sheepdog: fix loadvm operation

Currently the 'loadvm' opertaion works as following:
1. switch to the snapshot
2. mark current working VDI as a snapshot
3. rely on sd_create_branch to create a new working VDI based on the snapshot

This works not the same as other format as QCOW2. For e.g,

qemu > savevm # get a live snapshot snap1
qemu > savevm # snap2
qemu > loadvm 1 # This will steally create snap3 of the working VDI

Which will result in following snapshot chain:

base <-- snap1 <-- snap2 <-- snap3
          ^
          |
      working VDI

snap3 was unnecessarily created and might be annoying users.

This patch discard the unnecessary 'snap3' creation. and implement
rollback(loadvm) operation to the specified snapshot by
1. switch to the snapshot
2. delete working VDI
3. rely on sd_create_branch to create a new working VDI based on the snapshot

The snapshot chain for above example will be:

base <-- snap1 <-- snap2
          ^
          |
      working VDI

Cc: qemu-devel@nongnu.org
Cc: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Cc: Kevin Wolf <kwolf@redhat.com>
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Liu Yuan <tailai.ly@taobao.com>
Reviewed-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

diff --git a/block/sheepdog.c b/block/sheepdog.c
index 77e21fdb7f1ca8f1cc83f08c71cf811a759b03e2..21a4edf15befe3e673273c5814ccb21748455352 100644 (file)
--- a/block/sheepdog.c
+++ b/block/sheepdog.c
@@ -36,6 +36,7 @@
 #define SD_OP_GET_VDI_INFO   0x14
 #define SD_OP_READ_VDIS      0x15
 #define SD_OP_FLUSH_VDI      0x16
+#define SD_OP_DEL_VDI        0x17
 
 #define SD_FLAG_CMD_WRITE    0x01
 #define SD_FLAG_CMD_COW      0x02
@@ -1666,6 +1667,43 @@ out:
     sd_finish_aiocb(acb);
 }
 
+/* Delete current working VDI on the snapshot chain */
+static bool sd_delete(BDRVSheepdogState *s)
+{
+    unsigned int wlen = SD_MAX_VDI_LEN, rlen = 0;
+    SheepdogVdiReq hdr = {
+        .opcode = SD_OP_DEL_VDI,
+        .vdi_id = s->inode.vdi_id,
+        .data_length = wlen,
+        .flags = SD_FLAG_CMD_WRITE,
+    };
+    SheepdogVdiRsp *rsp = (SheepdogVdiRsp *)&hdr;
+    int fd, ret;
+
+    fd = connect_to_sdog(s);
+    if (fd < 0) {
+        return false;
+    }
+
+    ret = do_req(fd, (SheepdogReq *)&hdr, s->name, &wlen, &rlen);
+    closesocket(fd);
+    if (ret) {
+        return false;
+    }
+    switch (rsp->result) {
+    case SD_RES_NO_VDI:
+        error_report("%s was already deleted", s->name);
+        /* fall through */
+    case SD_RES_SUCCESS:
+        break;
+    default:
+        error_report("%s, %s", sd_strerror(rsp->result), s->name);
+        return false;
+    }
+
+    return true;
+}
+
 /*
  * Create a writable VDI from a snapshot
  */
@@ -1674,12 +1712,20 @@ static int sd_create_branch(BDRVSheepdogState *s)
     int ret, fd;
     uint32_t vid;
     char *buf;
+    bool deleted;
 
     dprintf("%" PRIx32 " is snapshot.\n", s->inode.vdi_id);
 
     buf = g_malloc(SD_INODE_SIZE);
 
-    ret = do_sd_create(s, s->name, s->inode.vdi_size, s->inode.vdi_id, &vid, 1);
+    /*
+     * Even If deletion fails, we will just create extra snapshot based on
+     * the workding VDI which was supposed to be deleted. So no need to
+     * false bail out.
+     */
+    deleted = sd_delete(s);
+    ret = do_sd_create(s, s->name, s->inode.vdi_size, s->inode.vdi_id, &vid,
+                       !deleted);
     if (ret) {
         goto out;
     }
@@ -1995,6 +2041,12 @@ cleanup:
     return ret;
 }
 
+/*
+ * We implement rollback(loadvm) operation to the specified snapshot by
+ * 1) switch to the snapshot
+ * 2) rely on sd_create_branch to delete working VDI and
+ * 3) create a new working VDI based on the speicified snapshot
+ */
 static int sd_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
 {
     BDRVSheepdogState *s = bs->opaque;