7 files changed, 175 insertions, 50 deletions

diff --git a/drivers/xen/xenbus/xenbus.h b/drivers/xen/xenbus/xenbus.h
index d75a2385b37c..88516a8a9f93 100644
--- a/drivers/xen/xenbus/xenbus.h
+++ b/drivers/xen/xenbus/xenbus.h
@@ -44,6 +44,8 @@ struct xen_bus_type {
 	int (*get_bus_id)(char bus_id[XEN_BUS_ID_SIZE], const char *nodename);
 	int (*probe)(struct xen_bus_type *bus, const char *type,
 		     const char *dir);
+	bool (*otherend_will_handle)(struct xenbus_watch *watch,
+				     const char *path, const char *token);
 	void (*otherend_changed)(struct xenbus_watch *watch, const char *path,
 				 const char *token);
 	struct bus_type bus;
diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index f7b553faadb1..6dde323dabd4 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -114,18 +114,22 @@ EXPORT_SYMBOL_GPL(xenbus_strstate);
  */
 int xenbus_watch_path(struct xenbus_device *dev, const char *path,
 		      struct xenbus_watch *watch,
+		      bool (*will_handle)(struct xenbus_watch *,
+					  const char *, const char *),
 		      void (*callback)(struct xenbus_watch *,
 				       const char *, const char *))
 {
 	int err;
 
 	watch->node = path;
+	watch->will_handle = will_handle;
 	watch->callback = callback;
 
 	err = register_xenbus_watch(watch);
 
 	if (err) {
 		watch->node = NULL;
+		watch->will_handle = NULL;
 		watch->callback = NULL;
 		xenbus_dev_fatal(dev, err, "adding watch on %s", path);
 	}
@@ -152,6 +156,8 @@ EXPORT_SYMBOL_GPL(xenbus_watch_path);
  */
 int xenbus_watch_pathfmt(struct xenbus_device *dev,
 			 struct xenbus_watch *watch,
+			 bool (*will_handle)(struct xenbus_watch *,
+					const char *, const char *),
 			 void (*callback)(struct xenbus_watch *,
 					  const char *, const char *),
 			 const char *pathfmt, ...)
@@ -168,7 +174,7 @@ int xenbus_watch_pathfmt(struct xenbus_device *dev,
 		xenbus_dev_fatal(dev, -ENOMEM, "allocating path for watch");
 		return -ENOMEM;
 	}
-	err = xenbus_watch_path(dev, path, watch, callback);
+	err = xenbus_watch_path(dev, path, watch, will_handle, callback);
 
 	if (err)
 		kfree(path);
@@ -362,7 +368,14 @@ int xenbus_grant_ring(struct xenbus_device *dev, void *vaddr,
 		      unsigned int nr_pages, grant_ref_t *grefs)
 {
 	int err;
-	int i, j;
+	unsigned int i;
+	grant_ref_t gref_head;
+
+	err = gnttab_alloc_grant_references(nr_pages, &gref_head);
+	if (err) {
+		xenbus_dev_fatal(dev, err, "granting access to ring page");
+		return err;
+	}
 
 	for (i = 0; i < nr_pages; i++) {
 		unsigned long gfn;
@@ -372,23 +385,14 @@ int xenbus_grant_ring(struct xenbus_device *dev, void *vaddr,
 		else
 			gfn = virt_to_gfn(vaddr);
 
-		err = gnttab_grant_foreign_access(dev->otherend_id, gfn, 0);
-		if (err < 0) {
-			xenbus_dev_fatal(dev, err,
-					 "granting access to ring page");
-			goto fail;
-		}
-		grefs[i] = err;
+		grefs[i] = gnttab_claim_grant_reference(&gref_head);
+		gnttab_grant_foreign_access_ref(grefs[i], dev->otherend_id,
+						gfn, 0);
 
 		vaddr = vaddr + XEN_PAGE_SIZE;
 	}
 
 	return 0;
-
-fail:
-	for (j = 0; j < i; j++)
-		gnttab_end_foreign_access_ref(grefs[j], 0);
-	return err;
 }
 EXPORT_SYMBOL_GPL(xenbus_grant_ring);
 
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_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index 454c6826abdb..1c1dadfd4e4d 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -128,7 +128,7 @@ static ssize_t xenbus_file_read(struct file *filp,
 {
 	struct xenbus_file_priv *u = filp->private_data;
 	struct read_buffer *rb;
-	unsigned i;
+	ssize_t i;
 	int ret;
 
 	mutex_lock(&u->reply_mutex);
@@ -148,7 +148,7 @@ again:
 	rb = list_entry(u->read_buffers.next, struct read_buffer, list);
 	i = 0;
 	while (i < len) {
-		unsigned sz = min((unsigned)len - i, rb->len - rb->cons);
+		size_t sz = min_t(size_t, len - i, rb->len - rb->cons);
 
 		ret = copy_to_user(ubuf + i, &rb->msg[rb->cons], sz);
 
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 5b471889d723..b911a91bce6b 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -136,6 +136,7 @@ static int watch_otherend(struct xenbus_device *dev)
 		container_of(dev->dev.bus, struct xen_bus_type, bus);
 
 	return xenbus_watch_pathfmt(dev, &dev->otherend_watch,
+				    bus->otherend_will_handle,
 				    bus->otherend_changed,
 				    "%s/%s", dev->otherend, "state");
 }
@@ -682,29 +683,107 @@ void unregister_xenstore_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL_GPL(unregister_xenstore_notifier);
 
-void xenbus_probe(struct work_struct *unused)
+static 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 xenbus_probe_thread(void *unused)
+{
+	DEFINE_WAIT(w);
 
-	xenbus_probe(NULL);
+	/*
+	 * We actually just want to wait for *any* trigger of xb_waitq,
+	 * and run xenbus_probe() the moment it occurs.
+	 */
+	prepare_to_wait(&xb_waitq, &w, TASK_INTERRUPTIBLE);
+	schedule();
+	finish_wait(&xb_waitq, &w);
+
+	DPRINTK("probing");
+	xenbus_probe();
 	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();
+
+	/*
+	 * For XS_LOCAL, spawn a thread which will wait for xenstored
+	 * or a xenstore-stubdom to be started, then probe. It will be
+	 * triggered when communication starts happening, by waiting
+	 * on xb_waitq.
+	 */
+	if (xen_store_domain_type == XS_LOCAL) {
+		struct task_struct *probe_task;
+
+		probe_task = kthread_run(xenbus_probe_thread, NULL,
+					 "xenbus_probe");
+		if (IS_ERR(probe_task))
+			return PTR_ERR(probe_task);
+	}
+	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)
  */
@@ -767,7 +846,7 @@ static struct notifier_block xenbus_resume_nb = {
 
 static int __init xenbus_init(void)
 {
-	int err = 0;
+	int err;
 	uint64_t v = 0;
 	xen_store_domain_type = XS_UNKNOWN;
 
@@ -807,6 +886,29 @@ static int __init xenbus_init(void)
 		err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v);
 		if (err)
 			goto out_error;
+		/*
+		 * Uninitialized hvm_params are zero and return no error.
+		 * Although it is theoretically possible to have
+		 * HVM_PARAM_STORE_PFN set to zero on purpose, in reality it is
+		 * not zero when valid. If zero, it means that Xenstore hasn't
+		 * been properly initialized. Instead of attempting to map a
+		 * wrong guest physical address return error.
+		 *
+		 * Also recognize all bits set as an invalid value.
+		 */
+		if (!v || !~v) {
+			err = -ENOENT;
+			goto out_error;
+		}
+		/* Avoid truncation on 32-bit. */
+#if BITS_PER_LONG == 32
+		if (v > ULONG_MAX) {
+			pr_err("%s: cannot handle HVM_PARAM_STORE_PFN=%llx > ULONG_MAX\n",
+			       __func__, v);
+			err = -EINVAL;
+			goto out_error;
+		}
+#endif
 		xen_store_gfn = (unsigned long)v;
 		xen_store_interface =
 			xen_remap(xen_store_gfn << XEN_PAGE_SHIFT,
@@ -817,11 +919,17 @@ 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) &&
@@ -835,8 +943,10 @@ static int __init xenbus_init(void)
 	 */
 	proc_create_mount_point("xen");
 #endif
+	return 0;
 
 out_error:
+	xen_store_domain_type = XS_UNKNOWN;
 	return err;
 }
 
diff --git a/drivers/xen/xenbus/xenbus_probe_backend.c b/drivers/xen/xenbus/xenbus_probe_backend.c
index b0bed4faf44c..4bb603051d5b 100644
--- a/drivers/xen/xenbus/xenbus_probe_backend.c
+++ b/drivers/xen/xenbus/xenbus_probe_backend.c
@@ -180,6 +180,12 @@ static int xenbus_probe_backend(struct xen_bus_type *bus, const char *type,
 	return err;
 }
 
+static bool frontend_will_handle(struct xenbus_watch *watch,
+				 const char *path, const char *token)
+{
+	return watch->nr_pending == 0;
+}
+
 static void frontend_changed(struct xenbus_watch *watch,
 			     const char *path, const char *token)
 {
@@ -191,6 +197,7 @@ static struct xen_bus_type xenbus_backend = {
 	.levels = 3,		/* backend/type/<frontend>/<id> */
 	.get_bus_id = backend_bus_id,
 	.probe = xenbus_probe_backend,
+	.otherend_will_handle = frontend_will_handle,
 	.otherend_changed = frontend_changed,
 	.bus = {
 		.name		= "xen-backend",
diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c
index 3a06eb699f33..12e02eb01f59 100644
--- a/drivers/xen/xenbus/xenbus_xs.c
+++ b/drivers/xen/xenbus/xenbus_xs.c
@@ -705,9 +705,13 @@ int xs_watch_msg(struct xs_watch_event *event)
 
 	spin_lock(&watches_lock);
 	event->handle = find_watch(event->token);
-	if (event->handle != NULL) {
+	if (event->handle != NULL &&
+			(!event->handle->will_handle ||
+			 event->handle->will_handle(event->handle,
+				 event->path, event->token))) {
 		spin_lock(&watch_events_lock);
 		list_add_tail(&event->list, &watch_events);
+		event->handle->nr_pending++;
 		wake_up(&watch_events_waitq);
 		spin_unlock(&watch_events_lock);
 	} else
@@ -765,6 +769,8 @@ int register_xenbus_watch(struct xenbus_watch *watch)
 
 	sprintf(token, "%lX", (long)watch);
 
+	watch->nr_pending = 0;
+
 	down_read(&xs_watch_rwsem);
 
 	spin_lock(&watches_lock);
@@ -814,11 +820,14 @@ void unregister_xenbus_watch(struct xenbus_watch *watch)
 
 	/* Cancel pending watch events. */
 	spin_lock(&watch_events_lock);
-	list_for_each_entry_safe(event, tmp, &watch_events, list) {
-		if (event->handle != watch)
-			continue;
-		list_del(&event->list);
-		kfree(event);
+	if (watch->nr_pending) {
+		list_for_each_entry_safe(event, tmp, &watch_events, list) {
+			if (event->handle != watch)
+				continue;
+			list_del(&event->list);
+			kfree(event);
+		}
+		watch->nr_pending = 0;
 	}
 	spin_unlock(&watch_events_lock);
 
@@ -865,7 +874,6 @@ void xs_suspend_cancel(void)
 
 static int xenwatch_thread(void *unused)
 {
-	struct list_head *ent;
 	struct xs_watch_event *event;
 
 	xenwatch_pid = current->pid;
@@ -880,13 +888,15 @@ static int xenwatch_thread(void *unused)
 		mutex_lock(&xenwatch_mutex);
 
 		spin_lock(&watch_events_lock);
-		ent = watch_events.next;
-		if (ent != &watch_events)
-			list_del(ent);
+		event = list_first_entry_or_null(&watch_events,
+				struct xs_watch_event, list);
+		if (event) {
+			list_del(&event->list);
+			event->handle->nr_pending--;
+		}
 		spin_unlock(&watch_events_lock);
 
-		if (ent != &watch_events) {
-			event = list_entry(ent, struct xs_watch_event, list);
+		if (event) {
 			event->handle->callback(event->handle, event->path,
 						event->token);
 			kfree(event);