Merge tag 'migration-20230509-pull-request' of https://gitlab.com/jua…

…n.quintela/qemu into staging

Migration Pull request (20230509 vintage) take 2

Hi

In this take 2:
- Change uint -> uint32_t to fix mingw32 compilation.

Please apply.
[take 1]
In this PULL request:
- 1st part of colo support for multifd (lukas)
- 1st part of disabling colo option (vladimir)

Please, apply.

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEGJn/jt6/WMzuA0uC9IfvGFhy1yMFAmRb3dgACgkQ9IfvGFhy
# 1yNLBxAAwHiAOdSPS7TqJXH2/PkBKsd42XMtWzC9UowZ6SUdQi0Q2bQUBnygJ8BA
# 59yLOTPdwUhaPWk4KsyKM2znOCJ+f9MF5V4QXbyILf1WCAq6d+mtPwArnYF1TRwi
# XIewVDeRopdOO5lnWGcfAKZZ5WIDzA/bn6NiGLi+pQa5HGyk84Bk+tFa8kJI6xBL
# 5CWfhNTcxDNYRFg/z/9YVirkuxIXEEL6VEeRFV+pmFuj05q9bysWJkLFoEcFNawO
# gp1foHDkU7wHmHDJ3D4AVTm3TW641ft1wdlHIHZRoOiIIu3EUOoDEVVsaCfdxrY8
# pPJZ5m37wb52GIaCJmigG8rkHxIJ8xKLk4HKu4umDqFq5jZQ2krnnj7AkQhpp7p2
# aEIOXJQQq7XCsKpuvSUIexPv4gbN5SEYKi7XKoOPe3sZ03Rkn0I5xY3KSyMQMamP
# jtk8tNlRA+9Wug82eb/FtIKDj3//4SbuQOJEdRXjKJBldd3mtWTT/FRj/8oo96/p
# hmTu/cGDrP5qgtWpz0kKI/xaBf8at1nwpDgdEzOjRw4zf6xQHFjbXgJ7tQBH/JUI
# T3A9pdiXN6QdRupcWUSV0iJsfS/5i3mOUTA/C529qGXabSnZzfMK+unL/I8N02yt
# 83o7jSg22etMjaS1c+VuDmzKCAfuZloDZv2Bms/+yM/8k8Xe5S4=
# =vbqf
# -----END PGP SIGNATURE-----
# gpg: Signature made Wed 10 May 2023 07:09:28 PM BST
# gpg:                using RSA key 1899FF8EDEBF58CCEE034B82F487EF185872D723
# gpg: Good signature from "Juan Quintela <quintela@redhat.com>" [undefined]
# gpg:                 aka "Juan Quintela <quintela@trasno.org>" [undefined]
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# Primary key fingerprint: 1899 FF8E DEBF 58CC EE03  4B82 F487 EF18 5872 D723

* tag 'migration-20230509-pull-request' of https://gitlab.com/juan.quintela/qemu:
  migration: block incoming colo when capability is disabled
  migration: disallow change capabilities in COLO state
  migration: process_incoming_migration_co: simplify code flow around ret
  migration: drop colo_incoming_thread from MigrationIncomingState
  build: move COLO under CONFIG_REPLICATION
  colo: make colo_checkpoint_notify static and provide simpler API
  block/meson.build: prefer positive condition for replication
  multifd: Add the ramblock to MultiFDRecvParams
  ram: Let colo_flush_ram_cache take the bitmap_mutex
  ram: Add public helper to set colo bitmap

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

block/meson.build

@@ -92,7 +92,7 @@ block_ss.add(when: 'CONFIG_WIN32', if_true: files('file-win32.c', 'win32-aio.c')
 block_ss.add(when: 'CONFIG_POSIX', if_true: [files('file-posix.c'), coref, iokit])
 block_ss.add(when: libiscsi, if_true: files('iscsi-opts.c'))
 block_ss.add(when: 'CONFIG_LINUX', if_true: files('nvme.c'))
-if not get_option('replication').disabled()
+if get_option('replication').allowed()
   block_ss.add(files('replication.c'))
 endif
 block_ss.add(when: libaio, if_true: files('linux-aio.c'))

docs/COLO-FT.txt

@@ -210,6 +210,7 @@ children.0=childs0 \
 
 3. On Secondary VM's QEMU monitor, issue command
 {"execute":"qmp_capabilities"}
+{"execute": "migrate-set-capabilities", "arguments": {"capabilities": [ {"capability": "x-colo", "state": true } ] } }
 {"execute": "nbd-server-start", "arguments": {"addr": {"type": "inet", "data": {"host": "0.0.0.0", "port": "9999"} } } }
 {"execute": "nbd-server-add", "arguments": {"device": "parent0", "writable": true } }
 

hmp-commands.hx

@@ -1052,6 +1052,7 @@ SRST
   migration (or once already in postcopy).
 ERST
 
+#ifdef CONFIG_REPLICATION
     {
         .name       = "x_colo_lost_heartbeat",
         .args_type  = "",
@@ -1060,6 +1061,7 @@ ERST
                       "a failover or takeover is needed.",
         .cmd = hmp_x_colo_lost_heartbeat,
     },
+#endif
 
 SRST
 ``x_colo_lost_heartbeat``

include/migration/colo.h

@@ -36,6 +36,13 @@ COLOMode get_colo_mode(void);
 /* failover */
 void colo_do_failover(void);
 
-void colo_checkpoint_notify(void *opaque);
+/*
+ * colo_checkpoint_delay_set
+ *
+ * Handles change of x-checkpoint-delay migration parameter, called from
+ * migrate_params_apply() to notify COLO module about the change.
+ */
+void colo_checkpoint_delay_set(void);
+
 void colo_shutdown(void);
 #endif

migration/colo.c

@@ -26,9 +26,7 @@
 #include "qemu/rcu.h"
 #include "migration/failover.h"
 #include "migration/ram.h"
-#ifdef CONFIG_REPLICATION
 #include "block/replication.h"
-#endif
 #include "net/colo-compare.h"
 #include "net/colo.h"
 #include "block/block.h"
@@ -65,10 +63,27 @@ static bool colo_runstate_is_stopped(void)
     return runstate_check(RUN_STATE_COLO) || !runstate_is_running();
 }
 
+static void colo_checkpoint_notify(void *opaque)
+{
+    MigrationState *s = opaque;
+    int64_t next_notify_time;
+
+    qemu_event_set(&s->colo_checkpoint_event);
+    s->colo_checkpoint_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
+    next_notify_time = s->colo_checkpoint_time + migrate_checkpoint_delay();
+    timer_mod(s->colo_delay_timer, next_notify_time);
+}
+
+void colo_checkpoint_delay_set(void)
+{
+    if (migration_in_colo_state()) {
+        colo_checkpoint_notify(migrate_get_current());
+    }
+}
+
 static void secondary_vm_do_failover(void)
 {
 /* COLO needs enable block-replication */
-#ifdef CONFIG_REPLICATION
     int old_state;
     MigrationIncomingState *mis = migration_incoming_get_current();
     Error *local_err = NULL;
@@ -133,14 +148,10 @@ static void secondary_vm_do_failover(void)
     if (mis->migration_incoming_co) {
         qemu_coroutine_enter(mis->migration_incoming_co);
     }
-#else
-    abort();
-#endif
 }
 
 static void primary_vm_do_failover(void)
 {
-#ifdef CONFIG_REPLICATION
     MigrationState *s = migrate_get_current();
     int old_state;
     Error *local_err = NULL;
@@ -181,9 +192,6 @@ static void primary_vm_do_failover(void)
 
     /* Notify COLO thread that failover work is finished */
     qemu_sem_post(&s->colo_exit_sem);
-#else
-    abort();
-#endif
 }
 
 COLOMode get_colo_mode(void)
@@ -217,7 +225,6 @@ void colo_do_failover(void)
     }
 }
 
-#ifdef CONFIG_REPLICATION
 void qmp_xen_set_replication(bool enable, bool primary,
                              bool has_failover, bool failover,
                              Error **errp)
@@ -271,7 +278,6 @@ void qmp_xen_colo_do_checkpoint(Error **errp)
     /* Notify all filters of all NIC to do checkpoint */
     colo_notify_filters_event(COLO_EVENT_CHECKPOINT, errp);
 }
-#endif
 
 COLOStatus *qmp_query_colo_status(Error **errp)
 {
@@ -435,15 +441,11 @@ static int colo_do_checkpoint_transaction(MigrationState *s,
     }
     qemu_mutex_lock_iothread();
 
-#ifdef CONFIG_REPLICATION
     replication_do_checkpoint_all(&local_err);
     if (local_err) {
         qemu_mutex_unlock_iothread();
         goto out;
     }
-#else
-        abort();
-#endif
 
     colo_send_message(s->to_dst_file, COLO_MESSAGE_VMSTATE_SEND, &local_err);
     if (local_err) {
@@ -561,15 +563,11 @@ static void colo_process_checkpoint(MigrationState *s)
     object_unref(OBJECT(bioc));
 
     qemu_mutex_lock_iothread();
-#ifdef CONFIG_REPLICATION
     replication_start_all(REPLICATION_MODE_PRIMARY, &local_err);
     if (local_err) {
         qemu_mutex_unlock_iothread();
         goto out;
     }
-#else
-        abort();
-#endif
 
     vm_start();
     qemu_mutex_unlock_iothread();
@@ -644,17 +642,6 @@ static void colo_process_checkpoint(MigrationState *s)
     }
 }
 
-void colo_checkpoint_notify(void *opaque)
-{
-    MigrationState *s = opaque;
-    int64_t next_notify_time;
-
-    qemu_event_set(&s->colo_checkpoint_event);
-    s->colo_checkpoint_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
-    next_notify_time = s->colo_checkpoint_time + migrate_checkpoint_delay();
-    timer_mod(s->colo_delay_timer, next_notify_time);
-}
-
 void migrate_start_colo_process(MigrationState *s)
 {
     qemu_mutex_unlock_iothread();
@@ -748,7 +735,6 @@ static void colo_incoming_process_checkpoint(MigrationIncomingState *mis,
         return;
     }
 
-#ifdef CONFIG_REPLICATION
     replication_get_error_all(&local_err);
     if (local_err) {
         error_propagate(errp, local_err);
@@ -765,9 +751,6 @@ static void colo_incoming_process_checkpoint(MigrationIncomingState *mis,
         qemu_mutex_unlock_iothread();
         return;
     }
-#else
-    abort();
-#endif
     /* Notify all filters of all NIC to do checkpoint */
     colo_notify_filters_event(COLO_EVENT_CHECKPOINT, &local_err);
 
@@ -874,15 +857,11 @@ void *colo_process_incoming_thread(void *opaque)
     object_unref(OBJECT(bioc));
 
     qemu_mutex_lock_iothread();
-#ifdef CONFIG_REPLICATION
     replication_start_all(REPLICATION_MODE_SECONDARY, &local_err);
     if (local_err) {
         qemu_mutex_unlock_iothread();
         goto out;
     }
-#else
-        abort();
-#endif
     vm_start();
     qemu_mutex_unlock_iothread();
     trace_colo_vm_state_change("stop", "run");

migration/meson.build

@@ -13,8 +13,6 @@ softmmu_ss.add(files(
   'block-dirty-bitmap.c',
   'channel.c',
   'channel-block.c',
-  'colo-failover.c',
-  'colo.c',
   'exec.c',
   'fd.c',
   'global_state.c',
@@ -33,6 +31,10 @@ softmmu_ss.add(files(
   'threadinfo.c',
 ), gnutls)
 
+if get_option('replication').allowed()
+  softmmu_ss.add(files('colo-failover.c', 'colo.c'))
+endif
+
 softmmu_ss.add(when: rdma, if_true: files('rdma.c'))
 if get_option('live_block_migration').allowed()
   softmmu_ss.add(files('block.c'))

migration/migration-hmp-cmds.c

@@ -643,13 +643,15 @@ void hmp_migrate_start_postcopy(Monitor *mon, const QDict *qdict)
     hmp_handle_error(mon, err);
 }
 
+#ifdef CONFIG_REPLICATION
 void hmp_x_colo_lost_heartbeat(Monitor *mon, const QDict *qdict)
 {
     Error *err = NULL;
 
     qmp_x_colo_lost_heartbeat(&err);
     hmp_handle_error(mon, err);
 }
+#endif
 
 typedef struct HMPMigrationStatus {
     QEMUTimer *timer;

migration/migration.c

@@ -392,6 +392,18 @@ void migration_incoming_disable_colo(void)
 
 int migration_incoming_enable_colo(void)
 {
+#ifndef CONFIG_REPLICATION
+    error_report("ENABLE_COLO command come in migration stream, but COLO "
+                 "module is not built in");
+    return -ENOTSUP;
+#endif
+
+    if (!migrate_colo()) {
+        error_report("ENABLE_COLO command come in migration stream, but c-colo "
+                     "capability is not set");
+        return -EINVAL;
+    }
+
     if (ram_block_discard_disable(true)) {
         error_report("COLO: cannot disable RAM discard");
         return -EBUSY;
@@ -536,32 +548,34 @@ process_incoming_migration_co(void *opaque)
         /* Else if something went wrong then just fall out of the normal exit */
     }
 
+    if (ret < 0) {
+        error_report("load of migration failed: %s", strerror(-ret));
+        goto fail;
+    }
+
     /* we get COLO info, and know if we are in COLO mode */
-    if (!ret && migration_incoming_colo_enabled()) {
+    if (migration_incoming_colo_enabled()) {
+        QemuThread colo_incoming_thread;
+
         /* Make sure all file formats throw away their mutable metadata */
         bdrv_activate_all(&local_err);
         if (local_err) {
             error_report_err(local_err);
             goto fail;
         }
 
-        qemu_thread_create(&mis->colo_incoming_thread, "COLO incoming",
+        qemu_thread_create(&colo_incoming_thread, "COLO incoming",
              colo_process_incoming_thread, mis, QEMU_THREAD_JOINABLE);
-        mis->have_colo_incoming_thread = true;
         qemu_coroutine_yield();
 
         qemu_mutex_unlock_iothread();
         /* Wait checkpoint incoming thread exit before free resource */
-        qemu_thread_join(&mis->colo_incoming_thread);
+        qemu_thread_join(&colo_incoming_thread);
         qemu_mutex_lock_iothread();
         /* We hold the global iothread lock, so it is safe here */
         colo_release_ram_cache();
     }
 
-    if (ret < 0) {
-        error_report("load of migration failed: %s", strerror(-ret));
-        goto fail;
-    }
     mis->bh = qemu_bh_new(process_incoming_migration_bh, mis);
     qemu_bh_schedule(mis->bh);
     mis->migration_incoming_co = NULL;
@@ -2777,10 +2791,7 @@ static void migration_iteration_finish(MigrationState *s)
         runstate_set(RUN_STATE_POSTMIGRATE);
         break;
     case MIGRATION_STATUS_COLO:
-        if (!migrate_colo()) {
-            error_report("%s: critical error: calling COLO code without "
-                         "COLO enabled", __func__);
-        }
+        assert(migrate_colo());
         migrate_start_colo_process(s);
         s->vm_was_running = true;
         /* Fallthrough */

migration/migration.h

@@ -162,8 +162,6 @@ struct MigrationIncomingState {
 
     int state;
 
-    bool have_colo_incoming_thread;
-    QemuThread colo_incoming_thread;
     /* The coroutine we should enter (back) after failover */
     Coroutine *migration_incoming_co;
     QemuSemaphore colo_incoming_sem;

migration/multifd.c

@@ -281,7 +281,6 @@ static void multifd_send_fill_packet(MultiFDSendParams *p)
 static int multifd_recv_unfill_packet(MultiFDRecvParams *p, Error **errp)
 {
     MultiFDPacket_t *packet = p->packet;
-    RAMBlock *block;
     int i;
 
     packet->magic = be32_to_cpu(packet->magic);
@@ -331,21 +330,21 @@ static int multifd_recv_unfill_packet(MultiFDRecvParams *p, Error **errp)
 
     /* make sure that ramblock is 0 terminated */
     packet->ramblock[255] = 0;
-    block = qemu_ram_block_by_name(packet->ramblock);
-    if (!block) {
+    p->block = qemu_ram_block_by_name(packet->ramblock);
+    if (!p->block) {
         error_setg(errp, "multifd: unknown ram block %s",
                    packet->ramblock);
         return -1;
     }
 
-    p->host = block->host;
+    p->host = p->block->host;
     for (i = 0; i < p->normal_num; i++) {
         uint64_t offset = be64_to_cpu(packet->offset[i]);
 
-        if (offset > (block->used_length - p->page_size)) {
+        if (offset > (p->block->used_length - p->page_size)) {
             error_setg(errp, "multifd: offset too long %" PRIu64
                        " (max " RAM_ADDR_FMT ")",
-                       offset, block->used_length);
+                       offset, p->block->used_length);
             return -1;
         }
         p->normal[i] = offset;

migration/multifd.h

@@ -175,6 +175,8 @@ typedef struct {
     uint32_t next_packet_size;
     /* packets sent through this channel */
     uint64_t num_packets;
+    /* ramblock */
+    RAMBlock *block;
     /* ramblock host address */
     uint8_t *host;
     /* non zero pages recv through this channel */

migration/options.c

@@ -598,7 +598,7 @@ void qmp_migrate_set_capabilities(MigrationCapabilityStatusList *params,
     MigrationCapabilityStatusList *cap;
     bool new_caps[MIGRATION_CAPABILITY__MAX];
 
-    if (migration_is_running(s->state)) {
+    if (migration_is_running(s->state) || migration_in_colo_state()) {
         error_setg(errp, QERR_MIGRATION_ACTIVE);
         return;
     }
@@ -1253,9 +1253,7 @@ static void migrate_params_apply(MigrateSetParameters *params, Error **errp)
 
     if (params->has_x_checkpoint_delay) {
         s->parameters.x_checkpoint_delay = params->x_checkpoint_delay;
-        if (migration_in_colo_state()) {
-            colo_checkpoint_notify(s);
-        }
+        colo_checkpoint_delay_set();
     }
 
     if (params->has_block_incremental) {