@@ -199,13 +199,18 @@ static void vhost_scsi_realize(DeviceState *dev, Error **errp)
goto close_fd;
}
- error_setg(&vsc->migration_blocker,
- "vhost-scsi does not support migration");
- migrate_add_blocker(vsc->migration_blocker, &err);
- if (err) {
- error_propagate(errp, err);
- error_free(vsc->migration_blocker);
- goto close_fd;
+ if (!vsc->migratable) {
+ error_setg(&vsc->migration_blocker,
+ "vhost-scsi does not support migration in all cases. "
+ "When external environment supports it (Orchestrator migrates "
+ "target SCSI device state or use shared storage over network), "
+ "set 'migratable' property to true to enable migration.");
+ migrate_add_blocker(vsc->migration_blocker, &err);
+ if (err) {
+ error_propagate(errp, err);
+ error_free(vsc->migration_blocker);
+ goto close_fd;
+ }
}
vsc->dev.nvqs = VHOST_SCSI_VQ_NUM_FIXED + vs->conf.num_queues;
@@ -230,7 +235,9 @@ static void vhost_scsi_realize(DeviceState *dev, Error **errp)
return;
free_vqs:
- migrate_del_blocker(vsc->migration_blocker);
+ if (!vsc->migratable) {
+ migrate_del_blocker(vsc->migration_blocker);
+ }
g_free(vsc->dev.vqs);
close_fd:
close(vhostfd);
@@ -243,8 +250,10 @@ static void vhost_scsi_unrealize(DeviceState *dev, Error **errp)
VHostSCSICommon *vsc = VHOST_SCSI_COMMON(dev);
struct vhost_virtqueue *vqs = vsc->dev.vqs;
- migrate_del_blocker(vsc->migration_blocker);
- error_free(vsc->migration_blocker);
+ if (!vsc->migratable) {
+ migrate_del_blocker(vsc->migration_blocker);
+ error_free(vsc->migration_blocker);
+ }
/* This will stop vhost backend. */
vhost_scsi_set_status(vdev, 0);
@@ -268,6 +277,7 @@ static Property vhost_scsi_properties[] = {
DEFINE_PROP_BIT64("t10_pi", VHostSCSICommon, host_features,
VIRTIO_SCSI_F_T10_PI,
false),
+ DEFINE_PROP_BOOL("migratable", VHostSCSICommon, migratable, false),
DEFINE_PROP_END_OF_LIST(),
};
@@ -36,6 +36,7 @@ typedef struct VHostSCSICommon {
int target;
int lun;
uint64_t host_features;
+ bool migratable;
} VHostSCSICommon;
int vhost_scsi_common_start(VHostSCSICommon *vsc);
In order to perform a valid migration of a vhost-scsi device, the following requirements must be met: (1) The virtio-scsi device state needs to be saved & loaded. (2) The vhost backend must be stopped before virtio-scsi device state is saved: (2.1) Sync vhost backend state to virtio-scsi device state. (2.2) No further I/O requests are made by vhost backend to target SCSI device. (2.3) No further guest memory access takes place after VM is stopped. (3) Requests in-flight to target SCSI device are completed before migration handover. (4) Target SCSI device state needs to be saved & loaded into the destination host target SCSI device. Previous commit ("vhost-scsi: Add VMState descriptor") add support to save & load the device state using VMState. This meets requirement (1). When VM is stopped by migration thread (On Pre-Copy complete), the following code path is executed: migration_completion() -> vm_stop_force_state() -> vm_stop() -> do_vm_stop(). do_vm_stop() calls first pause_all_vcpus() which pause all guest vCPUs and then call vm_state_notify(). In case of vhost-scsi device, this will lead to the following code path to be executed: vm_state_notify() -> virtio_vmstate_change() -> virtio_set_status() -> vhost_scsi_set_status() -> vhost_scsi_stop(). vhost_scsi_stop() then calls vhost_scsi_clear_endpoint() and vhost_scsi_common_stop(). vhost_scsi_clear_endpoint() sends VHOST_SCSI_CLEAR_ENDPOINT ioctl to vhost backend which will reach kernel's vhost_scsi_clear_endpoint() which process all pending I/O requests and wait for them to complete (vhost_scsi_flush()). This meets requirement (3). vhost_scsi_common_stop() will stop the vhost backend. As part of this stop, dirty-bitmap is synced and vhost backend state is synced with virtio-scsi device state. As at this point guest vCPUs are already paused, this meets requirement (2). At this point we are left with requirement (4) which is target SCSI device specific and therefore cannot be done by QEMU. Which is the main reason why vhost-scsi adds a migration blocker. However, as this can be handled either by an external orchestrator or by using shared-storage (i.e. iSCSI), there is no reason to limit the orchestrator from being able to explictly specify it wish to enable migration even when VM have a vhost-scsi device. Considering all the above, this commit allows orchestrator to explictly specify that it is responsbile for taking care of requirement (4) and therefore vhost-scsi should not add a migration blocker. Reviewed-by: Nir Weiner <nir.weiner@oracle.com> Reviewed-by: Bijan Mottahedeh <bijan.mottahedeh@oracle.com> Signed-off-by: Liran Alon <liran.alon@oracle.com> --- hw/scsi/vhost-scsi.c | 30 ++++++++++++++++++--------- include/hw/virtio/vhost-scsi-common.h | 1 + 2 files changed, 21 insertions(+), 10 deletions(-)