Block live migration

This patch introduces block migration called during live migration. Block
are being copied to the destination in an async way. First the code will
transfer the whole disk and then transfer all dirty blocks accumulted during
the migration.
Still need to improve transition from the iterative phase of migration to the
end phase. For now transition will take place when all blocks transfered once,
all the dirty blocks will be transfered during the end phase (guest is
suspended).

Changes from v4:
- Global variabels moved to a global state structure allocated dynamically.
- Minor coding style issues.
- Poll block.c for tracking of dirty blocks instead of manage it here.

Signed-off-by: Liran Schour <lirans@il.ibm.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>

14 files changed, 713 insertions, 40 deletions

diff --git a/Makefile b/Makefile
index fe5d868e58..489c5a074e 100644
--- a/Makefile
+++ b/Makefile
@@ -138,6 +138,7 @@ obj-y += qemu-char.o aio.o savevm.o
 obj-y += msmouse.o ps2.o
 obj-y += qdev.o qdev-properties.o
 obj-y += qint.o qstring.o qdict.o qlist.o qemu-config.o
+obj-y += block-migration.o
 
 obj-$(CONFIG_BRLAPI) += baum.o
 obj-$(CONFIG_POSIX) += migration-exec.o migration-unix.o migration-fd.o
diff --git a/block-migration.c b/block-migration.c
new file mode 100644
index 0000000000..4b4eddf62a
--- /dev/null
+++ b/block-migration.c
@@ -0,0 +1,558 @@
+/*
+ * QEMU live block migration
+ *
+ * Copyright IBM, Corp. 2009
+ *
+ * Authors:
+ *  Liran Schour   <lirans@il.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu-common.h"
+#include "block_int.h"
+#include "hw/hw.h"
+#include "block-migration.h"
+#include <assert.h>
+#include <pthread.h>
+
+#define SECTOR_BITS 9
+#define SECTOR_SIZE (1 << SECTOR_BITS)
+#define SECTOR_MASK ~(SECTOR_SIZE - 1);
+
+#define BLOCK_SIZE (block_mig_state->sectors_per_block << SECTOR_BITS) 
+
+#define BLK_MIG_FLAG_DEVICE_BLOCK       0x01
+#define BLK_MIG_FLAG_EOS                0x02
+
+#define MAX_IS_ALLOCATED_SEARCH 65536
+#define MAX_BLOCKS_READ 10000
+#define BLOCKS_READ_CHANGE 100
+#define INITIAL_BLOCKS_READ 100
+
+//#define DEBUG_BLK_MIGRATION
+
+#ifdef DEBUG_BLK_MIGRATION
+#define dprintf(fmt, ...)						\
+    do { printf("blk_migration: " fmt, ## __VA_ARGS__); } while (0)
+#else
+#define dprintf(fmt, ...)			\
+    do { } while (0)
+#endif
+
+typedef struct BlkMigBlock {
+    uint8_t *buf;
+    BlkMigDevState *bmds;
+    int64_t sector;
+    struct iovec iov;
+    QEMUIOVector qiov;
+    BlockDriverAIOCB *aiocb;
+    int ret;
+    struct BlkMigBlock *next;
+} BlkMigBlock;
+
+typedef struct BlkMigState {
+    int bulk_completed;
+    int blk_enable;
+    int shared_base;
+    int no_dirty;
+    QEMUFile *load_file;
+    BlkMigDevState *bmds_first;
+    int sectors_per_block;
+    BlkMigBlock *first_blk;
+    BlkMigBlock *last_blk;
+    int submitted;
+    int read_done;
+    int transferred;
+    int64_t print_completion;
+} BlkMigState;
+
+static BlkMigState *block_mig_state = NULL;  
+
+static void blk_mig_read_cb(void *opaque, int ret)
+{
+    BlkMigBlock *blk = opaque;
+  
+    blk->ret = ret;
+    
+    /* insert at the end */
+    if(block_mig_state->last_blk == NULL) {
+        block_mig_state->first_blk = blk;
+        block_mig_state->last_blk = blk;
+    } else {
+        block_mig_state->last_blk->next = blk;
+        block_mig_state->last_blk = blk;
+    }
+    
+    block_mig_state->submitted--;
+    block_mig_state->read_done++;
+    assert(block_mig_state->submitted >= 0);
+    
+    return;
+}
+
+static int mig_read_device_bulk(QEMUFile *f, BlkMigDevState *bms)
+{ 
+    int nr_sectors;
+    int64_t total_sectors, cur_sector = 0;
+    BlockDriverState *bs = bms->bs;
+    BlkMigBlock *blk;
+    
+    blk = qemu_malloc(sizeof(BlkMigBlock));
+    blk->buf = qemu_malloc(BLOCK_SIZE);
+    
+    cur_sector = bms->cur_sector;
+    total_sectors = bdrv_getlength(bs) >> SECTOR_BITS;
+  
+    if(bms->shared_base) {
+        while(cur_sector < bms->total_sectors && 
+              !bdrv_is_allocated(bms->bs, cur_sector, 
+                                 MAX_IS_ALLOCATED_SEARCH, &nr_sectors)) {
+            cur_sector += nr_sectors;
+        }
+    }
+    
+    if(cur_sector >= total_sectors) {
+        bms->cur_sector = total_sectors;
+        qemu_free(blk->buf);
+        qemu_free(blk);
+        return 1;
+    }
+  
+    if(cur_sector >= block_mig_state->print_completion) {
+        printf("Completed %" PRId64 " %%\r", cur_sector * 100 / total_sectors);
+        fflush(stdout);
+        block_mig_state->print_completion += 
+            (block_mig_state->sectors_per_block * 10000);
+    }
+  
+    /* we going to transfder BLOCK_SIZE any way even if it is not allocated */
+    nr_sectors = block_mig_state->sectors_per_block;
+
+    cur_sector &= ~((int64_t)block_mig_state->sectors_per_block -1);
+    
+    if(total_sectors - cur_sector < block_mig_state->sectors_per_block) {
+        nr_sectors = (total_sectors - cur_sector);
+    }
+  
+    bms->cur_sector = cur_sector + nr_sectors;
+    blk->sector = cur_sector;
+    blk->bmds = bms;
+    blk->next = NULL;
+  
+    blk->iov.iov_base = blk->buf;
+    blk->iov.iov_len = nr_sectors * SECTOR_SIZE;
+    qemu_iovec_init_external(&blk->qiov, &blk->iov, 1);
+  
+    blk->aiocb = bdrv_aio_readv(bs, cur_sector, &blk->qiov,
+                                nr_sectors, blk_mig_read_cb, blk);
+  
+    if(!blk->aiocb) {
+        printf("Error reading sector %" PRId64 "\n", cur_sector);
+        qemu_free(blk->buf);
+        qemu_free(blk);
+        return 0;
+    }
+
+    bdrv_reset_dirty(bms->bs, cur_sector, nr_sectors);
+    block_mig_state->submitted++;
+  
+    return (bms->cur_sector >= total_sectors);
+}
+
+static int mig_save_device_bulk(QEMUFile *f, BlkMigDevState *bmds)
+{ 
+    int len, nr_sectors;
+    int64_t total_sectors = bmds->total_sectors, cur_sector = 0;
+    uint8_t *tmp_buf = NULL;
+    BlockDriverState *bs = bmds->bs;
+
+    tmp_buf = qemu_malloc(BLOCK_SIZE);
+  
+    cur_sector = bmds->cur_sector;
+    
+    if(bmds->shared_base) {
+        while(cur_sector < bmds->total_sectors && 
+              !bdrv_is_allocated(bmds->bs, cur_sector, 
+                                 MAX_IS_ALLOCATED_SEARCH, &nr_sectors)) {
+            cur_sector += nr_sectors;
+        }
+    }
+    
+    if(cur_sector >= total_sectors) {
+        bmds->cur_sector = total_sectors;
+        qemu_free(tmp_buf);
+        return 1;
+    }
+    
+    if(cur_sector >= block_mig_state->print_completion) {
+        printf("Completed %" PRId64 " %%\r", cur_sector * 100 / total_sectors);
+        fflush(stdout);
+        block_mig_state->print_completion += 
+            (block_mig_state->sectors_per_block * 10000);
+    }
+    
+    cur_sector &= ~((int64_t)block_mig_state->sectors_per_block -1);
+        
+    /* we going to transfer 
+       BLOCK_SIZE 
+       any way even if it is not allocated */
+    nr_sectors = block_mig_state->sectors_per_block;
+  
+    if(total_sectors - cur_sector < block_mig_state->sectors_per_block) {
+        nr_sectors = (total_sectors - cur_sector);
+    }
+  
+    if(bdrv_read(bs, cur_sector, tmp_buf, nr_sectors) < 0) {
+        printf("Error reading sector %" PRId64 "\n", cur_sector);
+    }
+
+    bdrv_reset_dirty(bs, cur_sector, nr_sectors);
+  
+    /* Device name */
+    qemu_put_be64(f,(cur_sector << SECTOR_BITS) | BLK_MIG_FLAG_DEVICE_BLOCK);
+  
+    len = strlen(bs->device_name);
+    qemu_put_byte(f, len);
+    qemu_put_buffer(f, (uint8_t *)bs->device_name, len);
+  
+    qemu_put_buffer(f, tmp_buf, 
+                    BLOCK_SIZE);
+    
+    bmds->cur_sector = cur_sector + block_mig_state->sectors_per_block;
+  
+    qemu_free(tmp_buf);
+  
+    return (bmds->cur_sector >= total_sectors);
+}
+
+static void send_blk(QEMUFile *f, BlkMigBlock * blk)
+{
+    int len;
+  
+    /* Device name */ 
+    qemu_put_be64(f,(blk->sector << SECTOR_BITS) | BLK_MIG_FLAG_DEVICE_BLOCK);
+  
+    len = strlen(blk->bmds->bs->device_name);
+    qemu_put_byte(f, len);
+    qemu_put_buffer(f, (uint8_t *)blk->bmds->bs->device_name, len);
+  
+    qemu_put_buffer(f, blk->buf, 
+                    BLOCK_SIZE);
+  
+    return;
+}
+
+static void blk_mig_save_dev_info(QEMUFile *f, BlkMigDevState *bmds)
+{
+}
+
+static void set_dirty_tracking(int enable)
+{
+    BlkMigDevState *bmds;
+    for(bmds = block_mig_state->bmds_first; bmds != NULL; bmds = bmds->next) {
+        bdrv_set_dirty_tracking(bmds->bs,enable);
+    }
+    
+    return;
+}
+
+static void init_blk_migration(QEMUFile *f)
+{
+    BlkMigDevState **pbmds, *bmds;
+    BlockDriverState *bs;
+    
+    for (bs = bdrv_first; bs != NULL; bs = bs->next) {
+        if(bs->type == BDRV_TYPE_HD) {
+            bmds = qemu_mallocz(sizeof(BlkMigDevState));
+            bmds->bs = bs;
+            bmds->bulk_completed = 0;
+            bmds->total_sectors = bdrv_getlength(bs) >> SECTOR_BITS;
+            bmds->shared_base = block_mig_state->shared_base;
+	          
+            if(bmds->shared_base) {
+                printf("Start migration for %s with shared base image\n", 
+                       bs->device_name);
+            } else {
+                printf("Start full migration for %s\n", bs->device_name);
+            }
+      
+            /* insert at the end */
+            pbmds = &block_mig_state->bmds_first;
+            while (*pbmds != NULL)
+                pbmds = &(*pbmds)->next;
+            *pbmds = bmds;
+      
+            blk_mig_save_dev_info(f, bmds);
+	    
+        }
+    } 
+    
+    block_mig_state->sectors_per_block = bdrv_get_sectors_per_chunk();
+    
+    return;
+}
+
+static int blk_mig_save_bulked_block(QEMUFile *f, int is_async)
+{
+    BlkMigDevState *bmds;
+
+    for (bmds = block_mig_state->bmds_first; bmds != NULL; bmds = bmds->next) {
+        if(bmds->bulk_completed == 0) {
+            if(is_async) {
+                if(mig_read_device_bulk(f, bmds) == 1) {
+                    /* completed bulk section for this device */
+                    bmds->bulk_completed = 1;
+                }
+            } else {
+                if(mig_save_device_bulk(f,bmds) == 1) {
+                    /* completed bulk section for this device */
+                    bmds->bulk_completed = 1;
+                }
+            }
+            return 1;
+        }
+    }
+  
+    /* we reached here means bulk is completed */
+    block_mig_state->bulk_completed = 1;
+  
+    return 0;
+    
+}
+
+#define MAX_NUM_BLOCKS 4
+
+static void blk_mig_save_dirty_blocks(QEMUFile *f)
+{
+    BlkMigDevState *bmds;
+    uint8_t buf[BLOCK_SIZE];
+    int64_t sector;
+    int len;
+    
+    for(bmds = block_mig_state->bmds_first; bmds != NULL; bmds = bmds->next) {
+        for(sector = 0; sector < bmds->cur_sector;) {
+	    
+            if(bdrv_get_dirty(bmds->bs,sector)) {
+		
+                if(bdrv_read(bmds->bs, sector, buf, 
+                             block_mig_state->sectors_per_block) < 0) {
+                }
+		
+                /* device name */
+                qemu_put_be64(f,(sector << SECTOR_BITS) 
+                              | BLK_MIG_FLAG_DEVICE_BLOCK);
+	
+                len = strlen(bmds->bs->device_name);
+	
+                qemu_put_byte(f, len);
+                qemu_put_buffer(f, (uint8_t *)bmds->bs->device_name, len);
+	
+                qemu_put_buffer(f, buf, 
+                                (block_mig_state->sectors_per_block * 
+                                 SECTOR_SIZE));
+		
+                bdrv_reset_dirty(bmds->bs, sector, 
+                                 block_mig_state->sectors_per_block);
+	
+                sector += block_mig_state->sectors_per_block;
+            } else {
+                /* sector is clean */
+                sector += block_mig_state->sectors_per_block;
+            }  
+        }
+    }
+    
+    return;
+}
+
+static void flush_blks(QEMUFile* f)
+{
+    BlkMigBlock *blk, *tmp;
+    
+    dprintf("%s Enter submitted %d read_done %d transfered\n", __FUNCTION__, 
+            submitted, read_done, transfered);
+  
+    for(blk = block_mig_state->first_blk; 
+        blk != NULL && !qemu_file_rate_limit(f); blk = tmp) {
+        send_blk(f, blk);
+    
+        tmp = blk->next;
+        qemu_free(blk->buf);
+        qemu_free(blk);
+    
+        block_mig_state->read_done--;
+        block_mig_state->transferred++;
+        assert(block_mig_state->read_done >= 0);
+    }
+    block_mig_state->first_blk = blk;
+  
+    if(block_mig_state->first_blk == NULL) {
+        block_mig_state->last_blk = NULL;
+    }
+
+    dprintf("%s Exit submitted %d read_done %d transferred%d\n", __FUNCTION__, 
+            block_mig_state->submitted, block_mig_state->read_done, 
+            block_mig_state->transferred);
+
+    return;
+}
+
+static int is_stage2_completed(void)
+{
+    BlkMigDevState *bmds;
+  
+    if(block_mig_state->submitted > 0) {
+        return 0;
+    }
+  
+    for (bmds = block_mig_state->bmds_first; bmds != NULL; bmds = bmds->next) {
+        if(bmds->bulk_completed == 0) {
+            return 0;
+        }
+    }
+    
+    return 1;
+}
+
+static int block_save_live(QEMUFile *f, int stage, void *opaque)
+{
+    int ret = 1;
+    
+    dprintf("Enter save live stage %d submitted %d transferred %d\n", stage, 
+            submitted, transferred);
+  
+    if(block_mig_state->blk_enable != 1) {
+        /* no need to migrate storage */
+    
+        qemu_put_be64(f,BLK_MIG_FLAG_EOS);
+        return 1;
+    }
+  
+    if(stage == 1) {
+        init_blk_migration(f);
+	
+        /* start track dirty blocks */
+        set_dirty_tracking(1);
+	
+    }
+
+    flush_blks(f);
+  
+    /* control the rate of transfer */
+    while ((block_mig_state->submitted + block_mig_state->read_done) * 
+           (BLOCK_SIZE) < 
+           (qemu_file_get_rate_limit(f))) {
+	
+        ret = blk_mig_save_bulked_block(f, 1);
+	
+        if (ret == 0) /* no more bulk blocks for now*/
+            break;
+    }
+  
+    flush_blks(f);
+    
+    if(stage == 3) {
+	
+        while(blk_mig_save_bulked_block(f, 0) != 0);
+	
+        blk_mig_save_dirty_blocks(f);
+	
+        /* stop track dirty blocks */
+        set_dirty_tracking(0);;
+	
+        printf("\nBlock migration completed\n");  
+    }
+  
+    qemu_put_be64(f,BLK_MIG_FLAG_EOS);
+  
+    return ((stage == 2) && is_stage2_completed());
+}
+
+static int block_load(QEMUFile *f, void *opaque, int version_id)
+{
+    int len, flags;
+    char device_name[256];
+    int64_t addr;
+    BlockDriverState *bs;
+    uint8_t *buf;
+    
+    block_mig_state->sectors_per_block = bdrv_get_sectors_per_chunk();
+    buf = qemu_malloc(BLOCK_SIZE);
+    
+    do {
+    
+        addr = qemu_get_be64(f);
+    
+        flags = addr & ~SECTOR_MASK;
+        addr &= SECTOR_MASK;
+    
+        if(flags & BLK_MIG_FLAG_DEVICE_BLOCK) {
+	    
+            /* get device name */
+            len = qemu_get_byte(f);
+      
+            qemu_get_buffer(f, (uint8_t *)device_name, len);
+            device_name[len] = '\0';
+      
+            bs = bdrv_find(device_name);
+      
+            qemu_get_buffer(f, buf, 
+                            BLOCK_SIZE);
+            if(bs != NULL) {
+	
+                bdrv_write(bs, (addr >> SECTOR_BITS), 
+                           buf, block_mig_state->sectors_per_block);
+            } else {
+                printf("Error unknown block device %s\n", device_name);
+            }
+        } else if(flags & BLK_MIG_FLAG_EOS) {
+	    
+        } else {
+            printf("Unknown flags\n");
+        }
+    } while(!(flags & BLK_MIG_FLAG_EOS));
+  
+    qemu_free(buf);
+
+    return 0;
+}
+
+static void block_set_params(int blk_enable, int shared_base, void *opaque)
+{
+    assert(opaque == block_mig_state);
+
+    block_mig_state->blk_enable = blk_enable;
+    block_mig_state->shared_base = shared_base;
+  
+    /* shared base means that blk_enable = 1 */
+    block_mig_state->blk_enable |= shared_base;
+  
+    return;
+}
+
+void blk_mig_info(void)
+{
+    BlockDriverState *bs;
+  
+    for (bs = bdrv_first; bs != NULL; bs = bs->next) {
+        printf("Device %s\n", bs->device_name);
+        if(bs->type == BDRV_TYPE_HD) {
+            printf("device %s format %s\n", 
+                   bs->device_name, bs->drv->format_name);
+        }
+    }
+}
+
+void blk_mig_init(void)
+{ 
+    
+    block_mig_state = qemu_mallocz(sizeof(BlkMigState));
+    
+    register_savevm_live("block", 0, 1, block_set_params, block_save_live, 
+                         NULL, block_load, block_mig_state);
+
+ 
+}
diff --git a/block-migration.h b/block-migration.h
new file mode 100644
index 0000000000..c33d3cbf05
--- /dev/null
+++ b/block-migration.h
@@ -0,0 +1,29 @@
+/*
+ * QEMU live block migration
+ *
+ * Copyright IBM, Corp. 2009
+ *
+ * Authors:
+ *  Liran Schour   <lirans@il.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef BLOCK_MIGRATION_H
+#define BLOCK_MIGRATION_H
+
+typedef struct BlkMigDevState {
+    BlockDriverState *bs;
+    int bulk_completed;
+    int shared_base;
+    struct BlkMigDevState *next;
+    int64_t cur_sector;
+    int64_t total_sectors;
+    int64_t dirty;
+} BlkMigDevState;
+ 
+void blk_mig_init(void);
+void blk_mig_info(void);
+#endif /* BLOCK_MIGRATION_H */
diff --git a/buffered_file.c b/buffered_file.c
index 56b4418ed9..217f75e60e 100644
--- a/buffered_file.c
+++ b/buffered_file.c
@@ -211,6 +211,13 @@ out:
     return s->xfer_limit;
 }
 
+static size_t buffered_get_rate_limit(void *opaque)
+{
+    QEMUFileBuffered *s = opaque;
+  
+    return s->xfer_limit;
+}
+
 static void buffered_rate_tick(void *opaque)
 {
     QEMUFileBuffered *s = opaque;
@@ -251,7 +258,8 @@ QEMUFile *qemu_fopen_ops_buffered(void *opaque,
 
     s->file = qemu_fopen_ops(s, buffered_put_buffer, NULL,
                              buffered_close, buffered_rate_limit,
-                             buffered_set_rate_limit);
+                             buffered_set_rate_limit,
+			     buffered_get_rate_limit);
 
     s->timer = qemu_new_timer(rt_clock, buffered_rate_tick, s);
 
diff --git a/hw/hw.h b/hw/hw.h
index 1d4af2a9df..7889aa3cee 100644
--- a/hw/hw.h
+++ b/hw/hw.h
@@ -43,12 +43,14 @@ typedef int (QEMUFileRateLimit)(void *opaque);
  * the old rate otherwise
  */
 typedef size_t (QEMUFileSetRateLimit)(void *opaque, size_t new_rate);
+typedef size_t (QEMUFileGetRateLimit)(void *opaque);
 
 QEMUFile *qemu_fopen_ops(void *opaque, QEMUFilePutBufferFunc *put_buffer,
                          QEMUFileGetBufferFunc *get_buffer,
                          QEMUFileCloseFunc *close,
                          QEMUFileRateLimit *rate_limit,
-                         QEMUFileSetRateLimit *set_rate_limit);
+                         QEMUFileSetRateLimit *set_rate_limit,
+			 QEMUFileGetRateLimit *get_rate_limit);
 QEMUFile *qemu_fopen(const char *filename, const char *mode);
 QEMUFile *qemu_fdopen(int fd, const char *mode);
 QEMUFile *qemu_fopen_socket(int fd);
@@ -85,6 +87,7 @@ unsigned int qemu_get_be32(QEMUFile *f);
 uint64_t qemu_get_be64(QEMUFile *f);
 int qemu_file_rate_limit(QEMUFile *f);
 size_t qemu_file_set_rate_limit(QEMUFile *f, size_t new_rate);
+size_t qemu_file_get_rate_limit(QEMUFile *f);
 int qemu_file_has_error(QEMUFile *f);
 void qemu_file_set_error(QEMUFile *f);
 
@@ -239,6 +242,7 @@ static inline void qemu_get_sbe64s(QEMUFile *f, int64_t *pv)
 int64_t qemu_ftell(QEMUFile *f);
 int64_t qemu_fseek(QEMUFile *f, int64_t pos, int whence);
 
+typedef void SaveSetParamsHandler(int blk_enable, int shared, void * opaque);
 typedef void SaveStateHandler(QEMUFile *f, void *opaque);
 typedef int SaveLiveStateHandler(QEMUFile *f, int stage, void *opaque);
 typedef int LoadStateHandler(QEMUFile *f, void *opaque, int version_id);
@@ -253,7 +257,8 @@ int register_savevm(const char *idstr,
 int register_savevm_live(const char *idstr,
                          int instance_id,
                          int version_id,
-                         SaveLiveStateHandler *save_live_state,
+                         SaveSetParamsHandler *set_params,
+			 SaveLiveStateHandler *save_live_state,
                          SaveStateHandler *save_state,
                          LoadStateHandler *load_state,
                          void *opaque);
diff --git a/migration-exec.c b/migration-exec.c
index b45c83385a..c83066959a 100644
--- a/migration-exec.c
+++ b/migration-exec.c
@@ -53,8 +53,10 @@ static int exec_close(FdMigrationState *s)
 }
 
 MigrationState *exec_start_outgoing_migration(const char *command,
-                                             int64_t bandwidth_limit,
-                                             int detach)
+					      int64_t bandwidth_limit,
+					      int detach,
+					      int blk,
+					      int inc)
 {
     FdMigrationState *s;
     FILE *f;
@@ -84,6 +86,9 @@ MigrationState *exec_start_outgoing_migration(const char *command,
     s->mig_state.get_status = migrate_fd_get_status;
     s->mig_state.release = migrate_fd_release;
 
+    s->mig_state.blk = blk;
+    s->mig_state.shared = inc;
+    
     s->state = MIG_STATE_ACTIVE;
     s->mon_resume = NULL;
     s->bandwidth_limit = bandwidth_limit;
diff --git a/migration-fd.c b/migration-fd.c
index 15b44158ff..587f9d8e84 100644
--- a/migration-fd.c
+++ b/migration-fd.c
@@ -54,7 +54,9 @@ static int fd_close(FdMigrationState *s)
 MigrationState *fd_start_outgoing_migration(Monitor *mon,
 					    const char *fdname,
 					    int64_t bandwidth_limit,
-					    int detach)
+					    int detach,
+					    int blk,
+					    int inc)
 {
     FdMigrationState *s;
 
@@ -78,6 +80,9 @@ MigrationState *fd_start_outgoing_migration(Monitor *mon,
     s->mig_state.get_status = migrate_fd_get_status;
     s->mig_state.release = migrate_fd_release;
 
+    s->mig_state.blk = blk;
+    s->mig_state.shared = inc;
+    
     s->state = MIG_STATE_ACTIVE;
     s->mon_resume = NULL;
     s->bandwidth_limit = bandwidth_limit;
diff --git a/migration-tcp.c b/migration-tcp.c
index 9ed92b4427..efa7c74c67 100644
--- a/migration-tcp.c
+++ b/migration-tcp.c
@@ -78,7 +78,9 @@ static void tcp_wait_for_connect(void *opaque)
 
 MigrationState *tcp_start_outgoing_migration(const char *host_port,
                                              int64_t bandwidth_limit,
-                                             int detach)
+                                             int detach,
+					     int blk,
+					     int inc)
 {
     struct sockaddr_in addr;
     FdMigrationState *s;
@@ -96,6 +98,9 @@ MigrationState *tcp_start_outgoing_migration(const char *host_port,
     s->mig_state.get_status = migrate_fd_get_status;
     s->mig_state.release = migrate_fd_release;
 
+    s->mig_state.blk = blk;
+    s->mig_state.shared = inc;
+
     s->state = MIG_STATE_ACTIVE;
     s->mon_resume = NULL;
     s->bandwidth_limit = bandwidth_limit;
diff --git a/migration-unix.c b/migration-unix.c
index a26587a3ea..25cd6d3d2d 100644
--- a/migration-unix.c
+++ b/migration-unix.c
@@ -77,7 +77,9 @@ static void unix_wait_for_connect(void *opaque)
 
 MigrationState *unix_start_outgoing_migration(const char *path,
 					      int64_t bandwidth_limit,
-					      int detach)
+					      int detach,
+					      int blk,
+					      int inc)
 {
     FdMigrationState *s;
     struct sockaddr_un addr;
@@ -95,6 +97,9 @@ MigrationState *unix_start_outgoing_migration(const char *path,
     s->mig_state.get_status = migrate_fd_get_status;
     s->mig_state.release = migrate_fd_release;
 
+    s->mig_state.blk = blk;
+    s->mig_state.shared = inc;
+
     s->state = MIG_STATE_ACTIVE;
     s->mon_resume = NULL;
     s->bandwidth_limit = bandwidth_limit;
diff --git a/migration.c b/migration.c
index b20beb7302..3ae0be86c8 100644
--- a/migration.c
+++ b/migration.c
@@ -58,16 +58,24 @@ void do_migrate(Monitor *mon, const QDict *qdict, QObject **ret_data)
     const char *p;
     int detach = qdict_get_int(qdict, "detach");
     const char *uri = qdict_get_str(qdict, "uri");
-
+    
     if (strstart(uri, "tcp:", &p))
-        s = tcp_start_outgoing_migration(p, max_throttle, detach);
+        s = tcp_start_outgoing_migration(p, max_throttle, detach, 
+                                         (int)qdict_get_int(qdict, "blk"), 
+                                         (int)qdict_get_int(qdict, "inc"));
 #if !defined(WIN32)
     else if (strstart(uri, "exec:", &p))
-        s = exec_start_outgoing_migration(p, max_throttle, detach);
+        s = exec_start_outgoing_migration(p, max_throttle, detach, 
+                                          (int)qdict_get_int(qdict, "blk"), 
+                                          (int)qdict_get_int(qdict, "inc"));
     else if (strstart(uri, "unix:", &p))
-        s = unix_start_outgoing_migration(p, max_throttle, detach);
+        s = unix_start_outgoing_migration(p, max_throttle, detach, 
+					  (int)qdict_get_int(qdict, "blk"), 
+                                          (int)qdict_get_int(qdict, "inc"));
     else if (strstart(uri, "fd:", &p))
-        s = fd_start_outgoing_migration(mon, p, max_throttle, detach);
+        s = fd_start_outgoing_migration(mon, p, max_throttle, detach, 
+                                        (int)qdict_get_int(qdict, "blk"), 
+                                        (int)qdict_get_int(qdict, "inc"));
 #endif
     else
         monitor_printf(mon, "unknown migration protocol: %s\n", uri);
@@ -251,13 +259,14 @@ void migrate_fd_connect(FdMigrationState *s)
                                       migrate_fd_close);
 
     dprintf("beginning savevm\n");
-    ret = qemu_savevm_state_begin(s->file);
+    ret = qemu_savevm_state_begin(s->file, s->mig_state.blk, 
+                                  s->mig_state.shared);
     if (ret < 0) {
         dprintf("failed, %d\n", ret);
         migrate_fd_error(s);
         return;
     }
-
+    
     migrate_fd_put_ready(s);
 }
 
diff --git a/migration.h b/migration.h
index 2d28b8f395..56adf05e6f 100644
--- a/migration.h
+++ b/migration.h
@@ -30,6 +30,8 @@ struct MigrationState
     void (*cancel)(MigrationState *s);
     int (*get_status)(MigrationState *s);
     void (*release)(MigrationState *s);
+    int blk;
+    int shared;
 };
 
 typedef struct FdMigrationState FdMigrationState;
@@ -65,27 +67,35 @@ void do_info_migrate(Monitor *mon);
 int exec_start_incoming_migration(const char *host_port);
 
 MigrationState *exec_start_outgoing_migration(const char *host_port,
-					     int64_t bandwidth_limit,
-					     int detach);
+					      int64_t bandwidth_limit,
+					      int detach,
+					      int blk,
+					      int inc);
 
 int tcp_start_incoming_migration(const char *host_port);
 
 MigrationState *tcp_start_outgoing_migration(const char *host_port,
 					     int64_t bandwidth_limit,
-					     int detach);
+					     int detach,
+					     int blk,
+					     int inc);
 
 int unix_start_incoming_migration(const char *path);
 
 MigrationState *unix_start_outgoing_migration(const char *path,
 					      int64_t bandwidth_limit,
-					      int detach);
+					      int detach,
+					      int blk,
+					      int inc);
 
 int fd_start_incoming_migration(const char *path);
 
 MigrationState *fd_start_outgoing_migration(Monitor *mon,
 					    const char *fdname,
 					    int64_t bandwidth_limit,
-					    int detach);
+					    int detach,
+					    int blk,
+					    int inc);
 
 void migrate_fd_monitor_suspend(FdMigrationState *s);
 
diff --git a/savevm.c b/savevm.c
index 74f2c66d29..4668843c3f 100644
--- a/savevm.c
+++ b/savevm.c
@@ -169,6 +169,7 @@ struct QEMUFile {
     QEMUFileCloseFunc *close;
     QEMUFileRateLimit *rate_limit;
     QEMUFileSetRateLimit *set_rate_limit;
+    QEMUFileGetRateLimit *get_rate_limit;
     void *opaque;
     int is_write;
 
@@ -264,9 +265,11 @@ QEMUFile *qemu_popen(FILE *stdio_file, const char *mode)
     s->stdio_file = stdio_file;
 
     if(mode[0] == 'r') {
-        s->file = qemu_fopen_ops(s, NULL, stdio_get_buffer, stdio_pclose, NULL, NULL);
+        s->file = qemu_fopen_ops(s, NULL, stdio_get_buffer, stdio_pclose, 
+				 NULL, NULL, NULL);
     } else {
-        s->file = qemu_fopen_ops(s, stdio_put_buffer, NULL, stdio_pclose, NULL, NULL);
+        s->file = qemu_fopen_ops(s, stdio_put_buffer, NULL, stdio_pclose, 
+				 NULL, NULL, NULL);
     }
     return s->file;
 }
@@ -311,9 +314,11 @@ QEMUFile *qemu_fdopen(int fd, const char *mode)
         goto fail;
 
     if(mode[0] == 'r') {
-        s->file = qemu_fopen_ops(s, NULL, stdio_get_buffer, stdio_fclose, NULL, NULL);
+        s->file = qemu_fopen_ops(s, NULL, stdio_get_buffer, stdio_fclose, 
+				 NULL, NULL, NULL);
     } else {
-        s->file = qemu_fopen_ops(s, stdio_put_buffer, NULL, stdio_fclose, NULL, NULL);
+        s->file = qemu_fopen_ops(s, stdio_put_buffer, NULL, stdio_fclose, 
+				 NULL, NULL, NULL);
     }
     return s->file;
 
@@ -327,7 +332,8 @@ QEMUFile *qemu_fopen_socket(int fd)
     QEMUFileSocket *s = qemu_mallocz(sizeof(QEMUFileSocket));
 
     s->fd = fd;
-    s->file = qemu_fopen_ops(s, NULL, socket_get_buffer, socket_close, NULL, NULL);
+    s->file = qemu_fopen_ops(s, NULL, socket_get_buffer, socket_close, 
+			     NULL, NULL, NULL);
     return s->file;
 }
 
@@ -363,11 +369,13 @@ QEMUFile *qemu_fopen(const char *filename, const char *mode)
     s->stdio_file = fopen(filename, mode);
     if (!s->stdio_file)
         goto fail;
-
+    
     if(mode[0] == 'w') {
-        s->file = qemu_fopen_ops(s, file_put_buffer, NULL, stdio_fclose, NULL, NULL);
+        s->file = qemu_fopen_ops(s, file_put_buffer, NULL, stdio_fclose, 
+				 NULL, NULL, NULL);
     } else {
-        s->file = qemu_fopen_ops(s, NULL, file_get_buffer, stdio_fclose, NULL, NULL);
+        s->file = qemu_fopen_ops(s, NULL, file_get_buffer, stdio_fclose, 
+			       NULL, NULL, NULL);
     }
     return s->file;
 fail:
@@ -395,15 +403,17 @@ static int bdrv_fclose(void *opaque)
 static QEMUFile *qemu_fopen_bdrv(BlockDriverState *bs, int is_writable)
 {
     if (is_writable)
-        return qemu_fopen_ops(bs, block_put_buffer, NULL, bdrv_fclose, NULL, NULL);
-    return qemu_fopen_ops(bs, NULL, block_get_buffer, bdrv_fclose, NULL, NULL);
+        return qemu_fopen_ops(bs, block_put_buffer, NULL, bdrv_fclose, 
+			      NULL, NULL, NULL);
+    return qemu_fopen_ops(bs, NULL, block_get_buffer, bdrv_fclose, NULL, NULL, NULL);
 }
 
 QEMUFile *qemu_fopen_ops(void *opaque, QEMUFilePutBufferFunc *put_buffer,
                          QEMUFileGetBufferFunc *get_buffer,
                          QEMUFileCloseFunc *close,
                          QEMUFileRateLimit *rate_limit,
-                         QEMUFileSetRateLimit *set_rate_limit)
+                         QEMUFileSetRateLimit *set_rate_limit,
+                         QEMUFileGetRateLimit *get_rate_limit)
 {
     QEMUFile *f;
 
@@ -415,6 +425,7 @@ QEMUFile *qemu_fopen_ops(void *opaque, QEMUFilePutBufferFunc *put_buffer,
     f->close = close;
     f->rate_limit = rate_limit;
     f->set_rate_limit = set_rate_limit;
+    f->get_rate_limit = get_rate_limit;
     f->is_write = 0;
 
     return f;
@@ -592,6 +603,14 @@ int qemu_file_rate_limit(QEMUFile *f)
     return 0;
 }
 
+size_t qemu_file_get_rate_limit(QEMUFile *f)
+{
+    if (f->get_rate_limit)
+        return f->get_rate_limit(f->opaque);
+
+    return 0;
+}
+
 size_t qemu_file_set_rate_limit(QEMUFile *f, size_t new_rate)
 {
     /* any failed or completed migration keeps its state to allow probing of
@@ -964,6 +983,7 @@ typedef struct SaveStateEntry {
     int instance_id;
     int version_id;
     int section_id;
+    SaveSetParamsHandler *set_params;
     SaveLiveStateHandler *save_live_state;
     SaveStateHandler *save_state;
     LoadStateHandler *load_state;
@@ -971,6 +991,7 @@ typedef struct SaveStateEntry {
     void *opaque;
 } SaveStateEntry;
 
+
 static QTAILQ_HEAD(savevm_handlers, SaveStateEntry) savevm_handlers =
     QTAILQ_HEAD_INITIALIZER(savevm_handlers);
 static int global_section_id;
@@ -996,6 +1017,7 @@ static int calculate_new_instance_id(const char *idstr)
 int register_savevm_live(const char *idstr,
                          int instance_id,
                          int version_id,
+                         SaveSetParamsHandler *set_params,
                          SaveLiveStateHandler *save_live_state,
                          SaveStateHandler *save_state,
                          LoadStateHandler *load_state,
@@ -1003,10 +1025,11 @@ int register_savevm_live(const char *idstr,
 {
     SaveStateEntry *se;
 
-    se = qemu_malloc(sizeof(SaveStateEntry));
+    se = qemu_mallocz(sizeof(SaveStateEntry));
     pstrcpy(se->idstr, sizeof(se->idstr), idstr);
     se->version_id = version_id;
     se->section_id = global_section_id++;
+    se->set_params = set_params;
     se->save_live_state = save_live_state;
     se->save_state = save_state;
     se->load_state = load_state;
@@ -1031,7 +1054,7 @@ int register_savevm(const char *idstr,
                     void *opaque)
 {
     return register_savevm_live(idstr, instance_id, version_id,
-                                NULL, save_state, load_state, opaque);
+                                NULL, NULL, save_state, load_state, opaque);
 }
 
 void unregister_savevm(const char *idstr, void *opaque)
@@ -1051,7 +1074,7 @@ int vmstate_register(int instance_id, const VMStateDescription *vmsd,
 {
     SaveStateEntry *se;
 
-    se = qemu_malloc(sizeof(SaveStateEntry));
+    se = qemu_mallocz(sizeof(SaveStateEntry));
     pstrcpy(se->idstr, sizeof(se->idstr), vmsd->name);
     se->version_id = vmsd->version_id;
     se->section_id = global_section_id++;
@@ -1213,10 +1236,17 @@ static void vmstate_save(QEMUFile *f, SaveStateEntry *se)
 #define QEMU_VM_SECTION_END          0x03
 #define QEMU_VM_SECTION_FULL         0x04
 
-int qemu_savevm_state_begin(QEMUFile *f)
+int qemu_savevm_state_begin(QEMUFile *f, int blk_enable, int shared)
 {
     SaveStateEntry *se;
 
+    QTAILQ_FOREACH(se, &savevm_handlers, entry) {
+        if(se->set_params == NULL) {
+            continue;
+	}
+	se->set_params(blk_enable, shared, se->opaque);
+    }
+    
     qemu_put_be32(f, QEMU_VM_FILE_MAGIC);
     qemu_put_be32(f, QEMU_VM_FILE_VERSION);
 
@@ -1326,7 +1356,7 @@ int qemu_savevm_state(QEMUFile *f)
 
     bdrv_flush_all();
 
-    ret = qemu_savevm_state_begin(f);
+    ret = qemu_savevm_state_begin(f, 0, 0);
     if (ret < 0)
         goto out;
 
diff --git a/sysemu.h b/sysemu.h
index 96804b497b..b1887ef1f4 100644
--- a/sysemu.h
+++ b/sysemu.h
@@ -61,7 +61,7 @@ void qemu_announce_self(void);
 
 void main_loop_wait(int timeout);
 
-int qemu_savevm_state_begin(QEMUFile *f);
+int qemu_savevm_state_begin(QEMUFile *f, int blk_enable, int shared);
 int qemu_savevm_state_iterate(QEMUFile *f);
 int qemu_savevm_state_complete(QEMUFile *f);
 int qemu_savevm_state(QEMUFile *f);
diff --git a/vl.c b/vl.c
index 18353f289e..c3f3c8f195 100644
--- a/vl.c
+++ b/vl.c
@@ -148,6 +148,8 @@ int main(int argc, char **argv)
 #include "qemu-char.h"
 #include "cache-utils.h"
 #include "block.h"
+#include "block_int.h"
+#include "block-migration.h"
 #include "dma.h"
 #include "audio/audio.h"
 #include "migration.h"
@@ -2972,9 +2974,7 @@ static int ram_save_live(QEMUFile *f, int stage, void *opaque)
         bwidth = 0.000001;
 
     /* try transferring iterative blocks of memory */
-
     if (stage == 3) {
-
         /* flush all remaining blocks regardless of rate limiting */
         while (ram_save_block(f) != 0) {
             bytes_transferred += TARGET_PAGE_SIZE;
@@ -5553,6 +5553,8 @@ int main(int argc, char **argv, char **envp)
 
     bdrv_init_with_whitelist();
 
+    blk_mig_init();
+
     /* we always create the cdrom drive, even if no disk is there */
     drive_add(NULL, CDROM_ALIAS);
 
@@ -5569,7 +5571,8 @@ int main(int argc, char **argv, char **envp)
         exit(1);
 
     vmstate_register(0, &vmstate_timers ,&timers_state);
-    register_savevm_live("ram", 0, 3, ram_save_live, NULL, ram_load, NULL);
+    register_savevm_live("ram", 0, 3, NULL, ram_save_live, NULL, 
+                         ram_load, NULL);
 
     /* Maintain compatibility with multiple stdio monitors */
     if (!strcmp(monitor_devices[0],"stdio")) {