1 files changed, 183 insertions, 63 deletions

diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c
index 05c0fb2acbc4..d236aef80a8d 100644
--- a/drivers/iommu/iommu-sva.c
+++ b/drivers/iommu/iommu-sva.c
@@ -7,41 +7,52 @@
 #include <linux/sched/mm.h>
 #include <linux/iommu.h>
 
-#include "iommu-sva.h"
+#include "iommu-priv.h"
 
 static DEFINE_MUTEX(iommu_sva_lock);
-static DEFINE_IDA(iommu_global_pasid_ida);
+static bool iommu_sva_present;
+static LIST_HEAD(iommu_sva_mms);
+static struct iommu_domain *iommu_sva_domain_alloc(struct device *dev,
+						   struct mm_struct *mm);
 
 /* Allocate a PASID for the mm within range (inclusive) */
-static int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max)
+static struct iommu_mm_data *iommu_alloc_mm_data(struct mm_struct *mm, struct device *dev)
 {
-	int ret = 0;
+	struct iommu_mm_data *iommu_mm;
+	ioasid_t pasid;
 
-	if (min == IOMMU_PASID_INVALID ||
-	    max == IOMMU_PASID_INVALID ||
-	    min == 0 || max < min)
-		return -EINVAL;
+	lockdep_assert_held(&iommu_sva_lock);
 
 	if (!arch_pgtable_dma_compat(mm))
-		return -EBUSY;
+		return ERR_PTR(-EBUSY);
 
-	mutex_lock(&iommu_sva_lock);
+	iommu_mm = mm->iommu_mm;
 	/* Is a PASID already associated with this mm? */
-	if (mm_valid_pasid(mm)) {
-		if (mm->pasid < min || mm->pasid > max)
-			ret = -EOVERFLOW;
-		goto out;
+	if (iommu_mm) {
+		if (iommu_mm->pasid >= dev->iommu->max_pasids)
+			return ERR_PTR(-EOVERFLOW);
+		return iommu_mm;
 	}
 
-	ret = ida_alloc_range(&iommu_global_pasid_ida, min, max, GFP_KERNEL);
-	if (ret < 0)
-		goto out;
+	iommu_mm = kzalloc(sizeof(struct iommu_mm_data), GFP_KERNEL);
+	if (!iommu_mm)
+		return ERR_PTR(-ENOMEM);
 
-	mm->pasid = ret;
-	ret = 0;
-out:
-	mutex_unlock(&iommu_sva_lock);
-	return ret;
+	pasid = iommu_alloc_global_pasid(dev);
+	if (pasid == IOMMU_PASID_INVALID) {
+		kfree(iommu_mm);
+		return ERR_PTR(-ENOSPC);
+	}
+	iommu_mm->pasid = pasid;
+	iommu_mm->mm = mm;
+	INIT_LIST_HEAD(&iommu_mm->sva_domains);
+	/*
+	 * Make sure the write to mm->iommu_mm is not reordered in front of
+	 * initialization to iommu_mm fields. If it does, readers may see a
+	 * valid iommu_mm with uninitialized values.
+	 */
+	smp_store_release(&mm->iommu_mm, iommu_mm);
+	return iommu_mm;
 }
 
 /**
@@ -55,69 +66,94 @@ out:
  * reference is taken. Caller must call iommu_sva_unbind_device()
  * to release each reference.
  *
- * iommu_dev_enable_feature(dev, IOMMU_DEV_FEAT_SVA) must be called first, to
- * initialize the required SVA features.
- *
  * On error, returns an ERR_PTR value.
  */
 struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
 {
+	struct iommu_group *group = dev->iommu_group;
+	struct iommu_attach_handle *attach_handle;
+	struct iommu_mm_data *iommu_mm;
 	struct iommu_domain *domain;
 	struct iommu_sva *handle;
-	ioasid_t max_pasids;
 	int ret;
 
-	max_pasids = dev->iommu->max_pasids;
-	if (!max_pasids)
-		return ERR_PTR(-EOPNOTSUPP);
+	if (!group)
+		return ERR_PTR(-ENODEV);
+
+	mutex_lock(&iommu_sva_lock);
 
 	/* Allocate mm->pasid if necessary. */
-	ret = iommu_sva_alloc_pasid(mm, 1, max_pasids - 1);
-	if (ret)
-		return ERR_PTR(ret);
+	iommu_mm = iommu_alloc_mm_data(mm, dev);
+	if (IS_ERR(iommu_mm)) {
+		ret = PTR_ERR(iommu_mm);
+		goto out_unlock;
+	}
 
-	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
-	if (!handle)
-		return ERR_PTR(-ENOMEM);
+	/* A bond already exists, just take a reference`. */
+	attach_handle = iommu_attach_handle_get(group, iommu_mm->pasid, IOMMU_DOMAIN_SVA);
+	if (!IS_ERR(attach_handle)) {
+		handle = container_of(attach_handle, struct iommu_sva, handle);
+		if (attach_handle->domain->mm != mm) {
+			ret = -EBUSY;
+			goto out_unlock;
+		}
+		refcount_inc(&handle->users);
+		mutex_unlock(&iommu_sva_lock);
+		return handle;
+	}
 
-	mutex_lock(&iommu_sva_lock);
-	/* Search for an existing domain. */
-	domain = iommu_get_domain_for_dev_pasid(dev, mm->pasid,
-						IOMMU_DOMAIN_SVA);
-	if (IS_ERR(domain)) {
-		ret = PTR_ERR(domain);
+	if (PTR_ERR(attach_handle) != -ENOENT) {
+		ret = PTR_ERR(attach_handle);
 		goto out_unlock;
 	}
 
-	if (domain) {
-		domain->users++;
-		goto out;
+	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
+	if (!handle) {
+		ret = -ENOMEM;
+		goto out_unlock;
+	}
+
+	/* Search for an existing domain. */
+	list_for_each_entry(domain, &mm->iommu_mm->sva_domains, next) {
+		ret = iommu_attach_device_pasid(domain, dev, iommu_mm->pasid,
+						&handle->handle);
+		if (!ret) {
+			domain->users++;
+			goto out;
+		}
 	}
 
 	/* Allocate a new domain and set it on device pasid. */
 	domain = iommu_sva_domain_alloc(dev, mm);
-	if (!domain) {
-		ret = -ENOMEM;
-		goto out_unlock;
+	if (IS_ERR(domain)) {
+		ret = PTR_ERR(domain);
+		goto out_free_handle;
 	}
 
-	ret = iommu_attach_device_pasid(domain, dev, mm->pasid);
+	ret = iommu_attach_device_pasid(domain, dev, iommu_mm->pasid,
+					&handle->handle);
 	if (ret)
 		goto out_free_domain;
 	domain->users = 1;
+
+	if (list_empty(&iommu_mm->sva_domains)) {
+		if (list_empty(&iommu_sva_mms))
+			iommu_sva_present = true;
+		list_add(&iommu_mm->mm_list_elm, &iommu_sva_mms);
+	}
+	list_add(&domain->next, &iommu_mm->sva_domains);
 out:
+	refcount_set(&handle->users, 1);
 	mutex_unlock(&iommu_sva_lock);
 	handle->dev = dev;
-	handle->domain = domain;
-
 	return handle;
 
 out_free_domain:
 	iommu_domain_free(domain);
+out_free_handle:
+	kfree(handle);
 out_unlock:
 	mutex_unlock(&iommu_sva_lock);
-	kfree(handle);
-
 	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(iommu_sva_bind_device);
@@ -132,15 +168,28 @@ EXPORT_SYMBOL_GPL(iommu_sva_bind_device);
  */
 void iommu_sva_unbind_device(struct iommu_sva *handle)
 {
-	struct iommu_domain *domain = handle->domain;
-	ioasid_t pasid = domain->mm->pasid;
+	struct iommu_domain *domain = handle->handle.domain;
+	struct iommu_mm_data *iommu_mm = domain->mm->iommu_mm;
 	struct device *dev = handle->dev;
 
 	mutex_lock(&iommu_sva_lock);
+	if (!refcount_dec_and_test(&handle->users)) {
+		mutex_unlock(&iommu_sva_lock);
+		return;
+	}
+
+	iommu_detach_device_pasid(domain, dev, iommu_mm->pasid);
 	if (--domain->users == 0) {
-		iommu_detach_device_pasid(domain, dev, pasid);
+		list_del(&domain->next);
 		iommu_domain_free(domain);
 	}
+
+	if (list_empty(&iommu_mm->sva_domains)) {
+		list_del(&iommu_mm->mm_list_elm);
+		if (list_empty(&iommu_sva_mms))
+			iommu_sva_present = false;
+	}
+
 	mutex_unlock(&iommu_sva_lock);
 	kfree(handle);
 }
@@ -148,21 +197,31 @@ EXPORT_SYMBOL_GPL(iommu_sva_unbind_device);
 
 u32 iommu_sva_get_pasid(struct iommu_sva *handle)
 {
-	struct iommu_domain *domain = handle->domain;
+	struct iommu_domain *domain = handle->handle.domain;
 
-	return domain->mm->pasid;
+	return mm_get_enqcmd_pasid(domain->mm);
 }
 EXPORT_SYMBOL_GPL(iommu_sva_get_pasid);
 
+void mm_pasid_drop(struct mm_struct *mm)
+{
+	struct iommu_mm_data *iommu_mm = mm->iommu_mm;
+
+	if (!iommu_mm)
+		return;
+
+	iommu_free_global_pasid(iommu_mm->pasid);
+	kfree(iommu_mm);
+}
+
 /*
  * I/O page fault handler for SVA
  */
-enum iommu_page_response_code
-iommu_sva_handle_iopf(struct iommu_fault *fault, void *data)
+static enum iommu_page_response_code
+iommu_sva_handle_mm(struct iommu_fault *fault, struct mm_struct *mm)
 {
 	vm_fault_t ret;
 	struct vm_area_struct *vma;
-	struct mm_struct *mm = data;
 	unsigned int access_flags = 0;
 	unsigned int fault_flags = FAULT_FLAG_REMOTE;
 	struct iommu_fault_page_request *prm = &fault->prm;
@@ -212,10 +271,71 @@ out_put_mm:
 	return status;
 }
 
-void mm_pasid_drop(struct mm_struct *mm)
+static void iommu_sva_handle_iopf(struct work_struct *work)
 {
-	if (likely(!mm_valid_pasid(mm)))
+	struct iopf_fault *iopf;
+	struct iopf_group *group;
+	enum iommu_page_response_code status = IOMMU_PAGE_RESP_SUCCESS;
+
+	group = container_of(work, struct iopf_group, work);
+	list_for_each_entry(iopf, &group->faults, list) {
+		/*
+		 * For the moment, errors are sticky: don't handle subsequent
+		 * faults in the group if there is an error.
+		 */
+		if (status != IOMMU_PAGE_RESP_SUCCESS)
+			break;
+
+		status = iommu_sva_handle_mm(&iopf->fault,
+					     group->attach_handle->domain->mm);
+	}
+
+	iopf_group_response(group, status);
+	iopf_free_group(group);
+}
+
+static int iommu_sva_iopf_handler(struct iopf_group *group)
+{
+	struct iommu_fault_param *fault_param = group->fault_param;
+
+	INIT_WORK(&group->work, iommu_sva_handle_iopf);
+	if (!queue_work(fault_param->queue->wq, &group->work))
+		return -EBUSY;
+
+	return 0;
+}
+
+static struct iommu_domain *iommu_sva_domain_alloc(struct device *dev,
+						   struct mm_struct *mm)
+{
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
+	struct iommu_domain *domain;
+
+	if (!ops->domain_alloc_sva)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	domain = ops->domain_alloc_sva(dev, mm);
+	if (IS_ERR(domain))
+		return domain;
+
+	domain->type = IOMMU_DOMAIN_SVA;
+	domain->cookie_type = IOMMU_COOKIE_SVA;
+	mmgrab(mm);
+	domain->mm = mm;
+	domain->owner = ops;
+	domain->iopf_handler = iommu_sva_iopf_handler;
+
+	return domain;
+}
+
+void iommu_sva_invalidate_kva_range(unsigned long start, unsigned long end)
+{
+	struct iommu_mm_data *iommu_mm;
+
+	guard(mutex)(&iommu_sva_lock);
+	if (!iommu_sva_present)
 		return;
 
-	ida_free(&iommu_global_pasid_ida, mm->pasid);
+	list_for_each_entry(iommu_mm, &iommu_sva_mms, mm_list_elm)
+		mmu_notifier_arch_invalidate_secondary_tlbs(iommu_mm->mm, start, end);
 }