[Qemu-devel] [RFC v4 17/29] vfio: Set up nested stage mappings

[Eric Auger]

In nested mode, legacy vfio_iommu_map_notify cannot be used as
there is no "caching" mode and we do not trap on map.

On Intel, vfio_iommu_map_notify was used to DMA map the RAM
through the host single stage.

With nested mode, we need to setup the stage 2 and the stage 1
separately. This patch introduces a prereg_listener to setup
the stage 2 mapping.

The stage 1 mapping, owned by the guest, is passed to the host
when the guest invalidates the stage 1 configuration, through
a dedicated PCIPASIDOps callback. Guest IOTLB invalidations
are cascaded downto the host through another IOMMU MR UNMAP
notifier.

Signed-off-by: Eric Auger <address@hidden>

---

v4 -> v5:
- use VFIO_IOMMU_SET_PASID_TABLE
- use PCIPASIDOps for config notification

v3 -> v4:
- use iommu_inv_pasid_info for ASID invalidation

v2 -> v3:
- use VFIO_IOMMU_ATTACH_PASID_TABLE
- new user API
- handle leaf

v1 -> v2:
- adapt to uapi changes
- pass the asid
- pass IOMMU_NOTIFIER_S1_CFG when initializing the config notifier
---
 hw/vfio/common.c     | 123 +++++++++++++++++++++++++++++++++++++++----
 hw/vfio/pci.c        |  21 ++++++++
 hw/vfio/trace-events |   2 +
 3 files changed, 136 insertions(+), 10 deletions(-)

diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index ef8452a4bc..bd975c5b83 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -444,6 +444,52 @@ static bool vfio_get_vaddr(IOMMUTLBEntry *iotlb, void 
**vaddr,
     return true;
 }
 
+/* Propagate a guest IOTLB invalidation to the host (nested mode) */
+static void vfio_iommu_unmap_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
+{
+    VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n);
+    hwaddr start = iotlb->iova + giommu->iommu_offset;
+
+    VFIOContainer *container = giommu->container;
+    struct vfio_iommu_type1_cache_invalidate ustruct;
+    size_t size = iotlb->addr_mask + 1;
+    int ret;
+
+    assert(iotlb->perm == IOMMU_NONE);
+
+    ustruct.argsz = sizeof(ustruct);
+    ustruct.flags = 0;
+    ustruct.info.version = IOMMU_CACHE_INVALIDATE_INFO_VERSION_1;
+
+    if (size <= 0x10000) {
+        ustruct.info.cache = IOMMU_CACHE_INV_TYPE_IOTLB;
+        ustruct.info.granularity = IOMMU_INV_GRANU_ADDR;
+        ustruct.info.addr_info.flags = IOMMU_INV_ADDR_FLAGS_ARCHID;
+        if (iotlb->leaf) {
+            ustruct.info.addr_info.flags |= IOMMU_INV_ADDR_FLAGS_LEAF;
+        }
+        ustruct.info.addr_info.archid = iotlb->arch_id;
+        ustruct.info.addr_info.addr = start;
+        ustruct.info.addr_info.granule_size = size;
+        ustruct.info.addr_info.nb_granules = 1;
+        trace_vfio_iommu_addr_inv_iotlb(iotlb->arch_id, start, size, 1,
+                                        iotlb->leaf);
+    } else {
+        ustruct.info.cache = IOMMU_CACHE_INV_TYPE_IOTLB;
+        ustruct.info.granularity = IOMMU_INV_GRANU_PASID;
+        ustruct.info.pasid_info.archid = iotlb->arch_id;
+        ustruct.info.pasid_info.flags = IOMMU_INV_PASID_FLAGS_ARCHID;
+        trace_vfio_iommu_asid_inv_iotlb(iotlb->arch_id);
+    }
+
+    ret = ioctl(container->fd, VFIO_IOMMU_CACHE_INVALIDATE, &ustruct);
+    if (ret) {
+        error_report("%p: failed to invalidate CACHE for 0x%"PRIx64
+                     " mask=0x%"PRIx64" (%d)",
+                     container, start, iotlb->addr_mask, ret);
+    }
+}
+
 static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
 {
     VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n);
@@ -613,6 +659,32 @@ static void vfio_dma_unmap_ram_section(VFIOContainer 
*container,
     }
 }
 
+static void vfio_prereg_listener_region_add(MemoryListener *listener,
+                                            MemoryRegionSection *section)
+{
+    VFIOContainer *container =
+        container_of(listener, VFIOContainer, prereg_listener);
+
+    if (!memory_region_is_ram(section->mr)) {
+        return;
+    }
+
+    vfio_dma_map_ram_section(container, section);
+
+}
+static void vfio_prereg_listener_region_del(MemoryListener *listener,
+                                     MemoryRegionSection *section)
+{
+    VFIOContainer *container =
+        container_of(listener, VFIOContainer, prereg_listener);
+
+    if (!memory_region_is_ram(section->mr)) {
+        return;
+    }
+
+    vfio_dma_unmap_ram_section(container, section);
+}
+
 static void vfio_listener_region_add(MemoryListener *listener,
                                      MemoryRegionSection *section)
 {
@@ -709,10 +781,11 @@ static void vfio_listener_region_add(MemoryListener 
*listener,
     memory_region_ref(section->mr);
 
     if (memory_region_is_iommu(section->mr)) {
+        IOMMUNotify notify;
         VFIOGuestIOMMU *giommu;
         IOMMUMemoryRegion *iommu_mr = IOMMU_MEMORY_REGION(section->mr);
         bool nested;
-        int iommu_idx;
+        int iommu_idx, flags;
 
         trace_vfio_listener_region_add_iommu(iova, end);
 
@@ -738,15 +811,26 @@ static void vfio_listener_region_add(MemoryListener 
*listener,
         llend = int128_sub(llend, int128_one());
         iommu_idx = memory_region_iommu_attrs_to_index(iommu_mr,
                                                        MEMTXATTRS_UNSPECIFIED);
-        iommu_notifier_init(&giommu->n, vfio_iommu_map_notify,
-                            IOMMU_NOTIFIER_ALL,
-                            section->offset_within_region,
-                            int128_get64(llend),
-                            iommu_idx);
-        QLIST_INSERT_HEAD(&container->giommu_list, giommu, giommu_next);
 
+        if (container->iommu_type == VFIO_TYPE1_NESTING_IOMMU) {
+            /* IOTLB unmap notifier to propagate guest IOTLB invalidations */
+            flags = IOMMU_NOTIFIER_UNMAP;
+            notify = vfio_iommu_unmap_notify;
+        } else {
+            /* MAP/UNMAP IOTLB notifier */
+            flags = IOMMU_NOTIFIER_ALL;
+            notify = vfio_iommu_map_notify;
+        }
+
+        iommu_notifier_init(&giommu->n, notify, flags,
+                            section->offset_within_region,
+                            int128_get64(llend), iommu_idx);
+        QLIST_INSERT_HEAD(&container->giommu_list, giommu, giommu_next);
         memory_region_register_iommu_notifier(section->mr, &giommu->n);
-        memory_region_iommu_replay(giommu->iommu, &giommu->n);
+
+        if (flags & IOMMU_NOTIFIER_MAP) {
+            memory_region_iommu_replay(giommu->iommu, &giommu->n);
+        }
 
         return;
     }
@@ -835,15 +919,21 @@ static void vfio_listener_region_del(MemoryListener 
*listener,
     }
 }
 
-static const MemoryListener vfio_memory_listener = {
+static MemoryListener vfio_memory_listener = {
     .region_add = vfio_listener_region_add,
     .region_del = vfio_listener_region_del,
 };
 
+static MemoryListener vfio_memory_prereg_listener = {
+    .region_add = vfio_prereg_listener_region_add,
+    .region_del = vfio_prereg_listener_region_del,
+};
+
 static void vfio_listener_release(VFIOContainer *container)
 {
     memory_listener_unregister(&container->listener);
-    if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) {
+    if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU ||
+        container->iommu_type == VFIO_TYPE1_NESTING_IOMMU) {
         memory_listener_unregister(&container->prereg_listener);
     }
 }
@@ -1340,6 +1430,19 @@ static int vfio_connect_container(VFIOGroup *group, 
AddressSpace *as,
         }
         vfio_host_win_add(container, 0, (hwaddr)-1, info.iova_pgsizes);
         container->pgsizes = info.iova_pgsizes;
+
+        if (container->iommu_type == VFIO_TYPE1_NESTING_IOMMU) {
+            container->prereg_listener = vfio_memory_prereg_listener;
+            memory_listener_register(&container->prereg_listener,
+                                     &address_space_memory);
+            if (container->error) {
+                memory_listener_unregister(&container->prereg_listener);
+                ret = container->error;
+                error_setg(errp, "RAM memory listener initialization failed "
+                          " for container");
+                goto free_container_exit;
+            }
+        }
         break;
     }
     case VFIO_SPAPR_TCE_v2_IOMMU:
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index d7a4e1875c..729f1f353e 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -2693,6 +2693,25 @@ static void vfio_unregister_req_notifier(VFIOPCIDevice 
*vdev)
     vdev->req_enabled = false;
 }
 
+static int vfio_iommu_set_pasid_table(PCIBus *bus, int32_t devfn,
+                                      IOMMUConfig *config)
+{
+    PCIDevice *pdev = bus->devices[devfn];
+    VFIOPCIDevice *vdev = DO_UPCAST(VFIOPCIDevice, pdev, pdev);
+    VFIOContainer *container = vdev->vbasedev.group->container;
+    struct vfio_iommu_type1_set_pasid_table info;
+
+    info.argsz = sizeof(info);
+    info.flags = VFIO_PASID_TABLE_FLAG_SET;
+    memcpy(&info.config, &config->pasid_cfg, sizeof(config->pasid_cfg));
+
+    return ioctl(container->fd, VFIO_IOMMU_SET_PASID_TABLE, &info);
+}
+
+static PCIPASIDOps vfio_pci_pasid_ops = {
+    .set_pasid_table = vfio_iommu_set_pasid_table,
+};
+
 static void vfio_realize(PCIDevice *pdev, Error **errp)
 {
     VFIOPCIDevice *vdev = PCI_VFIO(pdev);
@@ -2994,6 +3013,8 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
     vfio_register_req_notifier(vdev);
     vfio_setup_resetfn_quirk(vdev);
 
+    pci_setup_pasid_ops(pdev, &vfio_pci_pasid_ops);
+
     return;
 
 out_teardown:
diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
index 410801de6e..9f1868af2d 100644
--- a/hw/vfio/trace-events
+++ b/hw/vfio/trace-events
@@ -115,6 +115,8 @@ vfio_region_sparse_mmap_header(const char *name, int index, 
int nr_areas) "Devic
 vfio_region_sparse_mmap_entry(int i, unsigned long start, unsigned long end) 
"sparse entry %d [0x%lx - 0x%lx]"
 vfio_get_dev_region(const char *name, int index, uint32_t type, uint32_t 
subtype) "%s index %d, %08x/%0x8"
 vfio_dma_unmap_overflow_workaround(void) ""
+vfio_iommu_addr_inv_iotlb(int asid, uint64_t addr, uint64_t size, uint64_t 
nb_granules, bool leaf) "nested IOTLB invalidate asid=%d, addr=0x%"PRIx64" 
granule_size=0x%"PRIx64" nb_granules=0x%"PRIx64" leaf=%d"
+vfio_iommu_asid_inv_iotlb(int asid) "nested IOTLB invalidate asid=%d"
 
 # platform.c
 vfio_platform_base_device_init(char *name, int groupid) "%s belongs to group 
#%d"
-- 
2.20.1