COLO: Load dirty pages into SVM's RAM cache firstly

We should not load PVM's state directly into SVM, because there maybe some
errors happen when SVM is receving data, which will break SVM.

We need to ensure receving all data before load the state into SVM. We use
an extra memory to cache these data (PVM's ram). The ram cache in secondary side
is initially the same as SVM/PVM's memory. And in the process of checkpoint,
we cache the dirty pages of PVM into this ram cache firstly, so this ram cache
always the same as PVM's memory at every checkpoint, then we flush this cached ram
to SVM after we receive all PVM's state.

Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com>
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Signed-off-by: Zhang Chen <zhangckid@gmail.com>
Signed-off-by: Zhang Chen <chen.zhang@intel.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>

1 files changed, 81 insertions, 2 deletions

diff --git a/migration/ram.c b/migration/ram.c
index bc38d98cc3..cd7a446c95 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -3447,6 +3447,20 @@ static inline void *host_from_ram_block_offset(RAMBlock *block,
     return block->host + offset;
 }
 
+static inline void *colo_cache_from_block_offset(RAMBlock *block,
+                                                 ram_addr_t offset)
+{
+    if (!offset_in_ramblock(block, offset)) {
+        return NULL;
+    }
+    if (!block->colo_cache) {
+        error_report("%s: colo_cache is NULL in block :%s",
+                     __func__, block->idstr);
+        return NULL;
+    }
+    return block->colo_cache + offset;
+}
+
 /**
  * ram_handle_compressed: handle the zero page case
  *
@@ -3651,6 +3665,58 @@ static void decompress_data_with_multi_threads(QEMUFile *f,
     qemu_mutex_unlock(&decomp_done_lock);
 }
 
+/*
+ * colo cache: this is for secondary VM, we cache the whole
+ * memory of the secondary VM, it is need to hold the global lock
+ * to call this helper.
+ */
+int colo_init_ram_cache(void)
+{
+    RAMBlock *block;
+
+    rcu_read_lock();
+    QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
+        block->colo_cache = qemu_anon_ram_alloc(block->used_length,
+                                                NULL,
+                                                false);
+        if (!block->colo_cache) {
+            error_report("%s: Can't alloc memory for COLO cache of block %s,"
+                         "size 0x" RAM_ADDR_FMT, __func__, block->idstr,
+                         block->used_length);
+            goto out_locked;
+        }
+        memcpy(block->colo_cache, block->host, block->used_length);
+    }
+    rcu_read_unlock();
+    return 0;
+
+out_locked:
+    QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
+        if (block->colo_cache) {
+            qemu_anon_ram_free(block->colo_cache, block->used_length);
+            block->colo_cache = NULL;
+        }
+    }
+
+    rcu_read_unlock();
+    return -errno;
+}
+
+/* It is need to hold the global lock to call this helper */
+void colo_release_ram_cache(void)
+{
+    RAMBlock *block;
+
+    rcu_read_lock();
+    QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
+        if (block->colo_cache) {
+            qemu_anon_ram_free(block->colo_cache, block->used_length);
+            block->colo_cache = NULL;
+        }
+    }
+    rcu_read_unlock();
+}
+
 /**
  * ram_load_setup: Setup RAM for migration incoming side
  *
@@ -3667,6 +3733,7 @@ static int ram_load_setup(QEMUFile *f, void *opaque)
 
     xbzrle_load_setup();
     ramblock_recv_map_init();
+
     return 0;
 }
 
@@ -3687,6 +3754,7 @@ static int ram_load_cleanup(void *opaque)
         g_free(rb->receivedmap);
         rb->receivedmap = NULL;
     }
+
     return 0;
 }
 
@@ -3924,13 +3992,24 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
                      RAM_SAVE_FLAG_COMPRESS_PAGE | RAM_SAVE_FLAG_XBZRLE)) {
             RAMBlock *block = ram_block_from_stream(f, flags);
 
-            host = host_from_ram_block_offset(block, addr);
+            /*
+             * After going into COLO, we should load the Page into colo_cache.
+             */
+            if (migration_incoming_in_colo_state()) {
+                host = colo_cache_from_block_offset(block, addr);
+            } else {
+                host = host_from_ram_block_offset(block, addr);
+            }
             if (!host) {
                 error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
                 ret = -EINVAL;
                 break;
             }
-            ramblock_recv_bitmap_set(block, host);
+
+            if (!migration_incoming_in_colo_state()) {
+                ramblock_recv_bitmap_set(block, host);
+            }
+
             trace_ram_load_loop(block->idstr, (uint64_t)addr, flags, host);
         }