[Qemu-devel] [RFC v5 18/29] vfio: Pass stage 1 MSI bindings to the host

[Eric Auger <eric.auger@redhat.com>]

We register the stage1 MSI bindings when enabling the vectors
and we unregister them on container disconnection.

Signed-off-by: Eric Auger <eric.auger@redhat.com>

---

v4 -> v5:
- use VFIO_IOMMU_SET_MSI_BINDING

v2 -> v3:
- only register the notifier if the IOMMU translates MSIs
- record the msi bindings in a container list and unregister on
  container release
---
 hw/vfio/common.c              | 52 +++++++++++++++++++++++++++++++++++
 hw/vfio/pci.c                 | 51 +++++++++++++++++++++++++++++++++-
 hw/vfio/trace-events          |  2 ++
 include/hw/vfio/vfio-common.h |  9 ++++++
 4 files changed, 113 insertions(+), 1 deletion(-)

diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index bd975c5b83..4bbce6a43a 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -490,6 +490,56 @@ static void vfio_iommu_unmap_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
     }
 }
 
+int vfio_iommu_set_msi_binding(VFIOContainer *container,
+                               IOMMUTLBEntry *iotlb)
+{
+    struct vfio_iommu_type1_set_msi_binding ustruct;
+    VFIOMSIBinding *binding;
+    int ret;
+
+    QLIST_FOREACH(binding, &container->msibinding_list, next) {
+        if (binding->iova == iotlb->iova) {
+            return 0;
+        }
+    }
+
+    ustruct.argsz = sizeof(struct vfio_iommu_type1_set_msi_binding);
+    ustruct.iova = iotlb->iova;
+    ustruct.flags = VFIO_IOMMU_BIND_MSI;
+    ustruct.gpa = iotlb->translated_addr;
+    ustruct.size = iotlb->addr_mask + 1;
+    ret = ioctl(container->fd, VFIO_IOMMU_SET_MSI_BINDING , &ustruct);
+    if (ret) {
+        error_report("%s: failed to register the stage1 MSI binding (%m)",
+                     __func__);
+        return ret;
+    }
+    binding =  g_new0(VFIOMSIBinding, 1);
+    binding->iova = ustruct.iova;
+    binding->gpa = ustruct.gpa;
+    binding->size = ustruct.size;
+
+    QLIST_INSERT_HEAD(&container->msibinding_list, binding, next);
+    return 0;
+}
+
+static void vfio_container_unbind_msis(VFIOContainer *container)
+{
+    VFIOMSIBinding *binding, *tmp;
+
+    QLIST_FOREACH_SAFE(binding, &container->msibinding_list, next, tmp) {
+        struct vfio_iommu_type1_set_msi_binding ustruct;
+
+        /* the MSI doorbell is not used anymore, unregister it */
+        ustruct.argsz = sizeof(struct vfio_iommu_type1_set_msi_binding);
+        ustruct.flags = VFIO_IOMMU_UNBIND_MSI;
+        ustruct.iova = binding->iova;
+        ioctl(container->fd, VFIO_IOMMU_SET_MSI_BINDING , &ustruct);
+        QLIST_REMOVE(binding, next);
+        g_free(binding);
+    }
+}
+
 static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
 {
     VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n);
@@ -1589,6 +1639,8 @@ static void vfio_disconnect_container(VFIOGroup *group)
             g_free(giommu);
         }
 
+        vfio_container_unbind_msis(container);
+
         trace_vfio_disconnect_container(container->fd);
         close(container->fd);
         g_free(container);
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 729f1f353e..45e007575e 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -359,6 +359,49 @@ static void vfio_msi_interrupt(void *opaque)
     notify(&vdev->pdev, nr);
 }
 
+static int vfio_register_msi_binding(VFIOPCIDevice *vdev, int vector_n)
+{
+    VFIOContainer *container = vdev->vbasedev.group->container;
+    PCIDevice *dev = &vdev->pdev;
+    AddressSpace *as = pci_device_iommu_address_space(dev);
+    MSIMessage msg = pci_get_msi_message(dev, vector_n);
+    IOMMUMemoryRegionClass *imrc;
+    IOMMUMemoryRegion *iommu_mr;
+    bool msi_translate = false, nested = false;;
+    IOMMUTLBEntry entry;
+
+    if (as == &address_space_memory) {
+        return 0;
+    }
+
+    iommu_mr = IOMMU_MEMORY_REGION(as->root);
+    memory_region_iommu_get_attr(iommu_mr, IOMMU_ATTR_MSI_TRANSLATE,
+                                 (void *)&msi_translate);
+    memory_region_iommu_get_attr(iommu_mr, IOMMU_ATTR_VFIO_NESTED,
+                                 (void *)&nested);
+    imrc = memory_region_get_iommu_class_nocheck(iommu_mr);
+
+    if (!nested || !msi_translate) {
+        return 0;
+    }
+
+    /* MSI doorbell address is translated by an IOMMU */
+
+    rcu_read_lock();
+    entry = imrc->translate(iommu_mr, msg.address, IOMMU_WO, 0);
+    rcu_read_unlock();
+
+    if (entry.perm == IOMMU_NONE) {
+        return -ENOENT;
+    }
+
+    trace_vfio_register_msi_binding(vdev->vbasedev.name, vector_n,
+                                    msg.address, entry.translated_addr);
+
+    vfio_iommu_set_msi_binding(container, &entry);
+    return 0;
+}
+
 static int vfio_enable_vectors(VFIOPCIDevice *vdev, bool msix)
 {
     struct vfio_irq_set *irq_set;
@@ -376,7 +419,7 @@ static int vfio_enable_vectors(VFIOPCIDevice *vdev, bool msix)
     fds = (int32_t *)&irq_set->data;
 
     for (i = 0; i < vdev->nr_vectors; i++) {
-        int fd = -1;
+        int ret, fd = -1;
 
         /*
          * MSI vs MSI-X - The guest has direct access to MSI mask and pending
@@ -391,6 +434,12 @@ static int vfio_enable_vectors(VFIOPCIDevice *vdev, bool msix)
             } else {
                 fd = event_notifier_get_fd(&vdev->msi_vectors[i].kvm_interrupt);
             }
+            ret = vfio_register_msi_binding(vdev, i);
+            if (ret) {
+                error_report("%s failed to register S1 MSI binding "
+                             "for vector %d(%d)", __func__, i, ret);
+                return ret;
+            }
         }
 
         fds[i] = fd;
diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
index 9f1868af2d..5de97a8882 100644
--- a/hw/vfio/trace-events
+++ b/hw/vfio/trace-events
@@ -117,6 +117,8 @@ vfio_get_dev_region(const char *name, int index, uint32_t type, uint32_t subtype
 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"
+vfio_register_msi_binding(const char *name, int vector, uint64_t giova, uint64_t gdb) "%s: register vector %d gIOVA=0x%"PRIx64 "-> gDB=0x%"PRIx64" stage 1 mapping"
+vfio_unregister_msi_binding(const char *name, int vector, uint64_t giova) "%s: unregister vector %d gIOVA=0x%"PRIx64 " stage 1 mapping"
 
 # platform.c
 vfio_platform_base_device_init(char *name, int groupid) "%s belongs to group #%d"
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index 9107bd41c0..a88b4dd986 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -63,6 +63,13 @@ typedef struct VFIOAddressSpace {
     QLIST_ENTRY(VFIOAddressSpace) list;
 } VFIOAddressSpace;
 
+typedef struct VFIOMSIBinding {
+    hwaddr iova;
+    hwaddr gpa;
+    hwaddr size;
+    QLIST_ENTRY(VFIOMSIBinding) next;
+} VFIOMSIBinding;
+
 struct VFIOGroup;
 
 typedef struct VFIOContainer {
@@ -77,6 +84,7 @@ typedef struct VFIOContainer {
     QLIST_HEAD(, VFIOGuestIOMMU) giommu_list;
     QLIST_HEAD(, VFIOHostDMAWindow) hostwin_list;
     QLIST_HEAD(, VFIOGroup) group_list;
+    QLIST_HEAD(, VFIOMSIBinding) msibinding_list;
     QLIST_ENTRY(VFIOContainer) next;
 } VFIOContainer;
 
@@ -178,6 +186,7 @@ VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **errp);
 void vfio_put_group(VFIOGroup *group);
 int vfio_get_device(VFIOGroup *group, const char *name,
                     VFIODevice *vbasedev, Error **errp);
+int vfio_iommu_set_msi_binding(VFIOContainer *container, IOMMUTLBEntry *entry);
 
 extern const MemoryRegionOps vfio_region_ops;
 typedef QLIST_HEAD(VFIOGroupList, VFIOGroup) VFIOGroupList;
-- 
2.20.1