vfio: Add ioctl to get dirty pages bitmap during dma unmap

With vIOMMU, IO virtual address range can get unmapped while in pre-copy
phase of migration. In that case, unmap ioctl should return pages pinned
in that range and QEMU should find its correcponding guest physical
addresses and report those dirty.

Suggested-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
Reviewed-by: Neo Jia <cjia@nvidia.com>
[aw: fix error_report types, fix cpu_physical_memory_set_dirty_lebitmap() cast]
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

1 files changed, 93 insertions, 4 deletions

diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 43e6e89..620358a 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -321,11 +321,95 @@ static bool vfio_devices_all_stopped_and_saving(VFIOContainer *container)
     return true;
 }
 
+static bool vfio_devices_all_running_and_saving(VFIOContainer *container)
+{
+    VFIOGroup *group;
+    VFIODevice *vbasedev;
+    MigrationState *ms = migrate_get_current();
+
+    if (!migration_is_setup_or_active(ms->state)) {
+        return false;
+    }
+
+    QLIST_FOREACH(group, &container->group_list, container_next) {
+        QLIST_FOREACH(vbasedev, &group->device_list, next) {
+            VFIOMigration *migration = vbasedev->migration;
+
+            if (!migration) {
+                return false;
+            }
+
+            if ((migration->device_state & VFIO_DEVICE_STATE_SAVING) &&
+                (migration->device_state & VFIO_DEVICE_STATE_RUNNING)) {
+                continue;
+            } else {
+                return false;
+            }
+        }
+    }
+    return true;
+}
+
+static int vfio_dma_unmap_bitmap(VFIOContainer *container,
+                                 hwaddr iova, ram_addr_t size,
+                                 IOMMUTLBEntry *iotlb)
+{
+    struct vfio_iommu_type1_dma_unmap *unmap;
+    struct vfio_bitmap *bitmap;
+    uint64_t pages = TARGET_PAGE_ALIGN(size) >> TARGET_PAGE_BITS;
+    int ret;
+
+    unmap = g_malloc0(sizeof(*unmap) + sizeof(*bitmap));
+
+    unmap->argsz = sizeof(*unmap) + sizeof(*bitmap);
+    unmap->iova = iova;
+    unmap->size = size;
+    unmap->flags |= VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP;
+    bitmap = (struct vfio_bitmap *)&unmap->data;
+
+    /*
+     * cpu_physical_memory_set_dirty_lebitmap() expects pages in bitmap of
+     * TARGET_PAGE_SIZE to mark those dirty. Hence set bitmap_pgsize to
+     * TARGET_PAGE_SIZE.
+     */
+
+    bitmap->pgsize = TARGET_PAGE_SIZE;
+    bitmap->size = ROUND_UP(pages, sizeof(__u64) * BITS_PER_BYTE) /
+                   BITS_PER_BYTE;
+
+    if (bitmap->size > container->max_dirty_bitmap_size) {
+        error_report("UNMAP: Size of bitmap too big 0x%"PRIx64,
+                     (uint64_t)bitmap->size);
+        ret = -E2BIG;
+        goto unmap_exit;
+    }
+
+    bitmap->data = g_try_malloc0(bitmap->size);
+    if (!bitmap->data) {
+        ret = -ENOMEM;
+        goto unmap_exit;
+    }
+
+    ret = ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, unmap);
+    if (!ret) {
+        cpu_physical_memory_set_dirty_lebitmap((unsigned long *)bitmap->data,
+                iotlb->translated_addr, pages);
+    } else {
+        error_report("VFIO_UNMAP_DMA with DIRTY_BITMAP : %m");
+    }
+
+    g_free(bitmap->data);
+unmap_exit:
+    g_free(unmap);
+    return ret;
+}
+
 /*
  * DMA - Mapping and unmapping for the "type1" IOMMU interface used on x86
  */
 static int vfio_dma_unmap(VFIOContainer *container,
-                          hwaddr iova, ram_addr_t size)
+                          hwaddr iova, ram_addr_t size,
+                          IOMMUTLBEntry *iotlb)
 {
     struct vfio_iommu_type1_dma_unmap unmap = {
         .argsz = sizeof(unmap),
@@ -334,6 +418,11 @@ static int vfio_dma_unmap(VFIOContainer *container,
         .size = size,
     };
 
+    if (iotlb && container->dirty_pages_supported &&
+        vfio_devices_all_running_and_saving(container)) {
+        return vfio_dma_unmap_bitmap(container, iova, size, iotlb);
+    }
+
     while (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) {
         /*
          * The type1 backend has an off-by-one bug in the kernel (71a7d3d78e3c
@@ -381,7 +470,7 @@ static int vfio_dma_map(VFIOContainer *container, hwaddr iova,
      * the VGA ROM space.
      */
     if (ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0 ||
-        (errno == EBUSY && vfio_dma_unmap(container, iova, size) == 0 &&
+        (errno == EBUSY && vfio_dma_unmap(container, iova, size, NULL) == 0 &&
          ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0)) {
         return 0;
     }
@@ -531,7 +620,7 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
                          iotlb->addr_mask + 1, vaddr, ret);
         }
     } else {
-        ret = vfio_dma_unmap(container, iova, iotlb->addr_mask + 1);
+        ret = vfio_dma_unmap(container, iova, iotlb->addr_mask + 1, iotlb);
         if (ret) {
             error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", "
                          "0x%"HWADDR_PRIx") = %d (%m)",
@@ -834,7 +923,7 @@ static void vfio_listener_region_del(MemoryListener *listener,
     }
 
     if (try_unmap) {
-        ret = vfio_dma_unmap(container, iova, int128_get64(llsize));
+        ret = vfio_dma_unmap(container, iova, int128_get64(llsize), NULL);
         if (ret) {
             error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", "
                          "0x%"HWADDR_PRIx") = %d (%m)",