diff mbox series

[v5,5/5] vfio/iommu_type1: Simplify group attachment

Message ID 20220701214455.14992-6-nicolinc@nvidia.com (mailing list archive)
State New, archived
Headers show
Series cover-letter: Simplify vfio_iommu_type1 attach/detach routine | expand

Commit Message

Nicolin Chen July 1, 2022, 9:44 p.m. UTC
Un-inline the domain specific logic from the attach/detach_group ops into
two paired functions vfio_iommu_alloc_attach_domain() and
vfio_iommu_detach_destroy_domain() that strictly deal with creating and
destroying struct vfio_domains.

Add the logic to check for EMEDIUMTYPE return code of iommu_attach_group()
and avoid the extra domain allocations and attach/detach sequences of the
old code. This allows properly detecting an actual attach error, like
-ENOMEM, vs treating all attach errors as an incompatible domain.

Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Co-developed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
---
 drivers/vfio/vfio_iommu_type1.c | 333 +++++++++++++++++---------------
 1 file changed, 180 insertions(+), 153 deletions(-)
diff mbox series

Patch

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 5624bbf02ab7..d3a4cedcd082 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -2155,14 +2155,179 @@  static int vfio_iommu_domain_alloc(struct device *dev, void *data)
 	return 1; /* Don't iterate */
 }
 
+static struct vfio_domain *
+vfio_iommu_alloc_attach_domain(struct vfio_iommu *iommu,
+			       struct vfio_iommu_group *group,
+			       struct list_head *group_resv_regions)
+{
+	struct iommu_domain *new_domain;
+	struct vfio_domain *domain;
+	phys_addr_t resv_msi_base;
+	int ret = 0;
+
+	/* Try to match an existing compatible domain */
+	list_for_each_entry (domain, &iommu->domain_list, next) {
+		ret = iommu_attach_group(domain->domain, group->iommu_group);
+		/* -EMEDIUMTYPE means an incompatible domain, so try next one */
+		if (ret == -EMEDIUMTYPE)
+			continue;
+		if (ret)
+			return ERR_PTR(ret);
+		goto done;
+	}
+
+	/*
+	 * Going via the iommu_group iterator avoids races, and trivially gives
+	 * us a representative device for the IOMMU API call. We don't actually
+	 * want to iterate beyond the first device (if any).
+	 */
+	iommu_group_for_each_dev(group->iommu_group, &new_domain,
+				 vfio_iommu_domain_alloc);
+	if (!new_domain)
+		return ERR_PTR(-EIO);
+
+	if (iommu->nesting) {
+		ret = iommu_enable_nesting(new_domain);
+		if (ret)
+			goto out_free_iommu_domain;
+	}
+
+	ret = iommu_attach_group(new_domain, group->iommu_group);
+	if (ret)
+		goto out_free_iommu_domain;
+
+	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
+	if (!domain) {
+		ret = -ENOMEM;
+		goto out_detach;
+	}
+
+	domain->domain = new_domain;
+	vfio_test_domain_fgsp(domain);
+
+	/*
+	 * If the IOMMU can block non-coherent operations (ie PCIe TLPs with
+	 * no-snoop set) then VFIO always turns this feature on because on Intel
+	 * platforms it optimizes KVM to disable wbinvd emulation.
+	 */
+	if (new_domain->ops->enforce_cache_coherency)
+		domain->enforce_cache_coherency =
+			new_domain->ops->enforce_cache_coherency(new_domain);
+
+	/* replay mappings on new domains */
+	ret = vfio_iommu_replay(iommu, domain);
+	if (ret)
+		goto out_free_domain;
+
+	if (vfio_iommu_has_sw_msi(group_resv_regions, &resv_msi_base)) {
+		ret = iommu_get_msi_cookie(domain->domain, resv_msi_base);
+		if (ret && ret != -ENODEV)
+			goto out_free_domain;
+	}
+
+	INIT_LIST_HEAD(&domain->group_list);
+	list_add(&domain->next, &iommu->domain_list);
+	vfio_update_pgsize_bitmap(iommu);
+
+done:
+	list_add(&group->next, &domain->group_list);
+
+	/*
+	 * An iommu backed group can dirty memory directly and therefore
+	 * demotes the iommu scope until it declares itself dirty tracking
+	 * capable via the page pinning interface.
+	 */
+	iommu->num_non_pinned_groups++;
+
+	return domain;
+
+out_free_domain:
+	kfree(domain);
+out_detach:
+	iommu_detach_group(new_domain, group->iommu_group);
+out_free_iommu_domain:
+	iommu_domain_free(new_domain);
+	return ERR_PTR(ret);
+}
+
+static void vfio_iommu_unmap_unpin_all(struct vfio_iommu *iommu)
+{
+	struct rb_node *node;
+
+	while ((node = rb_first(&iommu->dma_list)))
+		vfio_remove_dma(iommu, rb_entry(node, struct vfio_dma, node));
+}
+
+static void vfio_iommu_unmap_unpin_reaccount(struct vfio_iommu *iommu)
+{
+	struct rb_node *n, *p;
+
+	n = rb_first(&iommu->dma_list);
+	for (; n; n = rb_next(n)) {
+		struct vfio_dma *dma;
+		long locked = 0, unlocked = 0;
+
+		dma = rb_entry(n, struct vfio_dma, node);
+		unlocked += vfio_unmap_unpin(iommu, dma, false);
+		p = rb_first(&dma->pfn_list);
+		for (; p; p = rb_next(p)) {
+			struct vfio_pfn *vpfn = rb_entry(p, struct vfio_pfn,
+							 node);
+
+			if (!is_invalid_reserved_pfn(vpfn->pfn))
+				locked++;
+		}
+		vfio_lock_acct(dma, locked - unlocked, true);
+	}
+}
+
+static void vfio_iommu_detach_destroy_domain(struct vfio_domain *domain,
+					     struct vfio_iommu *iommu,
+					     struct vfio_iommu_group *group)
+{
+	iommu_detach_group(domain->domain, group->iommu_group);
+	list_del(&group->next);
+	if (!list_empty(&domain->group_list))
+		goto out_dirty;
+
+	/*
+	 * Group ownership provides privilege, if the group list is empty, the
+	 * domain goes away. If it's the last domain with iommu and external
+	 * domain doesn't exist, then all the mappings go away too. If it's the
+	 * last domain with iommu and external domain exist, update accounting
+	 */
+	if (list_is_singular(&iommu->domain_list)) {
+		if (list_empty(&iommu->emulated_iommu_groups)) {
+			WARN_ON(iommu->notifier.head);
+			vfio_iommu_unmap_unpin_all(iommu);
+		} else {
+			vfio_iommu_unmap_unpin_reaccount(iommu);
+		}
+	}
+	iommu_domain_free(domain->domain);
+	list_del(&domain->next);
+	kfree(domain);
+	vfio_update_pgsize_bitmap(iommu);
+
+out_dirty:
+	/*
+	 * Removal of a group without dirty tracking may allow the iommu scope
+	 * to be promoted.
+	 */
+	if (!group->pinned_page_dirty_scope) {
+		iommu->num_non_pinned_groups--;
+		if (iommu->dirty_page_tracking)
+			vfio_iommu_populate_bitmap_full(iommu);
+	}
+}
+
 static int vfio_iommu_type1_attach_group(void *iommu_data,
 		struct iommu_group *iommu_group, enum vfio_group_type type)
 {
 	struct vfio_iommu *iommu = iommu_data;
 	struct vfio_iommu_group *group;
-	struct vfio_domain *domain, *d;
-	bool resv_msi, msi_remap;
-	phys_addr_t resv_msi_base = 0;
+	struct vfio_domain *domain;
+	bool msi_remap;
 	struct iommu_domain_geometry *geo;
 	LIST_HEAD(iova_copy);
 	LIST_HEAD(group_resv_regions);
@@ -2193,32 +2358,17 @@  static int vfio_iommu_type1_attach_group(void *iommu_data,
 		goto out_unlock;
 	}
 
-	ret = -ENOMEM;
-	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
-	if (!domain)
+	ret = iommu_get_group_resv_regions(iommu_group, &group_resv_regions);
+	if (ret)
 		goto out_free_group;
 
-	/*
-	 * Going via the iommu_group iterator avoids races, and trivially gives
-	 * us a representative device for the IOMMU API call. We don't actually
-	 * want to iterate beyond the first device (if any).
-	 */
-	ret = -EIO;
-	iommu_group_for_each_dev(iommu_group, &domain->domain,
-				 vfio_iommu_domain_alloc);
-	if (!domain->domain)
-		goto out_free_domain;
-
-	if (iommu->nesting) {
-		ret = iommu_enable_nesting(domain->domain);
-		if (ret)
-			goto out_domain;
+	domain = vfio_iommu_alloc_attach_domain(iommu, group,
+						&group_resv_regions);
+	if (IS_ERR(domain)) {
+		ret = PTR_ERR(domain);
+		goto out_free_group;
 	}
 
-	ret = iommu_attach_group(domain->domain, group->iommu_group);
-	if (ret)
-		goto out_domain;
-
 	/* Get aperture info */
 	geo = &domain->domain->geometry;
 	if (vfio_iommu_aper_conflict(iommu, geo->aperture_start,
@@ -2227,10 +2377,6 @@  static int vfio_iommu_type1_attach_group(void *iommu_data,
 		goto out_detach;
 	}
 
-	ret = iommu_get_group_resv_regions(iommu_group, &group_resv_regions);
-	if (ret)
-		goto out_detach;
-
 	if (vfio_iommu_resv_conflict(iommu, &group_resv_regions)) {
 		ret = -EINVAL;
 		goto out_detach;
@@ -2254,11 +2400,6 @@  static int vfio_iommu_type1_attach_group(void *iommu_data,
 	if (ret)
 		goto out_detach;
 
-	resv_msi = vfio_iommu_has_sw_msi(&group_resv_regions, &resv_msi_base);
-
-	INIT_LIST_HEAD(&domain->group_list);
-	list_add(&group->next, &domain->group_list);
-
 	msi_remap = irq_domain_check_msi_remap() ||
 		    iommu_group_for_each_dev(iommu_group, (void *)IOMMU_CAP_INTR_REMAP,
 					     vfio_iommu_device_capable);
@@ -2270,107 +2411,25 @@  static int vfio_iommu_type1_attach_group(void *iommu_data,
 		goto out_detach;
 	}
 
-	/*
-	 * If the IOMMU can block non-coherent operations (ie PCIe TLPs with
-	 * no-snoop set) then VFIO always turns this feature on because on Intel
-	 * platforms it optimizes KVM to disable wbinvd emulation.
-	 */
-	if (domain->domain->ops->enforce_cache_coherency)
-		domain->enforce_cache_coherency =
-			domain->domain->ops->enforce_cache_coherency(
-				domain->domain);
-
-	/* Try to match an existing compatible domain */
-	list_for_each_entry(d, &iommu->domain_list, next) {
-		iommu_detach_group(domain->domain, group->iommu_group);
-		if (!iommu_attach_group(d->domain, group->iommu_group)) {
-			list_add(&group->next, &d->group_list);
-			iommu_domain_free(domain->domain);
-			kfree(domain);
-			goto done;
-		}
-
-		ret = iommu_attach_group(domain->domain,  group->iommu_group);
-		if (ret)
-			goto out_domain;
-	}
-
-	vfio_test_domain_fgsp(domain);
-
-	/* replay mappings on new domains */
-	ret = vfio_iommu_replay(iommu, domain);
-	if (ret)
-		goto out_detach;
-
-	if (resv_msi) {
-		ret = iommu_get_msi_cookie(domain->domain, resv_msi_base);
-		if (ret && ret != -ENODEV)
-			goto out_detach;
-	}
-
-	list_add(&domain->next, &iommu->domain_list);
-	vfio_update_pgsize_bitmap(iommu);
-done:
 	/* Delete the old one and insert new iova list */
 	vfio_iommu_iova_insert_copy(iommu, &iova_copy);
 
-	/*
-	 * An iommu backed group can dirty memory directly and therefore
-	 * demotes the iommu scope until it declares itself dirty tracking
-	 * capable via the page pinning interface.
-	 */
-	iommu->num_non_pinned_groups++;
 	mutex_unlock(&iommu->lock);
 	vfio_iommu_resv_free(&group_resv_regions);
 
 	return 0;
 
 out_detach:
-	iommu_detach_group(domain->domain, group->iommu_group);
-out_domain:
-	iommu_domain_free(domain->domain);
-	vfio_iommu_iova_free(&iova_copy);
-	vfio_iommu_resv_free(&group_resv_regions);
-out_free_domain:
-	kfree(domain);
+	vfio_iommu_detach_destroy_domain(domain, iommu, group);
 out_free_group:
 	kfree(group);
 out_unlock:
 	mutex_unlock(&iommu->lock);
+	vfio_iommu_iova_free(&iova_copy);
+	vfio_iommu_resv_free(&group_resv_regions);
 	return ret;
 }
 
-static void vfio_iommu_unmap_unpin_all(struct vfio_iommu *iommu)
-{
-	struct rb_node *node;
-
-	while ((node = rb_first(&iommu->dma_list)))
-		vfio_remove_dma(iommu, rb_entry(node, struct vfio_dma, node));
-}
-
-static void vfio_iommu_unmap_unpin_reaccount(struct vfio_iommu *iommu)
-{
-	struct rb_node *n, *p;
-
-	n = rb_first(&iommu->dma_list);
-	for (; n; n = rb_next(n)) {
-		struct vfio_dma *dma;
-		long locked = 0, unlocked = 0;
-
-		dma = rb_entry(n, struct vfio_dma, node);
-		unlocked += vfio_unmap_unpin(iommu, dma, false);
-		p = rb_first(&dma->pfn_list);
-		for (; p; p = rb_next(p)) {
-			struct vfio_pfn *vpfn = rb_entry(p, struct vfio_pfn,
-							 node);
-
-			if (!is_invalid_reserved_pfn(vpfn->pfn))
-				locked++;
-		}
-		vfio_lock_acct(dma, locked - unlocked, true);
-	}
-}
-
 /*
  * Called when a domain is removed in detach. It is possible that
  * the removed domain decided the iova aperture window. Modify the
@@ -2485,44 +2544,12 @@  static void vfio_iommu_type1_detach_group(void *iommu_data,
 		group = find_iommu_group(domain, iommu_group);
 		if (!group)
 			continue;
-
-		iommu_detach_group(domain->domain, group->iommu_group);
-		list_del(&group->next);
-		/*
-		 * Group ownership provides privilege, if the group list is
-		 * empty, the domain goes away. If it's the last domain with
-		 * iommu and external domain doesn't exist, then all the
-		 * mappings go away too. If it's the last domain with iommu and
-		 * external domain exist, update accounting
-		 */
-		if (list_empty(&domain->group_list)) {
-			if (list_is_singular(&iommu->domain_list)) {
-				if (list_empty(&iommu->emulated_iommu_groups)) {
-					WARN_ON(iommu->notifier.head);
-					vfio_iommu_unmap_unpin_all(iommu);
-				} else {
-					vfio_iommu_unmap_unpin_reaccount(iommu);
-				}
-			}
-			iommu_domain_free(domain->domain);
-			list_del(&domain->next);
-			kfree(domain);
-			vfio_iommu_aper_expand(iommu, &iova_copy);
-			vfio_update_pgsize_bitmap(iommu);
-		}
-		/*
-		 * Removal of a group without dirty tracking may allow
-		 * the iommu scope to be promoted.
-		 */
-		if (!group->pinned_page_dirty_scope) {
-			iommu->num_non_pinned_groups--;
-			if (iommu->dirty_page_tracking)
-				vfio_iommu_populate_bitmap_full(iommu);
-		}
+		vfio_iommu_detach_destroy_domain(domain, iommu, group);
 		kfree(group);
 		break;
 	}
 
+	vfio_iommu_aper_expand(iommu, &iova_copy);
 	if (!vfio_iommu_resv_refresh(iommu, &iova_copy))
 		vfio_iommu_iova_insert_copy(iommu, &iova_copy);
 	else