migration: poll the cm event while wait RDMA work request completion

If the peer qemu is crashed, the qemu_rdma_wait_comp_channel function
maybe loop forever. so we should also poll the cm event fd, and when
receive RDMA_CM_EVENT_DISCONNECTED and RDMA_CM_EVENT_DEVICE_REMOVAL,
we consider some error happened.

Signed-off-by: Lidong Chen <lidongchen@tencent.com>
Signed-off-by: Gal Shachaf <galsha@mellanox.com>
Signed-off-by: Aviad Yehezkel <aviadye@mellanox.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
This commit is contained in:
Lidong Chen 2018-08-06 21:29:33 +08:00 committed by Juan Quintela
parent 5d5f4d8436
commit d5882995a1

View File

@ -1489,6 +1489,9 @@ static uint64_t qemu_rdma_poll(RDMAContext *rdma, uint64_t *wr_id_out,
*/
static int qemu_rdma_wait_comp_channel(RDMAContext *rdma)
{
struct rdma_cm_event *cm_event;
int ret = -1;
/*
* Coroutine doesn't start until migration_fd_process_incoming()
* so don't yield unless we know we're running inside of a coroutine.
@ -1505,13 +1508,37 @@ static int qemu_rdma_wait_comp_channel(RDMAContext *rdma)
* without hanging forever.
*/
while (!rdma->error_state && !rdma->received_error) {
GPollFD pfds[1];
GPollFD pfds[2];
pfds[0].fd = rdma->comp_channel->fd;
pfds[0].events = G_IO_IN | G_IO_HUP | G_IO_ERR;
pfds[0].revents = 0;
pfds[1].fd = rdma->channel->fd;
pfds[1].events = G_IO_IN | G_IO_HUP | G_IO_ERR;
pfds[1].revents = 0;
/* 0.1s timeout, should be fine for a 'cancel' */
switch (qemu_poll_ns(pfds, 1, 100 * 1000 * 1000)) {
switch (qemu_poll_ns(pfds, 2, 100 * 1000 * 1000)) {
case 2:
case 1: /* fd active */
if (pfds[0].revents) {
return 0;
}
if (pfds[1].revents) {
ret = rdma_get_cm_event(rdma->channel, &cm_event);
if (!ret) {
rdma_ack_cm_event(cm_event);
}
error_report("receive cm event while wait comp channel,"
"cm event is %d", cm_event->event);
if (cm_event->event == RDMA_CM_EVENT_DISCONNECTED ||
cm_event->event == RDMA_CM_EVENT_DEVICE_REMOVAL) {
return -EPIPE;
}
}
break;
case 0: /* Timeout, go around again */
break;