vfio/common: Add device dirty page bitmap sync

Add device dirty page bitmap sync functionality. This uses the device
DMA logging uAPI to sync dirty page bitmap from the device.

Device dirty page bitmap sync is used only if all devices within a
container support device dirty page tracking.

Signed-off-by: Avihai Horon <avihaih@nvidia.com>
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/r/20230307125450.62409-13-joao.m.martins@oracle.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index ae81af6d326990a2b61bc27895ab5f7af39d40b8..334c62585829d1a53900120cb6f56aa7d99ae4cd 100644 (file)
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -339,6 +339,9 @@ static int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size)
     return 0;
 }
 
+static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova,
+                                 uint64_t size, ram_addr_t ram_addr);
+
 bool vfio_mig_active(void)
 {
     VFIOGroup *group;
@@ -562,10 +565,16 @@ static int vfio_dma_unmap(VFIOContainer *container,
         .iova = iova,
         .size = size,
     };
+    bool need_dirty_sync = false;
+    int ret;
+
+    if (iotlb && vfio_devices_all_running_and_mig_active(container)) {
+        if (!vfio_devices_all_device_dirty_tracking(container) &&
+            container->dirty_pages_supported) {
+            return vfio_dma_unmap_bitmap(container, iova, size, iotlb);
+        }
 
-    if (iotlb && container->dirty_pages_supported &&
-        vfio_devices_all_running_and_mig_active(container)) {
-        return vfio_dma_unmap_bitmap(container, iova, size, iotlb);
+        need_dirty_sync = true;
     }
 
     while (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) {
@@ -591,10 +600,12 @@ static int vfio_dma_unmap(VFIOContainer *container,
         return -errno;
     }
 
-    if (iotlb && vfio_devices_all_running_and_mig_active(container)) {
-        cpu_physical_memory_set_dirty_range(iotlb->translated_addr, size,
-                                            tcg_enabled() ? DIRTY_CLIENTS_ALL :
-                                            DIRTY_CLIENTS_NOCODE);
+    if (need_dirty_sync) {
+        ret = vfio_get_dirty_bitmap(container, iova, size,
+                                    iotlb->translated_addr);
+        if (ret) {
+            return ret;
+        }
     }
 
     return 0;
@@ -1595,6 +1606,58 @@ static void vfio_listener_log_global_stop(MemoryListener *listener)
     }
 }
 
+static int vfio_device_dma_logging_report(VFIODevice *vbasedev, hwaddr iova,
+                                          hwaddr size, void *bitmap)
+{
+    uint64_t buf[DIV_ROUND_UP(sizeof(struct vfio_device_feature) +
+                        sizeof(struct vfio_device_feature_dma_logging_report),
+                        sizeof(__u64))] = {};
+    struct vfio_device_feature *feature = (struct vfio_device_feature *)buf;
+    struct vfio_device_feature_dma_logging_report *report =
+        (struct vfio_device_feature_dma_logging_report *)feature->data;
+
+    report->iova = iova;
+    report->length = size;
+    report->page_size = qemu_real_host_page_size();
+    report->bitmap = (__u64)(uintptr_t)bitmap;
+
+    feature->argsz = sizeof(buf);
+    feature->flags = VFIO_DEVICE_FEATURE_GET |
+                     VFIO_DEVICE_FEATURE_DMA_LOGGING_REPORT;
+
+    if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) {
+        return -errno;
+    }
+
+    return 0;
+}
+
+static int vfio_devices_query_dirty_bitmap(VFIOContainer *container,
+                                           VFIOBitmap *vbmap, hwaddr iova,
+                                           hwaddr size)
+{
+    VFIODevice *vbasedev;
+    VFIOGroup *group;
+    int ret;
+
+    QLIST_FOREACH(group, &container->group_list, container_next) {
+        QLIST_FOREACH(vbasedev, &group->device_list, next) {
+            ret = vfio_device_dma_logging_report(vbasedev, iova, size,
+                                                 vbmap->bitmap);
+            if (ret) {
+                error_report("%s: Failed to get DMA logging report, iova: "
+                             "0x%" HWADDR_PRIx ", size: 0x%" HWADDR_PRIx
+                             ", err: %d (%s)",
+                             vbasedev->name, iova, size, ret, strerror(-ret));
+
+                return ret;
+            }
+        }
+    }
+
+    return 0;
+}
+
 static int vfio_query_dirty_bitmap(VFIOContainer *container, VFIOBitmap *vbmap,
                                    hwaddr iova, hwaddr size)
 {
@@ -1635,10 +1698,12 @@ static int vfio_query_dirty_bitmap(VFIOContainer *container, VFIOBitmap *vbmap,
 static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova,
                                  uint64_t size, ram_addr_t ram_addr)
 {
+    bool all_device_dirty_tracking =
+        vfio_devices_all_device_dirty_tracking(container);
     VFIOBitmap vbmap;
     int ret;
 
-    if (!container->dirty_pages_supported) {
+    if (!container->dirty_pages_supported && !all_device_dirty_tracking) {
         cpu_physical_memory_set_dirty_range(ram_addr, size,
                                             tcg_enabled() ? DIRTY_CLIENTS_ALL :
                                             DIRTY_CLIENTS_NOCODE);
@@ -1650,7 +1715,12 @@ static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova,
         return ret;
     }
 
-    ret = vfio_query_dirty_bitmap(container, &vbmap, iova, size);
+    if (all_device_dirty_tracking) {
+        ret = vfio_devices_query_dirty_bitmap(container, &vbmap, iova, size);
+    } else {
+        ret = vfio_query_dirty_bitmap(container, &vbmap, iova, size);
+    }
+
     if (ret) {
         goto out;
     }