[Qemu-devel] [PATCH COLO-Frame v16 10/35] COLO: Save PVM state to secondary side when do checkpoint

[zhanghailiang]

The main process of checkpoint is to synchronize SVM with PVM.
VM's state includes ram and device state. So we will migrate PVM's
state to SVM when do checkpoint, just like migration does.

We will cache PVM's state in slave, we use QEMUSizedBuffer
to store the data, we need to know the size of VM state, so in master,
we use qsb to store VM state temporarily, get the data size by call 
qsb_get_length()
and then migrate the data to the qsb in the secondary side.

Signed-off-by: zhanghailiang <address@hidden>
Signed-off-by: Gonglei <address@hidden>
Signed-off-by: Li Zhijian <address@hidden>
Reviewed-by: Dr. David Alan Gilbert <address@hidden>
Cc: Dr. David Alan Gilbert <address@hidden>
---
v16:
- Rename colo_put_cmd_value() to colo_send_message_value()
v13:
- Refactor colo_put_cmd_value() to use 'Error **errp' to indicate success
  or failure.
v12:
- Replace the old colo_ctl_get() with the new helper function 
colo_put_cmd_value()
v11:
- Add Reviewed-by tag
---
 migration/colo.c | 92 +++++++++++++++++++++++++++++++++++++++++++++++++++-----
 migration/ram.c  | 39 ++++++++++++++++++------
 2 files changed, 114 insertions(+), 17 deletions(-)

diff --git a/migration/colo.c b/migration/colo.c
index 027961b..19bffea 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -17,6 +17,9 @@
 #include "qemu/error-report.h"
 #include "qapi/error.h"
 
+/* colo buffer */
+#define COLO_BUFFER_BASE_SIZE (4 * 1024 * 1024)
+
 bool colo_supported(void)
 {
     return true;
@@ -55,6 +58,27 @@ static void colo_send_message(QEMUFile *f, COLOMessage msg,
     trace_colo_send_message(COLOMessage_lookup[msg]);
 }
 
+static void colo_send_message_value(QEMUFile *f, COLOMessage msg,
+                                    uint64_t value, Error **errp)
+{
+    Error *local_err = NULL;
+    int ret;
+
+    colo_send_message(f, msg, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
+    }
+    qemu_put_be64(f, value);
+    qemu_fflush(f);
+
+    ret = qemu_file_get_error(f);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret, "Failed to send value for message:%s",
+                         COLOMessage_lookup[msg]);
+    }
+}
+
 static COLOMessage colo_receive_message(QEMUFile *f, Error **errp)
 {
     COLOMessage msg;
@@ -91,9 +115,13 @@ static void colo_receive_check_message(QEMUFile *f, 
COLOMessage expect_msg,
     }
 }
 
-static int colo_do_checkpoint_transaction(MigrationState *s)
+static int colo_do_checkpoint_transaction(MigrationState *s,
+                                          QEMUSizedBuffer *buffer)
 {
+    QEMUFile *trans = NULL;
+    size_t size;
     Error *local_err = NULL;
+    int ret = -1;
 
     colo_send_message(s->to_dst_file, COLO_MESSAGE_CHECKPOINT_REQUEST,
                       &local_err);
@@ -106,15 +134,48 @@ static int colo_do_checkpoint_transaction(MigrationState 
*s)
     if (local_err) {
         goto out;
     }
+    /* Reset colo buffer and open it for write */
+    qsb_set_length(buffer, 0);
+    trans = qemu_bufopen("w", buffer);
+    if (!trans) {
+        error_report("Open colo buffer for write failed");
+        goto out;
+    }
 
-    /* TODO: suspend and save vm state to colo buffer */
+    qemu_mutex_lock_iothread();
+    vm_stop_force_state(RUN_STATE_COLO);
+    qemu_mutex_unlock_iothread();
+    trace_colo_vm_state_change("run", "stop");
+
+    /* Disable block migration */
+    s->params.blk = 0;
+    s->params.shared = 0;
+    qemu_savevm_state_header(trans);
+    qemu_savevm_state_begin(trans, &s->params);
+    qemu_mutex_lock_iothread();
+    qemu_savevm_state_complete_precopy(trans, false);
+    qemu_mutex_unlock_iothread();
+
+    qemu_fflush(trans);
 
     colo_send_message(s->to_dst_file, COLO_MESSAGE_VMSTATE_SEND, &local_err);
     if (local_err) {
         goto out;
     }
+    /* we send the total size of the vmstate first */
+    size = qsb_get_length(buffer);
+    colo_send_message_value(s->to_dst_file, COLO_MESSAGE_VMSTATE_SIZE,
+                            size, &local_err);
+    if (local_err) {
+        goto out;
+    }
 
-    /* TODO: send vmstate to Secondary */
+    qsb_put_buffer(s->to_dst_file, buffer, size);
+    qemu_fflush(s->to_dst_file);
+    ret = qemu_file_get_error(s->to_dst_file);
+    if (ret < 0) {
+        goto out;
+    }
 
     colo_receive_check_message(s->rp_state.from_dst_file,
                        COLO_MESSAGE_VMSTATE_RECEIVED, &local_err);
@@ -128,18 +189,26 @@ static int colo_do_checkpoint_transaction(MigrationState 
*s)
         goto out;
     }
 
-    /* TODO: resume Primary */
+    ret = 0;
+    /* Resume primary guest */
+    qemu_mutex_lock_iothread();
+    vm_start();
+    qemu_mutex_unlock_iothread();
+    trace_colo_vm_state_change("stop", "run");
 
-    return 0;
 out:
     if (local_err) {
         error_report_err(local_err);
     }
-    return -EINVAL;
+    if (trans) {
+        qemu_fclose(trans);
+    }
+    return ret;
 }
 
 static void colo_process_checkpoint(MigrationState *s)
 {
+    QEMUSizedBuffer *buffer = NULL;
     Error *local_err = NULL;
     int ret;
 
@@ -159,6 +228,12 @@ static void colo_process_checkpoint(MigrationState *s)
         goto out;
     }
 
+    buffer = qsb_create(NULL, COLO_BUFFER_BASE_SIZE);
+    if (buffer == NULL) {
+        error_report("Failed to allocate colo buffer!");
+        goto out;
+    }
+
     qemu_mutex_lock_iothread();
     vm_start();
     qemu_mutex_unlock_iothread();
@@ -166,7 +241,7 @@ static void colo_process_checkpoint(MigrationState *s)
 
     while (s->state == MIGRATION_STATUS_COLO) {
         /* start a colo checkpoint */
-        ret = colo_do_checkpoint_transaction(s);
+        ret = colo_do_checkpoint_transaction(s, buffer);
         if (ret < 0) {
             goto out;
         }
@@ -180,6 +255,9 @@ out:
     migrate_set_state(&s->state, MIGRATION_STATUS_COLO,
                       MIGRATION_STATUS_COMPLETED);
 
+    qsb_free(buffer);
+    buffer = NULL;
+
     if (s->rp_state.from_dst_file) {
         qemu_fclose(s->rp_state.from_dst_file);
     }
diff --git a/migration/ram.c b/migration/ram.c
index 3f05738..cbe8421 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -41,6 +41,7 @@
 #include "trace.h"
 #include "exec/ram_addr.h"
 #include "qemu/rcu_queue.h"
+#include "migration/colo.h"
 
 #ifdef DEBUG_MIGRATION_RAM
 #define DPRINTF(fmt, ...) \
@@ -1874,16 +1875,8 @@ err:
     return ret;
 }
 
-
-/* Each of ram_save_setup, ram_save_iterate and ram_save_complete has
- * long-running RCU critical section.  When rcu-reclaims in the code
- * start to become numerous it will be necessary to reduce the
- * granularity of these critical sections.
- */
-
-static int ram_save_setup(QEMUFile *f, void *opaque)
+static int ram_save_init_globals(void)
 {
-    RAMBlock *block;
     int64_t ram_bitmap_pages; /* Size of bitmap in pages, including gaps */
 
     dirty_rate_high_cnt = 0;
@@ -1949,6 +1942,31 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
     migration_bitmap_sync();
     qemu_mutex_unlock_ramlist();
     qemu_mutex_unlock_iothread();
+    rcu_read_unlock();
+
+    return 0;
+}
+
+/* Each of ram_save_setup, ram_save_iterate and ram_save_complete has
+ * long-running RCU critical section.  When rcu-reclaims in the code
+ * start to become numerous it will be necessary to reduce the
+ * granularity of these critical sections.
+ */
+
+static int ram_save_setup(QEMUFile *f, void *opaque)
+{
+    RAMBlock *block;
+
+    /*
+     * migration has already setup the bitmap, reuse it.
+     */
+    if (!migration_in_colo_state()) {
+        if (ram_save_init_globals() < 0) {
+            return -1;
+         }
+    }
+
+    rcu_read_lock();
 
     qemu_put_be64(f, ram_bytes_total() | RAM_SAVE_FLAG_MEM_SIZE);
 
@@ -2050,7 +2068,8 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
     while (true) {
         int pages;
 
-        pages = ram_find_and_save_block(f, true, &bytes_transferred);
+        pages = ram_find_and_save_block(f, !migration_in_colo_state(),
+                                        &bytes_transferred);
         /* no more blocks to sent */
         if (pages == 0) {
             break;
-- 
1.8.3.1