[PATCH v8 5/5] multifd: Implement zero copy write in multifd migration (multifd-zero-copy)

[Leonardo Bras <leobras@redhat.com>]

Implement zero copy send on nocomp_send_write(), by making use of QIOChannel
writev + flags & flush interface.

Change multifd_send_sync_main() so flush_zero_copy() can be called
after each iteration in order to make sure all dirty pages are sent before
a new iteration is started. It will also flush at the beginning and at the
end of migration.

Also make it return -1 if flush_zero_copy() fails, in order to cancel
the migration process, and avoid resuming the guest in the target host
without receiving all current RAM.

This will work fine on RAM migration because the RAM pages are not usually freed,
and there is no problem on changing the pages content between writev_zero_copy() and
the actual sending of the buffer, because this change will dirty the page and
cause it to be re-sent on a next iteration anyway.

A lot of locked memory may be needed in order to use multid migration
with zero-copy enabled, so disabling the feature should be necessary for
low-privileged users trying to perform multifd migrations.

Signed-off-by: Leonardo Bras <leobras@redhat.com>
---
 migration/multifd.h   |  4 +++-
 migration/migration.c | 11 ++++++++++-
 migration/multifd.c   | 41 +++++++++++++++++++++++++++++++++++------
 migration/ram.c       | 29 ++++++++++++++++++++++-------
 migration/socket.c    |  5 +++--
 5 files changed, 73 insertions(+), 17 deletions(-)

diff --git a/migration/multifd.h b/migration/multifd.h
index 4dda900a0b..7ec688fb4f 100644
--- a/migration/multifd.h
+++ b/migration/multifd.h
@@ -22,7 +22,7 @@ int multifd_load_cleanup(Error **errp);
 bool multifd_recv_all_channels_created(void);
 bool multifd_recv_new_channel(QIOChannel *ioc, Error **errp);
 void multifd_recv_sync_main(void);
-void multifd_send_sync_main(QEMUFile *f);
+int multifd_send_sync_main(QEMUFile *f);
 int multifd_queue_page(QEMUFile *f, RAMBlock *block, ram_addr_t offset);
 
 /* Multifd Compression flags */
@@ -96,6 +96,8 @@ typedef struct {
     uint32_t packet_len;
     /* pointer to the packet */
     MultiFDPacket_t *packet;
+    /* multifd flags for sending ram */
+    int write_flags;
     /* multifd flags for each packet */
     uint32_t flags;
     /* size of the next packet that contains pages */
diff --git a/migration/migration.c b/migration/migration.c
index 3e0a25bb5b..1450fd0370 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -1479,7 +1479,16 @@ static bool migrate_params_check(MigrationParameters *params, Error **errp)
         error_prepend(errp, "Invalid mapping given for block-bitmap-mapping: ");
         return false;
     }
-
+#ifdef CONFIG_LINUX
+    if (params->zero_copy_send &&
+        (!migrate_use_multifd() ||
+         params->multifd_compression != MULTIFD_COMPRESSION_NONE ||
+         (params->tls_creds && *params->tls_creds))) {
+        error_setg(errp,
+                   "Zero copy only available for non-compressed non-TLS multifd migration");
+        return false;
+    }
+#endif
     return true;
 }
 
diff --git a/migration/multifd.c b/migration/multifd.c
index 43998ad117..2d68b9cf4f 100644
--- a/migration/multifd.c
+++ b/migration/multifd.c
@@ -568,19 +568,28 @@ void multifd_save_cleanup(void)
     multifd_send_state = NULL;
 }
 
-void multifd_send_sync_main(QEMUFile *f)
+int multifd_send_sync_main(QEMUFile *f)
 {
     int i;
+    bool flush_zero_copy;
 
     if (!migrate_use_multifd()) {
-        return;
+        return 0;
     }
     if (multifd_send_state->pages->num) {
         if (multifd_send_pages(f) < 0) {
             error_report("%s: multifd_send_pages fail", __func__);
-            return;
+            return 0;
         }
     }
+
+    /*
+     * When using zero-copy, it's necessary to flush after each iteration to
+     * make sure pages from earlier iterations don't end up replacing newer
+     * pages.
+     */
+    flush_zero_copy = migrate_use_zero_copy_send();
+
     for (i = 0; i < migrate_multifd_channels(); i++) {
         MultiFDSendParams *p = &multifd_send_state->params[i];
 
@@ -591,7 +600,7 @@ void multifd_send_sync_main(QEMUFile *f)
         if (p->quit) {
             error_report("%s: channel %d has already quit", __func__, i);
             qemu_mutex_unlock(&p->mutex);
-            return;
+            return 0;
         }
 
         p->packet_num = multifd_send_state->packet_num++;
@@ -602,6 +611,17 @@ void multifd_send_sync_main(QEMUFile *f)
         ram_counters.transferred += p->packet_len;
         qemu_mutex_unlock(&p->mutex);
         qemu_sem_post(&p->sem);
+
+        if (flush_zero_copy) {
+            int ret;
+            Error *err = NULL;
+
+            ret = qio_channel_flush(p->c, &err);
+            if (ret < 0) {
+                error_report_err(err);
+                return -1;
+            }
+        }
     }
     for (i = 0; i < migrate_multifd_channels(); i++) {
         MultiFDSendParams *p = &multifd_send_state->params[i];
@@ -610,6 +630,8 @@ void multifd_send_sync_main(QEMUFile *f)
         qemu_sem_wait(&p->sem_sync);
     }
     trace_multifd_send_sync_main(multifd_send_state->packet_num);
+
+    return 0;
 }
 
 static void *multifd_send_thread(void *opaque)
@@ -668,8 +690,8 @@ static void *multifd_send_thread(void *opaque)
             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);
+            ret = qio_channel_writev_full_all(p->c, p->iov, p->iovs_num, NULL,
+                                              0, p->write_flags, &local_err);
             if (ret != 0) {
                 break;
             }
@@ -910,6 +932,13 @@ int multifd_save_setup(Error **errp)
         /* We need one extra place for the packet header */
         p->iov = g_new0(struct iovec, page_count + 1);
         p->normal = g_new0(ram_addr_t, page_count);
+
+        if (migrate_use_zero_copy_send()) {
+            p->write_flags = QIO_CHANNEL_WRITE_FLAG_ZERO_COPY;
+        } else {
+            p->write_flags = 0;
+        }
+
         socket_send_channel_create(multifd_new_send_channel_async, p);
     }
 
diff --git a/migration/ram.c b/migration/ram.c
index 91ca743ac8..d8c215e43a 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -2902,6 +2902,7 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
 {
     RAMState **rsp = opaque;
     RAMBlock *block;
+    int ret;
 
     if (compress_threads_save_setup()) {
         return -1;
@@ -2936,7 +2937,11 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
     ram_control_before_iterate(f, RAM_CONTROL_SETUP);
     ram_control_after_iterate(f, RAM_CONTROL_SETUP);
 
-    multifd_send_sync_main(f);
+    ret =  multifd_send_sync_main(f);
+    if (ret < 0) {
+        return ret;
+    }
+
     qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
     qemu_fflush(f);
 
@@ -3045,7 +3050,11 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
 out:
     if (ret >= 0
         && migration_is_setup_or_active(migrate_get_current()->state)) {
-        multifd_send_sync_main(rs->f);
+        ret = multifd_send_sync_main(rs->f);
+        if (ret < 0) {
+            return ret;
+        }
+
         qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
         qemu_fflush(f);
         ram_transferred_add(8);
@@ -3105,13 +3114,19 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
         ram_control_after_iterate(f, RAM_CONTROL_FINISH);
     }
 
-    if (ret >= 0) {
-        multifd_send_sync_main(rs->f);
-        qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
-        qemu_fflush(f);
+    if (ret < 0) {
+        return ret;
     }
 
-    return ret;
+    ret = multifd_send_sync_main(rs->f);
+    if (ret < 0) {
+        return ret;
+    }
+
+    qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
+    qemu_fflush(f);
+
+    return 0;
 }
 
 static void ram_save_pending(QEMUFile *f, void *opaque, uint64_t max_size,
diff --git a/migration/socket.c b/migration/socket.c
index f586f983b7..c49431425e 100644
--- a/migration/socket.c
+++ b/migration/socket.c
@@ -78,8 +78,9 @@ static void socket_outgoing_migration(QIOTask *task,
         trace_migration_socket_outgoing_connected(data->hostname);
     }
 
-    if (migrate_use_zero_copy_send()) {
-        error_setg(&err, "Zero copy send not available in migration");
+    if (migrate_use_zero_copy_send() &&
+        !qio_channel_has_feature(sioc, QIO_CHANNEL_FEATURE_WRITE_ZERO_COPY)) {
+        error_setg(&err, "Zero copy send feature not detected in host kernel");
     }
 
     migration_channel_connect(data->s, sioc, data->hostname, err);
-- 
2.34.1