migration: Sync requested pages after postcopy recovery

We synchronize the requested pages right after a postcopy recovery happens.
This helps to synchronize the prioritized pages on source so that the faulted
threads can be served faster.

Reported-by: Xiaohui Li <xiaohli@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20201021212721.440373-5-peterx@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

2 files changed, 58 insertions, 0 deletions

diff --git a/migration/savevm.c b/migration/savevm.c
index 6ebd7e66ad..21ccba9fb3 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -2010,6 +2010,49 @@ static int loadvm_postcopy_handle_run(MigrationIncomingState *mis)
     return LOADVM_QUIT;
 }
 
+/* We must be with page_request_mutex held */
+static gboolean postcopy_sync_page_req(gpointer key, gpointer value,
+                                       gpointer data)
+{
+    MigrationIncomingState *mis = data;
+    void *host_addr = (void *) key;
+    ram_addr_t rb_offset;
+    RAMBlock *rb;
+    int ret;
+
+    rb = qemu_ram_block_from_host(host_addr, true, &rb_offset);
+    if (!rb) {
+        /*
+         * This should _never_ happen.  However be nice for a migrating VM to
+         * not crash/assert.  Post an error (note: intended to not use *_once
+         * because we do want to see all the illegal addresses; and this can
+         * never be triggered by the guest so we're safe) and move on next.
+         */
+        error_report("%s: illegal host addr %p", __func__, host_addr);
+        /* Try the next entry */
+        return FALSE;
+    }
+
+    ret = migrate_send_rp_message_req_pages(mis, rb, rb_offset);
+    if (ret) {
+        /* Please refer to above comment. */
+        error_report("%s: send rp message failed for addr %p",
+                     __func__, host_addr);
+        return FALSE;
+    }
+
+    trace_postcopy_page_req_sync(host_addr);
+
+    return FALSE;
+}
+
+static void migrate_send_rp_req_pages_pending(MigrationIncomingState *mis)
+{
+    WITH_QEMU_LOCK_GUARD(&mis->page_request_mutex) {
+        g_tree_foreach(mis->page_requested, postcopy_sync_page_req, mis);
+    }
+}
+
 static int loadvm_postcopy_handle_resume(MigrationIncomingState *mis)
 {
     if (mis->state != MIGRATION_STATUS_POSTCOPY_RECOVER) {
@@ -2032,6 +2075,20 @@ static int loadvm_postcopy_handle_resume(MigrationIncomingState *mis)
     /* Tell source that "we are ready" */
     migrate_send_rp_resume_ack(mis, MIGRATION_RESUME_ACK_VALUE);
 
+    /*
+     * After a postcopy recovery, the source should have lost the postcopy
+     * queue, or potentially the requested pages could have been lost during
+     * the network down phase.  Let's re-sync with the source VM by re-sending
+     * all the pending pages that we eagerly need, so these threads won't get
+     * blocked too long due to the recovery.
+     *
+     * Without this procedure, the faulted destination VM threads (waiting for
+     * page requests right before the postcopy is interrupted) can keep hanging
+     * until the pages are sent by the source during the background copying of
+     * pages, or another thread faulted on the same address accidentally.
+     */
+    migrate_send_rp_req_pages_pending(mis);
+
     return 0;
 }
 
diff --git a/migration/trace-events b/migration/trace-events
index 5f0001f808..75de5004ac 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -49,6 +49,7 @@ vmstate_save(const char *idstr, const char *vmsd_name) "%s, %s"
 vmstate_load(const char *idstr, const char *vmsd_name) "%s, %s"
 postcopy_pause_incoming(void) ""
 postcopy_pause_incoming_continued(void) ""
+postcopy_page_req_sync(void *host_addr) "sync page req %p"
 
 # vmstate.c
 vmstate_load_field_error(const char *field, int ret) "field \"%s\" load failed, ret = %d"