From 33a38fef5e889b45571228bde519746fd90d8877 Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Wed, 18 May 2022 02:52:25 -0300
Subject: [PATCH 22/37] multifd: Send header packet without flags if
 zero-copy-send is enabled
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

RH-Author: Leonardo Brás <leobras@redhat.com>
RH-MergeRequest: 191: MSG_ZEROCOPY + Multifd @ rhel8.7
RH-Commit: [22/26] 9abfee42b72f11911cf128519826d09cbd2f5bc3
RH-Bugzilla: 2072049
RH-Acked-by: Peter Xu <peterx@redhat.com>
RH-Acked-by: Daniel P. Berrangé <berrange@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

Since d48c3a0445 ("multifd: Use a single writev on the send side"),
sending the header packet and the memory pages happens in the same
writev, which can potentially make the migration faster.

Using channel-socket as example, this works well with the default copying
mechanism of sendmsg(), but with zero-copy-send=true, it will cause
the migration to often break.

This happens because the header packet buffer gets reused quite often,
and there is a high chance that by the time the MSG_ZEROCOPY mechanism get
to send the buffer, it has already changed, sending the wrong data and
causing the migration to abort.

It means that, as it is, the buffer for the header packet is not suitable
for sending with MSG_ZEROCOPY.

In order to enable zero copy for multifd, send the header packet on an
individual write(), without any flags, and the remanining pages with a
writev(), as it was happening before. This only changes how a migration
with zero-copy-send=true works, not changing any current behavior for
migrations with zero-copy-send=false.

Signed-off-by: Leonardo Bras <leobras@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Message-Id: <20220513062836.965425-8-leobras@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit b7dbdd8e76cd03453c234dbb9578d20969859d74)
Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
 migration/multifd.c | 22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

diff --git a/migration/multifd.c b/migration/multifd.c
index 1e34e01ebc..193f70cdba 100644
--- a/migration/multifd.c
+++ b/migration/multifd.c
@@ -624,6 +624,7 @@ static void *multifd_send_thread(void *opaque)
     MultiFDSendParams *p = opaque;
     Error *local_err = NULL;
     int ret = 0;
+    bool use_zero_copy_send = migrate_use_zero_copy_send();
 
     trace_multifd_send_thread_start(p->id);
     rcu_register_thread();
@@ -646,9 +647,14 @@ static void *multifd_send_thread(void *opaque)
         if (p->pending_job) {
             uint64_t packet_num = p->packet_num;
             uint32_t flags = p->flags;
-            p->iovs_num = 1;
             p->normal_num = 0;
 
+            if (use_zero_copy_send) {
+                p->iovs_num = 0;
+            } else {
+                p->iovs_num = 1;
+            }
+
             for (int i = 0; i < p->pages->num; i++) {
                 p->normal[p->normal_num] = p->pages->offset[i];
                 p->normal_num++;
@@ -672,8 +678,18 @@ static void *multifd_send_thread(void *opaque)
             trace_multifd_send(p->id, packet_num, p->normal_num, flags,
                                p->next_packet_size);
 
-            p->iov[0].iov_len = p->packet_len;
-            p->iov[0].iov_base = p->packet;
+            if (use_zero_copy_send) {
+                /* Send header first, without zerocopy */
+                ret = qio_channel_write_all(p->c, (void *)p->packet,
+                                            p->packet_len, &local_err);
+                if (ret != 0) {
+                    break;
+                }
+            } else {
+                /* Send header using the same writev call */
+                p->iov[0].iov_len = p->packet_len;
+                p->iov[0].iov_base = p->packet;
+            }
 
             ret = qio_channel_writev_all(p->c, p->iov, p->iovs_num,
                                          &local_err);
-- 
2.35.3