xen: Fix event channel callback via INTX/GSI

For a while, event channel notification via the PCI platform device
has been broken, because we attempt to communicate with xenstore before
we even have notifications working, with the xs_reset_watches() call
in xs_init().

We tend to get away with this on Xen versions below 4.0 because we avoid
calling xs_reset_watches() anyway, because xenstore might not cope with
reading a non-existent key. And newer Xen *does* have the vector
callback support, so we rarely fall back to INTX/GSI delivery.

To fix it, clean up a bit of the mess of xs_init() and xenbus_probe()
startup. Call xs_init() directly from xenbus_init() only in the !XS_HVM
case, deferring it to be called from xenbus_probe() in the XS_HVM case
instead.

Then fix up the invocation of xenbus_probe() to happen either from its
device_initcall if the callback is available early enough, or when the
callback is finally set up. This means that the hack of calling
xenbus_probe() from a workqueue after the first interrupt, or directly
from the PCI platform device setup, is no longer needed.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Link: https://lore.kernel.org/r/20210113132606.422794-2-dwmw2@infradead.org
Signed-off-by: Juergen Gross <jgross@suse.com>

3 files changed, 68 insertions, 22 deletions

diff --git a/drivers/xen/xenbus/xenbus.h b/drivers/xen/xenbus/xenbus.h
index 2a93b7c9c159..dc1537335414 100644
--- a/drivers/xen/xenbus/xenbus.h
+++ b/drivers/xen/xenbus/xenbus.h
@@ -115,6 +115,7 @@ int xenbus_probe_node(struct xen_bus_type *bus,
 		      const char *type,
 		      const char *nodename);
 int xenbus_probe_devices(struct xen_bus_type *bus);
+void xenbus_probe(void);
 
 void xenbus_dev_changed(const char *node, struct xen_bus_type *bus);
 
diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c
index eb5151fc8efa..e5fda0256feb 100644
--- a/drivers/xen/xenbus/xenbus_comms.c
+++ b/drivers/xen/xenbus/xenbus_comms.c
@@ -57,16 +57,8 @@ DEFINE_MUTEX(xs_response_mutex);
 static int xenbus_irq;
 static struct task_struct *xenbus_task;
 
-static DECLARE_WORK(probe_work, xenbus_probe);
-
-
 static irqreturn_t wake_waiting(int irq, void *unused)
 {
-	if (unlikely(xenstored_ready == 0)) {
-		xenstored_ready = 1;
-		schedule_work(&probe_work);
-	}
-
 	wake_up(&xb_waitq);
 	return IRQ_HANDLED;
 }
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 44634d970a5c..c8f0282bb649 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -683,29 +683,76 @@ void unregister_xenstore_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL_GPL(unregister_xenstore_notifier);
 
-void xenbus_probe(struct work_struct *unused)
+void xenbus_probe(void)
 {
 	xenstored_ready = 1;
 
+	/*
+	 * In the HVM case, xenbus_init() deferred its call to
+	 * xs_init() in case callbacks were not operational yet.
+	 * So do it now.
+	 */
+	if (xen_store_domain_type == XS_HVM)
+		xs_init();
+
 	/* Notify others that xenstore is up */
 	blocking_notifier_call_chain(&xenstore_chain, 0, NULL);
 }
-EXPORT_SYMBOL_GPL(xenbus_probe);
 
-static int __init xenbus_probe_initcall(void)
+/*
+ * Returns true when XenStore init must be deferred in order to
+ * allow the PCI platform device to be initialised, before we
+ * can actually have event channel interrupts working.
+ */
+static bool xs_hvm_defer_init_for_callback(void)
 {
-	if (!xen_domain())
-		return -ENODEV;
+#ifdef CONFIG_XEN_PVHVM
+	return xen_store_domain_type == XS_HVM &&
+		!xen_have_vector_callback;
+#else
+	return false;
+#endif
+}
 
-	if (xen_initial_domain() || xen_hvm_domain())
-		return 0;
+static int __init xenbus_probe_initcall(void)
+{
+	/*
+	 * Probe XenBus here in the XS_PV case, and also XS_HVM unless we
+	 * need to wait for the platform PCI device to come up.
+	 */
+	if (xen_store_domain_type == XS_PV ||
+	    (xen_store_domain_type == XS_HVM &&
+	     !xs_hvm_defer_init_for_callback()))
+		xenbus_probe();
 
-	xenbus_probe(NULL);
 	return 0;
 }
-
 device_initcall(xenbus_probe_initcall);
 
+int xen_set_callback_via(uint64_t via)
+{
+	struct xen_hvm_param a;
+	int ret;
+
+	a.domid = DOMID_SELF;
+	a.index = HVM_PARAM_CALLBACK_IRQ;
+	a.value = via;
+
+	ret = HYPERVISOR_hvm_op(HVMOP_set_param, &a);
+	if (ret)
+		return ret;
+
+	/*
+	 * If xenbus_probe_initcall() deferred the xenbus_probe()
+	 * due to the callback not functioning yet, we can do it now.
+	 */
+	if (!xenstored_ready && xs_hvm_defer_init_for_callback())
+		xenbus_probe();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xen_set_callback_via);
+
 /* Set up event channel for xenstored which is run as a local process
  * (this is normally used only in dom0)
  */
@@ -818,11 +865,17 @@ static int __init xenbus_init(void)
 		break;
 	}
 
-	/* Initialize the interface to xenstore. */
-	err = xs_init();
-	if (err) {
-		pr_warn("Error initializing xenstore comms: %i\n", err);
-		goto out_error;
+	/*
+	 * HVM domains may not have a functional callback yet. In that
+	 * case let xs_init() be called from xenbus_probe(), which will
+	 * get invoked at an appropriate time.
+	 */
+	if (xen_store_domain_type != XS_HVM) {
+		err = xs_init();
+		if (err) {
+			pr_warn("Error initializing xenstore comms: %i\n", err);
+			goto out_error;
+		}
 	}
 
 	if ((xen_store_domain_type != XS_LOCAL) &&