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

# gpg: Signature made Fri 29 Mar 2019 07:30:26 GMT
# 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:
  net: tap: use qemu_set_nonblock
  MAINTAINERS: Update the latest email address
  e1000: Delay flush queue when receive RCTL
  net/socket: learn to talk with a unix dgram socket

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

4 files changed, 49 insertions, 12 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index c2ad5062f6..56139ac8ab 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2179,7 +2179,7 @@ F: include/migration/failover.h
 F: docs/COLO-FT.txt
 
 COLO Proxy
-M: Zhang Chen <zhangckid@gmail.com>
+M: Zhang Chen <chen.zhang@intel.com>
 M: Li Zhijian <lizhijian@cn.fujitsu.com>
 S: Supported
 F: docs/colo-proxy.txt
diff --git a/hw/net/e1000.c b/hw/net/e1000.c
index 5e144cb4e4..9b39bccfb2 100644
--- a/hw/net/e1000.c
+++ b/hw/net/e1000.c
@@ -120,6 +120,8 @@ typedef struct E1000State_st {
     bool mit_irq_level;        /* Tracks interrupt pin level. */
     uint32_t mit_ide;          /* Tracks E1000_TXD_CMD_IDE bit. */
 
+    QEMUTimer *flush_queue_timer;
+
 /* Compatibility flags for migration to/from qemu 1.3.0 and older */
 #define E1000_FLAG_AUTONEG_BIT 0
 #define E1000_FLAG_MIT_BIT 1
@@ -366,6 +368,7 @@ static void e1000_reset(void *opaque)
 
     timer_del(d->autoneg_timer);
     timer_del(d->mit_timer);
+    timer_del(d->flush_queue_timer);
     d->mit_timer_on = 0;
     d->mit_irq_level = 0;
     d->mit_ide = 0;
@@ -392,6 +395,14 @@ set_ctrl(E1000State *s, int index, uint32_t val)
 }
 
 static void
+e1000_flush_queue_timer(void *opaque)
+{
+    E1000State *s = opaque;
+
+    qemu_flush_queued_packets(qemu_get_queue(s->nic));
+}
+
+static void
 set_rx_control(E1000State *s, int index, uint32_t val)
 {
     s->mac_reg[RCTL] = val;
@@ -399,7 +410,8 @@ set_rx_control(E1000State *s, int index, uint32_t val)
     s->rxbuf_min_shift = ((val / E1000_RCTL_RDMTS_QUAT) & 3) + 1;
     DBGOUT(RX, "RCTL: %d, mac_reg[RCTL] = 0x%x\n", s->mac_reg[RDT],
            s->mac_reg[RCTL]);
-    qemu_flush_queued_packets(qemu_get_queue(s->nic));
+    timer_mod(s->flush_queue_timer,
+              qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + 1000);
 }
 
 static void
@@ -837,7 +849,7 @@ e1000_can_receive(NetClientState *nc)
     E1000State *s = qemu_get_nic_opaque(nc);
 
     return e1000x_rx_ready(&s->parent_obj, s->mac_reg) &&
-        e1000_has_rxbufs(s, 1);
+        e1000_has_rxbufs(s, 1) && !timer_pending(s->flush_queue_timer);
 }
 
 static uint64_t rx_desc_base(E1000State *s)
@@ -881,6 +893,10 @@ e1000_receive_iov(NetClientState *nc, const struct iovec *iov, int iovcnt)
         return -1;
     }
 
+    if (timer_pending(s->flush_queue_timer)) {
+        return 0;
+    }
+
     /* Pad to minimum Ethernet frame length */
     if (size < sizeof(min_buf)) {
         iov_to_buf(iov, iovcnt, 0, min_buf, size);
@@ -1637,6 +1653,8 @@ pci_e1000_uninit(PCIDevice *dev)
     timer_free(d->autoneg_timer);
     timer_del(d->mit_timer);
     timer_free(d->mit_timer);
+    timer_del(d->flush_queue_timer);
+    timer_free(d->flush_queue_timer);
     qemu_del_nic(d->nic);
 }
 
@@ -1700,6 +1718,8 @@ static void pci_e1000_realize(PCIDevice *pci_dev, Error **errp)
 
     d->autoneg_timer = timer_new_ms(QEMU_CLOCK_VIRTUAL, e1000_autoneg_timer, d);
     d->mit_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, e1000_mit_timer, d);
+    d->flush_queue_timer = timer_new_ms(QEMU_CLOCK_VIRTUAL,
+                                        e1000_flush_queue_timer, d);
 }
 
 static void qdev_e1000_reset(DeviceState *dev)
diff --git a/net/socket.c b/net/socket.c
index 90ef3517be..c92354049b 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -119,9 +119,13 @@ static ssize_t net_socket_receive_dgram(NetClientState *nc, const uint8_t *buf,
     ssize_t ret;
 
     do {
-        ret = qemu_sendto(s->fd, buf, size, 0,
-                          (struct sockaddr *)&s->dgram_dst,
-                          sizeof(s->dgram_dst));
+        if (s->dgram_dst.sin_family != AF_UNIX) {
+            ret = qemu_sendto(s->fd, buf, size, 0,
+                              (struct sockaddr *)&s->dgram_dst,
+                              sizeof(s->dgram_dst));
+        } else {
+            ret = send(s->fd, buf, size, 0);
+        }
     } while (ret == -1 && errno == EINTR);
 
     if (ret == -1 && errno == EAGAIN) {
@@ -336,6 +340,15 @@ static NetSocketState *net_socket_fd_init_dgram(NetClientState *peer,
     int newfd;
     NetClientState *nc;
     NetSocketState *s;
+    SocketAddress *sa;
+    SocketAddressType sa_type;
+
+    sa = socket_local_address(fd, errp);
+    if (!sa) {
+        return NULL;
+    }
+    sa_type = sa->type;
+    qapi_free_SocketAddress(sa);
 
     /* fd passed: multicast: "learn" dgram_dst address from bound address and save it
      * Because this may be "shared" socket from a "master" process, datagrams would be recv()
@@ -379,8 +392,12 @@ static NetSocketState *net_socket_fd_init_dgram(NetClientState *peer,
                  "socket: fd=%d (cloned mcast=%s:%d)",
                  fd, inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port));
     } else {
+        if (sa_type == SOCKET_ADDRESS_TYPE_UNIX) {
+            s->dgram_dst.sin_family = AF_UNIX;
+        }
+
         snprintf(nc->info_str, sizeof(nc->info_str),
-                 "socket: fd=%d", fd);
+                 "socket: fd=%d %s", fd, SocketAddressType_str(sa_type));
     }
 
     return s;
diff --git a/net/tap.c b/net/tap.c
index cc8525f154..e8aadd8d4b 100644
--- a/net/tap.c
+++ b/net/tap.c
@@ -592,7 +592,7 @@ int net_init_bridge(const Netdev *netdev, const char *name,
         return -1;
     }
 
-    fcntl(fd, F_SETFL, O_NONBLOCK);
+    qemu_set_nonblock(fd);
     vnet_hdr = tap_probe_vnet_hdr(fd);
     s = net_tap_fd_init(peer, "bridge", name, fd, vnet_hdr);
 
@@ -707,7 +707,7 @@ static void net_init_tap_one(const NetdevTapOptions *tap, NetClientState *peer,
                 }
                 return;
             }
-            fcntl(vhostfd, F_SETFL, O_NONBLOCK);
+            qemu_set_nonblock(vhostfd);
         }
         options.opaque = (void *)(uintptr_t)vhostfd;
 
@@ -791,7 +791,7 @@ int net_init_tap(const Netdev *netdev, const char *name,
             return -1;
         }
 
-        fcntl(fd, F_SETFL, O_NONBLOCK);
+        qemu_set_nonblock(fd);
 
         vnet_hdr = tap_probe_vnet_hdr(fd);
 
@@ -839,7 +839,7 @@ int net_init_tap(const Netdev *netdev, const char *name,
                 goto free_fail;
             }
 
-            fcntl(fd, F_SETFL, O_NONBLOCK);
+            qemu_set_nonblock(fd);
 
             if (i == 0) {
                 vnet_hdr = tap_probe_vnet_hdr(fd);
@@ -887,7 +887,7 @@ free_fail:
             return -1;
         }
 
-        fcntl(fd, F_SETFL, O_NONBLOCK);
+        qemu_set_nonblock(fd);
         vnet_hdr = tap_probe_vnet_hdr(fd);
 
         net_init_tap_one(tap, peer, "bridge", name, ifname,