[Qemu-devel] [RFC V2 4/4] vifo: introduce new VFIO ioctl VFIO_IOMMU_GET_DIRTY_BITMAP

[Yulei Zhang]

New VFIO ioctl VFIO_IOMMU_GET_DIRTY_BITMAP is used to fetch the
bitmap of pinned memory in iommu container, we need copy those
memory to the target during the migration as they are dirtied by
mdev devices.

Signed-off-by: Yulei Zhang <address@hidden>
---
 hw/vfio/common.c           | 32 ++++++++++++++++++++++++++++++++
 linux-headers/linux/vfio.h | 14 ++++++++++++++
 2 files changed, 46 insertions(+)

diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index f3ba9b9..54d43d5 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -35,6 +35,7 @@
 #include "sysemu/kvm.h"
 #include "trace.h"
 #include "qapi/error.h"
+#include "exec/ram_addr.h"
 
 struct vfio_group_head vfio_group_list =
     QLIST_HEAD_INITIALIZER(vfio_group_list);
@@ -603,9 +604,40 @@ static void vfio_listener_region_del(MemoryListener 
*listener,
     }
 }
 
+static void vfio_log_sync(MemoryListener *listener,
+                          MemoryRegionSection *section)
+{
+    VFIOContainer *container = container_of(listener, VFIOContainer, listener);
+    VFIOGroup *group = QLIST_FIRST(&container->group_list);
+    VFIODevice *vbasedev;
+    QLIST_FOREACH(vbasedev, &group->device_list, next) {
+       if (vbasedev->device_state == VFIO_DEVICE_START)
+               return;
+    }
+
+    struct vfio_iommu_get_dirty_bitmap *d;
+    ram_addr_t size = int128_get64(section->size);
+    unsigned long page_nr = size >> TARGET_PAGE_BITS;
+    unsigned long bitmap_size = (BITS_TO_LONGS(page_nr) + 1) * sizeof(unsigned 
long);
+    d = g_malloc0(sizeof(*d) + bitmap_size);
+    d->start_addr = section->offset_within_address_space;
+    d->page_nr = page_nr;
+
+    if (ioctl(container->fd, VFIO_IOMMU_GET_DIRTY_BITMAP, d)) {
+        error_report("vfio: Failed to fetch dirty pages for migration\n");
+        goto exit;
+    }
+
+    cpu_physical_memory_set_dirty_lebitmap((unsigned long*)&d->dirty_bitmap, 
d->start_addr, d->page_nr);
+
+exit:
+    g_free(d);
+}
+
 static const MemoryListener vfio_memory_listener = {
     .region_add = vfio_listener_region_add,
     .region_del = vfio_listener_region_del,
+    .log_sync = vfio_log_sync,
 };
 
 static void vfio_listener_release(VFIOContainer *container)
diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h
index dbbe7e1..cf3d163 100644
--- a/linux-headers/linux/vfio.h
+++ b/linux-headers/linux/vfio.h
@@ -553,6 +553,20 @@ struct vfio_iommu_type1_dma_unmap {
 #define VFIO_IOMMU_ENABLE      _IO(VFIO_TYPE, VFIO_BASE + 15)
 #define VFIO_IOMMU_DISABLE     _IO(VFIO_TYPE, VFIO_BASE + 16)
 
+/**
+ * VFIO_IOMMU_GET_DIRTY_BITMAP - _IOW(VFIO_TYPE, VFIO_BASE + 17,
+ *                                 struct vfio_iommu_get_dirty_bitmap)
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+struct vfio_iommu_get_dirty_bitmap{
+       __u64          start_addr;
+       __u64          page_nr;
+       __u8           dirty_bitmap[];
+};
+
+#define VFIO_IOMMU_GET_DIRTY_BITMAP _IO(VFIO_TYPE, VFIO_BASE + 17)
+
 /* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
 
 /*
-- 
2.7.4