[Qemu-devel] [PATCH COLO-Frame (Base) v20 08/17] COLO: Send PVM state to secondary side when do checkpoint

[zhanghailiang]

VM checkpointing is to synchronize the state of PVM to SVM, just
like migration does, we re-use save helpers to achieve migrating
PVM's state to Secondary side.

COLO need to cache the data of VM's state in the secondary side before
synchronize it to SVM. COLO need the size of the data to determine
how much data should be read in the secondary side.
So here, we can get the size of the data by saving it into I/O channel
before send it to 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>
---
v19:
- fix title and comment.
v17:
- Rebase to master, use the new channel-buffer API
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 | 83 ++++++++++++++++++++++++++++++++++++++++++++++++++------
 migration/ram.c  | 37 ++++++++++++++++++-------
 2 files changed, 102 insertions(+), 18 deletions(-)

diff --git a/migration/colo.c b/migration/colo.c
index bf32d63..d8ac34d 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -13,10 +13,13 @@
 #include "qemu/osdep.h"
 #include "sysemu/sysemu.h"
 #include "migration/colo.h"
+#include "io/channel-buffer.h"
 #include "trace.h"
 #include "qemu/error-report.h"
 #include "qapi/error.h"
 
+#define COLO_BUFFER_BASE_SIZE (4 * 1024 * 1024)
+
 bool colo_supported(void)
 {
     return false;
@@ -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 +115,12 @@ 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,
+                                          QIOChannelBuffer *bioc,
+                                          QEMUFile *fb)
 {
     Error *local_err = NULL;
+    int ret = -1;
 
     colo_send_message(s->to_dst_file, COLO_MESSAGE_CHECKPOINT_REQUEST,
                       &local_err);
@@ -106,15 +133,46 @@ static int colo_do_checkpoint_transaction(MigrationState 
*s)
     if (local_err) {
         goto out;
     }
+    /* Reset channel-buffer directly */
+    qio_channel_io_seek(QIO_CHANNEL(bioc), 0, 0, NULL);
+    bioc->usage = 0;
+
+    qemu_mutex_lock_iothread();
+    vm_stop_force_state(RUN_STATE_COLO);
+    qemu_mutex_unlock_iothread();
+    trace_colo_vm_state_change("run", "stop");
 
-    /* TODO: suspend and save vm state to colo buffer */
+    /* Disable block migration */
+    s->params.blk = 0;
+    s->params.shared = 0;
+    qemu_savevm_state_header(fb);
+    qemu_savevm_state_begin(fb, &s->params);
+    qemu_mutex_lock_iothread();
+    qemu_savevm_state_complete_precopy(fb, false);
+    qemu_mutex_unlock_iothread();
+
+    qemu_fflush(fb);
 
     colo_send_message(s->to_dst_file, COLO_MESSAGE_VMSTATE_SEND, &local_err);
     if (local_err) {
         goto out;
     }
+    /*
+     * We need the size of the VMstate data in Secondary side,
+     * With which we can decide how much data should be read.
+     */
+    colo_send_message_value(s->to_dst_file, COLO_MESSAGE_VMSTATE_SIZE,
+                            bioc->usage, &local_err);
+    if (local_err) {
+        goto out;
+    }
 
-    /* TODO: send vmstate to Secondary */
+    qemu_put_buffer(s->to_dst_file, bioc->data, bioc->usage);
+    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 +186,24 @@ static int colo_do_checkpoint_transaction(MigrationState 
*s)
         goto out;
     }
 
-    /* TODO: resume Primary */
+    ret = 0;
+
+    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;
+    return ret;
 }
 
 static void colo_process_checkpoint(MigrationState *s)
 {
+    QIOChannelBuffer *bioc;
+    QEMUFile *fb = NULL;
     Error *local_err = NULL;
     int ret;
 
@@ -158,6 +222,9 @@ static void colo_process_checkpoint(MigrationState *s)
     if (local_err) {
         goto out;
     }
+    bioc = qio_channel_buffer_new(COLO_BUFFER_BASE_SIZE);
+    fb = qemu_fopen_channel_output(QIO_CHANNEL(bioc));
+    object_unref(OBJECT(bioc));
 
     qemu_mutex_lock_iothread();
     vm_start();
@@ -165,7 +232,7 @@ static void colo_process_checkpoint(MigrationState *s)
     trace_colo_vm_state_change("stop", "run");
 
     while (s->state == MIGRATION_STATUS_COLO) {
-        ret = colo_do_checkpoint_transaction(s);
+        ret = colo_do_checkpoint_transaction(s, bioc, fb);
         if (ret < 0) {
             goto out;
         }
@@ -178,7 +245,7 @@ out:
     }
     migrate_set_state(&s->state, MIGRATION_STATUS_COLO,
                       MIGRATION_STATUS_COMPLETED);
-
+    qemu_fclose(fb);
     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 c8ec9f2..34cf416 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -43,6 +43,7 @@
 #include "trace.h"
 #include "exec/ram_addr.h"
 #include "qemu/rcu_queue.h"
+#include "migration/colo.h"
 
 #ifdef DEBUG_MIGRATION_RAM
 #define DPRINTF(fmt, ...) \
@@ -1868,16 +1869,8 @@ 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;
@@ -1943,6 +1936,29 @@ 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);
 
@@ -2044,7 +2060,8 @@ 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