migration/next for 20150316

-----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQIcBAABCAAGBQJVBtxlAAoJEPSH7xhYctcjokAQALpZdRqCAS89MSFfFMj0uSE+
 YL2jELoMHYoOutq7quc/dF5wpQpYeSWYAzcHBpdo63j9VlnoKfQ0CaOGdevnwhZT
 KUg9S+9UtvcqJUteZyd/JtY6HA83jXElJB6siTUMHJmdgYY4i5HSfUeYe/jqsfdT
 W2TYJQPMu1ecGFAjKJQafZRO0q5gYfR2XeEiAsdynIVvccPFKMKnE5CtoPnJtTPb
 83O36K3wi4lg0AgB7ti8QcNSf3JS2WuluKXG1TxrgoxfWAVQ0SQ79pq7xVZ7c4IZ
 BErm7ihhlOP/DlGaNsPzcYwVsP6uksm1TE/PO63QoWBxaVjmLPkV0ZLKbGkR8Cr0
 ulk/BUSAjXzMDoloVqz27e2SCrCA0p7tpGJ9nw/2xv01GNcVO6EFAJDHFLv8HmnH
 yVZDQnqO5wJkrUu5U5WQ1tKIktRZFRoyR0D6nzhAKSOWqFCOKMID6TH8ixmGSxA7
 HHzSxs48GHu9pztZ1tNqON1r1Ets5I+Zy760wC60DPeOrSlkcEvgRzfNF26V9cY/
 VSp8QedX5RE509HYvh73fVT5+brwPHMs36OSe/LSc4tomXZq83RjfDRjwYrAAAjW
 nBugr0hyBrATLiPQSYgt+GNly4Qg09jwkTvRcQqcNf22zKdFM4zjf+wvrbH/+9xa
 ZTuPQUSpHMNS3mv/Gj3b
 =DZVy
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/juanquintela/tags/migration/20150316' into staging

migration/next for 20150316

# gpg: Signature made Mon Mar 16 13:36:37 2015 GMT using RSA key ID 5872D723
# gpg: Can't check signature: public key not found

* remotes/juanquintela/tags/migration/20150316:
  pc: Disable vmdesc submission for old machines
  migration: Allow to suppress vmdesc submission
  migration: Read JSON VM description on incoming migration
  rename save_block_hdr to save_page_header
  save_block_hdr: we can recalculate the cont parameter here
  save_xbzrle_page: change calling convention
  ram_save_page: change calling covention
  ram_find_and_save_block:  change calling convention
  ram: make all save_page functions take a uint64_t parameter
  Add migrate_incoming
  Add -incoming defer

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

arch_init.c

@@ -305,23 +305,6 @@ uint64_t xbzrle_mig_pages_overflow(void)
     return acct_info.xbzrle_overflows;
 }
 
-static size_t save_block_hdr(QEMUFile *f, RAMBlock *block, ram_addr_t offset,
-                             int cont, int flag)
-{
-    size_t size;
-
-    qemu_put_be64(f, offset | cont | flag);
-    size = 8;
-
-    if (!cont) {
-        qemu_put_byte(f, strlen(block->idstr));
-        qemu_put_buffer(f, (uint8_t *)block->idstr,
-                        strlen(block->idstr));
-        size += 1 + strlen(block->idstr);
-    }
-    return size;
-}
-
 /* This is the last block that we have visited serching for dirty pages
  */
 static RAMBlock *last_seen_block;
@@ -333,6 +316,39 @@ static uint64_t migration_dirty_pages;
 static uint32_t last_version;
 static bool ram_bulk_stage;
 
+/**
+ * save_page_header: Write page header to wire
+ *
+ * If this is the 1st block, it also writes the block identification
+ *
+ * Returns: Number of bytes written
+ *
+ * @f: QEMUFile where to send the data
+ * @block: block that contains the page we want to send
+ * @offset: offset inside the block for the page
+ *          in the lower bits, it contains flags
+ */
+static size_t save_page_header(QEMUFile *f, RAMBlock *block, ram_addr_t offset)
+{
+    size_t size;
+
+    if (block == last_sent_block) {
+        offset |= RAM_SAVE_FLAG_CONTINUE;
+    }
+
+    qemu_put_be64(f, offset);
+    size = 8;
+
+    if (block != last_sent_block) {
+        qemu_put_byte(f, strlen(block->idstr));
+        qemu_put_buffer(f, (uint8_t *)block->idstr,
+                        strlen(block->idstr));
+        size += 1 + strlen(block->idstr);
+        last_sent_block = block;
+    }
+    return size;
+}
+
 /* Update the xbzrle cache to reflect a page that's been sent as all 0.
  * The important thing is that a stale (not-yet-0'd) page be replaced
  * by the new data.
@@ -353,11 +369,27 @@ static void xbzrle_cache_zero_page(ram_addr_t current_addr)
 
 #define ENCODING_FLAG_XBZRLE 0x1
 
+/**
+ * save_xbzrle_page: compress and send current page
+ *
+ * Returns: 1 means that we wrote the page
+ *          0 means that page is identical to the one already sent
+ *          -1 means that xbzrle would be longer than normal
+ *
+ * @f: QEMUFile where to send the data
+ * @current_data:
+ * @current_addr:
+ * @block: block that contains the page we want to send
+ * @offset: offset inside the block for the page
+ * @last_stage: if we are at the completion stage
+ * @bytes_transferred: increase it with the number of transferred bytes
+ */
 static int save_xbzrle_page(QEMUFile *f, uint8_t **current_data,
                             ram_addr_t current_addr, RAMBlock *block,
-                            ram_addr_t offset, int cont, bool last_stage)
+                            ram_addr_t offset, bool last_stage,
+                            uint64_t *bytes_transferred)
 {
-    int encoded_len = 0, bytes_sent = -1;
+    int encoded_len = 0, bytes_xbzrle;
     uint8_t *prev_cached_page;
 
     if (!cache_is_cached(XBZRLE.cache, current_addr, bitmap_sync_count)) {
@@ -404,15 +436,16 @@ static int save_xbzrle_page(QEMUFile *f, uint8_t **current_data,
     }
 
     /* Send XBZRLE based compressed page */
-    bytes_sent = save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_XBZRLE);
+    bytes_xbzrle = save_page_header(f, block, offset | RAM_SAVE_FLAG_XBZRLE);
     qemu_put_byte(f, ENCODING_FLAG_XBZRLE);
     qemu_put_be16(f, encoded_len);
     qemu_put_buffer(f, XBZRLE.encoded_buf, encoded_len);
-    bytes_sent += encoded_len + 1 + 2;
+    bytes_xbzrle += encoded_len + 1 + 2;
     acct_info.xbzrle_pages++;
-    acct_info.xbzrle_bytes += bytes_sent;
+    acct_info.xbzrle_bytes += bytes_xbzrle;
+    *bytes_transferred += bytes_xbzrle;
 
-    return bytes_sent;
+    return 1;
 }
 
 static inline
@@ -575,55 +608,64 @@ static void migration_bitmap_sync(void)
     }
 }
 
-/*
+/**
  * ram_save_page: Send the given page to the stream
  *
- * Returns: Number of bytes written.
+ * Returns: Number of pages written.
+ *
+ * @f: QEMUFile where to send the data
+ * @block: block that contains the page we want to send
+ * @offset: offset inside the block for the page
+ * @last_stage: if we are at the completion stage
+ * @bytes_transferred: increase it with the number of transferred bytes
  */
 static int ram_save_page(QEMUFile *f, RAMBlock* block, ram_addr_t offset,
-                         bool last_stage)
+                         bool last_stage, uint64_t *bytes_transferred)
 {
-    int bytes_sent;
+    int pages = -1;
-    int cont;
+    uint64_t bytes_xmit;
     ram_addr_t current_addr;
     MemoryRegion *mr = block->mr;
     uint8_t *p;
     int ret;
     bool send_async = true;
 
-    cont = (block == last_sent_block) ? RAM_SAVE_FLAG_CONTINUE : 0;
-
     p = memory_region_get_ram_ptr(mr) + offset;
 
     /* In doubt sent page as normal */
-    bytes_sent = -1;
+    bytes_xmit = 0;
     ret = ram_control_save_page(f, block->offset,
-                           offset, TARGET_PAGE_SIZE, &bytes_sent);
+                           offset, TARGET_PAGE_SIZE, &bytes_xmit);
+    if (bytes_xmit) {
+        *bytes_transferred += bytes_xmit;
+        pages = 1;
+    }
 
     XBZRLE_cache_lock();
 
     current_addr = block->offset + offset;
     if (ret != RAM_SAVE_CONTROL_NOT_SUPP) {
         if (ret != RAM_SAVE_CONTROL_DELAYED) {
-            if (bytes_sent > 0) {
+            if (bytes_xmit > 0) {
                 acct_info.norm_pages++;
-            } else if (bytes_sent == 0) {
+            } else if (bytes_xmit == 0) {
                 acct_info.dup_pages++;
             }
         }
     } else if (is_zero_range(p, TARGET_PAGE_SIZE)) {
         acct_info.dup_pages++;
-        bytes_sent = save_block_hdr(f, block, offset, cont,
+        *bytes_transferred += save_page_header(f, block,
-                                    RAM_SAVE_FLAG_COMPRESS);
+                                               offset | RAM_SAVE_FLAG_COMPRESS);
         qemu_put_byte(f, 0);
-        bytes_sent++;
+        *bytes_transferred += 1;
+        pages = 1;
         /* Must let xbzrle know, otherwise a previous (now 0'd) cached
          * page would be stale
          */
         xbzrle_cache_zero_page(current_addr);
     } else if (!ram_bulk_stage && migrate_use_xbzrle()) {
-        bytes_sent = save_xbzrle_page(f, &p, current_addr, block,
+        pages = save_xbzrle_page(f, &p, current_addr, block,
-                                      offset, cont, last_stage);
+                                 offset, last_stage, bytes_transferred);
         if (!last_stage) {
             /* Can't send this cached data async, since the cache page
              * might get updated before it gets to the wire
@@ -633,37 +675,44 @@ static int ram_save_page(QEMUFile *f, RAMBlock* block, ram_addr_t offset,
     }
 
     /* XBZRLE overflow or normal page */
-    if (bytes_sent == -1) {
+    if (pages == -1) {
-        bytes_sent = save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_PAGE);
+        *bytes_transferred += save_page_header(f, block,
+                                               offset | RAM_SAVE_FLAG_PAGE);
         if (send_async) {
             qemu_put_buffer_async(f, p, TARGET_PAGE_SIZE);
         } else {
             qemu_put_buffer(f, p, TARGET_PAGE_SIZE);
         }
-        bytes_sent += TARGET_PAGE_SIZE;
+        *bytes_transferred += TARGET_PAGE_SIZE;
+        pages = 1;
         acct_info.norm_pages++;
     }
 
     XBZRLE_cache_unlock();
 
-    return bytes_sent;
+    return pages;
 }
 
-/*
+/**
- * ram_find_and_save_block: Finds a page to send and sends it to f
+ * ram_find_and_save_block: Finds a dirty page and sends it to f
  *
  * Called within an RCU critical section.
  *
- * Returns:  The number of bytes written.
+ * Returns:  The number of pages written
  *           0 means no dirty pages
+ *
+ * @f: QEMUFile where to send the data
+ * @last_stage: if we are at the completion stage
+ * @bytes_transferred: increase it with the number of transferred bytes
  */
 
-static int ram_find_and_save_block(QEMUFile *f, bool last_stage)
+static int ram_find_and_save_block(QEMUFile *f, bool last_stage,
+                                   uint64_t *bytes_transferred)
 {
     RAMBlock *block = last_seen_block;
     ram_addr_t offset = last_offset;
     bool complete_round = false;
-    int bytes_sent = 0;
+    int pages = 0;
     MemoryRegion *mr;
 
     if (!block)
@@ -685,11 +734,11 @@ static int ram_find_and_save_block(QEMUFile *f, bool last_stage)
                 ram_bulk_stage = false;
             }
         } else {
-            bytes_sent = ram_save_page(f, block, offset, last_stage);
+            pages = ram_save_page(f, block, offset, last_stage,
+                                  bytes_transferred);
 
             /* if page is unmodified, continue to the next */
-            if (bytes_sent > 0) {
+            if (pages > 0) {
-                last_sent_block = block;
                 break;
             }
         }
@@ -697,7 +746,8 @@ static int ram_find_and_save_block(QEMUFile *f, bool last_stage)
 
     last_seen_block = block;
     last_offset = offset;
-    return bytes_sent;
+
+    return pages;
 }
 
 static uint64_t bytes_transferred;
@@ -881,7 +931,7 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
     int ret;
     int i;
     int64_t t0;
-    int total_sent = 0;
+    int pages_sent = 0;
 
     rcu_read_lock();
     if (ram_list.version != last_version) {
@@ -896,14 +946,14 @@ 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) {
-        int bytes_sent;
+        int pages;
 
-        bytes_sent = ram_find_and_save_block(f, false);
+        pages = ram_find_and_save_block(f, false, &bytes_transferred);
-        /* no more blocks to sent */
+        /* no more pages to sent */
-        if (bytes_sent == 0) {
+        if (pages == 0) {
             break;
         }
-        total_sent += bytes_sent;
+        pages_sent += pages;
         acct_info.iterations++;
         check_guest_throttling();
         /* we want to check in the 1st loop, just in case it was the 1st time
@@ -929,12 +979,6 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
      */
     ram_control_after_iterate(f, RAM_CONTROL_ROUND);
 
-    bytes_transferred += total_sent;
-
-    /*
-     * Do not count these 8 bytes into total_sent, so that we can
-     * return 0 if no page had been dirtied.
-     */
     qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
     bytes_transferred += 8;
 
@@ -943,7 +987,7 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
         return ret;
     }
 
-    return total_sent;
+    return pages_sent;
 }
 
 /* Called with iothread lock */
@@ -959,14 +1003,13 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
 
     /* flush all remaining blocks regardless of rate limiting */
     while (true) {
-        int bytes_sent;
+        int pages;
 
-        bytes_sent = ram_find_and_save_block(f, true);
+        pages = ram_find_and_save_block(f, true, &bytes_transferred);
         /* no more blocks to sent */
-        if (bytes_sent == 0) {
+        if (pages == 0) {
             break;
         }
-        bytes_transferred += bytes_sent;
     }
 
     ram_control_after_iterate(f, RAM_CONTROL_FINISH);

hmp-commands.hx

@@ -919,6 +919,22 @@ STEXI
 @findex migrate_cancel
 Cancel the current VM migration.
 
+ETEXI
+
+    {
+        .name       = "migrate_incoming",
+        .args_type  = "uri:s",
+        .params     = "uri",
+        .help       = "Continue an incoming migration from an -incoming defer",
+        .mhandler.cmd = hmp_migrate_incoming,
+    },
+
+STEXI
+@item migrate_incoming @var{uri}
+@findex migrate_incoming
+Continue an incoming migration using the @var{uri} (that has the same syntax
+as the -incoming option).
+
 ETEXI
 
     {

hmp.c

@@ -1116,6 +1116,20 @@ void hmp_migrate_cancel(Monitor *mon, const QDict *qdict)
     qmp_migrate_cancel(NULL);
 }
 
+void hmp_migrate_incoming(Monitor *mon, const QDict *qdict)
+{
+    Error *err = NULL;
+    const char *uri = qdict_get_str(qdict, "uri");
+
+    qmp_migrate_incoming(uri, &err);
+
+    if (err) {
+        monitor_printf(mon, "%s\n", error_get_pretty(err));
+        error_free(err);
+        return;
+    }
+}
+
 void hmp_migrate_set_downtime(Monitor *mon, const QDict *qdict)
 {
     double value = qdict_get_double(qdict, "value");

hmp.h

@@ -60,6 +60,7 @@ void hmp_snapshot_delete_blkdev_internal(Monitor *mon, const QDict *qdict);
 void hmp_drive_mirror(Monitor *mon, const QDict *qdict);
 void hmp_drive_backup(Monitor *mon, const QDict *qdict);
 void hmp_migrate_cancel(Monitor *mon, const QDict *qdict);
+void hmp_migrate_incoming(Monitor *mon, const QDict *qdict);
 void hmp_migrate_set_downtime(Monitor *mon, const QDict *qdict);
 void hmp_migrate_set_speed(Monitor *mon, const QDict *qdict);
 void hmp_migrate_set_capability(Monitor *mon, const QDict *qdict);

hw/core/machine.c

@@ -254,6 +254,20 @@ static void machine_set_iommu(Object *obj, bool value, Error **errp)
     ms->iommu = value;
 }
 
+static void machine_set_suppress_vmdesc(Object *obj, bool value, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    ms->suppress_vmdesc = value;
+}
+
+static bool machine_get_suppress_vmdesc(Object *obj, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    return ms->suppress_vmdesc;
+}
+
 static int error_on_sysbus_device(SysBusDevice *sbdev, void *opaque)
 {
     error_report("Option '-device %s' cannot be handled by this machine",
@@ -377,6 +391,12 @@ static void machine_initfn(Object *obj)
     object_property_set_description(obj, "iommu",
                                     "Set on/off to enable/disable Intel IOMMU (VT-d)",
                                     NULL);
+    object_property_add_bool(obj, "suppress-vmdesc",
+                             machine_get_suppress_vmdesc,
+                             machine_set_suppress_vmdesc, NULL);
+    object_property_set_description(obj, "suppress-vmdesc",
+                                    "Set on to disable self-describing migration",
+                                    NULL);
 
     /* Register notifier when init is done for sysbus sanity checks */
     ms->sysbus_notifier.notify = machine_init_notify;

hw/i386/pc_piix.c

@@ -335,6 +335,7 @@ static void pc_compat_2_2(MachineState *machine)
                                 CPUID_7_0_EBX_HLE | CPUID_7_0_EBX_RTM, 0);
     x86_cpu_compat_set_features("Broadwell", FEAT_7_0_EBX,
                                 CPUID_7_0_EBX_HLE | CPUID_7_0_EBX_RTM, 0);
+    machine->suppress_vmdesc = true;
 }
 
 static void pc_compat_2_1(MachineState *machine)

hw/i386/pc_q35.c

@@ -314,6 +314,7 @@ static void pc_compat_2_2(MachineState *machine)
                                 CPUID_7_0_EBX_HLE | CPUID_7_0_EBX_RTM, 0);
     x86_cpu_compat_set_features("Broadwell", FEAT_7_0_EBX,
                                 CPUID_7_0_EBX_HLE | CPUID_7_0_EBX_RTM, 0);
+    machine->suppress_vmdesc = true;
 }
 
 static void pc_compat_2_1(MachineState *machine)

include/hw/boards.h

@@ -143,6 +143,7 @@ struct MachineState {
     bool usb;
     char *firmware;
     bool iommu;
+    bool suppress_vmdesc;
 
     ram_addr_t ram_size;
     ram_addr_t maxram_size;

include/migration/migration.h

@@ -169,6 +169,6 @@ void ram_control_load_hook(QEMUFile *f, uint64_t flags);
 
 size_t ram_control_save_page(QEMUFile *f, ram_addr_t block_offset,
                              ram_addr_t offset, size_t size,
-                             int *bytes_sent);
+                             uint64_t *bytes_sent);
 
 #endif

include/migration/qemu-file.h

@@ -82,7 +82,7 @@ typedef size_t (QEMURamSaveFunc)(QEMUFile *f, void *opaque,
                                ram_addr_t block_offset,
                                ram_addr_t offset,
                                size_t size,
-                               int *bytes_sent);
+                               uint64_t *bytes_sent);
 
 /*
  * Stop any read or write (depending on flags) on the underlying

migration/migration.c

@@ -49,6 +49,8 @@ enum {
 static NotifierList migration_state_notifiers =
     NOTIFIER_LIST_INITIALIZER(migration_state_notifiers);
 
+static bool deferred_incoming;
+
 /* When we add fault tolerance, we could have several
    migrations at once.  For now we don't need to add
    dynamic creation of migration */
@@ -65,25 +67,40 @@ MigrationState *migrate_get_current(void)
     return &current_migration;
 }
 
+/*
+ * Called on -incoming with a defer: uri.
+ * The migration can be started later after any parameters have been
+ * changed.
+ */
+static void deferred_incoming_migration(Error **errp)
+{
+    if (deferred_incoming) {
+        error_setg(errp, "Incoming migration already deferred");
+    }
+    deferred_incoming = true;
+}
+
 void qemu_start_incoming_migration(const char *uri, Error **errp)
 {
     const char *p;
 
-    if (strstart(uri, "tcp:", &p))
+    if (!strcmp(uri, "defer")) {
+        deferred_incoming_migration(errp);
+    } else if (strstart(uri, "tcp:", &p)) {
         tcp_start_incoming_migration(p, errp);
 #ifdef CONFIG_RDMA
-    else if (strstart(uri, "rdma:", &p))
+    } else if (strstart(uri, "rdma:", &p)) {
         rdma_start_incoming_migration(p, errp);
 #endif
 #if !defined(WIN32)
-    else if (strstart(uri, "exec:", &p))
+    } else if (strstart(uri, "exec:", &p)) {
         exec_start_incoming_migration(p, errp);
-    else if (strstart(uri, "unix:", &p))
+    } else if (strstart(uri, "unix:", &p)) {
         unix_start_incoming_migration(p, errp);
-    else if (strstart(uri, "fd:", &p))
+    } else if (strstart(uri, "fd:", &p)) {
         fd_start_incoming_migration(p, errp);
 #endif
-    else {
+    } else {
         error_setg(errp, "unknown migration protocol: %s", uri);
     }
 }
@@ -415,6 +432,25 @@ void migrate_del_blocker(Error *reason)
     migration_blockers = g_slist_remove(migration_blockers, reason);
 }
 
+void qmp_migrate_incoming(const char *uri, Error **errp)
+{
+    Error *local_err = NULL;
+
+    if (!deferred_incoming) {
+        error_setg(errp, "'-incoming defer' is required for migrate_incoming");
+        return;
+    }
+
+    qemu_start_incoming_migration(uri, &local_err);
+
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
+    }
+
+    deferred_incoming = false;
+}
+
 void qmp_migrate(const char *uri, bool has_blk, bool blk,
                  bool has_inc, bool inc, bool has_detach, bool detach,
                  Error **errp)

migration/qemu-file.c

@@ -161,7 +161,8 @@ void ram_control_load_hook(QEMUFile *f, uint64_t flags)
 }
 
 size_t ram_control_save_page(QEMUFile *f, ram_addr_t block_offset,
-                         ram_addr_t offset, size_t size, int *bytes_sent)
+                             ram_addr_t offset, size_t size,
+                             uint64_t *bytes_sent)
 {
     if (f->ops->save_page) {
         int ret = f->ops->save_page(f, f->opaque, block_offset,

migration/rdma.c

@@ -2654,7 +2654,7 @@ static int qemu_rdma_close(void *opaque)
  */
 static size_t qemu_rdma_save_page(QEMUFile *f, void *opaque,
                                   ram_addr_t block_offset, ram_addr_t offset,
-                                  size_t size, int *bytes_sent)
+                                  size_t size, uint64_t *bytes_sent)
 {
     QEMUFileRDMA *rfile = opaque;
     RDMAContext *rdma = rfile->rdma;

qapi-schema.json

@@ -1738,6 +1738,21 @@
 { 'command': 'migrate',
   'data': {'uri': 'str', '*blk': 'bool', '*inc': 'bool', '*detach': 'bool' } }
 
+##
+# @migrate-incoming
+#
+# Start an incoming migration, the qemu must have been started
+# with -incoming defer
+#
+# @uri: The Uniform Resource Identifier identifying the source or
+#       address to listen on
+#
+# Returns: nothing on success
+#
+# Since: 2.3
+##
+{ 'command': 'migrate-incoming', 'data': {'uri': 'str' } }
+
 # @xen-save-devices-state:
 #
 # Save the state of all devices to file. The RAM and the block devices

qemu-options.hx

@@ -39,7 +39,8 @@ DEF("machine", HAS_ARG, QEMU_OPTION_machine, \
     "                mem-merge=on|off controls memory merge support (default: on)\n"
     "                iommu=on|off controls emulated Intel IOMMU (VT-d) support (default=off)\n"
     "                aes-key-wrap=on|off controls support for AES key wrapping (default=on)\n"
-    "                dea-key-wrap=on|off controls support for DEA key wrapping (default=on)\n",
+    "                dea-key-wrap=on|off controls support for DEA key wrapping (default=on)\n"
+    "                suppress-vmdesc=on|off disables self-describing migration (default=off)\n",
     QEMU_ARCH_ALL)
 STEXI
 @item -machine [type=]@var{name}[,prop=@var{value}[,...]]

qmp-commands.hx

@@ -661,7 +661,36 @@ Example:
 <- { "return": {} }
 
 EQMP
-{
+
+    {
+        .name       = "migrate-incoming",
+        .args_type  = "uri:s",
+        .mhandler.cmd_new = qmp_marshal_input_migrate_incoming,
+    },
+
+SQMP
+migrate-incoming
+----------------
+
+Continue an incoming migration
+
+Arguments:
+
+- "uri": Source/listening URI (json-string)
+
+Example:
+
+-> { "execute": "migrate-incoming", "arguments": { "uri": "tcp::4446" } }
+<- { "return": {} }
+
+Notes:
+
+(1) QEMU must be started with -incoming defer to allow migrate-incoming to
+    be used
+(2) The uri format is the same as to -incoming
+
+EQMP
+    {
         .name       = "migrate-set-cache-size",
         .args_type  = "value:o",
         .mhandler.cmd_new = qmp_marshal_input_migrate_set_cache_size,

savevm.c

@@ -710,6 +710,12 @@ int qemu_savevm_state_iterate(QEMUFile *f)
     return ret;
 }
 
+static bool should_send_vmdesc(void)
+{
+    MachineState *machine = MACHINE(qdev_get_machine());
+    return !machine->suppress_vmdesc;
+}
+
 void qemu_savevm_state_complete(QEMUFile *f)
 {
     QJSON *vmdesc;
@@ -782,9 +788,11 @@ void qemu_savevm_state_complete(QEMUFile *f)
     qjson_finish(vmdesc);
     vmdesc_len = strlen(qjson_get_str(vmdesc));
 
-    qemu_put_byte(f, QEMU_VM_VMDESCRIPTION);
+    if (should_send_vmdesc()) {
-    qemu_put_be32(f, vmdesc_len);
+        qemu_put_byte(f, QEMU_VM_VMDESCRIPTION);
-    qemu_put_buffer(f, (uint8_t *)qjson_get_str(vmdesc), vmdesc_len);
+        qemu_put_be32(f, vmdesc_len);
+        qemu_put_buffer(f, (uint8_t *)qjson_get_str(vmdesc), vmdesc_len);
+    }
     object_unref(OBJECT(vmdesc));
 
     qemu_fflush(f);
@@ -930,6 +938,7 @@ int qemu_loadvm_state(QEMUFile *f)
     uint8_t section_type;
     unsigned int v;
     int ret;
+    int file_error_after_eof = -1;
 
     if (qemu_savevm_state_blocked(&local_err)) {
         error_report("%s", error_get_pretty(local_err));
@@ -1035,6 +1044,24 @@ int qemu_loadvm_state(QEMUFile *f)
         }
     }
 
+    file_error_after_eof = qemu_file_get_error(f);
+
+    /*
+     * Try to read in the VMDESC section as well, so that dumping tools that
+     * intercept our migration stream have the chance to see it.
+     */
+    if (qemu_get_byte(f) == QEMU_VM_VMDESCRIPTION) {
+        uint32_t size = qemu_get_be32(f);
+        uint8_t *buf = g_malloc(0x1000);
+
+        while (size > 0) {
+            uint32_t read_chunk = MIN(size, 0x1000);
+            qemu_get_buffer(f, buf, read_chunk);
+            size -= read_chunk;
+        }
+        g_free(buf);
+    }
+
     cpu_synchronize_all_post_init();
 
     ret = 0;
@@ -1046,7 +1073,8 @@ out:
     }
 
     if (ret == 0) {
-        ret = qemu_file_get_error(f);
+        /* We may not have a VMDESC section, so ignore relative errors */
+        ret = file_error_after_eof;
     }
 
     return ret;