qemu-kvm/kvm-multifd-Send-header-packet-without-flags-if-zero-cop.patch

From 63255c13492f42a3236d96e706e5f8e70bb4e219 Mon Sep 17 00:00:00 2001
From: Leonardo Bras <leobras@redhat.com>
Date: Fri, 13 May 2022 03:28:36 -0300
Subject: [PATCH 13/18] 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: 95: MSG_ZEROCOPY + Multifd
RH-Commit: [7/11] 137eea685e387d3d6aff187ec3fcac05bc16b6e3 (LeoBras/centos-qemu-kvm)
RH-Bugzilla: 1968509
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
RH-Acked-by: Peter Xu <peterx@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 cdb57439a7..8fca6c970e 100644
--- a/migration/multifd.c
+++ b/migration/multifd.c
@@ -619,6 +619,7 @@ 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();
@@ -641,9 +642,14 @@ 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++;
@@ -667,8 +673,18 @@ 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