[PULL,03/25] migration/multifd: Allow to sync with sender threads only

Commit Message

Fabiano Rosas Jan. 10, 2025, 12:13 p.m. UTC

From: Peter Xu <[e-mail]>

Teach multifd_send_sync_main() to sync with threads only.

We already have such requests, which is when mapped-ram is enabled with
multifd.  In that case, no SYNC messages will be pushed to the stream when
multifd syncs the sender threads because there's no destination threads
waiting for that.  The whole point of the sync is to make sure all threads
finished their jobs.

So fundamentally we have a request to do the sync in different ways:

  - Either to sync the threads only,
  - Or to sync the threads but also with the destination side.

Mapped-ram did it already because of the use_packet check in the sync
handler of the sender thread.  It works.

However it may stop working when e.g. VFIO may start to reuse multifd
channels to push device states.  In that case VFIO has similar request on
"thread-only sync" however we can't check a flag because such sync request
can still come from RAM which needs the on-wire notifications.

Paving way for that by allowing the multifd_send_sync_main() to specify
what kind of sync the caller needs.  We can use it for mapped-ram already.

No functional change intended.

Signed-off-by: Peter Xu <[e-mail]>
Reviewed-by: Fabiano Rosas <[e-mail]>
Message-Id: <[e-mail]>
Signed-off-by: Fabiano Rosas <[e-mail]>
---
 migration/multifd-nocomp.c |  7 ++++++-
 migration/multifd.c        | 17 +++++++++++------
 migration/multifd.h        | 23 ++++++++++++++++++++---
 3 files changed, 37 insertions(+), 10 deletions(-)

Patch

diff --git a/migration/multifd-nocomp.c b/migration/multifd-nocomp.c
index 55191152f9..219f9e58ef 100644
--- a/migration/multifd-nocomp.c
+++ b/migration/multifd-nocomp.c
@@ -345,6 +345,8 @@  retry:
 
 int multifd_ram_flush_and_sync(void)
 {
+    MultiFDSyncReq req;
+
     if (!migrate_multifd()) {
         return 0;
     }
@@ -356,7 +358,10 @@  int multifd_ram_flush_and_sync(void)
         }
     }
 
-    return multifd_send_sync_main();
+    /* File migrations only need to sync with threads */
+    req = migrate_mapped_ram() ? MULTIFD_SYNC_LOCAL : MULTIFD_SYNC_ALL;
+
+    return multifd_send_sync_main(req);
 }
 
 bool multifd_send_prepare_common(MultiFDSendParams *p)
diff --git a/migration/multifd.c b/migration/multifd.c
index 4f973d70e0..64e0ac2488 100644
--- a/migration/multifd.c
+++ b/migration/multifd.c
@@ -523,11 +523,13 @@  static int multifd_zero_copy_flush(QIOChannel *c)
     return ret;
 }
 
-int multifd_send_sync_main(void)
+int multifd_send_sync_main(MultiFDSyncReq req)
 {
     int i;
     bool flush_zero_copy;
 
+    assert(req != MULTIFD_SYNC_NONE);
+
     flush_zero_copy = migrate_zero_copy_send();
 
     for (i = 0; i < migrate_multifd_channels(); i++) {
@@ -543,8 +545,8 @@  int multifd_send_sync_main(void)
          * We should be the only user so far, so not possible to be set by
          * others concurrently.
          */
-        assert(qatomic_read(&p->pending_sync) == false);
-        qatomic_set(&p->pending_sync, true);
+        assert(qatomic_read(&p->pending_sync) == MULTIFD_SYNC_NONE);
+        qatomic_set(&p->pending_sync, req);
         qemu_sem_post(&p->sem);
     }
     for (i = 0; i < migrate_multifd_channels(); i++) {
@@ -635,14 +637,17 @@  static void *multifd_send_thread(void *opaque)
              */
             qatomic_store_release(&p->pending_job, false);
         } else {
+            MultiFDSyncReq req = qatomic_read(&p->pending_sync);
+
             /*
              * If not a normal job, must be a sync request.  Note that
              * pending_sync is a standalone flag (unlike pending_job), so
              * it doesn't require explicit memory barriers.
              */
-            assert(qatomic_read(&p->pending_sync));
+            assert(req != MULTIFD_SYNC_NONE);
 
-            if (use_packets) {
+            /* Only push the SYNC message if it involves a remote sync */
+            if (req == MULTIFD_SYNC_ALL) {
                 p->flags = MULTIFD_FLAG_SYNC;
                 multifd_send_fill_packet(p);
                 ret = qio_channel_write_all(p->c, (void *)p->packet,
@@ -654,7 +659,7 @@  static void *multifd_send_thread(void *opaque)
                 stat64_add(&mig_stats.multifd_bytes, p->packet_len);
             }
 
-            qatomic_set(&p->pending_sync, false);
+            qatomic_set(&p->pending_sync, MULTIFD_SYNC_NONE);
             qemu_sem_post(&p->sem_sync);
         }
     }
diff --git a/migration/multifd.h b/migration/multifd.h
index 50d58c0c9c..6493512305 100644
--- a/migration/multifd.h
+++ b/migration/multifd.h
@@ -19,6 +19,22 @@ 
 typedef struct MultiFDRecvData MultiFDRecvData;
 typedef struct MultiFDSendData MultiFDSendData;
 
+typedef enum {
+    /* No sync request */
+    MULTIFD_SYNC_NONE = 0,
+    /* Sync locally on the sender threads without pushing messages */
+    MULTIFD_SYNC_LOCAL,
+    /*
+     * Sync not only on the sender threads, but also push MULTIFD_FLAG_SYNC
+     * message to the wire for each iochannel (which is for a remote sync).
+     *
+     * When remote sync is used, need to be paired with a follow up
+     * RAM_SAVE_FLAG_EOS / RAM_SAVE_FLAG_MULTIFD_FLUSH message on the main
+     * channel.
+     */
+    MULTIFD_SYNC_ALL,
+} MultiFDSyncReq;
+
 bool multifd_send_setup(void);
 void multifd_send_shutdown(void);
 void multifd_send_channel_created(void);
@@ -28,7 +44,7 @@  void multifd_recv_shutdown(void);
 bool multifd_recv_all_channels_created(void);
 void multifd_recv_new_channel(QIOChannel *ioc, Error **errp);
 void multifd_recv_sync_main(void);
-int multifd_send_sync_main(void);
+int multifd_send_sync_main(MultiFDSyncReq req);
 bool multifd_queue_page(RAMBlock *block, ram_addr_t offset);
 bool multifd_recv(void);
 MultiFDRecvData *multifd_get_recv_data(void);
@@ -143,7 +159,7 @@  typedef struct {
     /* multifd flags for each packet */
     uint32_t flags;
     /*
-     * The sender thread has work to do if either of below boolean is set.
+     * The sender thread has work to do if either of below field is set.
      *
      * @pending_job:  a job is pending
      * @pending_sync: a sync request is pending
@@ -152,7 +168,8 @@  typedef struct {
      * cleared by the multifd sender threads.
      */
     bool pending_job;
-    bool pending_sync;
+    MultiFDSyncReq pending_sync;
+
     MultiFDSendData *data;
 
     /* thread local variables. No locking required */