@@ -1776,18 +1776,6 @@ static void migrate_handle_rp_req_pages(MigrationState *ms, const char* rbname,
}
}
-/* Return true to retry, false to quit */
-static bool postcopy_pause_return_path_thread(MigrationState *s)
-{
- trace_postcopy_pause_return_path();
-
- qemu_sem_wait(&s->postcopy_pause_rp_sem);
-
- trace_postcopy_pause_return_path_continued();
-
- return true;
-}
-
static int migrate_handle_rp_recv_bitmap(MigrationState *s, char *block_name)
{
RAMBlock *block = qemu_ram_block_by_name(block_name);
@@ -1871,7 +1859,6 @@ static void *source_return_path_thread(void *opaque)
trace_source_return_path_thread_entry();
rcu_register_thread();
-retry:
while (!ms->rp_state.error && !qemu_file_get_error(rp) &&
migration_is_setup_or_active(ms->state)) {
trace_source_return_path_thread_loop_top();
@@ -1993,26 +1980,7 @@ retry:
}
out:
- res = qemu_file_get_error(rp);
- if (res) {
- if (res && migration_in_postcopy()) {
- /*
- * Maybe there is something we can do: it looks like a
- * network down issue, and we pause for a recovery.
- */
- migration_release_dst_files(ms);
- rp = NULL;
- if (postcopy_pause_return_path_thread(ms)) {
- /*
- * Reload rp, reset the rest. Referencing it is safe since
- * it's reset only by us above, or when migration completes
- */
- rp = ms->rp_state.from_dst_file;
- ms->rp_state.error = false;
- goto retry;
- }
- }
-
+ if (qemu_file_get_error(rp)) {
trace_source_return_path_thread_bad_end();
mark_source_rp_bad(ms);
}
@@ -2023,8 +1991,7 @@ out:
return NULL;
}
-static int open_return_path_on_source(MigrationState *ms,
- bool create_thread)
+static int open_return_path_on_source(MigrationState *ms)
{
ms->rp_state.from_dst_file = qemu_file_get_return_path(ms->to_dst_file);
if (!ms->rp_state.from_dst_file) {
@@ -2033,11 +2000,6 @@ static int open_return_path_on_source(MigrationState *ms,
trace_open_return_path_on_source();
- if (!create_thread) {
- /* We're done */
- return 0;
- }
-
qemu_thread_create(&ms->rp_state.rp_thread, "return path",
source_return_path_thread, ms, QEMU_THREAD_JOINABLE);
ms->rp_state.rp_thread_created = true;
@@ -2077,6 +2039,7 @@ static int await_return_path_close_on_source(MigrationState *ms)
trace_await_return_path_close_on_source_close();
ret = ms->rp_state.error;
+ ms->rp_state.error = false;
trace_migration_return_path_end_after(ret);
return ret;
}
@@ -2552,6 +2515,13 @@ static MigThrError postcopy_pause(MigrationState *s)
qemu_file_shutdown(file);
qemu_fclose(file);
+ /*
+ * We're already pausing, so ignore any errors on the return
+ * path and just wait for the thread to finish. It will be
+ * re-created when we resume.
+ */
+ await_return_path_close_on_source(s);
+
migrate_set_state(&s->state, s->state,
MIGRATION_STATUS_POSTCOPY_PAUSED);
@@ -2569,12 +2539,6 @@ static MigThrError postcopy_pause(MigrationState *s)
if (s->state == MIGRATION_STATUS_POSTCOPY_RECOVER) {
/* Woken up by a recover procedure. Give it a shot */
- /*
- * Firstly, let's wake up the return path now, with a new
- * return path channel.
- */
- qemu_sem_post(&s->postcopy_pause_rp_sem);
-
/* Do the resume logic */
if (postcopy_do_resume(s) == 0) {
/* Let's continue! */
@@ -3264,7 +3228,7 @@ void migrate_fd_connect(MigrationState *s, Error *error_in)
* QEMU uses the return path.
*/
if (migrate_postcopy_ram() || migrate_return_path()) {
- if (open_return_path_on_source(s, !resume)) {
+ if (open_return_path_on_source(s)) {
error_setg(&local_err, "Unable to open return-path for postcopy");
migrate_set_state(&s->state, s->state, MIGRATION_STATUS_FAILED);
migrate_set_error(s, local_err);
@@ -3328,7 +3292,6 @@ static void migration_instance_finalize(Object *obj)
qemu_sem_destroy(&ms->rate_limit_sem);
qemu_sem_destroy(&ms->pause_sem);
qemu_sem_destroy(&ms->postcopy_pause_sem);
- qemu_sem_destroy(&ms->postcopy_pause_rp_sem);
qemu_sem_destroy(&ms->rp_state.rp_sem);
qemu_sem_destroy(&ms->rp_state.rp_pong_acks);
qemu_sem_destroy(&ms->postcopy_qemufile_src_sem);
@@ -3348,7 +3311,6 @@ static void migration_instance_init(Object *obj)
migrate_params_init(&ms->parameters);
qemu_sem_init(&ms->postcopy_pause_sem, 0);
- qemu_sem_init(&ms->postcopy_pause_rp_sem, 0);
qemu_sem_init(&ms->rp_state.rp_sem, 0);
qemu_sem_init(&ms->rp_state.rp_pong_acks, 0);
qemu_sem_init(&ms->rate_limit_sem, 0);
@@ -393,7 +393,6 @@ struct MigrationState {
/* Needed by postcopy-pause state */
QemuSemaphore postcopy_pause_sem;
- QemuSemaphore postcopy_pause_rp_sem;
/*
* Whether we abort the migration if decompression errors are
* detected at the destination. It is left at false for qemu