Add device dirty page tracking start/stop functionality. This uses the
device DMA logging uAPI to start and stop dirty page tracking by device.
Device dirty page tracking 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>
---
hw/vfio/common.c | 173 +++++++++++++++++++++++++++++++++-
hw/vfio/trace-events | 1 +
include/hw/vfio/vfio-common.h | 2 +
3 files changed, 171 insertions(+), 5 deletions(-)
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 811502dbc97c..80f2d287bab5 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -450,6 +450,22 @@ static bool vfio_devices_all_dirty_tracking(VFIOContainer
*container)
return true;
}
+static bool vfio_devices_all_device_dirty_tracking(VFIOContainer *container)
+{
+ VFIOGroup *group;
+ VFIODevice *vbasedev;
+
+ QLIST_FOREACH(group, &container->group_list, container_next) {
+ QLIST_FOREACH(vbasedev, &group->device_list, next) {
+ if (!vbasedev->dirty_pages_supported) {
+ return false;
+ }
+ }
+ }
+
+ return true;
+}
+
/*
* Check if all VFIO devices are running and migration is active, which is
* essentially equivalent to the migration being in pre-copy phase.
@@ -1407,16 +1423,156 @@ static void vfio_dirty_tracking_init(VFIOContainer
*container,
memory_listener_unregister(&dirty.listener);
}
+static void vfio_devices_dma_logging_stop(VFIOContainer *container)
+{
+ uint64_t buf[DIV_ROUND_UP(sizeof(struct vfio_device_feature),
+ sizeof(uint64_t))] = {};
+ struct vfio_device_feature *feature = (struct vfio_device_feature *)buf;
+ VFIODevice *vbasedev;
+ VFIOGroup *group;
+
+ feature->argsz = sizeof(buf);
+ feature->flags = VFIO_DEVICE_FEATURE_SET |
+ VFIO_DEVICE_FEATURE_DMA_LOGGING_STOP;
+
+ QLIST_FOREACH(group, &container->group_list, container_next) {
+ QLIST_FOREACH(vbasedev, &group->device_list, next) {
+ if (!vbasedev->dirty_tracking) {
+ continue;
+ }
+
+ if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) {
+ warn_report("%s: Failed to stop DMA logging, err %d (%s)",
+ vbasedev->name, -errno, strerror(errno));
+ }
+ vbasedev->dirty_tracking = false;
+ }
+ }
+}
+
+static struct vfio_device_feature *
+vfio_device_feature_dma_logging_start_create(VFIOContainer *container,
+ VFIODirtyRanges *tracking)
+{
+ struct vfio_device_feature *feature;
+ size_t feature_size;
+ struct vfio_device_feature_dma_logging_control *control;
+ struct vfio_device_feature_dma_logging_range *ranges;
+
+ feature_size = sizeof(struct vfio_device_feature) +
+ sizeof(struct vfio_device_feature_dma_logging_control);
+ feature = g_try_malloc0(feature_size);
+ if (!feature) {
+ errno = ENOMEM;
+ return NULL;
+ }
+ feature->argsz = feature_size;
+ feature->flags = VFIO_DEVICE_FEATURE_SET |
+ VFIO_DEVICE_FEATURE_DMA_LOGGING_START;
+
+ control = (struct vfio_device_feature_dma_logging_control *)feature->data;
+ control->page_size = qemu_real_host_page_size();
+
+ /*
+ * DMA logging uAPI guarantees to support at least a number of ranges that
+ * fits into a single host kernel base page.
+ */
+ control->num_ranges = !!tracking->max32 + !!tracking->max64;
+ ranges = g_try_new0(struct vfio_device_feature_dma_logging_range,
+ control->num_ranges);
+ if (!ranges) {
+ g_free(feature);
+ errno = ENOMEM;
+
+ return NULL;
+ }
+
+ control->ranges = (__u64)(uintptr_t)ranges;
+ if (tracking->max32) {
+ ranges->iova = tracking->min32;
+ ranges->length = (tracking->max32 - tracking->min32) + 1;
+ ranges++;
+ }
+ if (tracking->max64) {
+ ranges->iova = tracking->min64;
+ ranges->length = (tracking->max64 - tracking->min64) + 1;
+ }
+
+ trace_vfio_device_dirty_tracking_start(control->num_ranges,
+ tracking->min32, tracking->max32,
+ tracking->min64, tracking->max64);
+
+ return feature;
+}
+
+static void vfio_device_feature_dma_logging_start_destroy(
+ struct vfio_device_feature *feature)
+{
+ struct vfio_device_feature_dma_logging_control *control =
+ (struct vfio_device_feature_dma_logging_control *)feature->data;
+ struct vfio_device_feature_dma_logging_range *ranges =
+ (struct vfio_device_feature_dma_logging_range *)(uintptr_t)
control->ranges;
+
+ g_free(ranges);
+ g_free(feature);
+}
+
+static int vfio_devices_dma_logging_start(VFIOContainer *container)
+{
+ struct vfio_device_feature *feature;
+ VFIODirtyRanges ranges;
+ VFIODevice *vbasedev;
+ VFIOGroup *group;
+ int ret = 0;
+
+ vfio_dirty_tracking_init(container, &ranges);
+ feature = vfio_device_feature_dma_logging_start_create(container,
+ &ranges);
+ if (!feature) {
+ return -errno;
+ }
+
+ QLIST_FOREACH(group, &container->group_list, container_next) {
+ QLIST_FOREACH(vbasedev, &group->device_list, next) {
+ if (vbasedev->dirty_tracking) {
+ continue;
+ }
+
+ ret = ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature);
+ if (ret) {
+ ret = -errno;
+ error_report("%s: Failed to start DMA logging, err %d (%s)",
+ vbasedev->name, ret, strerror(errno));
+ goto out;
+ }
+ vbasedev->dirty_tracking = true;
+ }
+ }
+
+out:
+ if (ret) {
+ vfio_devices_dma_logging_stop(container);
+ }
+
+ vfio_device_feature_dma_logging_start_destroy(feature);
+
+ return ret;
+}
+
static void vfio_listener_log_global_start(MemoryListener *listener)
{
VFIOContainer *container = container_of(listener, VFIOContainer,
listener);
- VFIODirtyRanges ranges;
int ret;
- vfio_dirty_tracking_init(container, &ranges);
+ if (vfio_devices_all_device_dirty_tracking(container)) {
+ ret = vfio_devices_dma_logging_start(container);
+ } else {
+ ret = vfio_set_dirty_page_tracking(container, true);
+ }
- ret = vfio_set_dirty_page_tracking(container, true);
if (ret) {
+ error_report("vfio: Could not start dirty page tracking, err: %d (%s)",
+ ret, strerror(-ret));
vfio_set_migration_error(ret);
}
}
@@ -1424,10 +1580,17 @@ static void
vfio_listener_log_global_start(MemoryListener *listener)
static void vfio_listener_log_global_stop(MemoryListener *listener)
{
VFIOContainer *container = container_of(listener, VFIOContainer,
listener);
- int ret;
+ int ret = 0;
+
+ if (vfio_devices_all_device_dirty_tracking(container)) {
+ vfio_devices_dma_logging_stop(container);
+ } else {
+ ret = vfio_set_dirty_page_tracking(container, false);
+ }
- ret = vfio_set_dirty_page_tracking(container, false);
if (ret) {
+ error_report("vfio: Could not stop dirty page tracking, err: %d (%s)",
+ ret, strerror(-ret));
vfio_set_migration_error(ret);
}
}
diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
index dd9fd7b9bddb..bee95dbd977a 100644
--- a/hw/vfio/trace-events
+++ b/hw/vfio/trace-events
@@ -104,6 +104,7 @@ vfio_known_safe_misalignment(const char *name, uint64_t
iova, uint64_t offset_wi
vfio_listener_region_add_no_dma_map(const char *name, uint64_t iova, uint64_t size, uint64_t page_size) "Region
\"%s\" 0x%"PRIx64" size=0x%"PRIx64" is not aligned to 0x%"PRIx64" and cannot be mapped
for DMA"
vfio_listener_region_del(uint64_t start, uint64_t end) "region_del 0x%"PRIx64" -
0x%"PRIx64
vfio_device_dirty_tracking_update(uint64_t start, uint64_t end, uint64_t min, uint64_t max) "section 0x%"PRIx64" -
0x%"PRIx64" -> update [0x%"PRIx64" - 0x%"PRIx64"]"
+vfio_device_dirty_tracking_start(int nr_ranges, uint64_t min32, uint64_t max32, uint64_t min64, uint64_t max64) "nr_ranges
%d 32:[0x%"PRIx64" - 0x%"PRIx64"], 64:[0x%"PRIx64" - 0x%"PRIx64"]"
vfio_disconnect_container(int fd) "close container->fd=%d"
vfio_put_group(int fd) "close group->fd=%d"
vfio_get_device(const char * name, unsigned int flags, unsigned int num_regions,
unsigned int num_irqs) "Device %s flags: %u, regions: %u, irqs: %u"
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index 87524c64a443..9551d2d43025 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -143,6 +143,8 @@ typedef struct VFIODevice {
VFIOMigration *migration;
Error *migration_blocker;
OnOffAuto pre_copy_dirty_page_tracking;
+ bool dirty_pages_supported;
+ bool dirty_tracking;
} VFIODevice;
struct VFIODeviceOps {