vfio: Add vfio_listener_log_sync to mark dirty pages

vfio_listener_log_sync gets list of dirty pages from container using
VFIO_IOMMU_GET_DIRTY_BITMAP ioctl and mark those pages dirty when all
devices are stopped and saving state.
Return early for the RAM block section of mapped MMIO region.

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>

2 files changed, 117 insertions, 0 deletions

diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index d4959c036d..0a97fbfefb 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -29,6 +29,7 @@
 #include "hw/vfio/vfio.h"
 #include "exec/address-spaces.h"
 #include "exec/memory.h"
+#include "exec/ram_addr.h"
 #include "hw/hw.h"
 #include "qemu/error-report.h"
 #include "qemu/main-loop.h"
@@ -37,6 +38,7 @@
 #include "sysemu/reset.h"
 #include "trace.h"
 #include "qapi/error.h"
+#include "migration/migration.h"
 
 VFIOGroupList vfio_group_list =
     QLIST_HEAD_INITIALIZER(vfio_group_list);
@@ -287,6 +289,39 @@ const MemoryRegionOps vfio_region_ops = {
 };
 
 /*
+ * Device state interfaces
+ */
+
+static bool vfio_devices_all_stopped_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;
+}
+
+/*
  * DMA - Mapping and unmapping for the "type1" IOMMU interface used on x86
  */
 static int vfio_dma_unmap(VFIOContainer *container,
@@ -812,9 +847,90 @@ static void vfio_listener_region_del(MemoryListener *listener,
     }
 }
 
+static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova,
+                                 uint64_t size, ram_addr_t ram_addr)
+{
+    struct vfio_iommu_type1_dirty_bitmap *dbitmap;
+    struct vfio_iommu_type1_dirty_bitmap_get *range;
+    uint64_t pages;
+    int ret;
+
+    dbitmap = g_malloc0(sizeof(*dbitmap) + sizeof(*range));
+
+    dbitmap->argsz = sizeof(*dbitmap) + sizeof(*range);
+    dbitmap->flags = VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP;
+    range = (struct vfio_iommu_type1_dirty_bitmap_get *)&dbitmap->data;
+    range->iova = iova;
+    range->size = size;
+
+    /*
+     * cpu_physical_memory_set_dirty_lebitmap() expects pages in bitmap of
+     * TARGET_PAGE_SIZE to mark those dirty. Hence set bitmap's pgsize to
+     * TARGET_PAGE_SIZE.
+     */
+    range->bitmap.pgsize = TARGET_PAGE_SIZE;
+
+    pages = TARGET_PAGE_ALIGN(range->size) >> TARGET_PAGE_BITS;
+    range->bitmap.size = ROUND_UP(pages, sizeof(__u64) * BITS_PER_BYTE) /
+                                         BITS_PER_BYTE;
+    range->bitmap.data = g_try_malloc0(range->bitmap.size);
+    if (!range->bitmap.data) {
+        ret = -ENOMEM;
+        goto err_out;
+    }
+
+    ret = ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, dbitmap);
+    if (ret) {
+        error_report("Failed to get dirty bitmap for iova: 0x%"PRIx64
+                " size: 0x%"PRIx64" err: %d", (uint64_t)range->iova,
+                (uint64_t)range->size, errno);
+        goto err_out;
+    }
+
+    cpu_physical_memory_set_dirty_lebitmap((unsigned long *)range->bitmap.data,
+                                            ram_addr, pages);
+
+    trace_vfio_get_dirty_bitmap(container->fd, range->iova, range->size,
+                                range->bitmap.size, ram_addr);
+err_out:
+    g_free(range->bitmap.data);
+    g_free(dbitmap);
+
+    return ret;
+}
+
+static int vfio_sync_dirty_bitmap(VFIOContainer *container,
+                                  MemoryRegionSection *section)
+{
+    ram_addr_t ram_addr;
+
+    ram_addr = memory_region_get_ram_addr(section->mr) +
+               section->offset_within_region;
+
+    return vfio_get_dirty_bitmap(container,
+                       TARGET_PAGE_ALIGN(section->offset_within_address_space),
+                       int128_get64(section->size), ram_addr);
+}
+
+static void vfio_listerner_log_sync(MemoryListener *listener,
+        MemoryRegionSection *section)
+{
+    VFIOContainer *container = container_of(listener, VFIOContainer, listener);
+
+    if (vfio_listener_skipped_section(section) ||
+        !container->dirty_pages_supported) {
+        return;
+    }
+
+    if (vfio_devices_all_stopped_and_saving(container)) {
+        vfio_sync_dirty_bitmap(container, section);
+    }
+}
+
 static const MemoryListener vfio_memory_listener = {
     .region_add = vfio_listener_region_add,
     .region_del = vfio_listener_region_del,
+    .log_sync = vfio_listerner_log_sync,
 };
 
 static void vfio_listener_release(VFIOContainer *container)
diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
index a75b520881..dd991bd8f2 100644
--- a/hw/vfio/trace-events
+++ b/hw/vfio/trace-events
@@ -163,3 +163,4 @@ vfio_load_device_config_state(const char *name) " (%s)"
 vfio_load_state(const char *name, uint64_t data) " (%s) data 0x%"PRIx64
 vfio_load_state_device_data(const char *name, uint64_t data_offset, uint64_t data_size) " (%s) Offset 0x%"PRIx64" size 0x%"PRIx64
 vfio_load_cleanup(const char *name) " (%s)"
+vfio_get_dirty_bitmap(int fd, uint64_t iova, uint64_t size, uint64_t bitmap_size, uint64_t start) "container fd=%d, iova=0x%"PRIx64" size= 0x%"PRIx64" bitmap_size=0x%"PRIx64" start=0x%"PRIx64