Merge remote-tracking branch 'remotes/jasowang/tags/net-pull-request' into staging

# gpg: Signature made Fri 11 Jun 2021 03:54:51 BST
# gpg:                using RSA key EF04965B398D6211
# gpg: Good signature from "Jason Wang (Jason Wang on RedHat) <jasowang@redhat.com>" [marginal]
# gpg: WARNING: This key is not certified with sufficiently trusted signatures!
# gpg:          It is not certain that the signature belongs to the owner.
# Primary key fingerprint: 215D 46F4 8246 689E C77F  3562 EF04 965B 398D 6211

* remotes/jasowang/tags/net-pull-request:
  Fixed calculation error of pkt->header_size in fill_pkt_tcp_info()
  Add the function of colo_compare_cleanup
  Add a function named packet_new_nocopy for COLO.
  Remove migrate_set_block_enabled in checkpoint
  Optimize the function of filter_send
  Fix the qemu crash when guest shutdown during checkpoint
  Remove some duplicate trace code.
  netdev: add more commands to preconfig mode
  vhost-vdpa: remove the unused vhost_vdpa_get_acked_features()
  vhost-vdpa: don't initialize backend_features
  vhost-vdpa: map virtqueue notification area if possible
  vhost-vdpa: skip ram device from the IOTLB mapping

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

16 files changed, 143 insertions, 59 deletions

diff --git a/hmp-commands.hx b/hmp-commands.hx
index 84dcc3aae6..8e45bce2cd 100644
--- a/hmp-commands.hx
+++ b/hmp-commands.hx
@@ -1269,6 +1269,7 @@ ERST
         .help       = "add host network device",
         .cmd        = hmp_netdev_add,
         .command_completion = netdev_add_completion,
+        .flags      = "p",
     },
 
 SRST
@@ -1283,6 +1284,7 @@ ERST
         .help       = "remove host network device",
         .cmd        = hmp_netdev_del,
         .command_completion = netdev_del_completion,
+        .flags      = "p",
     },
 
 SRST
diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c
index ee51863d28..61ba313331 100644
--- a/hw/virtio/vhost-vdpa.c
+++ b/hw/virtio/vhost-vdpa.c
@@ -28,6 +28,8 @@ static bool vhost_vdpa_listener_skipped_section(MemoryRegionSection *section)
 {
     return (!memory_region_is_ram(section->mr) &&
             !memory_region_is_iommu(section->mr)) ||
+           /* vhost-vDPA doesn't allow MMIO to be mapped  */
+            memory_region_is_ram_device(section->mr) ||
            /*
             * Sizing an enabled 64-bit BAR can cause spurious mappings to
             * addresses in the upper part of the 64-bit address space.  These
@@ -172,22 +174,12 @@ static void vhost_vdpa_listener_region_add(MemoryListener *listener,
                              vaddr, section->readonly);
     if (ret) {
         error_report("vhost vdpa map fail!");
-        if (memory_region_is_ram_device(section->mr)) {
-            /* Allow unexpected mappings not to be fatal for RAM devices */
-            error_report("map ram fail!");
-          return ;
-        }
         goto fail;
     }
 
     return;
 
 fail:
-    if (memory_region_is_ram_device(section->mr)) {
-        error_report("failed to vdpa_dma_map. pci p2p may not work");
-        return;
-
-    }
     /*
      * On the initfn path, store the first error in the container so we
      * can gracefully fail.  Runtime, there's not much we can do other
@@ -276,15 +268,12 @@ static void vhost_vdpa_add_status(struct vhost_dev *dev, uint8_t status)
 static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque)
 {
     struct vhost_vdpa *v;
-    uint64_t features;
     assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_VDPA);
     trace_vhost_vdpa_init(dev, opaque);
 
     v = opaque;
     v->dev = dev;
     dev->opaque =  opaque ;
-    vhost_vdpa_call(dev, VHOST_GET_FEATURES, &features);
-    dev->backend_features = features;
     v->listener = vhost_vdpa_memory_listener;
     v->msg_type = VHOST_IOTLB_MSG_V2;
 
@@ -294,12 +283,95 @@ static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque)
     return 0;
 }
 
+static void vhost_vdpa_host_notifier_uninit(struct vhost_dev *dev,
+                                            int queue_index)
+{
+    size_t page_size = qemu_real_host_page_size;
+    struct vhost_vdpa *v = dev->opaque;
+    VirtIODevice *vdev = dev->vdev;
+    VhostVDPAHostNotifier *n;
+
+    n = &v->notifier[queue_index];
+
+    if (n->addr) {
+        virtio_queue_set_host_notifier_mr(vdev, queue_index, &n->mr, false);
+        object_unparent(OBJECT(&n->mr));
+        munmap(n->addr, page_size);
+        n->addr = NULL;
+    }
+}
+
+static void vhost_vdpa_host_notifiers_uninit(struct vhost_dev *dev, int n)
+{
+    int i;
+
+    for (i = 0; i < n; i++) {
+        vhost_vdpa_host_notifier_uninit(dev, i);
+    }
+}
+
+static int vhost_vdpa_host_notifier_init(struct vhost_dev *dev, int queue_index)
+{
+    size_t page_size = qemu_real_host_page_size;
+    struct vhost_vdpa *v = dev->opaque;
+    VirtIODevice *vdev = dev->vdev;
+    VhostVDPAHostNotifier *n;
+    int fd = v->device_fd;
+    void *addr;
+    char *name;
+
+    vhost_vdpa_host_notifier_uninit(dev, queue_index);
+
+    n = &v->notifier[queue_index];
+
+    addr = mmap(NULL, page_size, PROT_WRITE, MAP_SHARED, fd,
+                queue_index * page_size);
+    if (addr == MAP_FAILED) {
+        goto err;
+    }
+
+    name = g_strdup_printf("vhost-vdpa/host-notifier@%p mmaps[%d]",
+                           v, queue_index);
+    memory_region_init_ram_device_ptr(&n->mr, OBJECT(vdev), name,
+                                      page_size, addr);
+    g_free(name);
+
+    if (virtio_queue_set_host_notifier_mr(vdev, queue_index, &n->mr, true)) {
+        munmap(addr, page_size);
+        goto err;
+    }
+    n->addr = addr;
+
+    return 0;
+
+err:
+    return -1;
+}
+
+static void vhost_vdpa_host_notifiers_init(struct vhost_dev *dev)
+{
+    int i;
+
+    for (i = dev->vq_index; i < dev->vq_index + dev->nvqs; i++) {
+        if (vhost_vdpa_host_notifier_init(dev, i)) {
+            goto err;
+        }
+    }
+
+    return;
+
+err:
+    vhost_vdpa_host_notifiers_uninit(dev, i);
+    return;
+}
+
 static int vhost_vdpa_cleanup(struct vhost_dev *dev)
 {
     struct vhost_vdpa *v;
     assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_VDPA);
     v = dev->opaque;
     trace_vhost_vdpa_cleanup(dev, v);
+    vhost_vdpa_host_notifiers_uninit(dev, dev->nvqs);
     memory_listener_unregister(&v->listener);
 
     dev->opaque = NULL;
@@ -476,6 +548,7 @@ static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started)
     if (started) {
         uint8_t status = 0;
         memory_listener_register(&v->listener, &address_space_memory);
+        vhost_vdpa_host_notifiers_init(dev);
         vhost_vdpa_set_vring_ready(dev);
         vhost_vdpa_add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK);
         vhost_vdpa_call(dev, VHOST_VDPA_GET_STATUS, &status);
@@ -485,6 +558,7 @@ static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started)
         vhost_vdpa_reset_device(dev);
         vhost_vdpa_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE |
                                    VIRTIO_CONFIG_S_DRIVER);
+        vhost_vdpa_host_notifiers_uninit(dev, dev->nvqs);
         memory_listener_unregister(&v->listener);
 
         return 0;
diff --git a/include/hw/virtio/vhost-vdpa.h b/include/hw/virtio/vhost-vdpa.h
index ae9ee7adb2..9188226d8b 100644
--- a/include/hw/virtio/vhost-vdpa.h
+++ b/include/hw/virtio/vhost-vdpa.h
@@ -14,11 +14,17 @@
 
 #include "hw/virtio/virtio.h"
 
+typedef struct VhostVDPAHostNotifier {
+    MemoryRegion mr;
+    void *addr;
+} VhostVDPAHostNotifier;
+
 typedef struct vhost_vdpa {
     int device_fd;
     uint32_t msg_type;
     MemoryListener listener;
     struct vhost_dev *dev;
+    VhostVDPAHostNotifier notifier[VIRTIO_QUEUE_MAX];
 } VhostVDPA;
 
 #endif
diff --git a/include/net/vhost-vdpa.h b/include/net/vhost-vdpa.h
index 45e34b7cfc..b81f9a6f2a 100644
--- a/include/net/vhost-vdpa.h
+++ b/include/net/vhost-vdpa.h
@@ -15,7 +15,6 @@
 #define TYPE_VHOST_VDPA "vhost-vdpa"
 
 struct vhost_net *vhost_vdpa_get_vhost_net(NetClientState *nc);
-uint64_t vhost_vdpa_get_acked_features(NetClientState *nc);
 
 extern const int vdpa_feature_bits[];
 
diff --git a/migration/colo.c b/migration/colo.c
index e498fdb125..79fa1f6619 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -435,12 +435,6 @@ static int colo_do_checkpoint_transaction(MigrationState *s,
     if (failover_get_state() != FAILOVER_STATUS_NONE) {
         goto out;
     }
-
-    /* Disable block migration */
-    migrate_set_block_enabled(false, &local_err);
-    if (local_err) {
-        goto out;
-    }
     qemu_mutex_lock_iothread();
 
 #ifdef CONFIG_REPLICATION
diff --git a/migration/migration.c b/migration/migration.c
index 393299e150..4828997f63 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -2217,6 +2217,10 @@ static bool migrate_prepare(MigrationState *s, bool blk, bool blk_inc,
     }
 
     if (blk || blk_inc) {
+        if (migrate_colo_enabled()) {
+            error_setg(errp, "No disk migration is required in COLO mode");
+            return false;
+        }
         if (migrate_use_block() || migrate_use_block_incremental()) {
             error_setg(errp, "Command options are incompatible with "
                        "current migration capabilities");
diff --git a/net/colo-compare.c b/net/colo-compare.c
index 9d1ad99941..b100e7b51f 100644
--- a/net/colo-compare.c
+++ b/net/colo-compare.c
@@ -211,7 +211,7 @@ static void fill_pkt_tcp_info(void *data, uint32_t *max_ack)
     pkt->tcp_ack = ntohl(tcphd->th_ack);
     *max_ack = *max_ack > pkt->tcp_ack ? *max_ack : pkt->tcp_ack;
     pkt->header_size = pkt->transport_header - (uint8_t *)pkt->data
-                       + (tcphd->th_off << 2) - pkt->vnet_hdr_len;
+                       + (tcphd->th_off << 2);
     pkt->payload_size = pkt->size - pkt->header_size;
     pkt->seq_end = pkt->tcp_seq + pkt->payload_size;
     pkt->flags = tcphd->th_flags;
@@ -590,19 +590,6 @@ static int colo_packet_compare_other(Packet *spkt, Packet *ppkt)
     uint16_t offset = ppkt->vnet_hdr_len;
 
     trace_colo_compare_main("compare other");
-    if (trace_event_get_state_backends(TRACE_COLO_COMPARE_IP_INFO)) {
-        char pri_ip_src[20], pri_ip_dst[20], sec_ip_src[20], sec_ip_dst[20];
-
-        strcpy(pri_ip_src, inet_ntoa(ppkt->ip->ip_src));
-        strcpy(pri_ip_dst, inet_ntoa(ppkt->ip->ip_dst));
-        strcpy(sec_ip_src, inet_ntoa(spkt->ip->ip_src));
-        strcpy(sec_ip_dst, inet_ntoa(spkt->ip->ip_dst));
-
-        trace_colo_compare_ip_info(ppkt->size, pri_ip_src,
-                                   pri_ip_dst, spkt->size,
-                                   sec_ip_src, sec_ip_dst);
-    }
-
     if (ppkt->size != spkt->size) {
         trace_colo_compare_main("Other: payload size of packets are different");
         return -1;
@@ -1415,6 +1402,16 @@ static void colo_compare_init(Object *obj)
                              compare_set_vnet_hdr);
 }
 
+void colo_compare_cleanup(void)
+{
+    CompareState *tmp = NULL;
+    CompareState *n = NULL;
+
+    QTAILQ_FOREACH_SAFE(tmp, &net_compares, next, n) {
+        object_unparent(OBJECT(tmp));
+    }
+}
+
 static void colo_compare_finalize(Object *obj)
 {
     CompareState *s = COLO_COMPARE(obj);
diff --git a/net/colo-compare.h b/net/colo-compare.h
index 22ddd512e2..b055270da2 100644
--- a/net/colo-compare.h
+++ b/net/colo-compare.h
@@ -20,5 +20,6 @@
 void colo_notify_compares_event(void *opaque, int event, Error **errp);
 void colo_compare_register_notifier(Notifier *notify);
 void colo_compare_unregister_notifier(Notifier *notify);
+void colo_compare_cleanup(void);
 
 #endif /* QEMU_COLO_COMPARE_H */
diff --git a/net/colo.c b/net/colo.c
index ef00609848..3a3e6e89a0 100644
--- a/net/colo.c
+++ b/net/colo.c
@@ -157,19 +157,28 @@ void connection_destroy(void *opaque)
 
 Packet *packet_new(const void *data, int size, int vnet_hdr_len)
 {
-    Packet *pkt = g_slice_new(Packet);
+    Packet *pkt = g_slice_new0(Packet);
 
     pkt->data = g_memdup(data, size);
     pkt->size = size;
     pkt->creation_ms = qemu_clock_get_ms(QEMU_CLOCK_HOST);
     pkt->vnet_hdr_len = vnet_hdr_len;
-    pkt->tcp_seq = 0;
-    pkt->tcp_ack = 0;
-    pkt->seq_end = 0;
-    pkt->header_size = 0;
-    pkt->payload_size = 0;
-    pkt->offset = 0;
-    pkt->flags = 0;
+
+    return pkt;
+}
+
+/*
+ * packet_new_nocopy will not copy data, so the caller can't release
+ * the data. And it will be released in packet_destroy.
+ */
+Packet *packet_new_nocopy(void *data, int size, int vnet_hdr_len)
+{
+    Packet *pkt = g_slice_new0(Packet);
+
+    pkt->data = data;
+    pkt->size = size;
+    pkt->creation_ms = qemu_clock_get_ms(QEMU_CLOCK_HOST);
+    pkt->vnet_hdr_len = vnet_hdr_len;
 
     return pkt;
 }
diff --git a/net/colo.h b/net/colo.h
index 573ab91785..d91cd245c4 100644
--- a/net/colo.h
+++ b/net/colo.h
@@ -101,6 +101,7 @@ bool connection_has_tracked(GHashTable *connection_track_table,
                             ConnectionKey *key);
 void connection_hashtable_reset(GHashTable *connection_track_table);
 Packet *packet_new(const void *data, int size, int vnet_hdr_len);
+Packet *packet_new_nocopy(void *data, int size, int vnet_hdr_len);
 void packet_destroy(void *opaque, void *user_data);
 void packet_destroy_partial(void *opaque, void *user_data);
 
diff --git a/net/filter-mirror.c b/net/filter-mirror.c
index f8e65007c0..f20240cc9f 100644
--- a/net/filter-mirror.c
+++ b/net/filter-mirror.c
@@ -88,7 +88,7 @@ static int filter_send(MirrorState *s,
         goto err;
     }
 
-    return 0;
+    return size;
 
 err:
     return ret < 0 ? ret : -EIO;
@@ -159,7 +159,7 @@ static ssize_t filter_mirror_receive_iov(NetFilterState *nf,
     int ret;
 
     ret = filter_send(s, iov, iovcnt);
-    if (ret) {
+    if (ret < 0) {
         error_report("filter mirror send failed(%s)", strerror(-ret));
     }
 
@@ -182,10 +182,10 @@ static ssize_t filter_redirector_receive_iov(NetFilterState *nf,
 
     if (qemu_chr_fe_backend_connected(&s->chr_out)) {
         ret = filter_send(s, iov, iovcnt);
-        if (ret) {
+        if (ret < 0) {
             error_report("filter redirector send failed(%s)", strerror(-ret));
         }
-        return iov_size(iov, iovcnt);
+        return ret;
     } else {
         return 0;
     }
diff --git a/net/filter-rewriter.c b/net/filter-rewriter.c
index 10fe3939b1..cb3a96cde1 100644
--- a/net/filter-rewriter.c
+++ b/net/filter-rewriter.c
@@ -270,8 +270,7 @@ static ssize_t colo_rewriter_receive_iov(NetFilterState *nf,
         vnet_hdr_len = nf->netdev->vnet_hdr_len;
     }
 
-    pkt = packet_new(buf, size, vnet_hdr_len);
-    g_free(buf);
+    pkt = packet_new_nocopy(buf, size, vnet_hdr_len);
 
     /*
      * if we get tcp packet
diff --git a/net/net.c b/net/net.c
index 2a472604ec..76bbb7c31b 100644
--- a/net/net.c
+++ b/net/net.c
@@ -52,6 +52,7 @@
 #include "qapi/error.h"
 #include "qapi/opts-visitor.h"
 #include "sysemu/runstate.h"
+#include "net/colo-compare.h"
 #include "net/filter.h"
 #include "qapi/string-output-visitor.h"
 
@@ -1402,6 +1403,9 @@ void net_cleanup(void)
 {
     NetClientState *nc;
 
+    /*cleanup colo compare module for COLO*/
+    colo_compare_cleanup();
+
     /* We may del multiple entries during qemu_del_net_client(),
      * so QTAILQ_FOREACH_SAFE() is also not safe here.
      */
diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index 8b14215549..19187dce8c 100644
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -68,15 +68,6 @@ VHostNetState *vhost_vdpa_get_vhost_net(NetClientState *nc)
     return s->vhost_net;
 }
 
-uint64_t vhost_vdpa_get_acked_features(NetClientState *nc)
-{
-    VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc);
-    assert(nc->info->type == NET_CLIENT_DRIVER_VHOST_VDPA);
-    s->acked_features = vhost_net_get_acked_features(s->vhost_net);
-
-    return s->acked_features;
-}
-
 static int vhost_vdpa_net_check_device_id(struct vhost_net *net)
 {
     uint32_t device_id;
diff --git a/qapi/net.json b/qapi/net.json
index af3f5b0fda..7fab2e7cd8 100644
--- a/qapi/net.json
+++ b/qapi/net.json
@@ -55,7 +55,8 @@
 # <- { "return": {} }
 #
 ##
-{ 'command': 'netdev_add', 'data': 'Netdev', 'boxed': true }
+{ 'command': 'netdev_add', 'data': 'Netdev', 'boxed': true,
+  'allow-preconfig': true }
 
 ##
 # @netdev_del:
@@ -75,7 +76,8 @@
 # <- { "return": {} }
 #
 ##
-{ 'command': 'netdev_del', 'data': {'id': 'str'} }
+{ 'command': 'netdev_del', 'data': {'id': 'str'},
+  'allow-preconfig': true }
 
 ##
 # @NetLegacyNicOptions:
diff --git a/softmmu/runstate.c b/softmmu/runstate.c
index ce8977c6a2..15640572c0 100644
--- a/softmmu/runstate.c
+++ b/softmmu/runstate.c
@@ -126,6 +126,7 @@ static const RunStateTransition runstate_transitions_def[] = {
     { RUN_STATE_RESTORE_VM, RUN_STATE_PRELAUNCH },
 
     { RUN_STATE_COLO, RUN_STATE_RUNNING },
+    { RUN_STATE_COLO, RUN_STATE_SHUTDOWN},
 
     { RUN_STATE_RUNNING, RUN_STATE_DEBUG },
     { RUN_STATE_RUNNING, RUN_STATE_INTERNAL_ERROR },