar_writeq(iommu->reg + DMAR_PQH_REG, 0ULL);
 	dmar_writeq(iommu->reg + DMAR_PQT_REG, 0ULL);
@@ -71,6 +133,18 @@ int intel_svm_enable_prq(struct intel_iommu *iommu)
 	init_completion(&iommu->prq_complete);
 
 	return 0;
+
+free_iopfq:
+	iopf_queue_free(iommu->iopf_queue);
+	iommu->iopf_queue = NULL;
+free_hwirq:
+	dmar_free_hwirq(irq);
+	iommu->pr_irq = 0;
+free_prq:
+	free_pages((unsigned long)iommu->prq, PRQ_ORDER);
+	iommu->prq = NULL;
+
+	return ret;
 }
 
 int intel_svm_finish_prq(struct intel_iommu *iommu)
@@ -85,6 +159,11 @@ int intel_svm_finish_prq(struct intel_iommu *iommu)
 		iommu->pr_irq = 0;
 	}
 
+	if (iommu->iopf_queue) {
+		iopf_queue_free(iommu->iopf_queue);
+		iommu->iopf_queue = NULL;
+	}
+
 	free_pages((unsigned long)iommu->prq, PRQ_ORDER);
 	iommu->prq = NULL;
 
@@ -204,17 +283,12 @@ static const struct mmu_notifier_ops intel_mmuops = {
 };
 
 static DEFINE_MUTEX(pasid_mutex);
-static LIST_HEAD(global_svm_list);
-
-#define for_each_svm_dev(sdev, svm, d)			\
-	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_dev *sdev = NULL;
 	struct intel_svm *svm;
 
 	/* The caller should hold the pasid_mutex lock */
@@ -224,7 +298,7 @@ static int pasid_to_svm_sdev(struct device *dev, unsigned int pasid,
 	if (pasid == INVALID_IOASID || pasid >= PASID_MAX)
 		return -EINVAL;
 
-	svm = ioasid_find(NULL, pasid, NULL);
+	svm = pasid_private_find(pasid);
 	if (IS_ERR(svm))
 		return PTR_ERR(svm);
 
@@ -237,15 +311,7 @@ static int pasid_to_svm_sdev(struct device *dev, unsigned int pasid,
 	 */
 	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();
+	sdev = svm_lookup_device_by_dev(svm, dev);
 
 out:
 	*rsvm = svm;
@@ -334,7 +400,7 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 			svm->gpasid = data->gpasid;
 			svm->flags |= SVM_FLAG_GUEST_PASID;
 		}
-		ioasid_set_data(data->hpasid, svm);
+		pasid_private_add(data->hpasid, svm);
 		INIT_LIST_HEAD_RCU(&svm->devs);
 		mmput(svm->mm);
 	}
@@ -388,7 +454,7 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 	list_add_rcu(&sdev->list, &svm->devs);
  out:
 	if (!IS_ERR_OR_NULL(svm) && list_empty(&svm->devs)) {
-		ioasid_set_data(data->hpasid, NULL);
+		pasid_private_remove(data->hpasid);
 		kfree(svm);
 	}
 
@@ -431,7 +497,7 @@ int intel_svm_unbind_gpasid(struct device *dev, u32 pasid)
 				 * the unbind, IOMMU driver will get notified
 				 * and perform cleanup.
 				 */
-				ioasid_set_data(pasid, NULL);
+				pasid_private_remove(pasid);
 				kfree(svm);
 			}
 		}
@@ -459,79 +525,81 @@ static void load_pasid(struct mm_struct *mm, u32 pasid)
 	mutex_unlock(&mm->context.lock);
 }
 
-/* Caller must hold pasid_mutex, mm reference */
-static int
-intel_svm_bind_mm(struct device *dev, unsigned int flags,
-		  struct mm_struct *mm, struct intel_svm_dev **sd)
+static int intel_svm_alloc_pasid(struct device *dev, struct mm_struct *mm,
+				 unsigned int flags)
 {
-	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
-	struct intel_svm *svm = NULL, *t;
-	struct device_domain_info *info;
-	struct intel_svm_dev *sdev;
-	unsigned long iflags;
-	int pasid_max;
-	int ret;
+	ioasid_t max_pasid = dev_is_pci(dev) ?
+			pci_max_pasids(to_pci_dev(dev)) : intel_pasid_max_id;
 
-	if (!iommu || dmar_disabled)
-		return -EINVAL;
+	return iommu_sva_alloc_pasid(mm, PASID_MIN, max_pasid - 1);
+}
 
-	if (!intel_svm_capable(iommu))
-		return -ENOTSUPP;
+static void intel_svm_free_pasid(struct mm_struct *mm)
+{
+	iommu_sva_free_pasid(mm);
+}
 
-	if (dev_is_pci(dev)) {
-		pasid_max = pci_max_pasids(to_pci_dev(dev));
-		if (pasid_max < 0)
-			return -EINVAL;
-	} else
-		pasid_max = 1 << 20;
+static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu,
+					   struct device *dev,
+					   struct mm_struct *mm,
+					   unsigned int flags)
+{
+	struct device_domain_info *info = get_domain_info(dev);
+	unsigned long iflags, sflags;
+	struct intel_svm_dev *sdev;
+	struct intel_svm *svm;
+	int ret = 0;
 
-	/* Bind supervisor PASID shuld have mm = NULL */
-	if (flags & SVM_FLAG_SUPERVISOR_MODE) {
-		if (!ecap_srs(iommu->ecap) || mm) {
-			pr_err("Supervisor PASID with user provided mm.\n");
-			return -EINVAL;
-		}
-	}
+	svm = pasid_private_find(mm->pasid);
+	if (!svm) {
+		svm = kzalloc(sizeof(*svm), GFP_KERNEL);
+		if (!svm)
+			return ERR_PTR(-ENOMEM);
 
-	list_for_each_entry(t, &global_svm_list, list) {
-		if (t->mm != mm)
-			continue;
+		svm->pasid = mm->pasid;
+		svm->mm = mm;
+		svm->flags = flags;
+		INIT_LIST_HEAD_RCU(&svm->devs);
 
-		svm = t;
-		if (svm->pasid >= pasid_max) {
-			dev_warn(dev,
-				 "Limited PASID width. Cannot use existing PASID %d\n",
-				 svm->pasid);
-			ret = -ENOSPC;
-			goto out;
+		if (!(flags & SVM_FLAG_SUPERVISOR_MODE)) {
+			svm->notifier.ops = &intel_mmuops;
+			ret = mmu_notifier_register(&svm->notifier, mm);
+			if (ret) {
+				kfree(svm);
+				return ERR_PTR(ret);
+			}
 		}
 
-		/* Find the matching device in svm list */
-		for_each_svm_dev(sdev, svm, dev) {
-			sdev->users++;
-			goto success;
+		ret = pasid_private_add(svm->pasid, svm);
+		if (ret) {
+			if (svm->notifier.ops)
+				mmu_notifier_unregister(&svm->notifier, mm);
+			kfree(svm);
+			return ERR_PTR(ret);
 		}
+	}
 
-		break;
+	/* Find the matching device in svm list */
+	sdev = svm_lookup_device_by_dev(svm, dev);
+	if (sdev) {
+		sdev->users++;
+		goto success;
 	}
 
 	sdev = kzalloc(sizeof(*sdev), GFP_KERNEL);
 	if (!sdev) {
 		ret = -ENOMEM;
-		goto out;
+		goto free_svm;
 	}
+
 	sdev->dev = dev;
 	sdev->iommu = iommu;
-
-	ret = intel_iommu_enable_pasid(iommu, dev);
-	if (ret) {
-		kfree(sdev);
-		goto out;
-	}
-
-	info = get_domain_info(dev);
 	sdev->did = FLPT_DEFAULT_DID;
 	sdev->sid = PCI_DEVID(info->bus, info->devfn);
+	sdev->users = 1;
+	sdev->pasid = svm->pasid;
+	sdev->sva.dev = dev;
+	init_rcu_head(&sdev->rcu);
 	if (info->ats_enabled) {
 		sdev->dev_iotlb = 1;
 		sdev->qdep = info->ats_qdep;
@@ -539,95 +607,37 @@ intel_svm_bind_mm(struct device *dev, unsigned int flags,
 			sdev->qdep = 0;
 	}
 
-	/* Finish the setup now we know we're keeping it */
-	sdev->users = 1;
-	init_rcu_head(&sdev->rcu);
-
-	if (!svm) {
-		svm = kzalloc(sizeof(*svm), GFP_KERNEL);
-		if (!svm) {
-			ret = -ENOMEM;
-			kfree(sdev);
-			goto out;
-		}
-
-		if (pasid_max > intel_pasid_max_id)
-			pasid_max = intel_pasid_max_id;
+	/* Setup the pasid table: */
+	sflags = (flags & SVM_FLAG_SUPERVISOR_MODE) ?
+			PASID_FLAG_SUPERVISOR_MODE : 0;
+	sflags |= cpu_feature_enabled(X86_FEATURE_LA57) ? PASID_FLAG_FL5LP : 0;
+	spin_lock_irqsave(&iommu->lock, iflags);
+	ret = intel_pasid_setup_first_level(iommu, dev, mm->pgd, mm->pasid,
+					    FLPT_DEFAULT_DID, sflags);
+	spin_unlock_irqrestore(&iommu->lock, iflags);
 
-		/* Do not use PASID 0, reserved for RID to PASID */
-		svm->pasid = ioasid_alloc(NULL, PASID_MIN,
-					  pasid_max - 1, svm);
-		if (svm->pasid == INVALID_IOASID) {
-			kfree(svm);
-			kfree(sdev);
-			ret = -ENOSPC;
-			goto out;
-		}
-		svm->notifier.ops = &intel_mmuops;
-		svm->mm = mm;
-		svm->flags = flags;
-		INIT_LIST_HEAD_RCU(&svm->devs);
-		INIT_LIST_HEAD(&svm->list);
-		ret = -ENOMEM;
-		if (mm) {
-			ret = mmu_notifier_register(&svm->notifier, mm);
-			if (ret) {
-				ioasid_put(svm->pasid);
-				kfree(svm);
-				kfree(sdev);
-				goto out;
-			}
-		}
+	if (ret)
+		goto free_sdev;
 
-		spin_lock_irqsave(&iommu->lock, iflags);
-		ret = intel_pasid_setup_first_level(iommu, dev,
-				mm ? mm->pgd : init_mm.pgd,
-				svm->pasid, FLPT_DEFAULT_DID,
-				(mm ? 0 : PASID_FLAG_SUPERVISOR_MODE) |
-				(cpu_feature_enabled(X86_FEATURE_LA57) ?
-				 PASID_FLAG_FL5LP : 0));
-		spin_unlock_irqrestore(&iommu->lock, iflags);
-		if (ret) {
-			if (mm)
-				mmu_notifier_unregister(&svm->notifier, mm);
-			ioasid_put(svm->pasid);
-			kfree(svm);
-			kfree(sdev);
-			goto out;
-		}
+	/* The newly allocated pasid is loaded to the mm. */
+	if (!(flags & SVM_FLAG_SUPERVISOR_MODE) && list_empty(&svm->devs))
+		load_pasid(mm, svm->pasid);
 
-		list_add_tail(&svm->list, &global_svm_list);
-		if (mm) {
-			/* The newly allocated pasid is loaded to the mm. */
-			load_pasid(mm, svm->pasid);
-		}
-	} else {
-		/*
-		 * Binding a new device with existing PASID, need to setup
-		 * the PASID entry.
-		 */
-		spin_lock_irqsave(&iommu->lock, iflags);
-		ret = intel_pasid_setup_first_level(iommu, dev,
-						mm ? mm->pgd : init_mm.pgd,
-						svm->pasid, FLPT_DEFAULT_DID,
-						(mm ? 0 : PASID_FLAG_SUPERVISOR_MODE) |
-						(cpu_feature_enabled(X86_FEATURE_LA57) ?
-						PASID_FLAG_FL5LP : 0));
-		spin_unlock_irqrestore(&iommu->lock, iflags);
-		if (ret) {
-			kfree(sdev);
-			goto out;
-		}
-	}
 	list_add_rcu(&sdev->list, &svm->devs);
 success:
-	sdev->pasid = svm->pasid;
-	sdev->sva.dev = dev;
-	if (sd)
-		*sd = sdev;
-	ret = 0;
-out:
-	return ret;
+	return &sdev->sva;
+
+free_sdev:
+	kfree(sdev);
+free_svm:
+	if (list_empty(&svm->devs)) {
+		if (svm->notifier.ops)
+			mmu_notifier_unregister(&svm->notifier, mm);
+		pasid_private_remove(mm->pasid);
+		kfree(svm);
+	}
+
+	return ERR_PTR(ret);
 }
 
 /* Caller must hold pasid_mutex */
@@ -636,6 +646,7 @@ static int intel_svm_unbind_mm(struct device *dev, u32 pasid)
 	struct intel_svm_dev *sdev;
 	struct intel_iommu *iommu;
 	struct intel_svm *svm;
+	struct mm_struct *mm;
 	int ret = -EINVAL;
 
 	iommu = device_to_iommu(dev, NULL, NULL);
@@ -645,6 +656,7 @@ static int intel_svm_unbind_mm(struct device *dev, u32 pasid)
 	ret = pasid_to_svm_sdev(dev, pasid, &svm, &sdev);
 	if (ret)
 		goto out;
+	mm = svm->mm;
 
 	if (sdev) {
 		sdev->users--;
@@ -663,13 +675,13 @@ static int intel_svm_unbind_mm(struct device *dev, u32 pasid)
 			kfree_rcu(sdev, rcu);
 
 			if (list_empty(&svm->devs)) {
-				ioasid_put(svm->pasid);
-				if (svm->mm) {
-					mmu_notifier_unregister(&svm->notifier, svm->mm);
+				intel_svm_free_pasid(mm);
+				if (svm->notifier.ops) {
+					mmu_notifier_unregister(&svm->notifier, mm);
 					/* Clear mm's pasid. */
-					load_pasid(svm->mm, PASID_DISABLED);
+					load_pasid(mm, PASID_DISABLED);
 				}
-				list_del(&svm->list);
+				pasid_private_remove(svm->pasid);
 				/* We mandate that no page faults may be outstanding
 				 * for the PASID when intel_svm_unbind_mm() is called.
 				 * If that is not obeyed, subtle errors will happen.
@@ -714,22 +726,6 @@ struct page_req_dsc {
 
 #define PRQ_RING_MASK	((0x1000 << PRQ_ORDER) - 0x20)
 
-static bool access_error(struct vm_area_struct *vma, struct page_req_dsc *req)
-{
-	unsigned long requested = 0;
-
-	if (req->exe_req)
-		requested |= VM_EXEC;
-
-	if (req->rd_req)
-		requested |= VM_READ;
-
-	if (req->wr_req)
-		requested |= VM_WRITE;
-
-	return (requested & ~vma->vm_flags) != 0;
-}
-
 static bool is_canonical_address(u64 addr)
 {
 	int shift = 64 - (__VIRTUAL_MASK_SHIFT + 1);
@@ -799,6 +795,8 @@ prq_retry:
 		goto prq_retry;
 	}
 
+	iopf_queue_flush_dev(dev);
+
 	/*
 	 * Perform steps described in VT-d spec CH7.10 to drain page
 	 * requests and responses in hardware.
@@ -841,8 +839,8 @@ static int prq_to_iommu_prot(struct page_req_dsc *req)
 	return prot;
 }
 
-static int
-intel_svm_prq_report(struct device *dev, struct page_req_dsc *desc)
+static int intel_svm_prq_report(struct intel_iommu *iommu, struct device *dev,
+				struct page_req_dsc *desc)
 {
 	struct iommu_fault_event event;
 
@@ -872,159 +870,136 @@ intel_svm_prq_report(struct device *dev, struct page_req_dsc *desc)
 		 */
 		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));
+		event.fault.prm.private_data[0] = desc->priv_data[0];
+		event.fault.prm.private_data[1] = desc->priv_data[1];
+	} else if (dmar_latency_enabled(iommu, DMAR_LATENCY_PRQ)) {
+		/*
+		 * If the private data fields are not used by hardware, use it
+		 * to monitor the prq handle latency.
+		 */
+		event.fault.prm.private_data[0] = ktime_to_ns(ktime_get());
 	}
 
 	return iommu_report_device_fault(dev, &event);
 }
 
+static void handle_bad_prq_event(struct intel_iommu *iommu,
+				 struct page_req_dsc *req, int result)
+{
+	struct qi_desc desc;
+
+	pr_err("%s: Invalid page request: %08llx %08llx\n",
+	       iommu->name, ((unsigned long long *)req)[0],
+	       ((unsigned long long *)req)[1]);
+
+	/*
+	 * 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 feature beyond
+	 * PCI ATS spec.
+	 */
+	if (!req->lpig && !req->priv_data_present)
+		return;
+
+	desc.qw0 = QI_PGRP_PASID(req->pasid) |
+			QI_PGRP_DID(req->rid) |
+			QI_PGRP_PASID_P(req->pasid_present) |
+			QI_PGRP_PDP(req->priv_data_present) |
+			QI_PGRP_RESP_CODE(result) |
+			QI_PGRP_RESP_TYPE;
+	desc.qw1 = QI_PGRP_IDX(req->prg_index) |
+			QI_PGRP_LPIG(req->lpig);
+
+	if (req->priv_data_present) {
+		desc.qw2 = req->priv_data[0];
+		desc.qw3 = req->priv_data[1];
+	} else {
+		desc.qw2 = 0;
+		desc.qw3 = 0;
+	}
+
+	qi_submit_sync(iommu, &desc, 1, 0);
+}
+
 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;
-	unsigned int flags = 0;
+	struct page_req_dsc *req;
+	int head, tail, handled;
+	u64 address;
 
-	/* Clear PPR bit before reading head/tail registers, to
-	 * ensure that we get a new interrupt if needed. */
+	/*
+	 * Clear PPR bit before reading head/tail registers, to ensure that
+	 * we get a new interrupt if needed.
+	 */
 	writel(DMA_PRS_PPR, iommu->reg + DMAR_PRS_REG);
 
 	tail = dmar_readq(iommu->reg + DMAR_PQT_REG) & PRQ_RING_MASK;
 	head = dmar_readq(iommu->reg + DMAR_PQH_REG) & PRQ_RING_MASK;
+	handled = (head != tail);
 	while (head != tail) {
-		struct vm_area_struct *vma;
-		struct page_req_dsc *req;
-		struct qi_desc resp;
-		int result;
-		vm_fault_t ret;
-		u64 address;
-
-		handled = 1;
 		req = &iommu->prq[head / sizeof(*req)];
-		result = QI_RESP_INVALID;
 		address = (u64)req->addr << VTD_PAGE_SHIFT;
-		if (!req->pasid_present) {
-			pr_err("%s: Page request without PASID: %08llx %08llx\n",
-			       iommu->name, ((unsigned long long *)req)[0],
-			       ((unsigned long long *)req)[1]);
-			goto no_pasid;
+
+		if (unlikely(!req->pasid_present)) {
+			pr_err("IOMMU: %s: Page request without PASID\n",
+			       iommu->name);
+bad_req:
+			svm = NULL;
+			sdev = NULL;
+			handle_bad_prq_event(iommu, req, QI_RESP_INVALID);
+			goto prq_advance;
 		}
-		/* We shall not receive page request for supervisor SVM */
-		if (req->pm_req && (req->rd_req | req->wr_req)) {
-			pr_err("Unexpected page request in Privilege Mode");
-			/* No need to find the matching sdev as for bad_req */
-			goto no_pasid;
+
+		if (unlikely(!is_canonical_address(address))) {
+			pr_err("IOMMU: %s: Address is not canonical\n",
+			       iommu->name);
+			goto bad_req;
 		}
-		/* DMA read with exec requeset is not supported. */
-		if (req->exe_req && req->rd_req) {
-			pr_err("Execution request not supported\n");
-			goto no_pasid;
+
+		if (unlikely(req->pm_req && (req->rd_req | req->wr_req))) {
+			pr_err("IOMMU: %s: Page request in Privilege Mode\n",
+			       iommu->name);
+			goto bad_req;
 		}
+
+		if (unlikely(req->exe_req && req->rd_req)) {
+			pr_err("IOMMU: %s: Execution request not supported\n",
+			       iommu->name);
+			goto bad_req;
+		}
+
 		if (!svm || svm->pasid != req->pasid) {
-			rcu_read_lock();
-			svm = ioasid_find(NULL, req->pasid, NULL);
-			/* It *can't* go away, because the driver is not permitted
+			/*
+			 * It can't go away, because the driver is not permitted
 			 * to unbind the mm while any page faults are outstanding.
-			 * So we only need RCU to protect the internal idr code. */
-			rcu_read_unlock();
-			if (IS_ERR_OR_NULL(svm)) {
-				pr_err("%s: Page request for invalid PASID %d: %08llx %08llx\n",
-				       iommu->name, req->pasid, ((unsigned long long *)req)[0],
-				       ((unsigned long long *)req)[1]);
-				goto no_pasid;
-			}
+			 */
+			svm = pasid_private_find(req->pasid);
+			if (IS_ERR_OR_NULL(svm) || (svm->flags & SVM_FLAG_SUPERVISOR_MODE))
+				goto bad_req;
 		}
 
 		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();
+			sdev = svm_lookup_device_by_sid(svm, req->rid);
+			if (!sdev)
+				goto bad_req;
 		}
 
-		/* Since we're using init_mm.pgd directly, we should never take
-		 * any faults on kernel addresses. */
-		if (!svm->mm)
-			goto bad_req;
-
-		/* If address is not canonical, return invalid response */
-		if (!is_canonical_address(address))
-			goto bad_req;
+		sdev->prq_seq_number++;
 
 		/*
 		 * 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;
-
-		mmap_read_lock(svm->mm);
-		vma = find_extend_vma(svm->mm, address);
-		if (!vma || address < vma->vm_start)
-			goto invalid;
-
-		if (access_error(vma, req))
-			goto invalid;
+		if (intel_svm_prq_report(iommu, sdev->dev, req))
+			handle_bad_prq_event(iommu, req, QI_RESP_INVALID);
 
-		flags = FAULT_FLAG_USER | FAULT_FLAG_REMOTE;
-		if (req->wr_req)
-			flags |= FAULT_FLAG_WRITE;
-
-		ret = handle_mm_fault(vma, address, flags, NULL);
-		if (ret & VM_FAULT_ERROR)
-			goto invalid;
-
-		result = QI_RESP_SUCCESS;
-invalid:
-		mmap_read_unlock(svm->mm);
-		mmput(svm->mm);
-bad_req:
-		/* We get here in the error case where the PASID lookup failed,
-		   and these can be NULL. Do not use them below this point! */
-		sdev = NULL;
-		svm = NULL;
-no_pasid:
-		if (req->lpig || req->priv_data_present) {
-			/*
-			 * 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 feature beyond
-			 * PCI ATS spec.
-			 */
-			resp.qw0 = QI_PGRP_PASID(req->pasid) |
-				QI_PGRP_DID(req->rid) |
-				QI_PGRP_PASID_P(req->pasid_present) |
-				QI_PGRP_PDP(req->priv_data_present) |
-				QI_PGRP_RESP_CODE(result) |
-				QI_PGRP_RESP_TYPE;
-			resp.qw1 = QI_PGRP_IDX(req->prg_index) |
-				QI_PGRP_LPIG(req->lpig);
-			resp.qw2 = 0;
-			resp.qw3 = 0;
-
-			if (req->priv_data_present)
-				memcpy(&resp.qw2, req->priv_data,
-				       sizeof(req->priv_data));
-			qi_submit_sync(iommu, &resp, 1, 0);
-		}
+		trace_prq_report(iommu, sdev->dev, req->qw_0, req->qw_1,
+				 req->priv_data[0], req->priv_data[1],
+				 sdev->prq_seq_number);
 prq_advance:
 		head = (head + sizeof(*req)) & PRQ_RING_MASK;
 	}
@@ -1041,6 +1016,7 @@ prq_advance:
 		head = dmar_readq(iommu->reg + DMAR_PQH_REG) & PRQ_RING_MASK;
 		tail = dmar_readq(iommu->reg + DMAR_PQT_REG) & PRQ_RING_MASK;
 		if (head == tail) {
+			iopf_queue_discard_partial(iommu->iopf_queue);
 			writel(DMA_PRS_PRO, iommu->reg + DMAR_PRS_REG);
 			pr_info_ratelimited("IOMMU: %s: PRQ overflow cleared",
 					    iommu->name);
@@ -1053,31 +1029,42 @@ prq_advance:
 	return IRQ_RETVAL(handled);
 }
 
-#define to_intel_svm_dev(handle) container_of(handle, struct intel_svm_dev, sva)
-struct iommu_sva *
-intel_svm_bind(struct device *dev, struct mm_struct *mm, void *drvdata)
+struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm, void *drvdata)
 {
-	struct iommu_sva *sva = ERR_PTR(-EINVAL);
-	struct intel_svm_dev *sdev = NULL;
+	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
 	unsigned int flags = 0;
+	struct iommu_sva *sva;
 	int ret;
 
-	/*
-	 * TODO: Consolidate with generic iommu-sva bind after it is merged.
-	 * It will require shared SVM data structures, i.e. combine io_mm
-	 * and intel_svm etc.
-	 */
 	if (drvdata)
 		flags = *(unsigned int *)drvdata;
+
+	if (flags & SVM_FLAG_SUPERVISOR_MODE) {
+		if (!ecap_srs(iommu->ecap)) {
+			dev_err(dev, "%s: Supervisor PASID not supported\n",
+				iommu->name);
+			return ERR_PTR(-EOPNOTSUPP);
+		}
+
+		if (mm) {
+			dev_err(dev, "%s: Supervisor PASID with user provided mm\n",
+				iommu->name);
+			return ERR_PTR(-EINVAL);
+		}
+
+		mm = &init_mm;
+	}
+
 	mutex_lock(&pasid_mutex);
-	ret = intel_svm_bind_mm(dev, flags, mm, &sdev);
-	if (ret)
-		sva = ERR_PTR(ret);
-	else if (sdev)
-		sva = &sdev->sva;
-	else
-		WARN(!sdev, "SVM bind succeeded with no sdev!\n");
+	ret = intel_svm_alloc_pasid(dev, mm, flags);
+	if (ret) {
+		mutex_unlock(&pasid_mutex);
+		return ERR_PTR(ret);
+	}
 
+	sva = intel_svm_bind_mm(iommu, dev, mm, flags);
+	if (IS_ERR_OR_NULL(sva))
+		intel_svm_free_pasid(mm);
 	mutex_unlock(&pasid_mutex);
 
 	return sva;
@@ -1085,10 +1072,9 @@ intel_svm_bind(struct device *dev, struct mm_struct *mm, void *drvdata)
 
 void intel_svm_unbind(struct iommu_sva *sva)
 {
-	struct intel_svm_dev *sdev;
+	struct intel_svm_dev *sdev = to_intel_svm_dev(sva);
 
 	mutex_lock(&pasid_mutex);
-	sdev = to_intel_svm_dev(sva);
 	intel_svm_unbind_mm(sdev->dev, sdev->pasid);
 	mutex_unlock(&pasid_mutex);
 }
@@ -1194,9 +1180,14 @@ int intel_svm_page_response(struct device *dev,
 		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));
+
+		if (private_present) {
+			desc.qw2 = prm->private_data[0];
+			desc.qw3 = prm->private_data[1];
+		} else if (prm->private_data[0]) {
+			dmar_latency_update(iommu, DMAR_LATENCY_PRQ,
+				ktime_to_ns(ktime_get()) - prm->private_data[0]);
+		}
 
 		qi_submit_sync(iommu, &desc, 1, 0);
 	}