@@ -86,6 +86,7 @@ struct vfio_domain {
struct list_head group_list;
bool fgsp : 1; /* Fine-grained super pages */
bool enforce_cache_coherency : 1;
+ bool msi_cookie : 1;
};
struct vfio_dma {
@@ -2153,12 +2154,161 @@ static void vfio_iommu_iova_insert_copy(struct vfio_iommu *iommu,
list_splice_tail(iova_copy, iova);
}
+static struct vfio_domain *
+vfio_iommu_alloc_attach_domain(struct bus_type *bus, struct vfio_iommu *iommu,
+ struct vfio_iommu_group *group)
+{
+ struct iommu_domain *new_domain;
+ struct vfio_domain *domain;
+ 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);
+ if (ret == -EMEDIUMTYPE)
+ continue;
+ if (ret)
+ return ERR_PTR(ret);
+ list_add(&group->next, &domain->group_list);
+ return domain;
+ }
+
+ new_domain = iommu_domain_alloc(bus);
+ 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;
+
+ /*
+ * 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++;
+
+ INIT_LIST_HEAD(&domain->group_list);
+ list_add(&group->next, &domain->group_list);
+ list_add(&domain->next, &iommu->domain_list);
+ vfio_update_pgsize_bitmap(iommu);
+ return domain;
+
+out_free_domain:
+ kfree(domain);
+out_detach:
+ iommu_detach_group(domain->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))
+ return;
+
+ /*
+ * 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);
+
+ /*
+ * 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_update_pgsize_bitmap(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;
+ struct vfio_domain *domain;
struct bus_type *bus = NULL;
bool resv_msi, msi_remap;
phys_addr_t resv_msi_base = 0;
@@ -2197,26 +2347,12 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
if (ret)
goto out_free_group;
- ret = -ENOMEM;
- domain = kzalloc(sizeof(*domain), GFP_KERNEL);
- if (!domain)
+ domain = vfio_iommu_alloc_attach_domain(bus, iommu, group);
+ if (IS_ERR(domain)) {
+ ret = PTR_ERR(domain);
goto out_free_group;
-
- ret = -EIO;
- domain->domain = iommu_domain_alloc(bus);
- if (!domain->domain)
- goto out_free_domain;
-
- if (iommu->nesting) {
- ret = iommu_enable_nesting(domain->domain);
- if (ret)
- goto out_domain;
}
- 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,
@@ -2254,9 +2390,6 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
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_capable(bus, IOMMU_CAP_INTR_REMAP);
@@ -2267,117 +2400,32 @@ 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. We don't want to
- * preclude an IOMMU driver supporting multiple bus_types and being
- * able to include different bus_types in the same IOMMU domain, so
- * we test whether the domains use the same iommu_ops rather than
- * testing if they're on the same bus_type.
- */
- list_for_each_entry(d, &iommu->domain_list, next) {
- if (d->domain->ops == domain->domain->ops) {
- 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) {
+ if (resv_msi && !domain->msi_cookie) {
ret = iommu_get_msi_cookie(domain->domain, resv_msi_base);
if (ret && ret != -ENODEV)
goto out_detach;
+ domain->msi_cookie = true;
}
- 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
@@ -2491,44 +2539,12 @@ 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