[Qemu-devel] [PATCH v8 22/54] Rework loadvm path for subloops

["Dr. David Alan Gilbert (git)" <dgilbert@redhat.com>]

From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>

Postcopy needs to have two migration streams loading concurrently;
one from memory (with the device state) and the other from the fd
with the memory transactions.

Split the core of qemu_loadvm_state out so we can use it for both.

Allow the inner loadvm loop to quit and cause the parent loops to
exit as well.

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Amit Shah <amit.shah@redhat.com>
---
 include/migration/migration.h |   6 ++
 migration/migration.c         |   2 +
 migration/savevm.c            | 141 ++++++++++++++++++++++--------------------
 trace-events                  |   4 ++
 4 files changed, 86 insertions(+), 67 deletions(-)

diff --git a/include/migration/migration.h b/include/migration/migration.h
index 571466b..3dc95f4 100644
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -57,6 +57,12 @@ typedef QLIST_HEAD(, LoadStateEntry) LoadStateEntry_Head;
 struct MigrationIncomingState {
     QEMUFile *from_src_file;
 
+    /*
+     * Free at the start of the main state load, set as the main thread finishes
+     * loading state.
+     */
+    QemuEvent main_thread_load_event;
+
     QEMUFile *to_src_file;
     QemuMutex rp_mutex;    /* We send replies from multiple threads */
 
diff --git a/migration/migration.c b/migration/migration.c
index 26bcb25..6691a28 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -90,12 +90,14 @@ MigrationIncomingState *migration_incoming_state_new(QEMUFile* f)
     mis_current->from_src_file = f;
     QLIST_INIT(&mis_current->loadvm_handlers);
     qemu_mutex_init(&mis_current->rp_mutex);
+    qemu_event_init(&mis_current->main_thread_load_event, false);
 
     return mis_current;
 }
 
 void migration_incoming_state_destroy(void)
 {
+    qemu_event_destroy(&mis_current->main_thread_load_event);
     loadvm_free_handlers(mis_current);
     g_free(mis_current);
     mis_current = NULL;
diff --git a/migration/savevm.c b/migration/savevm.c
index f51cbcd..f9baaa8 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -1049,11 +1049,18 @@ static SaveStateEntry *find_se(const char *idstr, int instance_id)
     return NULL;
 }
 
+enum LoadVMExitCodes {
+    /* Allow a command to quit all layers of nested loadvm loops */
+    LOADVM_QUIT     =  1,
+};
+
+static int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis);
 /**
  * loadvm_process_command: Process an incoming 'QEMU_VM_COMMAND'
  *
- * Returns: 0 on success, negative on error (in which case it will issue an
- *          error message).
+ * Returns: 0 on just a normal return
+ *          LOADVM_QUIT All good, but exit the loop
+ *          <0 error (in which case it will issue an error message).
  * @f: The stream to read the command data from.
  */
 static int loadvm_process_command(QEMUFile *f)
@@ -1159,47 +1166,10 @@ void loadvm_free_handlers(MigrationIncomingState *mis)
     }
 }
 
-int qemu_loadvm_state(QEMUFile *f)
+static int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis)
 {
-    MigrationIncomingState *mis = migration_incoming_get_current();
-    Error *local_err = NULL;
     uint8_t section_type;
-    unsigned int v;
     int ret;
-    int file_error_after_eof = -1;
-
-    if (qemu_savevm_state_blocked(&local_err)) {
-        error_report_err(local_err);
-        return -EINVAL;
-    }
-
-    v = qemu_get_be32(f);
-    if (v != QEMU_VM_FILE_MAGIC) {
-        error_report("Not a migration stream");
-        return -EINVAL;
-    }
-
-    v = qemu_get_be32(f);
-    if (v == QEMU_VM_FILE_VERSION_COMPAT) {
-        error_report("SaveVM v2 format is obsolete and don't work anymore");
-        return -ENOTSUP;
-    }
-    if (v != QEMU_VM_FILE_VERSION) {
-        error_report("Unsupported migration stream version");
-        return -ENOTSUP;
-    }
-
-    if (!savevm_state.skip_configuration) {
-        if (qemu_get_byte(f) != QEMU_VM_CONFIGURATION) {
-            error_report("Configuration section missing");
-            return -EINVAL;
-        }
-        ret = vmstate_load_state(f, &vmstate_configuration, &savevm_state, 0);
-
-        if (ret) {
-            return ret;
-        }
-    }
 
     while ((section_type = qemu_get_byte(f)) != QEMU_VM_EOF) {
         uint32_t instance_id, version_id, section_id;
@@ -1228,16 +1198,14 @@ int qemu_loadvm_state(QEMUFile *f)
             if (se == NULL) {
                 error_report("Unknown savevm section or instance '%s' %d",
                              idstr, instance_id);
-                ret = -EINVAL;
-                goto out;
+                return -EINVAL;
             }
 
             /* Validate version */
             if (version_id > se->version_id) {
                 error_report("savevm: unsupported version %d for '%s' v%d",
                              version_id, idstr, se->version_id);
-                ret = -EINVAL;
-                goto out;
+                return -EINVAL;
             }
 
             /* Add entry */
@@ -1252,11 +1220,10 @@ int qemu_loadvm_state(QEMUFile *f)
             if (ret < 0) {
                 error_report("error while loading state for instance 0x%x of"
                              " device '%s'", instance_id, idstr);
-                goto out;
+                return ret;
             }
             if (!check_section_footer(f, le)) {
-                ret = -EINVAL;
-                goto out;
+                return -EINVAL;
             }
             break;
         case QEMU_VM_SECTION_PART:
@@ -1271,35 +1238,83 @@ int qemu_loadvm_state(QEMUFile *f)
             }
             if (le == NULL) {
                 error_report("Unknown savevm section %d", section_id);
-                ret = -EINVAL;
-                goto out;
+                return -EINVAL;
             }
 
             ret = vmstate_load(f, le->se, le->version_id);
             if (ret < 0) {
                 error_report("error while loading state section id %d(%s)",
                              section_id, le->se->idstr);
-                goto out;
+                return ret;
             }
             if (!check_section_footer(f, le)) {
-                ret = -EINVAL;
-                goto out;
+                return -EINVAL;
             }
             break;
         case QEMU_VM_COMMAND:
             ret = loadvm_process_command(f);
-            if (ret < 0) {
-                goto out;
+            trace_qemu_loadvm_state_section_command(ret);
+            if ((ret < 0) || (ret & LOADVM_QUIT)) {
+                return ret;
             }
             break;
         default:
             error_report("Unknown savevm section type %d", section_type);
-            ret = -EINVAL;
-            goto out;
+            return -EINVAL;
+        }
+    }
+
+    return 0;
+}
+
+int qemu_loadvm_state(QEMUFile *f)
+{
+    MigrationIncomingState *mis = migration_incoming_get_current();
+    Error *local_err = NULL;
+    unsigned int v;
+    int ret;
+
+    if (qemu_savevm_state_blocked(&local_err)) {
+        error_report_err(local_err);
+        return -EINVAL;
+    }
+
+    v = qemu_get_be32(f);
+    if (v != QEMU_VM_FILE_MAGIC) {
+        error_report("Not a migration stream");
+        return -EINVAL;
+    }
+
+    v = qemu_get_be32(f);
+    if (v == QEMU_VM_FILE_VERSION_COMPAT) {
+        error_report("SaveVM v2 format is obsolete and don't work anymore");
+        return -ENOTSUP;
+    }
+    if (v != QEMU_VM_FILE_VERSION) {
+        error_report("Unsupported migration stream version");
+        return -ENOTSUP;
+    }
+
+    if (!savevm_state.skip_configuration) {
+        if (qemu_get_byte(f) != QEMU_VM_CONFIGURATION) {
+            error_report("Configuration section missing");
+            return -EINVAL;
+        }
+        ret = vmstate_load_state(f, &vmstate_configuration, &savevm_state, 0);
+
+        if (ret) {
+            return ret;
         }
     }
 
-    file_error_after_eof = qemu_file_get_error(f);
+    ret = qemu_loadvm_state_main(f, mis);
+    qemu_event_set(&mis->main_thread_load_event);
+
+    trace_qemu_loadvm_state_post_main(ret);
+
+    if (ret == 0) {
+        ret = qemu_file_get_error(f);
+    }
 
     /*
      * Try to read in the VMDESC section as well, so that dumping tools that
@@ -1311,10 +1326,10 @@ int qemu_loadvm_state(QEMUFile *f)
      * We also mustn't read data that isn't there; some transports (RDMA)
      * will stall waiting for that data when the source has already closed.
      */
-    if (should_send_vmdesc()) {
+    if (ret == 0 && should_send_vmdesc()) {
         uint8_t *buf;
         uint32_t size;
-        section_type = qemu_get_byte(f);
+        uint8_t  section_type = qemu_get_byte(f);
 
         if (section_type != QEMU_VM_VMDESCRIPTION) {
             error_report("Expected vmdescription section, but got %d",
@@ -1338,14 +1353,6 @@ int qemu_loadvm_state(QEMUFile *f)
 
     cpu_synchronize_all_post_init();
 
-    ret = 0;
-
-out:
-    if (ret == 0) {
-        /* We may not have a VMDESC section, so ignore relative errors */
-        ret = file_error_after_eof;
-    }
-
     return ret;
 }
 
diff --git a/trace-events b/trace-events
index 5bbfdf7..228f5b6 100644
--- a/trace-events
+++ b/trace-events
@@ -1195,7 +1195,11 @@ virtio_gpu_fence_resp(uint64_t fence) "fence 0x%" PRIx64
 
 # migration/savevm.c
 qemu_loadvm_state_section(unsigned int section_type) "%d"
+qemu_loadvm_state_section_command(int ret) "%d"
 qemu_loadvm_state_section_partend(uint32_t section_id) "%u"
+qemu_loadvm_state_main(void) ""
+qemu_loadvm_state_main_quit_parent(void) ""
+qemu_loadvm_state_post_main(int ret) "%d"
 qemu_loadvm_state_section_startfull(uint32_t section_id, const char *idstr, uint32_t instance_id, uint32_t version_id) "%u(%s) %u %u"
 loadvm_process_command(uint16_t com, uint16_t len) "com=0x%x len=%d"
 loadvm_process_command_ping(uint32_t val) "%x"
-- 
2.5.0