Merge tag 'migration-20230518-pull-request' of https://gitlab.com/jua…

…n.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 @@ void *colo_process_incoming_thread(void *opaque)
     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