[PATCH V7 22/29] vfio-pci: recover from unmap-all-vaddr failure

[Steve Sistare]

If vfio_cpr_save fails to unmap all vaddr's, then recover by walking all
flat sections to restore the vaddr for each.  Do so by invoking the
vfio listener callback, and passing a new "replay" flag that tells it
to replay a mapping without re-allocating new userland data structures.

Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
---
 hw/vfio/common.c              | 65 ++++++++++++++++++++++++++++++++-----------
 hw/vfio/cpr.c                 | 41 +++++++++++++++++++++++++--
 include/hw/vfio/vfio-common.h |  2 +-
 3 files changed, 88 insertions(+), 20 deletions(-)

diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 90f66ad..f2b4a81 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -878,15 +878,35 @@ static void 
vfio_unregister_ram_discard_listener(VFIOContainer *container,
     g_free(vrdl);
 }
 
+static VFIORamDiscardListener *vfio_find_ram_discard_listener(
+    VFIOContainer *container, MemoryRegionSection *section)
+{
+    VFIORamDiscardListener *vrdl = NULL;
+
+    QLIST_FOREACH(vrdl, &container->vrdl_list, next) {
+        if (vrdl->mr == section->mr &&
+            vrdl->offset_within_address_space ==
+            section->offset_within_address_space) {
+            break;
+        }
+    }
+
+    if (!vrdl) {
+        hw_error("vfio: Trying to sync missing RAM discard listener");
+        /* does not return */
+    }
+    return vrdl;
+}
+
 static void vfio_listener_region_add(MemoryListener *listener,
                                      MemoryRegionSection *section)
 {
     VFIOContainer *container = container_of(listener, VFIOContainer, listener);
-    vfio_container_region_add(container, section);
+    vfio_container_region_add(container, section, false);
 }
 
 void vfio_container_region_add(VFIOContainer *container,
-                               MemoryRegionSection *section)
+                               MemoryRegionSection *section, bool replay)
 {
     hwaddr iova, end;
     Int128 llend, llsize;
@@ -1009,6 +1029,22 @@ void vfio_container_region_add(VFIOContainer *container,
 
         trace_vfio_listener_region_add_iommu(iova, end);
 
+        if (replay) {
+            hwaddr as_offset = section->offset_within_address_space;
+            hwaddr iommu_offset = as_offset - section->offset_within_region;
+
+            QLIST_FOREACH(giommu, &container->giommu_list, giommu_next) {
+                if (giommu->iommu == iommu_mr &&
+                    giommu->iommu_offset == iommu_offset) {
+                    memory_region_iommu_replay(giommu->iommu, &giommu->n);
+                    return;
+                }
+            }
+            error_report("Container cannot find iommu region %s offset %lx",
+                memory_region_name(section->mr), iommu_offset);
+            goto fail;
+        }
+
         /*
          * FIXME: For VFIO iommu types which have KVM acceleration to
          * avoid bouncing all map/unmaps through qemu this way, this
@@ -1059,7 +1095,15 @@ void vfio_container_region_add(VFIOContainer *container,
      * about changes.
      */
     if (memory_region_has_ram_discard_manager(section->mr)) {
-        vfio_register_ram_discard_listener(container, section);
+        if (replay)  {
+            VFIORamDiscardListener *vrdl =
+                vfio_find_ram_discard_listener(container, section);
+            if (vfio_ram_discard_notify_populate(&vrdl->listener, section)) {
+                error_report("ram_discard_manager_replay_populated failed");
+            }
+        } else {
+            vfio_register_ram_discard_listener(container, section);
+        }
         return;
     }
 
@@ -1385,19 +1429,8 @@ static int 
vfio_sync_ram_discard_listener_dirty_bitmap(VFIOContainer *container,
                                                    MemoryRegionSection 
*section)
 {
     RamDiscardManager *rdm = 
memory_region_get_ram_discard_manager(section->mr);
-    VFIORamDiscardListener *vrdl = NULL;
-
-    QLIST_FOREACH(vrdl, &container->vrdl_list, next) {
-        if (vrdl->mr == section->mr &&
-            vrdl->offset_within_address_space ==
-            section->offset_within_address_space) {
-            break;
-        }
-    }
-
-    if (!vrdl) {
-        hw_error("vfio: Trying to sync missing RAM discard listener");
-    }
+    VFIORamDiscardListener *vrdl =
+        vfio_find_ram_discard_listener(container, section);
 
     /*
      * We only want/can synchronize the bitmap for actually mapped parts -
diff --git a/hw/vfio/cpr.c b/hw/vfio/cpr.c
index 2c39cd5..ea673ea 100644
--- a/hw/vfio/cpr.c
+++ b/hw/vfio/cpr.c
@@ -29,6 +29,14 @@ vfio_dma_unmap_vaddr_all(VFIOContainer *container, Error 
**errp)
     return 0;
 }
 
+static int
+vfio_region_remap(MemoryRegionSection *section, void *handle, Error **errp)
+{
+    VFIOContainer *container = handle;
+    vfio_container_region_add(container, section, true);
+    return 0;
+}
+
 bool vfio_is_cpr_capable(VFIOContainer *container, Error **errp)
 {
     if (!ioctl(container->fd, VFIO_CHECK_EXTENSION, VFIO_UPDATE_VADDR) ||
@@ -48,20 +56,47 @@ int vfio_cpr_save(Error **errp)
 {
     ERRP_GUARD();
     VFIOAddressSpace *space;
-    VFIOContainer *container;
+    VFIOContainer *container, *last_container;
 
     QLIST_FOREACH(space, &vfio_address_spaces, list) {
         QLIST_FOREACH(container, &space->containers, next) {
             if (!vfio_is_cpr_capable(container, errp)) {
                 return -1;
             }
+        }
+    }
+
+    QLIST_FOREACH(space, &vfio_address_spaces, list) {
+        QLIST_FOREACH(container, &space->containers, next) {
             if (vfio_dma_unmap_vaddr_all(container, errp)) {
-                return -1;
+                goto unwind;
             }
         }
     }
-
     return 0;
+
+unwind:
+    last_container = container;
+    QLIST_FOREACH(space, &vfio_address_spaces, list) {
+        QLIST_FOREACH(container, &space->containers, next) {
+            Error *err;
+
+            if (container == last_container) {
+                break;
+            }
+
+            /* Set reused so vfio_dma_map restores vaddr */
+            container->reused = true;
+            if (address_space_flat_for_each_section(space->as,
+                                                    vfio_region_remap,
+                                                    container, &err)) {
+                error_prepend(errp, "%s", error_get_pretty(err));
+                error_free(err);
+            }
+            container->reused = false;
+        }
+    }
+    return -1;
 }
 
 /*
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index bc23c29..af960dc 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -243,7 +243,7 @@ vfio_get_device_info_cap(struct vfio_device_info *info, 
uint16_t id);
 extern const MemoryListener vfio_prereg_listener;
 void vfio_listener_register(VFIOContainer *container);
 void vfio_container_region_add(VFIOContainer *container,
-                               MemoryRegionSection *section);
+                               MemoryRegionSection *section, bool replay);
 
 int vfio_spapr_create_window(VFIOContainer *container,
                              MemoryRegionSection *section,
-- 
1.8.3.1