vhost, pc: fixes for 2.5

Minor vhost fixes.  HW version tweak for PC.
 Documentation and test updates.
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQEcBAABAgAGBQJWVzX5AAoJECgfDbjSjVRp3UUH/jmankS57MaFIfB2plhrFlk0
 BAjMLhJ6GCLrDEAaMaes9wJXJJMQHfoZnwAqkfkvjabKbiq6yPZz2FIfjSKuV86Z
 F6XNuMxiM2qwt/HJ5IaBX0c0Bm9bsF3zQpVAs082KfLvTrmOf8SHk4b8OFOCJMvu
 asSl9J8DTo3LZwC1TNpbxvTj5k3OFhB8i16WT3lvdLv9QUxBwdUaG6WxUCZD/35C
 CJnjut7n09ZbG4dfVxAVl7KubX1llpNBopbTQEyoHaaVfOvFDL5R2Gf7/YG9G0+x
 aI4+rMmRt0KCTii7xjN63j88+YpGlTgrAZETzwxVolZGMOe74jGtCNQqlIBwPZI=
 =I1ki
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/mst/tags/for_upstream' into staging

vhost, pc: fixes for 2.5

Minor vhost fixes.  HW version tweak for PC.
Documentation and test updates.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Thu 26 Nov 2015 16:40:25 GMT using RSA key ID D28D5469
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>"
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>"

* remotes/mst/tags/for_upstream:
  vhost-user-test: fix migration overlap test
  Fix memory leak on error
  Revert "vhost: send SET_VRING_ENABLE at start/stop"
  tests/vhost-user-bridge: read command line arguments
  tests/vhost-user-bridge: propose GUEST_ANNOUNCE feature
  vhost-user: clarify start and enable
  vhost-user: set link down when the char device is closed
  pc: Don't set hw_version on pc-*-2.5
  osdep: Change default value of qemu_hw_version() to "2.5+"

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

docs/specs/vhost-user.txt

@@ -148,13 +148,23 @@ a feature bit was dedicated for this purpose:
 
 Starting and stopping rings
 ----------------------
-Client must only process each ring when it is both started and enabled.
+Client must only process each ring when it is started.
+
+Client must only pass data between the ring and the
+backend, when the ring is enabled.
+
+If ring is started but disabled, client must process the
+ring without talking to the backend.
+
+For example, for a networking device, in the disabled state
+client must not supply any new RX packets, but must process
+and discard any TX packets.
 
 If VHOST_USER_F_PROTOCOL_FEATURES has not been negotiated, the ring is initialized
 in an enabled state.
 
 If VHOST_USER_F_PROTOCOL_FEATURES has been negotiated, the ring is initialized
-in a disabled state. Client must not process it until ring is enabled by
+in a disabled state. Client must not pass data to/from the backend until ring is enabled by
 VHOST_USER_SET_VRING_ENABLE with parameter 1, or after it has been disabled by
 VHOST_USER_SET_VRING_ENABLE with parameter 0.
 
@@ -166,7 +176,7 @@ descriptor is readable) on the descriptor specified by
 VHOST_USER_SET_VRING_KICK, and stop ring upon receiving
 VHOST_USER_GET_VRING_BASE.
 
-While processing the rings (when they are started and enabled), client must
+While processing the rings (whether they are enabled or not), client must
 support changing some configuration aspects on the fly.
 
 Multiple queue support
@@ -309,11 +319,11 @@ Message types
       Id: 4
       Master payload: N/A
 
-      This is no longer used. Used to be sent to request stopping
+      This is no longer used. Used to be sent to request disabling
       all rings, but some clients interpreted it to also discard
       connection state (this interpretation would lead to bugs).
       It is recommended that clients either ignore this message,
-      or use it to stop all rings.
+      or use it to disable all rings.
 
  * VHOST_USER_SET_MEM_TABLE
 

hw/acpi/memory_hotplug.c

@@ -155,6 +155,7 @@ static void acpi_memory_hotplug_write(void *opaque, hwaddr addr, uint64_t data,
                 qapi_event_send_mem_unplug_error(dev->id,
                                                  error_get_pretty(local_err),
                                                  &error_abort);
+                error_free(local_err);
                 break;
             }
             trace_mhp_acpi_pc_dimm_deleted(mem_st->selector);

hw/i386/pc_piix.c

@@ -472,7 +472,6 @@ static void pc_i440fx_machine_options(MachineClass *m)
 static void pc_i440fx_2_5_machine_options(MachineClass *m)
 {
     pc_i440fx_machine_options(m);
-    m->hw_version = QEMU_VERSION;
     m->alias = "pc";
     m->is_default = 1;
 }

hw/i386/pc_q35.c

@@ -373,7 +373,6 @@ static void pc_q35_machine_options(MachineClass *m)
 static void pc_q35_2_5_machine_options(MachineClass *m)
 {
     pc_q35_machine_options(m);
-    m->hw_version = QEMU_VERSION;
     m->alias = "q35";
 }
 

hw/ppc/spapr.c

@@ -125,6 +125,7 @@ static XICSState *xics_system_init(MachineState *machine,
             error_report("kernel_irqchip requested but unavailable: %s",
                          error_get_pretty(err));
         }
+        error_free(err);
     }
 
     if (!icp) {

hw/virtio/vhost.c

@@ -1226,11 +1226,6 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev)
         }
     }
 
-    if (hdev->vhost_ops->vhost_set_vring_enable) {
-        /* only enable first vq pair by default */
-        hdev->vhost_ops->vhost_set_vring_enable(hdev, hdev->vq_index == 0);
-    }
-
     return 0;
 fail_log:
     vhost_log_put(hdev, false);
@@ -1261,10 +1256,6 @@ void vhost_dev_stop(struct vhost_dev *hdev, VirtIODevice *vdev)
                              hdev->vq_index + i);
     }
 
-    if (hdev->vhost_ops->vhost_set_vring_enable) {
-        hdev->vhost_ops->vhost_set_vring_enable(hdev, 0);
-    }
-
     vhost_log_put(hdev, true);
     hdev->started = false;
     hdev->log = NULL;

include/hw/boards.h

@@ -51,6 +51,11 @@ bool machine_mem_merge(MachineState *machine);
  *    used to provide @cpu_index to socket number mapping, allowing
  *    a machine to group CPU threads belonging to the same socket/package
  *    Returns: socket number given cpu_index belongs to.
+ * @hw_version:
+ *    Value of QEMU_VERSION when the machine was added to QEMU.
+ *    Set only by old machines because they need to keep
+ *    compatibility on code that exposed QEMU_VERSION to guests in
+ *    the past (and now use qemu_hw_version()).
  */
 struct MachineClass {
     /*< private >*/

include/qemu/osdep.h

@@ -256,6 +256,10 @@ static inline void qemu_timersub(const struct timeval *val1,
 
 void qemu_set_cloexec(int fd);
 
+/* QEMU "hardware version" setting. Used to replace code that exposed
+ * QEMU_VERSION to guests in the past and need to keep compatibilty.
+ * Do not use qemu_hw_version() in new code.
+ */
 void qemu_set_hw_version(const char *);
 const char *qemu_hw_version(void);
 

net/vhost-user.c

@@ -188,7 +188,7 @@ static void net_vhost_user_event(void *opaque, int event)
         qmp_set_link(name, true, &err);
         break;
     case CHR_EVENT_CLOSED:
-        qmp_set_link(name, true, &err);
+        qmp_set_link(name, false, &err);
         vhost_user_stop(queues, ncs);
         break;
     }

tests/vhost-user-bridge.c

@@ -45,6 +45,8 @@
 #include <sys/mman.h>
 #include <sys/eventfd.h>
 #include <arpa/inet.h>
+#include <ctype.h>
+#include <netdb.h>
 
 #include <linux/vhost.h>
 
@@ -747,6 +749,7 @@ vubr_get_features_exec(VubrDev *dev, VhostUserMsg *vmsg)
     vmsg->payload.u64 =
             ((1ULL << VIRTIO_NET_F_MRG_RXBUF) |
              (1ULL << VHOST_F_LOG_ALL) |
+             (1ULL << VIRTIO_NET_F_GUEST_ANNOUNCE) |
              (1ULL << VHOST_USER_F_PROTOCOL_FEATURES));
 
     vmsg->size = sizeof(vmsg->payload.u64);
@@ -1209,33 +1212,62 @@ vubr_new(const char *path)
     return dev;
 }
 
+static void
+vubr_set_host(struct sockaddr_in *saddr, const char *host)
+{
+    if (isdigit(host[0])) {
+        if (!inet_aton(host, &saddr->sin_addr)) {
+            fprintf(stderr, "inet_aton() failed.\n");
+            exit(1);
+        }
+    } else {
+        struct hostent *he = gethostbyname(host);
+
+        if (!he) {
+            fprintf(stderr, "gethostbyname() failed.\n");
+            exit(1);
+        }
+        saddr->sin_addr = *(struct in_addr *)he->h_addr;
+    }
+}
+
 static void
 vubr_backend_udp_setup(VubrDev *dev,
                        const char *local_host,
-                       uint16_t local_port,
+                       const char *local_port,
-                       const char *dest_host,
+                       const char *remote_host,
-                       uint16_t dest_port)
+                       const char *remote_port)
 {
     int sock;
-    struct sockaddr_in si_local = {
+    const char *r;
-        .sin_family = AF_INET,
-        .sin_port = htons(local_port),
-    };
 
-    if (inet_aton(local_host, &si_local.sin_addr) == 0) {
+    int lport, rport;
-        fprintf(stderr, "inet_aton() failed.\n");
+
+    lport = strtol(local_port, (char **)&r, 0);
+    if (r == local_port) {
+        fprintf(stderr, "lport parsing failed.\n");
         exit(1);
     }
 
+    rport = strtol(remote_port, (char **)&r, 0);
+    if (r == remote_port) {
+        fprintf(stderr, "rport parsing failed.\n");
+        exit(1);
+    }
+
+    struct sockaddr_in si_local = {
+        .sin_family = AF_INET,
+        .sin_port = htons(lport),
+    };
+
+    vubr_set_host(&si_local, local_host);
+
     /* setup destination for sends */
     dev->backend_udp_dest = (struct sockaddr_in) {
         .sin_family = AF_INET,
-        .sin_port = htons(dest_port),
+        .sin_port = htons(rport),
     };
-    if (inet_aton(dest_host, &dev->backend_udp_dest.sin_addr) == 0) {
+    vubr_set_host(&dev->backend_udp_dest, remote_host);
-        fprintf(stderr, "inet_aton() failed.\n");
-        exit(1);
-    }
 
     sock = socket(AF_INET, SOCK_DGRAM, IPPROTO_UDP);
     if (sock == -1) {
@@ -1249,7 +1281,7 @@ vubr_backend_udp_setup(VubrDev *dev,
     dev->backend_udp_sock = sock;
     dispatcher_add(&dev->dispatcher, sock, dev, vubr_backend_recv_cb);
     DPRINT("Waiting for data from udp backend on %s:%d...\n",
-           local_host, local_port);
+           local_host, lport);
 }
 
 static void
@@ -1262,19 +1294,81 @@ vubr_run(VubrDev *dev)
     }
 }
 
+static int
+vubr_parse_host_port(const char **host, const char **port, const char *buf)
+{
+    char *p = strchr(buf, ':');
+
+    if (!p) {
+        return -1;
+    }
+    *p = '\0';
+    *host = strdup(buf);
+    *port = strdup(p + 1);
+    return 0;
+}
+
+#define DEFAULT_UD_SOCKET "/tmp/vubr.sock"
+#define DEFAULT_LHOST "127.0.0.1"
+#define DEFAULT_LPORT "4444"
+#define DEFAULT_RHOST "127.0.0.1"
+#define DEFAULT_RPORT "5555"
+
+static const char *ud_socket_path = DEFAULT_UD_SOCKET;
+static const char *lhost = DEFAULT_LHOST;
+static const char *lport = DEFAULT_LPORT;
+static const char *rhost = DEFAULT_RHOST;
+static const char *rport = DEFAULT_RPORT;
+
 int
 main(int argc, char *argv[])
 {
     VubrDev *dev;
+    int opt;
 
-    dev = vubr_new("/tmp/vubr.sock");
+    while ((opt = getopt(argc, argv, "l:r:u:")) != -1) {
+
+        switch (opt) {
+        case 'l':
+            if (vubr_parse_host_port(&lhost, &lport, optarg) < 0) {
+                goto out;
+            }
+            break;
+        case 'r':
+            if (vubr_parse_host_port(&rhost, &rport, optarg) < 0) {
+                goto out;
+            }
+            break;
+        case 'u':
+            ud_socket_path = strdup(optarg);
+            break;
+        default:
+            goto out;
+        }
+    }
+
+    DPRINT("ud socket: %s\n", ud_socket_path);
+    DPRINT("local:     %s:%s\n", lhost, lport);
+    DPRINT("remote:    %s:%s\n", rhost, rport);
+
+    dev = vubr_new(ud_socket_path);
     if (!dev) {
         return 1;
     }
 
-    vubr_backend_udp_setup(dev,
+    vubr_backend_udp_setup(dev, lhost, lport, rhost, rport);
-                                 "127.0.0.1", 4444,
-                                 "127.0.0.1", 5555);
     vubr_run(dev);
     return 0;
+
+out:
+    fprintf(stderr, "Usage: %s ", argv[0]);
+    fprintf(stderr, "[-u ud_socket_path] [-l lhost:lport] [-r rhost:rport]\n");
+    fprintf(stderr, "\t-u path to unix doman socket. default: %s\n",
+            DEFAULT_UD_SOCKET);
+    fprintf(stderr, "\t-l local host and port. default: %s:%s\n",
+            DEFAULT_LHOST, DEFAULT_LPORT);
+    fprintf(stderr, "\t-r remote host and port. default: %s:%s\n",
+            DEFAULT_RHOST, DEFAULT_RPORT);
+
+    return 1;
 }

tests/vhost-user-test.c

@@ -131,6 +131,7 @@ typedef struct TestServer {
     GMutex data_mutex;
     GCond data_cond;
     int log_fd;
+    uint64_t rings;
 } TestServer;
 
 #if !GLIB_CHECK_VERSION(2, 32, 0)
@@ -279,6 +280,9 @@ static void chr_read(void *opaque, const uint8_t *buf, int size)
         msg.payload.state.num = 0;
         p = (uint8_t *) &msg;
         qemu_chr_fe_write_all(chr, p, VHOST_USER_HDR_SIZE + msg.size);
+
+        assert(msg.payload.state.index < 2);
+        s->rings &= ~(0x1ULL << msg.payload.state.index);
         break;
 
     case VHOST_USER_SET_MEM_TABLE:
@@ -316,10 +320,9 @@ static void chr_read(void *opaque, const uint8_t *buf, int size)
         g_cond_signal(&s->data_cond);
         break;
 
-    case VHOST_USER_SET_VRING_ENABLE:
+    case VHOST_USER_SET_VRING_BASE:
-        if (!msg.payload.state.num) {
+        assert(msg.payload.state.index < 2);
-            s->fds_num = 0;
+        s->rings |= 0x1ULL << msg.payload.state.index;
-        }
         break;
 
     default:
@@ -486,7 +489,7 @@ static gboolean
 test_migrate_source_check(GSource *source)
 {
     TestMigrateSource *t = (TestMigrateSource *)source;
-    gboolean overlap = t->src->fds_num > 0 && t->dest->fds_num > 0;
+    gboolean overlap = t->src->rings && t->dest->rings;
 
     g_assert(!overlap);
 

util/osdep.c

@@ -52,7 +52,14 @@ extern int madvise(caddr_t, size_t, int);
 
 static bool fips_enabled = false;
 
-static const char *hw_version = QEMU_VERSION;
+/* Starting on QEMU 2.5, qemu_hw_version() returns "2.5+" by default
+ * instead of QEMU_VERSION, so setting hw_version on MachineClass
+ * is no longer mandatory.
+ *
+ * Do NOT change this string, or it will break compatibility on all
+ * machine classes that don't set hw_version.
+ */
+static const char *hw_version = "2.5+";
 
 int socket_set_cork(int fd, int v)
 {