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.
Co-developed-by: Jason Gunthorpe
Signed-off-by: Jason Gunthorpe
Signed-off-by: Nicolin Chen
---
drivers/vfio/vfio_iommu_type1.c | 321 +---
1 file changed, 174 insertions(+), 147 deletions(-)
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index b9ccb3cfac5d..3ffa4e2d9d18 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -2153,15 +2153,174 @@ 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 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;
+ }
+
+ 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;
+
+ 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);
+
+