Wait for the devices configured at start-up, before allowing the boot to

proceed.  This avoids the race (bug #549) that would result in the infamous
VFS: Cannot open root device "sda1" or unknown-block(0,0) message even when
the hotplug layer had succeeded to configure the device.

Note that The Infamous Message has many possible root causes -- this change
only fixes one of them.  This particular root cause is characterised by
successful boots interleaved with unsuccessful ones, and diagnose.py showing
both front and backend drivers in the Connected state.

Closes bug #549.

Signed-off-by: Ewan Mellor <ewan@xensource.com>

diff --git a/linux-2.6-xen-sparse/drivers/xen/xenbus/xenbus_probe.c b/linux-2.6-xen-sparse/drivers/xen/xenbus/xenbus_probe.c
index ca97e341a8f29233a6965624dc606997a9237101..cab6d5bec8e34fd5f5853c18ef397c57d91b948b 100644 (file)
--- a/linux-2.6-xen-sparse/drivers/xen/xenbus/xenbus_probe.c
+++ b/linux-2.6-xen-sparse/drivers/xen/xenbus/xenbus_probe.c
@@ -884,9 +884,36 @@ void unregister_xenstore_notifier(struct notifier_block *nb)
 EXPORT_SYMBOL(unregister_xenstore_notifier);
 
 
+static int all_devices_ready_(struct device *dev, void *data)
+{
+       struct xenbus_device *xendev = to_xenbus_device(dev);
+       int *result = data;
+       int state;
+
+       int err = xenbus_scanf(XBT_NULL, xendev->nodename, "state", "%d",
+                              &state);
+       if (err != 1 || state != XenbusStateConnected) {
+               result = 0;
+               return 1;
+       }
+
+       return 1;
+}
+
+
+static int all_devices_ready(void)
+{
+       int ready = 1;
+       bus_for_each_dev(&xenbus_frontend.bus, NULL, &ready,
+                        all_devices_ready_);
+       return ready;
+}
+
 
 void xenbus_probe(void *unused)
 {
+       int i;
+
        BUG_ON((xenstored_ready <= 0));
 
        /* Enumerate devices in xenstore. */
@@ -899,6 +926,28 @@ void xenbus_probe(void *unused)
 
        /* Notify others that xenstore is up */
        notifier_call_chain(&xenstore_chain, 0, NULL);
+
+       /* On a 10 second timeout, waiting for all devices currently
+          configured.  We need to do this to guarantee that the filesystems
+          and / or network devices needed for boot are available, before we
+          can allow the boot to proceed.
+
+          A possible improvement here would be to have the tools add a
+          per-device flag to the store entry, indicating whether it is needed
+          at boot time.  This would allow people who knew what they were
+          doing to accelerate their boot slightly, but of course needs tools
+          or manual intervention to set up those flags correctly.
+        */
+       for (i = 0; i < 10 * HZ; i++) {
+               if (all_devices_ready())
+                       return;
+
+               set_current_state(TASK_INTERRUPTIBLE);
+               schedule_timeout(1);
+       }
+
+       printk(KERN_WARNING
+              "XENBUS: Timeout connecting to devices!\n");
 }