vdpa/ifc: add block device SW live-migration

Add SW live-migration support to block device.
For block device, it is critical that no packet
should be dropped. So when virtio blk device is
paused, make sure hardware last_avail_idx and
last_used_idx are the same. This indicates all
requests have received acks, and no inflight IO.

Signed-off-by: Andy Pei <andy.pei@intel.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>

diff --git a/drivers/vdpa/ifc/base/ifcvf.h b/drivers/vdpa/ifc/base/ifcvf.h
index b6fdfdb055f13e63a131283542d6de729f8a4c68..9d95aaceeaaf7e85f6966363a75dad6425f967b8 100644 (file)
--- a/drivers/vdpa/ifc/base/ifcvf.h
+++ b/drivers/vdpa/ifc/base/ifcvf.h
@@ -63,6 +63,7 @@
 #define IFCVF_MEDIATED_VRING           0x200000000000
 
 #define IFCVF_32_BIT_MASK              0xffffffff
+#define IFCVF_16_BIT_MASK              0xffff
 
 
 #ifndef VHOST_USER_PROTOCOL_F_CONFIG

diff --git a/drivers/vdpa/ifc/ifcvf_vdpa.c b/drivers/vdpa/ifc/ifcvf_vdpa.c
index 61fb427a591b297c128bd870b92cecf1eff432be..0f9db8ae6157514f2a954e8c28af2246034de5f3 100644 (file)
--- a/drivers/vdpa/ifc/ifcvf_vdpa.c
+++ b/drivers/vdpa/ifc/ifcvf_vdpa.c
@@ -316,8 +316,34 @@ vdpa_ifcvf_stop(struct ifcvf_internal *internal)
        uint64_t features = 0;
        uint64_t log_base = 0, log_size = 0;
        uint64_t len;
+       u32 ring_state = 0;
 
        vid = internal->vid;
+
+       /* to make sure no packet is lost for blk device
+        * do not stop until last_avail_idx == last_used_idx
+        */
+       if (internal->hw.device_type == IFCVF_BLK) {
+               for (i = 0; i < hw->nr_vring; i++) {
+                       do {
+                               if (hw->lm_cfg != NULL)
+                                       ring_state = *(u32 *)(hw->lm_cfg +
+                                               IFCVF_LM_RING_STATE_OFFSET +
+                                               i * IFCVF_LM_CFG_SIZE);
+                               hw->vring[i].last_avail_idx =
+                                       (u16)(ring_state & IFCVF_16_BIT_MASK);
+                               hw->vring[i].last_used_idx =
+                                       (u16)(ring_state >> 16);
+                               if (hw->vring[i].last_avail_idx !=
+                                       hw->vring[i].last_used_idx) {
+                                       ifcvf_notify_queue(hw, i);
+                                       usleep(10);
+                               }
+                       } while (hw->vring[i].last_avail_idx !=
+                               hw->vring[i].last_used_idx);
+               }
+       }
+
        ifcvf_stop_hw(hw);
 
        for (i = 0; i < hw->nr_vring; i++)
@@ -641,8 +667,10 @@ m_ifcvf_start(struct ifcvf_internal *internal)
                }
                hw->vring[i].avail = gpa;
 
-               /* Direct I/O for Tx queue, relay for Rx queue */
-               if (i & 1) {
+               /* NET: Direct I/O for Tx queue, relay for Rx queue
+                * BLK: relay every queue
+                */
+               if ((internal->hw.device_type == IFCVF_NET) && (i & 1)) {
                        gpa = hva_to_gpa(vid, (uint64_t)(uintptr_t)vq.used);
                        if (gpa == 0) {
                                DRV_LOG(ERR, "Fail to get GPA for used ring.");
@@ -692,8 +720,12 @@ m_ifcvf_stop(struct ifcvf_internal *internal)
 
        for (i = 0; i < hw->nr_vring; i++) {
                /* synchronize remaining new used entries if any */
-               if ((i & 1) == 0)
+               if (internal->hw.device_type == IFCVF_NET) {
+                       if ((i & 1) == 0)
+                               update_used_ring(internal, i);
+               } else if (internal->hw.device_type == IFCVF_BLK) {
                        update_used_ring(internal, i);
+               }
 
                rte_vhost_get_vhost_vring(vid, i, &vq);
                len = IFCVF_USED_RING_LEN(vq.size);
@@ -755,7 +787,9 @@ vring_relay(void *arg)
                }
        }
 
-       for (qid = 0; qid < q_num; qid += 2) {
+       for (qid = 0; qid < q_num; qid += 1) {
+               if ((internal->hw.device_type == IFCVF_NET) && (qid & 1))
+                       continue;
                ev.events = EPOLLIN | EPOLLPRI;
                /* leave a flag to mark it's for interrupt */
                ev.data.u64 = 1 | qid << 1 |