Merge tag 'migration-20230518-pull-request' of https://gitlab.com/juan.quintela/qemu into staging

Migration Pull request

Hi

Based on latest reviewed parts of migration:
- Disable colo (vladimir)
- Migration atomic counters (juan)

Please apply.

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEGJn/jt6/WMzuA0uC9IfvGFhy1yMFAmRmXJUACgkQ9IfvGFhy
# 1yNRAxAAjDYJELL34Qovt/WE9qKhYJEvIUGTl1IMWJ22YMFnqIFKRdka57dWoU3P
# 7EK1BHmokEEtzGT7Fe1ecERXsOwQIJDIkDTJ5g8Oc8Jt1iqY1AC8h5T+LghijCar
# mbZ6qWHaSjsg2lmek/xc9quymzFGGK36PSyB5WkaLRviKQn4RIkEDpUaWny7nDbA
# Q8zJJpBqNFqKfC5/DN0ePa3QQscXQJhey3nxqFd8hYp8RFNIV5UJVW5Lf6ombtK7
# atgdWC4ckkfO2z3OsghKeo/UiMFWpPktgBVVMhDLmk+P/E6czc2gfzD6SCvrPKTj
# XowI8hro22HVmq9bEY8PtbjMOfpxrAxer+tM2KR/0O9l3UzUacFsi7KGqCJ1/trQ
# 1tSDjlgyczb8GOgLwwxj8XE+jPHPfVrzCNfDqrBKBNxz6nnZSdZUwhV5mG8FdVtm
# oVVV96BIrNXLl/lIxYIFD/Zyvl8/lrSWQdLkEHTzihYQeXaQfyvPVbV/dOLT4sii
# YUuGCuEhF+DW/qz43G1krwq5/bfxsiZoQzrMV/Odtf0wYQKkabA3KNBIda/vxBCR
# dsLQ7QtmOwKmCzjqw4LUov9vDNYOYr98o7ZqwJ3qeKL4QgFwtEZUFO3VW6UR8fnF
# arVXiTn9wVlkTpu4sT5hLm9400iadhX4Fppji7Ce0tUpLbWbghA=
# =3x32
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu 18 May 2023 10:12:53 AM PDT
# 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-20230518-pull-request' of https://gitlab.com/juan.quintela/qemu:
  migration: Fix duplicated included in meson.build
  migration/multifd: Compute transferred bytes correctly
  migration: We don't need the field rate_limit_used anymore
  migration: Use migration_transferred_bytes() to calculate rate_limit
  migration: Add a trace for migration_transferred_bytes
  migration: Move migration_total_bytes() to migration-stats.c
  migration: Move rate_limit_max and rate_limit_used to migration_stats
  qemu-file: Account for rate_limit usage on qemu_fflush()
  migration: Don't use INT64_MAX for unlimited rate
  migration: process_incoming_migration_co(): move colo part to colo
  migration: split migration_incoming_co
  configure: add --disable-colo-proxy option

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

hw/ppc/spapr.c

@@ -2166,7 +2166,7 @@ static void htab_save_first_pass(QEMUFile *f, SpaprMachineState *spapr,
                 break;
             }
         }
-    } while ((index < htabslots) && !qemu_file_rate_limit(f));
+    } while ((index < htabslots) && !migration_rate_exceeded(f));
 
     if (index >= htabslots) {
         assert(index == htabslots);
@@ -2237,7 +2237,7 @@ static int htab_save_later_pass(QEMUFile *f, SpaprMachineState *spapr,
             assert(index == htabslots);
             index = 0;
         }
-    } while ((examined < htabslots) && (!qemu_file_rate_limit(f) || final));
+    } while ((examined < htabslots) && (!migration_rate_exceeded(f) || final));
 
     if (index >= htabslots) {
         assert(index == htabslots);

hw/s390x/s390-stattrib.c

@@ -209,7 +209,7 @@ static int cmma_save(QEMUFile *f, void *opaque, int final)
         return -ENOMEM;
     }
 
-    while (final ? 1 : qemu_file_rate_limit(f) == 0) {
+    while (final ? 1 : migration_rate_exceeded(f) == 0) {
         reallen = sac->get_stattr(sas, &start_gfn, buflen, buf);
         if (reallen < 0) {
             g_free(buf);

include/migration/colo.h

@@ -28,7 +28,6 @@ bool migration_in_colo_state(void);
 int migration_incoming_enable_colo(void);
 void migration_incoming_disable_colo(void);
 bool migration_incoming_colo_enabled(void);
-void *colo_process_incoming_thread(void *opaque);
 bool migration_incoming_in_colo_state(void);
 
 COLOMode get_colo_mode(void);
@@ -44,5 +43,13 @@ void colo_do_failover(void);
  */
 void colo_checkpoint_delay_set(void);
 
+/*
+ * Starts COLO incoming process. Called from process_incoming_migration_co()
+ * after loading the state.
+ *
+ * Called with BQL locked, may temporary release BQL.
+ */
+int coroutine_fn colo_incoming_co(void);
+
 void colo_shutdown(void);
 #endif

include/migration/qemu-file-types.h

@@ -165,6 +165,16 @@ size_t coroutine_mixed_fn qemu_get_counted_string(QEMUFile *f, char buf[256]);
 
 void qemu_put_counted_string(QEMUFile *f, const char *name);
 
-int qemu_file_rate_limit(QEMUFile *f);
+/**
+ * migration_rate_exceeded: Check if we have exceeded rate for this interval
+ *
+ * Checks if we have already transferred more data that we are allowed
+ * in the current interval.
+ *
+ * @f: QEMUFile used for main migration channel
+ *
+ * Returns if we should stop sending data for this interval.
+ */
+bool migration_rate_exceeded(QEMUFile *f);
 
 #endif

meson_options.txt

@@ -304,6 +304,8 @@ option('live_block_migration', type: 'feature', value: 'auto',
        description: 'block migration in the main migration stream')
 option('replication', type: 'feature', value: 'auto',
        description: 'replication support')
+option('colo_proxy', type: 'feature', value: 'auto',
+       description: 'colo-proxy support')
 option('bochs', type: 'feature', value: 'auto',
        description: 'bochs image format support')
 option('cloop', type: 'feature', value: 'auto',

migration/block-dirty-bitmap.c

@@ -706,7 +706,7 @@ static void bulk_phase(QEMUFile *f, DBMSaveState *s, bool limit)
     QSIMPLEQ_FOREACH(dbms, &s->dbms_list, entry) {
         while (!dbms->bulk_completed) {
             bulk_phase_send_chunk(f, s, dbms);
-            if (limit && qemu_file_rate_limit(f)) {
+            if (limit && migration_rate_exceeded(f)) {
                 return;
             }
         }

migration/block.c

@@ -23,6 +23,7 @@
 #include "block/dirty-bitmap.h"
 #include "migration/misc.h"
 #include "migration.h"
+#include "migration-stats.h"
 #include "migration/register.h"
 #include "qemu-file.h"
 #include "migration/vmstate.h"
@@ -625,7 +626,7 @@ static int flush_blks(QEMUFile *f)
 
     blk_mig_lock();
     while ((blk = QSIMPLEQ_FIRST(&block_mig_state.blk_list)) != NULL) {
-        if (qemu_file_rate_limit(f)) {
+        if (migration_rate_exceeded(f)) {
             break;
         }
         if (blk->ret < 0) {
@@ -762,7 +763,7 @@ static int block_save_iterate(QEMUFile *f, void *opaque)
     /* control the rate of transfer */
     blk_mig_lock();
     while (block_mig_state.read_done * BLK_MIG_BLOCK_SIZE <
-           qemu_file_get_rate_limit(f) &&
+           migration_rate_get() &&
            block_mig_state.submitted < MAX_PARALLEL_IO &&
            (block_mig_state.submitted + block_mig_state.read_done) <
            MAX_IO_BUFFERS) {

migration/colo.c

@@ -145,8 +145,8 @@ static void secondary_vm_do_failover(void)
     qemu_sem_post(&mis->colo_incoming_sem);
 
     /* For Secondary VM, jump to incoming co */
-    if (mis->migration_incoming_co) {
-        qemu_coroutine_enter(mis->migration_incoming_co);
+    if (mis->colo_incoming_co) {
+        qemu_coroutine_enter(mis->colo_incoming_co);
     }
 }
 
@@ -817,7 +817,7 @@ void colo_shutdown(void)
     }
 }
 
-void *colo_process_incoming_thread(void *opaque)
+static void *colo_process_incoming_thread(void *opaque)
 {
     MigrationIncomingState *mis = opaque;
     QEMUFile *fb = NULL;
@@ -918,3 +918,40 @@ out:
     rcu_unregister_thread();
     return NULL;
 }
+
+int coroutine_fn colo_incoming_co(void)
+{
+    MigrationIncomingState *mis = migration_incoming_get_current();
+    Error *local_err = NULL;
+    QemuThread th;
+
+    assert(qemu_mutex_iothread_locked());
+
+    if (!migration_incoming_colo_enabled()) {
+        return 0;
+    }
+
+    /* Make sure all file formats throw away their mutable metadata */
+    bdrv_activate_all(&local_err);
+    if (local_err) {
+        error_report_err(local_err);
+        return -EINVAL;
+    }
+
+    qemu_thread_create(&th, "COLO incoming", colo_process_incoming_thread,
+                       mis, QEMU_THREAD_JOINABLE);
+
+    mis->colo_incoming_co = qemu_coroutine_self();
+    qemu_coroutine_yield();
+    mis->colo_incoming_co = NULL;
+
+    qemu_mutex_unlock_iothread();
+    /* Wait checkpoint incoming thread exit before free resource */
+    qemu_thread_join(&th);
+    qemu_mutex_lock_iothread();
+
+    /* We hold the global iothread lock, so it is safe here */
+    colo_release_ram_cache();
+
+    return 0;
+}

migration/meson.build

@@ -1,5 +1,6 @@
 # Files needed by unit tests
 migration_files = files(
+  'migration-stats.c',
   'page_cache.c',
   'xbzrle.c',
   'vmstate-types.c',
@@ -18,11 +19,9 @@ softmmu_ss.add(files(
   'fd.c',
   'global_state.c',
   'migration-hmp-cmds.c',
-  'migration-stats.c',
   'migration.c',
   'multifd.c',
   'multifd-zlib.c',
-  'multifd-zlib.c',
   'ram-compress.c',
   'options.c',
   'postcopy-ram.c',

migration/migration-stats.c

@@ -12,6 +12,57 @@
 
 #include "qemu/osdep.h"
 #include "qemu/stats64.h"
+#include "qemu-file.h"
+#include "trace.h"
 #include "migration-stats.h"
 
 MigrationAtomicStats mig_stats;
+
+bool migration_rate_exceeded(QEMUFile *f)
+{
+    if (qemu_file_get_error(f)) {
+        return true;
+    }
+
+    uint64_t rate_limit_start = stat64_get(&mig_stats.rate_limit_start);
+    uint64_t rate_limit_current = migration_transferred_bytes(f);
+    uint64_t rate_limit_used = rate_limit_current - rate_limit_start;
+    uint64_t rate_limit_max = stat64_get(&mig_stats.rate_limit_max);
+
+    if (rate_limit_max == RATE_LIMIT_DISABLED) {
+        return false;
+    }
+    if (rate_limit_max > 0 && rate_limit_used > rate_limit_max) {
+        return true;
+    }
+    return false;
+}
+
+uint64_t migration_rate_get(void)
+{
+    return stat64_get(&mig_stats.rate_limit_max);
+}
+
+#define XFER_LIMIT_RATIO (1000 / BUFFER_DELAY)
+
+void migration_rate_set(uint64_t limit)
+{
+    /*
+     * 'limit' is per second.  But we check it each BUFER_DELAY miliseconds.
+     */
+    stat64_set(&mig_stats.rate_limit_max, limit / XFER_LIMIT_RATIO);
+}
+
+void migration_rate_reset(QEMUFile *f)
+{
+    stat64_set(&mig_stats.rate_limit_start, migration_transferred_bytes(f));
+}
+
+uint64_t migration_transferred_bytes(QEMUFile *f)
+{
+    uint64_t multifd = stat64_get(&mig_stats.multifd_bytes);
+    uint64_t qemu_file = qemu_file_transferred(f);
+
+    trace_migration_transferred_bytes(qemu_file, multifd);
+    return qemu_file + multifd;
+}

migration/migration-stats.h

@@ -15,6 +15,18 @@
 
 #include "qemu/stats64.h"
 
+/*
+ * Amount of time to allocate to each "chunk" of bandwidth-throttled
+ * data.
+ */
+#define BUFFER_DELAY     100
+
+/*
+ * If rate_limit_max is 0, there is special code to remove the rate
+ * limit.
+ */
+#define RATE_LIMIT_DISABLED 0
+
 /*
  * These are the ram migration statistic counters.  It is loosely
  * based on MigrationStats.  We change to Stat64 any counter that
@@ -69,6 +81,14 @@ typedef struct {
      * Number of bytes sent during precopy stage.
      */
     Stat64 precopy_bytes;
+    /*
+     * Amount of transferred data at the start of current cycle.
+     */
+    Stat64 rate_limit_start;
+    /*
+     * Maximum amount of data we can send in a cycle.
+     */
+    Stat64 rate_limit_max;
     /*
      * Total number of bytes transferred.
      */
@@ -81,4 +101,39 @@ typedef struct {
 
 extern MigrationAtomicStats mig_stats;
 
+/**
+ * migration_rate_get: Get the maximum amount that can be transferred.
+ *
+ * Returns the maximum number of bytes that can be transferred in a cycle.
+ */
+uint64_t migration_rate_get(void);
+
+/**
+ * migration_rate_reset: Reset the rate limit counter.
+ *
+ * This is called when we know we start a new transfer cycle.
+ *
+ * @f: QEMUFile used for main migration channel
+ */
+void migration_rate_reset(QEMUFile *f);
+
+/**
+ * migration_rate_set: Set the maximum amount that can be transferred.
+ *
+ * Sets the maximum amount of bytes that can be transferred in one cycle.
+ *
+ * @new_rate: new maximum amount
+ */
+void migration_rate_set(uint64_t new_rate);
+
+/**
+ * migration_transferred_bytes: Return number of bytes transferred
+ *
+ * @f: QEMUFile used for main migration channel
+ *
+ * Returns how many bytes have we transferred since the beginning of
+ * the migration.  It accounts for bytes sent through any migration
+ * channel, multifd, qemu_file, rdma, ....
+ */
+uint64_t migration_transferred_bytes(QEMUFile *f);
 #endif

migration/migration.c

@@ -511,7 +511,6 @@ process_incoming_migration_co(void *opaque)
     MigrationIncomingState *mis = migration_incoming_get_current();
     PostcopyState ps;
     int ret;
-    Error *local_err = NULL;
 
     assert(mis->from_src_file);
 
@@ -520,12 +519,14 @@ process_incoming_migration_co(void *opaque)
         goto fail;
     }
 
-    mis->migration_incoming_co = qemu_coroutine_self();
     mis->largest_page_size = qemu_ram_pagesize_largest();
     postcopy_state_set(POSTCOPY_INCOMING_NONE);
     migrate_set_state(&mis->state, MIGRATION_STATUS_NONE,
                       MIGRATION_STATUS_ACTIVE);
+
+    mis->loadvm_co = qemu_coroutine_self();
     ret = qemu_loadvm_state(mis->from_src_file);
+    mis->loadvm_co = NULL;
 
     ps = postcopy_state_get();
     trace_process_incoming_migration_co_end(ret, ps);
@@ -553,35 +554,14 @@ process_incoming_migration_co(void *opaque)
         goto fail;
     }
 
-    /* we get COLO info, and know if we are in COLO mode */
-    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(&colo_incoming_thread, "COLO incoming",
-             colo_process_incoming_thread, mis, QEMU_THREAD_JOINABLE);
-        qemu_coroutine_yield();
-
-        qemu_mutex_unlock_iothread();
-        /* Wait checkpoint incoming thread exit before free resource */
-        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 (colo_incoming_co() < 0) {
+        goto fail;
     }
 
     mis->bh = qemu_bh_new(process_incoming_migration_bh, mis);
     qemu_bh_schedule(mis->bh);
-    mis->migration_incoming_co = NULL;
     return;
 fail:
-    local_err = NULL;
     migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
                       MIGRATION_STATUS_FAILED);
     qemu_fclose(mis->from_src_file);
@@ -2140,7 +2120,7 @@ static int postcopy_start(MigrationState *ms)
      * will notice we're in POSTCOPY_ACTIVE and not actually
      * wrap their state up here
      */
-    qemu_file_set_rate_limit(ms->to_dst_file, bandwidth);
+    migration_rate_set(bandwidth);
     if (migrate_postcopy_ram()) {
         /* Ping just for debugging, helps line traces up */
         qemu_savevm_send_ping(ms->to_dst_file, 2);
@@ -2324,7 +2304,7 @@ static void migration_completion(MigrationState *s)
                  * them if migration fails or is cancelled.
                  */
                 s->block_inactive = !migrate_colo();
-                qemu_file_set_rate_limit(s->to_dst_file, INT64_MAX);
+                migration_rate_set(RATE_LIMIT_DISABLED);
                 ret = qemu_savevm_state_complete_precopy(s->to_dst_file, false,
                                                          s->block_inactive);
             }
@@ -2645,16 +2625,9 @@ static MigThrError migration_detect_error(MigrationState *s)
     }
 }
 
-/* How many bytes have we transferred since the beginning of the migration */
-static uint64_t migration_total_bytes(MigrationState *s)
-{
-    return qemu_file_transferred(s->to_dst_file) +
-        stat64_get(&mig_stats.multifd_bytes);
-}
-
 static void migration_calculate_complete(MigrationState *s)
 {
-    uint64_t bytes = migration_total_bytes(s);
+    uint64_t bytes = migration_transferred_bytes(s->to_dst_file);
     int64_t end_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
     int64_t transfer_time;
 
@@ -2680,7 +2653,7 @@ static void update_iteration_initial_status(MigrationState *s)
      * wrong speed calculation.
      */
     s->iteration_start_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
-    s->iteration_initial_bytes = migration_total_bytes(s);
+    s->iteration_initial_bytes = migration_transferred_bytes(s->to_dst_file);
     s->iteration_initial_pages = ram_get_total_transferred_pages();
 }
 
@@ -2695,7 +2668,7 @@ static void migration_update_counters(MigrationState *s,
         return;
     }
 
-    current_bytes = migration_total_bytes(s);
+    current_bytes = migration_transferred_bytes(s->to_dst_file);
     transferred = current_bytes - s->iteration_initial_bytes;
     time_spent = current_time - s->iteration_start_time;
     bandwidth = (double)transferred / time_spent;
@@ -2719,7 +2692,7 @@ static void migration_update_counters(MigrationState *s,
             stat64_get(&mig_stats.dirty_bytes_last_sync) / bandwidth;
     }
 
-    qemu_file_reset_rate_limit(s->to_dst_file);
+    migration_rate_reset(s->to_dst_file);
 
     update_iteration_initial_status(s);
 
@@ -2872,7 +2845,7 @@ bool migration_rate_limit(void)
 
     bool urgent = false;
     migration_update_counters(s, now);
-    if (qemu_file_rate_limit(s->to_dst_file)) {
+    if (migration_rate_exceeded(s->to_dst_file)) {
 
         if (qemu_file_get_error(s->to_dst_file)) {
             return false;
@@ -2994,7 +2967,7 @@ static void *migration_thread(void *opaque)
     trace_migration_thread_setup_complete();
 
     while (migration_is_active(s)) {
-        if (urgent || !qemu_file_rate_limit(s->to_dst_file)) {
+        if (urgent || !migration_rate_exceeded(s->to_dst_file)) {
             MigIterateState iter_state = migration_iteration_run(s);
             if (iter_state == MIG_ITERATE_SKIP) {
                 continue;
@@ -3068,7 +3041,7 @@ static void *bg_migration_thread(void *opaque)
     rcu_register_thread();
     object_ref(OBJECT(s));
 
-    qemu_file_set_rate_limit(s->to_dst_file, INT64_MAX);
+    migration_rate_set(RATE_LIMIT_DISABLED);
 
     setup_start = qemu_clock_get_ms(QEMU_CLOCK_HOST);
     /*
@@ -3240,7 +3213,7 @@ void migrate_fd_connect(MigrationState *s, Error *error_in)
         notifier_list_notify(&migration_state_notifiers, s);
     }
 
-    qemu_file_set_rate_limit(s->to_dst_file, rate_limit);
+    migration_rate_set(rate_limit);
     qemu_file_set_blocking(s->to_dst_file, true);
 
     /*

migration/migration.h

@@ -162,8 +162,15 @@ struct MigrationIncomingState {
 
     int state;
 
+    /*
+     * The incoming migration coroutine, non-NULL during qemu_loadvm_state().
+     * Used to wake the migration incoming coroutine from rdma code. How much is
+     * it safe - it's a question.
+     */
+    Coroutine *loadvm_co;
+
     /* The coroutine we should enter (back) after failover */
-    Coroutine *migration_incoming_co;
+    Coroutine *colo_incoming_co;
     QemuSemaphore colo_incoming_sem;
 
     /*

migration/multifd.c

@@ -175,6 +175,7 @@ void multifd_register_ops(int method, MultiFDMethods *ops)
 static int multifd_send_initial_packet(MultiFDSendParams *p, Error **errp)
 {
     MultiFDInit_t msg = {};
+    size_t size = sizeof(msg);
     int ret;
 
     msg.magic = cpu_to_be32(MULTIFD_MAGIC);
@@ -182,10 +183,12 @@ static int multifd_send_initial_packet(MultiFDSendParams *p, Error **errp)
     msg.id = p->id;
     memcpy(msg.uuid, &qemu_uuid.data, sizeof(msg.uuid));
 
-    ret = qio_channel_write_all(p->c, (char *)&msg, sizeof(msg), errp);
+    ret = qio_channel_write_all(p->c, (char *)&msg, size, errp);
     if (ret != 0) {
         return -1;
     }
+    stat64_add(&mig_stats.multifd_bytes, size);
+    stat64_add(&mig_stats.transferred, size);
     return 0;
 }
 
@@ -395,7 +398,6 @@ static int multifd_send_pages(QEMUFile *f)
     static int next_channel;
     MultiFDSendParams *p = NULL; /* make happy gcc */
     MultiFDPages_t *pages = multifd_send_state->pages;
-    uint64_t transferred;
 
     if (qatomic_read(&multifd_send_state->exiting)) {
         return -1;
@@ -430,11 +432,7 @@ static int multifd_send_pages(QEMUFile *f)
     p->packet_num = multifd_send_state->packet_num++;
     multifd_send_state->pages = p->pages;
     p->pages = pages;
-    transferred = ((uint64_t) pages->num) * p->page_size + p->packet_len;
-    qemu_file_acct_rate_limit(f, transferred);
     qemu_mutex_unlock(&p->mutex);
-    stat64_add(&mig_stats.transferred, transferred);
-    stat64_add(&mig_stats.multifd_bytes, transferred);
     qemu_sem_post(&p->sem);
 
     return 1;
@@ -716,6 +714,8 @@ static void *multifd_send_thread(void *opaque)
                 if (ret != 0) {
                     break;
                 }
+                stat64_add(&mig_stats.multifd_bytes, p->packet_len);
+                stat64_add(&mig_stats.transferred, p->packet_len);
             } else {
                 /* Send header using the same writev call */
                 p->iov[0].iov_len = p->packet_len;
@@ -728,6 +728,8 @@ static void *multifd_send_thread(void *opaque)
                 break;
             }
 
+            stat64_add(&mig_stats.multifd_bytes, p->next_packet_size);
+            stat64_add(&mig_stats.transferred, p->next_packet_size);
             qemu_mutex_lock(&p->mutex);
             p->pending_job--;
             qemu_mutex_unlock(&p->mutex);

migration/options.c

@@ -23,6 +23,7 @@
 #include "migration/colo.h"
 #include "migration/misc.h"
 #include "migration.h"
+#include "migration-stats.h"
 #include "qemu-file.h"
 #include "ram.h"
 #include "options.h"
@@ -1242,8 +1243,7 @@ static void migrate_params_apply(MigrateSetParameters *params, Error **errp)
     if (params->has_max_bandwidth) {
         s->parameters.max_bandwidth = params->max_bandwidth;
         if (s->to_dst_file && !migration_in_postcopy()) {
-            qemu_file_set_rate_limit(s->to_dst_file,
-                                s->parameters.max_bandwidth);
+            migration_rate_set(s->parameters.max_bandwidth);
         }
     }
 
@@ -1272,8 +1272,7 @@ static void migrate_params_apply(MigrateSetParameters *params, Error **errp)
     if (params->has_max_postcopy_bandwidth) {
         s->parameters.max_postcopy_bandwidth = params->max_postcopy_bandwidth;
         if (s->to_dst_file && migration_in_postcopy()) {
-            qemu_file_set_rate_limit(s->to_dst_file,
-                    s->parameters.max_postcopy_bandwidth);
+            migration_rate_set(s->parameters.max_postcopy_bandwidth);
         }
     }
     if (params->has_max_cpu_throttle) {

migration/options.h

@@ -17,13 +17,6 @@
 #include "hw/qdev-properties.h"
 #include "hw/qdev-properties-system.h"
 
-/* constants */
-
-/* Amount of time to allocate to each "chunk" of bandwidth-throttled
- * data. */
-#define BUFFER_DELAY     100
-#define XFER_LIMIT_RATIO (1000 / BUFFER_DELAY)
-
 /* migration properties */
 
 extern Property migration_properties[];

migration/qemu-file.c

@@ -27,6 +27,7 @@
 #include "qemu/error-report.h"
 #include "qemu/iov.h"
 #include "migration.h"
+#include "migration-stats.h"
 #include "qemu-file.h"
 #include "trace.h"
 #include "options.h"
@@ -40,17 +41,6 @@ struct QEMUFile {
     QIOChannel *ioc;
     bool is_writable;
 
-    /*
-     * Maximum amount of data in bytes to transfer during one
-     * rate limiting time window
-     */
-    uint64_t rate_limit_max;
-    /*
-     * Total amount of data in bytes queued for transfer
-     * during this rate limiting time window
-     */
-    uint64_t rate_limit_used;
-
     /* The sum of bytes transferred on the wire */
     uint64_t total_transferred;
 
@@ -301,7 +291,8 @@ void qemu_fflush(QEMUFile *f)
                                    &local_error) < 0) {
             qemu_file_set_error_obj(f, -EIO, local_error);
         } else {
-            f->total_transferred += iov_size(f->iov, f->iovcnt);
+            uint64_t size = iov_size(f->iov, f->iovcnt);
+            f->total_transferred += size;
         }
 
         qemu_iovec_release_ram(f);
@@ -352,9 +343,6 @@ size_t ram_control_save_page(QEMUFile *f, ram_addr_t block_offset,
     if (f->hooks && f->hooks->save_page) {
         int ret = f->hooks->save_page(f, block_offset,
                                       offset, size, bytes_sent);
-        if (ret != RAM_SAVE_CONTROL_NOT_SUPP) {
-            qemu_file_acct_rate_limit(f, size);
-        }
 
         if (ret != RAM_SAVE_CONTROL_DELAYED &&
             ret != RAM_SAVE_CONTROL_NOT_SUPP) {
@@ -518,7 +506,6 @@ void qemu_put_buffer_async(QEMUFile *f, const uint8_t *buf, size_t size,
         return;
     }
 
-    f->rate_limit_used += size;
     add_to_iovec(f, buf, size, may_free);
 }
 
@@ -536,7 +523,6 @@ void qemu_put_buffer(QEMUFile *f, const uint8_t *buf, size_t size)
             l = size;
         }
         memcpy(f->buf + f->buf_index, buf, l);
-        f->rate_limit_used += l;
         add_buf_to_iovec(f, l);
         if (qemu_file_get_error(f)) {
             break;
@@ -553,7 +539,6 @@ void qemu_put_byte(QEMUFile *f, int v)
     }
 
     f->buf[f->buf_index] = v;
-    f->rate_limit_used++;
     add_buf_to_iovec(f, 1);
 }
 
@@ -727,40 +712,6 @@ uint64_t qemu_file_transferred(QEMUFile *f)
     return f->total_transferred;
 }
 
-int qemu_file_rate_limit(QEMUFile *f)
-{
-    if (qemu_file_get_error(f)) {
-        return 1;
-    }
-    if (f->rate_limit_max > 0 && f->rate_limit_used > f->rate_limit_max) {
-        return 1;
-    }
-    return 0;
-}
-
-uint64_t qemu_file_get_rate_limit(QEMUFile *f)
-{
-    return f->rate_limit_max;
-}
-
-void qemu_file_set_rate_limit(QEMUFile *f, uint64_t limit)
-{
-    /*
-     * 'limit' is per second.  But we check it each 100 miliseconds.
-     */
-    f->rate_limit_max = limit / XFER_LIMIT_RATIO;
-}
-
-void qemu_file_reset_rate_limit(QEMUFile *f)
-{
-    f->rate_limit_used = 0;
-}
-
-void qemu_file_acct_rate_limit(QEMUFile *f, uint64_t len)
-{
-    f->rate_limit_used += len;
-}
-
 void qemu_put_be16(QEMUFile *f, unsigned int v)
 {
     qemu_put_byte(f, v >> 8);

migration/qemu-file.h

@@ -130,17 +130,6 @@ void qemu_file_skip(QEMUFile *f, int size);
  * accounting information tracks the total migration traffic.
  */
 void qemu_file_credit_transfer(QEMUFile *f, size_t size);
-void qemu_file_reset_rate_limit(QEMUFile *f);
-/*
- * qemu_file_acct_rate_limit:
- *
- * Report on a number of bytes the have been transferred
- * out of band from the main file object I/O methods, and
- * need to be applied to the rate limiting calcuations
- */
-void qemu_file_acct_rate_limit(QEMUFile *f, uint64_t len);
-void qemu_file_set_rate_limit(QEMUFile *f, uint64_t new_rate);
-uint64_t qemu_file_get_rate_limit(QEMUFile *f);
 int qemu_file_get_error_obj(QEMUFile *f, Error **errp);
 int qemu_file_get_error_obj_any(QEMUFile *f1, QEMUFile *f2, Error **errp);
 void qemu_file_set_error_obj(QEMUFile *f, int ret, Error *err);

migration/ram.c

@@ -3116,7 +3116,7 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
 
         t0 = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
         i = 0;
-        while ((ret = qemu_file_rate_limit(f)) == 0 ||
+        while ((ret = migration_rate_exceeded(f)) == 0 ||
                postcopy_has_request(rs)) {
             int pages;
 

migration/rdma.c

@@ -3342,9 +3342,8 @@ static void rdma_cm_poll_handler(void *opaque)
             }
         }
         rdma_ack_cm_event(cm_event);
-
-        if (mis->migration_incoming_co) {
-            qemu_coroutine_enter(mis->migration_incoming_co);
+        if (mis->loadvm_co) {
+            qemu_coroutine_enter(mis->loadvm_co);
         }
         return;
     }

migration/savevm.c

@@ -1338,7 +1338,7 @@ int qemu_savevm_state_iterate(QEMUFile *f, bool postcopy)
             !(se->ops->has_postcopy && se->ops->has_postcopy(se->opaque))) {
             continue;
         }
-        if (qemu_file_rate_limit(f)) {
+        if (migration_rate_exceeded(f)) {
             return 0;
         }
         trace_savevm_section_start(se->idstr, se->section_id);

migration/trace-events

@@ -186,6 +186,9 @@ process_incoming_migration_co_end(int ret, int ps) "ret=%d postcopy-state=%d"
 process_incoming_migration_co_postcopy_end_main(void) ""
 postcopy_preempt_enabled(bool value) "%d"
 
+# migration-stats
+migration_transferred_bytes(uint64_t qemu_file, uint64_t multifd) "qemu_file %" PRIu64 " multifd %" PRIu64
+
 # channel.c
 migration_set_incoming_channel(void *ioc, const char *ioctype) "ioc=%p ioctype=%s"
 migration_set_outgoing_channel(void *ioc, const char *ioctype, const char *hostname, void *err)  "ioc=%p ioctype=%s hostname=%s err=%p"

net/meson.build

@@ -1,13 +1,10 @@
 softmmu_ss.add(files(
   'announce.c',
   'checksum.c',
-  'colo-compare.c',
-  'colo.c',
   'dump.c',
   'eth.c',
   'filter-buffer.c',
   'filter-mirror.c',
-  'filter-rewriter.c',
   'filter.c',
   'hub.c',
   'net-hmp-cmds.c',
@@ -19,6 +16,16 @@ softmmu_ss.add(files(
   'util.c',
 ))
 
+if get_option('replication').allowed() or \
+    get_option('colo_proxy').allowed()
+  softmmu_ss.add(files('colo-compare.c'))
+  softmmu_ss.add(files('colo.c'))
+endif
+
+if get_option('colo_proxy').allowed()
+  softmmu_ss.add(files('filter-rewriter.c'))
+endif
+
 softmmu_ss.add(when: 'CONFIG_TCG', if_true: files('filter-replay.c'))
 
 if have_l2tpv3

scripts/meson-buildoptions.sh

@@ -91,6 +91,7 @@ meson_options_help() {
   printf "%s\n" '  capstone        Whether and how to find the capstone library'
   printf "%s\n" '  cloop           cloop image format support'
   printf "%s\n" '  cocoa           Cocoa user interface (macOS only)'
+  printf "%s\n" '  colo-proxy      colo-proxy support'
   printf "%s\n" '  coreaudio       CoreAudio sound support'
   printf "%s\n" '  crypto-afalg    Linux AF_ALG crypto backend driver'
   printf "%s\n" '  curl            CURL block device driver'
@@ -252,6 +253,8 @@ _meson_option_parse() {
     --disable-cloop) printf "%s" -Dcloop=disabled ;;
     --enable-cocoa) printf "%s" -Dcocoa=enabled ;;
     --disable-cocoa) printf "%s" -Dcocoa=disabled ;;
+    --enable-colo-proxy) printf "%s" -Dcolo_proxy=enabled ;;
+    --disable-colo-proxy) printf "%s" -Dcolo_proxy=disabled ;;
     --enable-coreaudio) printf "%s" -Dcoreaudio=enabled ;;
     --disable-coreaudio) printf "%s" -Dcoreaudio=disabled ;;
     --with-coroutine=*) quote_sh "-Dcoroutine_backend=$2" ;;

stubs/colo-compare.c

@@ -0,0 +1,7 @@
+#include "qemu/osdep.h"
+#include "qemu/notify.h"
+#include "net/colo-compare.h"
+
+void colo_compare_cleanup(void)
+{
+}

stubs/colo.c

@@ -10,11 +10,9 @@ void colo_shutdown(void)
 {
 }
 
-void *colo_process_incoming_thread(void *opaque)
+int coroutine_fn colo_incoming_co(void)
 {
-    error_report("Impossible happend: trying to start COLO thread when COLO "
-                 "module is not built in");
-    abort();
+    return 0;
 }
 
 void colo_checkpoint_delay_set(void)

stubs/meson.build

@@ -46,6 +46,7 @@ stub_ss.add(files('target-monitor-defs.c'))
 stub_ss.add(files('trace-control.c'))
 stub_ss.add(files('uuid.c'))
 stub_ss.add(files('colo.c'))
+stub_ss.add(files('colo-compare.c'))
 stub_ss.add(files('vmstate.c'))
 stub_ss.add(files('vm-stop.c'))
 stub_ss.add(files('win32-kbd-hook.c'))