@@ -148,6 +148,7 @@ MigrationIncomingState *migration_incoming_get_current(void)
qemu_mutex_init(&mis_current.rp_mutex);
qemu_event_init(&mis_current.main_thread_load_event, false);
qemu_sem_init(&mis_current.postcopy_pause_sem_dst, 0);
+ qemu_sem_init(&mis_current.postcopy_pause_sem_fault, 0);
once = true;
}
return &mis_current;
@@ -64,6 +64,7 @@ struct MigrationIncomingState {
/* notify PAUSED postcopy incoming migrations to try to continue */
QemuSemaphore postcopy_pause_sem_dst;
+ QemuSemaphore postcopy_pause_sem_fault;
};
MigrationIncomingState *migration_incoming_get_current(void);
@@ -500,6 +500,17 @@ static int ram_block_enable_notify(const char *block_name, void *host_addr,
return 0;
}
+static bool postcopy_pause_fault_thread(MigrationIncomingState *mis)
+{
+ trace_postcopy_pause_fault_thread();
+
+ qemu_sem_wait(&mis->postcopy_pause_sem_fault);
+
+ trace_postcopy_pause_fault_thread_continued();
+
+ return true;
+}
+
/*
* Handle faults detected by the USERFAULT markings
*/
@@ -547,6 +558,22 @@ static void *postcopy_ram_fault_thread(void *opaque)
}
}
+ if (!mis->to_src_file) {
+ /*
+ * Possibly someone tells us that the return path is
+ * broken already using the event. We should hold until
+ * the channel is rebuilt.
+ */
+ if (postcopy_pause_fault_thread(mis)) {
+ last_rb = NULL;
+ /* Continue to read the userfaultfd */
+ } else {
+ error_report("%s: paused but don't allow to continue",
+ __func__);
+ break;
+ }
+ }
+
ret = read(mis->userfault_fd, &msg, sizeof(msg));
if (ret != sizeof(msg)) {
if (errno == EAGAIN) {
@@ -586,18 +613,33 @@ static void *postcopy_ram_fault_thread(void *opaque)
qemu_ram_get_idstr(rb),
rb_offset);
+retry:
/*
* Send the request to the source - we want to request one
* of our host page sizes (which is >= TPS)
*/
if (rb != last_rb) {
last_rb = rb;
- migrate_send_rp_req_pages(mis, qemu_ram_get_idstr(rb),
- rb_offset, qemu_ram_pagesize(rb));
+ ret = migrate_send_rp_req_pages(mis, qemu_ram_get_idstr(rb),
+ rb_offset, qemu_ram_pagesize(rb));
} else {
/* Save some space */
- migrate_send_rp_req_pages(mis, NULL,
- rb_offset, qemu_ram_pagesize(rb));
+ ret = migrate_send_rp_req_pages(mis, NULL,
+ rb_offset, qemu_ram_pagesize(rb));
+ }
+
+ if (ret) {
+ /* May be network failure, try to wait for recovery */
+ if (ret == -EIO && postcopy_pause_fault_thread(mis)) {
+ /* We got reconnected somehow, try to continue */
+ last_rb = NULL;
+ goto retry;
+ } else {
+ /* This is a unavoidable fault */
+ error_report("%s: migrate_send_rp_req_pages() get %d",
+ __func__, ret);
+ break;
+ }
}
}
trace_postcopy_ram_fault_thread_exit();
@@ -2039,6 +2039,9 @@ static bool postcopy_pause_incoming(MigrationIncomingState *mis)
mis->to_src_file = NULL;
qemu_mutex_unlock(&mis->rp_mutex);
+ /* Notify the fault thread for the invalidated file handle */
+ postcopy_fault_thread_notify(mis);
+
error_report("Detected IO failure for postcopy. "
"Migration paused.");
@@ -101,6 +101,8 @@ open_return_path_on_source_continue(void) ""
postcopy_start(void) ""
postcopy_pause_return_path(void) ""
postcopy_pause_return_path_continued(void) ""
+postcopy_pause_fault_thread(void) ""
+postcopy_pause_fault_thread_continued(void) ""
postcopy_pause_continued(void) ""
postcopy_pause_incoming(void) ""
postcopy_pause_incoming_continued(void) ""