3 files changed, 56 insertions, 8 deletions

diff --git a/migration/migration.c b/migration/migration.c
index ae2025d9d8..37fc4fb3e2 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -3464,8 +3464,12 @@ static void migration_completion(MigrationState *s)
         qemu_savevm_state_complete_postcopy(s->to_dst_file);
         qemu_mutex_unlock_iothread();
 
-        /* Shutdown the postcopy fast path thread */
-        if (migrate_postcopy_preempt()) {
+        /*
+         * Shutdown the postcopy fast path thread.  This is only needed
+         * when dest QEMU binary is old (7.1/7.2).  QEMU 8.0+ doesn't need
+         * this.
+         */
+        if (migrate_postcopy_preempt() && s->preempt_pre_7_2) {
             postcopy_preempt_shutdown_file(s);
         }
 
@@ -4443,6 +4447,8 @@ static Property migration_properties[] = {
                       decompress_error_check, true),
     DEFINE_PROP_UINT8("x-clear-bitmap-shift", MigrationState,
                       clear_bitmap_shift, CLEAR_BITMAP_SHIFT_DEFAULT),
+    DEFINE_PROP_BOOL("x-preempt-pre-7-2", MigrationState,
+                     preempt_pre_7_2, false),
 
     /* Migration parameters */
     DEFINE_PROP_UINT8("x-compress-level", MigrationState,
diff --git a/migration/migration.h b/migration/migration.h
index 2da2f8a164..67baba2184 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -65,6 +65,12 @@ typedef struct {
     bool all_zero;
 } PostcopyTmpPage;
 
+typedef enum {
+    PREEMPT_THREAD_NONE = 0,
+    PREEMPT_THREAD_CREATED,
+    PREEMPT_THREAD_QUIT,
+} PreemptThreadStatus;
+
 /* State for the incoming migration */
 struct MigrationIncomingState {
     QEMUFile *from_src_file;
@@ -124,7 +130,12 @@ struct MigrationIncomingState {
     QemuSemaphore postcopy_qemufile_dst_done;
     /* Postcopy priority thread is used to receive postcopy requested pages */
     QemuThread postcopy_prio_thread;
-    bool postcopy_prio_thread_created;
+    /*
+     * Always set by the main vm load thread only, but can be read by the
+     * postcopy preempt thread.  "volatile" makes sure all reads will be
+     * uptodate across cores.
+     */
+    volatile PreemptThreadStatus preempt_thread_status;
     /*
      * Used to sync between the ram load main thread and the fast ram load
      * thread.  It protects postcopy_qemufile_dst, which is the postcopy
@@ -364,6 +375,27 @@ struct MigrationState {
      * do not trigger spurious decompression errors.
      */
     bool decompress_error_check;
+    /*
+     * This variable only affects behavior when postcopy preempt mode is
+     * enabled.
+     *
+     * When set:
+     *
+     * - postcopy preempt src QEMU instance will generate an EOS message at
+     *   the end of migration to shut the preempt channel on dest side.
+     *
+     * When clear:
+     *
+     * - postcopy preempt src QEMU instance will _not_ generate an EOS
+     *   message at the end of migration, the dest qemu will shutdown the
+     *   channel itself.
+     *
+     * NOTE: See message-id <ZBoShWArKDPpX/D7@work-vm> on qemu-devel
+     * mailing list for more information on the possible race.  Everyone
+     * should probably just keep this value untouched after set by the
+     * machine type (or the default).
+     */
+    bool preempt_pre_7_2;
 
     /*
      * This decides the size of guest memory chunk that will be used
diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index 41c0713650..263bab75ec 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -568,9 +568,14 @@ int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis)
 {
     trace_postcopy_ram_incoming_cleanup_entry();
 
-    if (mis->postcopy_prio_thread_created) {
+    if (mis->preempt_thread_status == PREEMPT_THREAD_CREATED) {
+        /* Notify the fast load thread to quit */
+        mis->preempt_thread_status = PREEMPT_THREAD_QUIT;
+        if (mis->postcopy_qemufile_dst) {
+            qemu_file_shutdown(mis->postcopy_qemufile_dst);
+        }
         qemu_thread_join(&mis->postcopy_prio_thread);
-        mis->postcopy_prio_thread_created = false;
+        mis->preempt_thread_status = PREEMPT_THREAD_NONE;
     }
 
     if (mis->have_fault_thread) {
@@ -1203,7 +1208,7 @@ int postcopy_ram_incoming_setup(MigrationIncomingState *mis)
          */
         postcopy_thread_create(mis, &mis->postcopy_prio_thread, "fault-fast",
                                postcopy_preempt_thread, QEMU_THREAD_JOINABLE);
-        mis->postcopy_prio_thread_created = true;
+        mis->preempt_thread_status = PREEMPT_THREAD_CREATED;
     }
 
     trace_postcopy_ram_enable_notify();
@@ -1652,6 +1657,11 @@ static void postcopy_pause_ram_fast_load(MigrationIncomingState *mis)
     trace_postcopy_pause_fast_load_continued();
 }
 
+static bool preempt_thread_should_run(MigrationIncomingState *mis)
+{
+    return mis->preempt_thread_status != PREEMPT_THREAD_QUIT;
+}
+
 void *postcopy_preempt_thread(void *opaque)
 {
     MigrationIncomingState *mis = opaque;
@@ -1671,11 +1681,11 @@ void *postcopy_preempt_thread(void *opaque)
 
     /* Sending RAM_SAVE_FLAG_EOS to terminate this thread */
     qemu_mutex_lock(&mis->postcopy_prio_thread_mutex);
-    while (1) {
+    while (preempt_thread_should_run(mis)) {
         ret = ram_load_postcopy(mis->postcopy_qemufile_dst,
                                 RAM_CHANNEL_POSTCOPY);
         /* If error happened, go into recovery routine */
-        if (ret) {
+        if (ret && preempt_thread_should_run(mis)) {
             postcopy_pause_ram_fast_load(mis);
         } else {
             /* We're done */