[Qemu-devel] [PATCH 1/3] block: allow migration to work with image files

[Anthony Liguori <aliguori@us.ibm.com>]

Image files have two types of data: immutable data that describes things like
image size, backing files, etc. and mutable data that includes offset and
reference count tables.

Today, image formats aggressively cache mutable data to improve performance.  In
some cases, this happens before a guest even starts.  When dealing with live
migration, since a file is open on two machines, the caching of meta data can
lead to data corruption.

This patch addresses this by introducing a mechanism to invalidate any cached
mutable data a block driver may have which is then used by the live migration
code.

NB, this still requires coherent shared storage.  Addressing migration without
coherent shared storage (i.e. NFS) requires additional work.

Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>

diff --git a/block.c b/block.c
index ebbc376..cd2ee31 100644
--- a/block.c
+++ b/block.c
@@ -1453,6 +1453,22 @@ const char *bdrv_get_device_name(BlockDriverState *bs)
     return bs->device_name;
 }
 
+void bdrv_invalidate_cache(BlockDriverState *bs)
+{
+    if (bs->drv && bs->drv->bdrv_invalidate_cache) {
+        bs->drv->bdrv_invalidate_cache(bs);
+    }
+}
+
+void bdrv_invalidate_cache_all(void)
+{
+    BlockDriverState *bs;
+
+    QTAILQ_FOREACH(bs, &bdrv_states, list) {
+        bdrv_invalidate_cache(bs);
+    }
+}
+
 void bdrv_flush(BlockDriverState *bs)
 {
     if (bs->open_flags & BDRV_O_NO_FLUSH) {
diff --git a/block.h b/block.h
index 5f64380..387f6d3 100644
--- a/block.h
+++ b/block.h
@@ -141,6 +141,10 @@ BlockDriverAIOCB *bdrv_aio_ioctl(BlockDriverState *bs,
         unsigned long int req, void *buf,
         BlockDriverCompletionFunc *cb, void *opaque);
 
+/* Invalidate any cached metadata used by image formats */
+void bdrv_invalidate_cache(BlockDriverState *bs);
+void bdrv_invalidate_cache_all(void);
+
 /* Ensure contents are flushed to disk.  */
 void bdrv_flush(BlockDriverState *bs);
 void bdrv_flush_all(void);
diff --git a/block_int.h b/block_int.h
index e8e7156..bca99b2 100644
--- a/block_int.h
+++ b/block_int.h
@@ -60,6 +60,7 @@ struct BlockDriver {
     void (*bdrv_close)(BlockDriverState *bs);
     int (*bdrv_create)(const char *filename, QEMUOptionParameter *options);
     void (*bdrv_flush)(BlockDriverState *bs);
+    void (*bdrv_invalidate_cache)(BlockDriverState *bs);
     int (*bdrv_is_allocated)(BlockDriverState *bs, int64_t sector_num,
                              int nb_sectors, int *pnum);
     int (*bdrv_set_key)(BlockDriverState *bs, const char *key);
diff --git a/migration.c b/migration.c
index 468d517..64d3d15 100644
--- a/migration.c
+++ b/migration.c
@@ -69,6 +69,9 @@ void process_incoming_migration(QEMUFile *f)
 
     incoming_expected = false;
 
+    /* Make sure all file formats flush their mutable metadata */
+    bdrv_invalidate_cache_all();
+
     if (autostart)
         vm_start();
 }
@@ -370,6 +373,7 @@ void migrate_fd_put_ready(void *opaque)
 
         qemu_aio_flush();
         bdrv_flush_all();
+        bdrv_invalidate_cache_all();
         if ((qemu_savevm_state_complete(s->mon, s->file)) < 0) {
             if (old_vm_running) {
                 vm_start();
-- 
1.7.0.4