From: Yanfei Xu <yanfei.xu@bytedance.com>
Date: Wed, 14 May 2025 11:58:27 +0000 (+0800)
Subject: migration/ram: avoid to do log clear in the last round
X-Git-Tag: v10.1.0-rc0~43^2~10
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=fd0377150d5dd4b02b2e7fbe9e8c1ab4dcbd16bb;p=thirdparty%2Fqemu.git

migration/ram: avoid to do log clear in the last round

There won't be any ram sync after the stage of save_complete, therefore
it's unnecessary to do manually protect for dirty pages being sent. Skip
to do this in last round can reduce noticeable downtime.

Signed-off-by: Yanfei Xu <yanfei.xu@bytedance.com>
Tested-by: Fabiano Rosas <farosas@suse.de>
Reviewed-by: Fabiano Rosas <farosas@suse.de>
Link: https://lore.kernel.org/r/20250514115827.3216082-1-yanfei.xu@bytedance.com
[peterx: add comments]
Signed-off-by: Peter Xu <peterx@redhat.com>
---

diff --git a/migration/ram.c b/migration/ram.c
index d26dbd37c40..fd8d83b63cb 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -831,14 +831,22 @@ static inline bool migration_bitmap_clear_dirty(RAMState *rs,
     bool ret;
 
     /*
-     * Clear dirty bitmap if needed.  This _must_ be called before we
-     * send any of the page in the chunk because we need to make sure
-     * we can capture further page content changes when we sync dirty
-     * log the next time.  So as long as we are going to send any of
-     * the page in the chunk we clear the remote dirty bitmap for all.
-     * Clearing it earlier won't be a problem, but too late will.
+     * During the last stage (after source VM stopped), resetting the write
+     * protections isn't needed as we know there will be either (1) no
+     * further writes if migration will complete, or (2) migration fails
+     * at last then tracking isn't needed either.
      */
-    migration_clear_memory_region_dirty_bitmap(rb, page);
+    if (!rs->last_stage) {
+        /*
+         * Clear dirty bitmap if needed.  This _must_ be called before we
+         * send any of the page in the chunk because we need to make sure
+         * we can capture further page content changes when we sync dirty
+         * log the next time.  So as long as we are going to send any of
+         * the page in the chunk we clear the remote dirty bitmap for all.
+         * Clearing it earlier won't be a problem, but too late will.
+         */
+        migration_clear_memory_region_dirty_bitmap(rb, page);
+    }
 
     ret = test_and_clear_bit(page, rb->bmap);
     if (ret) {