[PATCH v7 18/21] multi-process: heartbeat messages to remote

[elena.ufimtseva@oracle.com]

From: Elena Ufimtseva <elena.ufimtseva@oracle.com>

In order to detect remote processes which are hung, the
proxy periodically sends heartbeat messages to confirm if
the remote process is alive. The remote process responds
to this heartbeat message to confirm it is alive.

Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
---
 hw/i386/remote-msg.c     | 14 ++++++++++
 hw/pci/proxy.c           | 58 ++++++++++++++++++++++++++++++++++++++++
 include/hw/pci/proxy.h   |  2 ++
 include/io/mpqemu-link.h |  1 +
 io/mpqemu-link.c         |  1 +
 5 files changed, 76 insertions(+)

diff --git a/hw/i386/remote-msg.c b/hw/i386/remote-msg.c
index 9379ee6442..919bddc1d5 100644
--- a/hw/i386/remote-msg.c
+++ b/hw/i386/remote-msg.c
@@ -22,6 +22,7 @@ static void process_bar_write(QIOChannel *ioc, MPQemuMsg *msg, Error **errp);
 static void process_bar_read(QIOChannel *ioc, MPQemuMsg *msg, Error **errp);
 static void process_get_pci_info_msg(QIOChannel *ioc, MPQemuMsg *msg,
                                      PCIDevice *pci_dev);
+static void process_proxy_ping_msg(QIOChannel *ioc);
 
 gboolean mpqemu_process_msg(QIOChannel *ioc, GIOCondition cond,
                             gpointer opaque)
@@ -76,6 +77,9 @@ gboolean mpqemu_process_msg(QIOChannel *ioc, GIOCondition cond,
     case GET_PCI_INFO:
         process_get_pci_info_msg(ioc, &msg, pci_dev);
         break;
+    case PROXY_PING:
+        process_proxy_ping_msg(ioc);
+        break;
     default:
         error_setg(&local_err, "Unknown command (%d) received from proxy \
                    in remote process pid=%d", msg.cmd, getpid());
@@ -269,3 +273,13 @@ static void process_get_pci_info_msg(QIOChannel *ioc, MPQemuMsg *msg,
 
     mpqemu_msg_send(&ret, ioc);
 }
+
+static void process_proxy_ping_msg(QIOChannel *ioc)
+{
+    MPQemuMsg ret = { 0 };
+
+    ret.cmd = RET_MSG;
+    ret.size = sizeof(ret.data1);
+
+    mpqemu_msg_send(&ret, ioc);
+}
diff --git a/hw/pci/proxy.c b/hw/pci/proxy.c
index 449341e459..e2e9a13287 100644
--- a/hw/pci/proxy.c
+++ b/hw/pci/proxy.c
@@ -24,6 +24,8 @@
 #include "util/event_notifier-posix.c"
 
 static void probe_pci_info(PCIDevice *dev);
+static void start_hb_timer(PCIProxyDev *dev);
+static void pci_proxy_dev_exit(PCIDevice *pdev);
 
 static void proxy_set_socket(PCIProxyDev *pdev, int fd, Error **errp)
 {
@@ -132,6 +134,8 @@ static void pci_proxy_dev_realize(PCIDevice *device, Error **errp)
     setup_irqfd(dev);
 
     probe_pci_info(PCI_DEVICE(dev));
+
+    start_hb_timer(dev);
 }
 
 static int config_op_send(PCIProxyDev *pdev, uint32_t addr, uint32_t *val,
@@ -192,6 +196,7 @@ static void pci_proxy_dev_class_init(ObjectClass *klass, void *data)
     k->realize = pci_proxy_dev_realize;
     k->config_read = pci_proxy_read_config;
     k->config_write = pci_proxy_write_config;
+    k->exit = pci_proxy_dev_exit;
 
     device_class_set_props(dc, proxy_properties);
 }
@@ -356,3 +361,56 @@ static void probe_pci_info(PCIDevice *dev)
         }
     }
 }
+
+static void hb_msg(PCIProxyDev *dev)
+{
+    DeviceState *ds = DEVICE(dev);
+    MPQemuMsg msg = { 0 };
+    long ret = -EINVAL;
+    Error *local_err = NULL;
+
+    msg.cmd = PROXY_PING;
+    msg.bytestream = 0;
+    msg.size = 0;
+
+    ret = mpqemu_msg_send_reply_co(&msg, dev->com, &local_err);
+    if (local_err) {
+        error_report("Lost contact with remote device %s, error code %ld",
+                     ds->id, ret);
+    }
+}
+
+#define NOP_INTERVAL 1000
+
+static void remote_ping(void *opaque)
+{
+    PCIProxyDev *dev = opaque;
+
+    hb_msg(dev);
+
+    timer_mod(dev->hb_timer,
+              qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + NOP_INTERVAL);
+}
+
+static void start_hb_timer(PCIProxyDev *dev)
+{
+    dev->hb_timer = timer_new_ms(QEMU_CLOCK_VIRTUAL,
+                                 remote_ping,
+                                 dev);
+
+    timer_mod(dev->hb_timer,
+              qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + NOP_INTERVAL);
+}
+
+static void stop_hb_timer(PCIProxyDev *dev)
+{
+    timer_del(dev->hb_timer);
+    timer_free(dev->hb_timer);
+}
+
+static void pci_proxy_dev_exit(PCIDevice *pdev)
+{
+    PCIProxyDev *dev = PCI_PROXY_DEV(pdev);
+
+    stop_hb_timer(dev);
+}
diff --git a/include/hw/pci/proxy.h b/include/hw/pci/proxy.h
index e6f076ae95..037740309d 100644
--- a/include/hw/pci/proxy.h
+++ b/include/hw/pci/proxy.h
@@ -53,6 +53,8 @@ struct PCIProxyDev {
     EventNotifier intr;
     EventNotifier resample;
 
+    QEMUTimer *hb_timer;
+
     ProxyMemoryRegion region[PCI_NUM_REGIONS];
 };
 
diff --git a/include/io/mpqemu-link.h b/include/io/mpqemu-link.h
index 4b96cb8ccb..676d7eb3ef 100644
--- a/include/io/mpqemu-link.h
+++ b/include/io/mpqemu-link.h
@@ -44,6 +44,7 @@ typedef enum {
     BAR_READ,
     SET_IRQFD,
     GET_PCI_INFO,
+    PROXY_PING,
     MAX = INT_MAX,
 } MPQemuCmd;
 
diff --git a/io/mpqemu-link.c b/io/mpqemu-link.c
index d09b2a2f50..7452e55e17 100644
--- a/io/mpqemu-link.c
+++ b/io/mpqemu-link.c
@@ -264,6 +264,7 @@ bool mpqemu_msg_valid(MPQemuMsg *msg)
         }
         break;
     case GET_PCI_INFO:
+    case PROXY_PING:
         if (msg->size) {
             return false;
         }
-- 
2.25.GIT