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

# gpg: Signature made Wed 15 Jul 2020 14:49:07 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:
  ftgmac100: fix dblac write test
  net: detect errors from probing vnet hdr flag for TAP devices
  net: check if the file descriptor is valid before using it
  qemu-options.hx: Clean up and fix typo for colo-compare
  net/colo-compare.c: Expose compare "max_queue_size" to users
  hw/net: Added CSO for IPv6
  virtio-net: fix removal of failover device

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

15 files changed, 188 insertions, 77 deletions

diff --git a/hw/net/ftgmac100.c b/hw/net/ftgmac100.c
index 043ba61b86..5f4b26fc5f 100644
--- a/hw/net/ftgmac100.c
+++ b/hw/net/ftgmac100.c
@@ -810,16 +810,18 @@ static void ftgmac100_write(void *opaque, hwaddr addr,
         s->phydata = value & 0xffff;
         break;
     case FTGMAC100_DBLAC: /* DMA Burst Length and Arbitration Control */
-        if (FTGMAC100_DBLAC_TXDES_SIZE(s->dblac) < sizeof(FTGMAC100Desc)) {
+        if (FTGMAC100_DBLAC_TXDES_SIZE(value) < sizeof(FTGMAC100Desc)) {
             qemu_log_mask(LOG_GUEST_ERROR,
-                          "%s: transmit descriptor too small : %d bytes\n",
-                          __func__, FTGMAC100_DBLAC_TXDES_SIZE(s->dblac));
+                          "%s: transmit descriptor too small: %" PRIx64
+                          " bytes\n", __func__,
+                          FTGMAC100_DBLAC_TXDES_SIZE(value));
             break;
         }
-        if (FTGMAC100_DBLAC_RXDES_SIZE(s->dblac) < sizeof(FTGMAC100Desc)) {
+        if (FTGMAC100_DBLAC_RXDES_SIZE(value) < sizeof(FTGMAC100Desc)) {
             qemu_log_mask(LOG_GUEST_ERROR,
-                          "%s: receive descriptor too small : %d bytes\n",
-                          __func__, FTGMAC100_DBLAC_RXDES_SIZE(s->dblac));
+                          "%s: receive descriptor too small : %" PRIx64
+                          " bytes\n", __func__,
+                          FTGMAC100_DBLAC_RXDES_SIZE(value));
             break;
         }
         s->dblac = value;
diff --git a/hw/net/net_tx_pkt.c b/hw/net/net_tx_pkt.c
index 162f802dd7..331c73cfc0 100644
--- a/hw/net/net_tx_pkt.c
+++ b/hw/net/net_tx_pkt.c
@@ -468,8 +468,8 @@ static void net_tx_pkt_do_sw_csum(struct NetTxPkt *pkt)
     /* num of iovec without vhdr */
     uint32_t iov_len = pkt->payload_frags + NET_TX_PKT_PL_START_FRAG - 1;
     uint16_t csl;
-    struct ip_header *iphdr;
     size_t csum_offset = pkt->virt_hdr.csum_start + pkt->virt_hdr.csum_offset;
+    uint16_t l3_proto = eth_get_l3_proto(iov, 1, iov->iov_len);
 
     /* Put zero to checksum field */
     iov_from_buf(iov, iov_len, csum_offset, &csum, sizeof csum);
@@ -477,9 +477,18 @@ static void net_tx_pkt_do_sw_csum(struct NetTxPkt *pkt)
     /* Calculate L4 TCP/UDP checksum */
     csl = pkt->payload_len;
 
+    csum_cntr = 0;
+    cso = 0;
     /* add pseudo header to csum */
-    iphdr = pkt->vec[NET_TX_PKT_L3HDR_FRAG].iov_base;
-    csum_cntr = eth_calc_ip4_pseudo_hdr_csum(iphdr, csl, &cso);
+    if (l3_proto == ETH_P_IP) {
+        csum_cntr = eth_calc_ip4_pseudo_hdr_csum(
+                pkt->vec[NET_TX_PKT_L3HDR_FRAG].iov_base,
+                csl, &cso);
+    } else if (l3_proto == ETH_P_IPV6) {
+        csum_cntr = eth_calc_ip6_pseudo_hdr_csum(
+                pkt->vec[NET_TX_PKT_L3HDR_FRAG].iov_base,
+                csl, pkt->l4proto, &cso);
+    }
 
     /* data checksum */
     csum_cntr +=
diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 10cc958396..4895af1cbe 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -3416,6 +3416,7 @@ static void virtio_net_device_unrealize(DeviceState *dev)
     g_free(n->vlans);
 
     if (n->failover) {
+        device_listener_unregister(&n->primary_listener);
         g_free(n->primary_device_id);
         g_free(n->standby_id);
         qobject_unref(n->primary_device_dict);
diff --git a/include/qemu/sockets.h b/include/qemu/sockets.h
index 57cd049d6e..7d1f813576 100644
--- a/include/qemu/sockets.h
+++ b/include/qemu/sockets.h
@@ -18,6 +18,7 @@ int qemu_accept(int s, struct sockaddr *addr, socklen_t *addrlen);
 int socket_set_cork(int fd, int v);
 int socket_set_nodelay(int fd);
 void qemu_set_block(int fd);
+int qemu_try_set_nonblock(int fd);
 void qemu_set_nonblock(int fd);
 int socket_set_fast_reuse(int fd);
 
diff --git a/net/colo-compare.c b/net/colo-compare.c
index 398b7546ff..cc15f23dea 100644
--- a/net/colo-compare.c
+++ b/net/colo-compare.c
@@ -59,6 +59,7 @@ static bool colo_compare_active;
 static QemuMutex event_mtx;
 static QemuCond event_complete_cond;
 static int event_unhandled_count;
+static uint32_t max_queue_size;
 
 /*
  *  + CompareState ++
@@ -222,7 +223,7 @@ static void fill_pkt_tcp_info(void *data, uint32_t *max_ack)
  */
 static int colo_insert_packet(GQueue *queue, Packet *pkt, uint32_t *max_ack)
 {
-    if (g_queue_get_length(queue) <= MAX_QUEUE_SIZE) {
+    if (g_queue_get_length(queue) <= max_queue_size) {
         if (pkt->ip->ip_p == IPPROTO_TCP) {
             fill_pkt_tcp_info(pkt, max_ack);
             g_queue_insert_sorted(queue,
@@ -1134,6 +1135,37 @@ static void compare_set_expired_scan_cycle(Object *obj, Visitor *v,
     s->expired_scan_cycle = value;
 }
 
+static void get_max_queue_size(Object *obj, Visitor *v,
+                               const char *name, void *opaque,
+                               Error **errp)
+{
+    uint32_t value = max_queue_size;
+
+    visit_type_uint32(v, name, &value, errp);
+}
+
+static void set_max_queue_size(Object *obj, Visitor *v,
+                               const char *name, void *opaque,
+                               Error **errp)
+{
+    Error *local_err = NULL;
+    uint32_t value;
+
+    visit_type_uint32(v, name, &value, &local_err);
+    if (local_err) {
+        goto out;
+    }
+    if (!value) {
+        error_setg(&local_err, "Property '%s.%s' requires a positive value",
+                   object_get_typename(obj), name);
+        goto out;
+    }
+    max_queue_size = value;
+
+out:
+    error_propagate(errp, local_err);
+}
+
 static void compare_pri_rs_finalize(SocketReadState *pri_rs)
 {
     CompareState *s = container_of(pri_rs, CompareState, pri_rs);
@@ -1251,6 +1283,11 @@ static void colo_compare_complete(UserCreatable *uc, Error **errp)
         s->expired_scan_cycle = REGULAR_PACKET_CHECK_MS;
     }
 
+    if (!max_queue_size) {
+        /* Set default queue size to 1024 */
+        max_queue_size = MAX_QUEUE_SIZE;
+    }
+
     if (find_and_check_chardev(&chr, s->pri_indev, errp) ||
         !qemu_chr_fe_init(&s->chr_pri_in, chr, errp)) {
         return;
@@ -1370,6 +1407,10 @@ static void colo_compare_init(Object *obj)
                         compare_get_expired_scan_cycle,
                         compare_set_expired_scan_cycle, NULL, NULL);
 
+    object_property_add(obj, "max_queue_size", "uint32",
+                        get_max_queue_size,
+                        set_max_queue_size, NULL, NULL);
+
     s->vnet_hdr = false;
     object_property_add_bool(obj, "vnet_hdr_support", compare_get_vnet_hdr,
                              compare_set_vnet_hdr);
diff --git a/net/socket.c b/net/socket.c
index c92354049b..2d21fddd9c 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -725,13 +725,18 @@ int net_init_socket(const Netdev *netdev, const char *name,
     }
 
     if (sock->has_fd) {
-        int fd;
+        int fd, ret;
 
         fd = monitor_fd_param(cur_mon, sock->fd, errp);
         if (fd == -1) {
             return -1;
         }
-        qemu_set_nonblock(fd);
+        ret = qemu_try_set_nonblock(fd);
+        if (ret < 0) {
+            error_setg_errno(errp, -ret, "%s: Can't use file descriptor %d",
+                             name, fd);
+            return -1;
+        }
         if (!net_socket_fd_init(peer, "socket", name, fd, 1, sock->mcast,
                                 errp)) {
             return -1;
diff --git a/net/tap-bsd.c b/net/tap-bsd.c
index a5c3707f80..77aaf674b1 100644
--- a/net/tap-bsd.c
+++ b/net/tap-bsd.c
@@ -211,7 +211,7 @@ void tap_set_sndbuf(int fd, const NetdevTapOptions *tap, Error **errp)
 {
 }
 
-int tap_probe_vnet_hdr(int fd)
+int tap_probe_vnet_hdr(int fd, Error **errp)
 {
     return 0;
 }
diff --git a/net/tap-linux.c b/net/tap-linux.c
index e0dd442ee3..b0635e9e32 100644
--- a/net/tap-linux.c
+++ b/net/tap-linux.c
@@ -147,13 +147,15 @@ void tap_set_sndbuf(int fd, const NetdevTapOptions *tap, Error **errp)
     }
 }
 
-int tap_probe_vnet_hdr(int fd)
+int tap_probe_vnet_hdr(int fd, Error **errp)
 {
     struct ifreq ifr;
 
     if (ioctl(fd, TUNGETIFF, &ifr) != 0) {
-        error_report("TUNGETIFF ioctl() failed: %s", strerror(errno));
-        return 0;
+        /* TUNGETIFF is available since kernel v2.6.27 */
+        error_setg_errno(errp, errno,
+                         "Unable to query TUNGETIFF on FD %d", fd);
+        return -1;
     }
 
     return ifr.ifr_flags & IFF_VNET_HDR;
diff --git a/net/tap-solaris.c b/net/tap-solaris.c
index d03165c57c..0475a58207 100644
--- a/net/tap-solaris.c
+++ b/net/tap-solaris.c
@@ -207,7 +207,7 @@ void tap_set_sndbuf(int fd, const NetdevTapOptions *tap, Error **errp)
 {
 }
 
-int tap_probe_vnet_hdr(int fd)
+int tap_probe_vnet_hdr(int fd, Error **errp)
 {
     return 0;
 }
diff --git a/net/tap-stub.c b/net/tap-stub.c
index a9ab8f8293..de525a2e69 100644
--- a/net/tap-stub.c
+++ b/net/tap-stub.c
@@ -37,7 +37,7 @@ void tap_set_sndbuf(int fd, const NetdevTapOptions *tap, Error **errp)
 {
 }
 
-int tap_probe_vnet_hdr(int fd)
+int tap_probe_vnet_hdr(int fd, Error **errp)
 {
     return 0;
 }
diff --git a/net/tap.c b/net/tap.c
index f9dcc2ef51..14dc904fca 100644
--- a/net/tap.c
+++ b/net/tap.c
@@ -598,7 +598,11 @@ int net_init_bridge(const Netdev *netdev, const char *name,
     }
 
     qemu_set_nonblock(fd);
-    vnet_hdr = tap_probe_vnet_hdr(fd);
+    vnet_hdr = tap_probe_vnet_hdr(fd, errp);
+    if (vnet_hdr < 0) {
+        close(fd);
+        return -1;
+    }
     s = net_tap_fd_init(peer, "bridge", name, fd, vnet_hdr);
 
     snprintf(s->nc.info_str, sizeof(s->nc.info_str), "helper=%s,br=%s", helper,
@@ -690,6 +694,8 @@ static void net_init_tap_one(const NetdevTapOptions *tap, NetClientState *peer,
         }
 
         if (vhostfdname) {
+            int ret;
+
             vhostfd = monitor_fd_param(cur_mon, vhostfdname, &err);
             if (vhostfd == -1) {
                 if (tap->has_vhostforce && tap->vhostforce) {
@@ -699,7 +705,12 @@ static void net_init_tap_one(const NetdevTapOptions *tap, NetClientState *peer,
                 }
                 return;
             }
-            qemu_set_nonblock(vhostfd);
+            ret = qemu_try_set_nonblock(vhostfd);
+            if (ret < 0) {
+                error_setg_errno(errp, -ret, "%s: Can't use file descriptor %d",
+                                 name, fd);
+                return;
+            }
         } else {
             vhostfd = open("/dev/vhost-net", O_RDWR);
             if (vhostfd < 0) {
@@ -767,6 +778,7 @@ int net_init_tap(const Netdev *netdev, const char *name,
     Error *err = NULL;
     const char *vhostfdname;
     char ifname[128];
+    int ret = 0;
 
     assert(netdev->type == NET_CLIENT_DRIVER_TAP);
     tap = &netdev->u.tap;
@@ -795,9 +807,18 @@ int net_init_tap(const Netdev *netdev, const char *name,
             return -1;
         }
 
-        qemu_set_nonblock(fd);
+        ret = qemu_try_set_nonblock(fd);
+        if (ret < 0) {
+            error_setg_errno(errp, -ret, "%s: Can't use file descriptor %d",
+                             name, fd);
+            return -1;
+        }
 
-        vnet_hdr = tap_probe_vnet_hdr(fd);
+        vnet_hdr = tap_probe_vnet_hdr(fd, errp);
+        if (vnet_hdr < 0) {
+            close(fd);
+            return -1;
+        }
 
         net_init_tap_one(tap, peer, "tap", name, NULL,
                          script, downscript,
@@ -810,7 +831,6 @@ int net_init_tap(const Netdev *netdev, const char *name,
         char **fds;
         char **vhost_fds;
         int nfds = 0, nvhosts = 0;
-        int ret = 0;
 
         if (tap->has_ifname || tap->has_script || tap->has_downscript ||
             tap->has_vnet_hdr || tap->has_helper || tap->has_queues ||
@@ -842,11 +862,19 @@ int net_init_tap(const Netdev *netdev, const char *name,
                 goto free_fail;
             }
 
-            qemu_set_nonblock(fd);
+            ret = qemu_try_set_nonblock(fd);
+            if (ret < 0) {
+                error_setg_errno(errp, -ret, "%s: Can't use file descriptor %d",
+                                 name, fd);
+                goto free_fail;
+            }
 
             if (i == 0) {
-                vnet_hdr = tap_probe_vnet_hdr(fd);
-            } else if (vnet_hdr != tap_probe_vnet_hdr(fd)) {
+                vnet_hdr = tap_probe_vnet_hdr(fd, errp);
+                if (vnet_hdr < 0) {
+                    goto free_fail;
+                }
+            } else if (vnet_hdr != tap_probe_vnet_hdr(fd, NULL)) {
                 error_setg(errp,
                            "vnet_hdr not consistent across given tap fds");
                 ret = -1;
@@ -891,7 +919,11 @@ free_fail:
         }
 
         qemu_set_nonblock(fd);
-        vnet_hdr = tap_probe_vnet_hdr(fd);
+        vnet_hdr = tap_probe_vnet_hdr(fd, errp);
+        if (vnet_hdr < 0) {
+            close(fd);
+            return -1;
+        }
 
         net_init_tap_one(tap, peer, "bridge", name, ifname,
                          script, downscript, vhostfdname,
diff --git a/net/tap_int.h b/net/tap_int.h
index e3194b23f4..225a49ea48 100644
--- a/net/tap_int.h
+++ b/net/tap_int.h
@@ -34,7 +34,7 @@ int tap_open(char *ifname, int ifname_size, int *vnet_hdr,
 ssize_t tap_read_packet(int tapfd, uint8_t *buf, int maxlen);
 
 void tap_set_sndbuf(int fd, const NetdevTapOptions *tap, Error **errp);
-int tap_probe_vnet_hdr(int fd);
+int tap_probe_vnet_hdr(int fd, Error **errp);
 int tap_probe_vnet_hdr_len(int fd, int len);
 int tap_probe_has_ufo(int fd);
 void tap_fd_set_offload(int fd, int csum, int tso4, int tso6, int ecn, int ufo);
diff --git a/qemu-options.hx b/qemu-options.hx
index d2c1e95bcf..65147ad971 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -4695,24 +4695,25 @@ SRST
         stored. The file format is libpcap, so it can be analyzed with
         tools such as tcpdump or Wireshark.
 
-    ``-object colo-compare,id=id,primary_in=chardevid,secondary_in=chardevid,outdev=chardevid,iothread=id[,vnet_hdr_support][,notify_dev=id][,compare_timeout=@var{ms}][,expired_scan_cycle=@var{ms}``
-        Colo-compare gets packet from primary\_inchardevid and
-        secondary\_inchardevid, than compare primary packet with
-        secondary packet. If the packets are same, we will output
-        primary packet to outdevchardevid, else we will notify
-        colo-frame do checkpoint and send primary packet to
-        outdevchardevid. In order to improve efficiency, we need to put
-        the task of comparison in another thread. If it has the
-        vnet\_hdr\_support flag, colo compare will send/recv packet with
-        vnet\_hdr\_len. Then compare\_timeout=@var{ms} determines the
-        maximum delay colo-compare wait for the packet.
-        The expired\_scan\_cycle=@var{ms} to set the period of scanning
-        expired primary node network packets.
-        If you want to use Xen COLO, will need the notify\_dev to
+    ``-object colo-compare,id=id,primary_in=chardevid,secondary_in=chardevid,outdev=chardevid,iothread=id[,vnet_hdr_support][,notify_dev=id][,compare_timeout=@var{ms}][,expired_scan_cycle=@var{ms}][,max_queue_size=@var{size}]``
+        Colo-compare gets packet from primary\_in chardevid and
+        secondary\_in, then compare whether the payload of primary packet
+        and secondary packet are the same. If same, it will output
+        primary packet to out\_dev, else it will notify COLO-framework to do
+        checkpoint and send primary packet to out\_dev. In order to
+        improve efficiency, we need to put the task of comparison in
+        another iothread. If it has the vnet\_hdr\_support flag,
+        colo compare will send/recv packet with vnet\_hdr\_len.
+        The compare\_timeout=@var{ms} determines the maximum time of the
+        colo-compare hold the packet. The expired\_scan\_cycle=@var{ms}
+        is to set the period of scanning expired primary node network packets.
+        The max\_queue\_size=@var{size} is to set the max compare queue
+        size depend on user environment.
+        If user want to use Xen COLO, need to add the notify\_dev to
         notify Xen colo-frame to do checkpoint.
 
-        we must use it with the help of filter-mirror and
-        filter-redirector.
+        COLO-compare must be used with the help of filter-mirror,
+        filter-redirector and filter-rewriter.
 
         ::
 
diff --git a/util/oslib-posix.c b/util/oslib-posix.c
index e60aea85b6..36bf8593f8 100644
--- a/util/oslib-posix.c
+++ b/util/oslib-posix.c
@@ -260,25 +260,35 @@ void qemu_set_block(int fd)
     assert(f != -1);
 }
 
-void qemu_set_nonblock(int fd)
+int qemu_try_set_nonblock(int fd)
 {
     int f;
     f = fcntl(fd, F_GETFL);
-    assert(f != -1);
-    f = fcntl(fd, F_SETFL, f | O_NONBLOCK);
-#ifdef __OpenBSD__
     if (f == -1) {
+        return -errno;
+    }
+    if (fcntl(fd, F_SETFL, f | O_NONBLOCK) == -1) {
+#ifdef __OpenBSD__
         /*
          * Previous to OpenBSD 6.3, fcntl(F_SETFL) is not permitted on
          * memory devices and sets errno to ENODEV.
          * It's OK if we fail to set O_NONBLOCK on devices like /dev/null,
          * because they will never block anyway.
          */
-        assert(errno == ENODEV);
-    }
-#else
-    assert(f != -1);
+        if (errno == ENODEV) {
+            return 0;
+        }
 #endif
+        return -errno;
+    }
+    return 0;
+}
+
+void qemu_set_nonblock(int fd)
+{
+    int f;
+    f = qemu_try_set_nonblock(fd);
+    assert(f == 0);
 }
 
 int socket_set_fast_reuse(int fd)
diff --git a/util/oslib-win32.c b/util/oslib-win32.c
index 3b49d27297..7eedbe5859 100644
--- a/util/oslib-win32.c
+++ b/util/oslib-win32.c
@@ -132,31 +132,6 @@ struct tm *localtime_r(const time_t *timep, struct tm *result)
 }
 #endif /* CONFIG_LOCALTIME_R */
 
-void qemu_set_block(int fd)
-{
-    unsigned long opt = 0;
-    WSAEventSelect(fd, NULL, 0);
-    ioctlsocket(fd, FIONBIO, &opt);
-}
-
-void qemu_set_nonblock(int fd)
-{
-    unsigned long opt = 1;
-    ioctlsocket(fd, FIONBIO, &opt);
-    qemu_fd_register(fd);
-}
-
-int socket_set_fast_reuse(int fd)
-{
-    /* Enabling the reuse of an endpoint that was used by a socket still in
-     * TIME_WAIT state is usually performed by setting SO_REUSEADDR. On Windows
-     * fast reuse is the default and SO_REUSEADDR does strange things. So we
-     * don't have to do anything here. More info can be found at:
-     * http://msdn.microsoft.com/en-us/library/windows/desktop/ms740621.aspx */
-    return 0;
-}
-
-
 static int socket_error(void)
 {
     switch (WSAGetLastError()) {
@@ -233,6 +208,38 @@ static int socket_error(void)
     }
 }
 
+void qemu_set_block(int fd)
+{
+    unsigned long opt = 0;
+    WSAEventSelect(fd, NULL, 0);
+    ioctlsocket(fd, FIONBIO, &opt);
+}
+
+int qemu_try_set_nonblock(int fd)
+{
+    unsigned long opt = 1;
+    if (ioctlsocket(fd, FIONBIO, &opt) != NO_ERROR) {
+        return -socket_error();
+    }
+    qemu_fd_register(fd);
+    return 0;
+}
+
+void qemu_set_nonblock(int fd)
+{
+    (void)qemu_try_set_nonblock(fd);
+}
+
+int socket_set_fast_reuse(int fd)
+{
+    /* Enabling the reuse of an endpoint that was used by a socket still in
+     * TIME_WAIT state is usually performed by setting SO_REUSEADDR. On Windows
+     * fast reuse is the default and SO_REUSEADDR does strange things. So we
+     * don't have to do anything here. More info can be found at:
+     * http://msdn.microsoft.com/en-us/library/windows/desktop/ms740621.aspx */
+    return 0;
+}
+
 int inet_aton(const char *cp, struct in_addr *ia)
 {
     uint32_t addr = inet_addr(cp);