1 files changed, 250 insertions, 28 deletions

diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 8c4d05b687b7..58b732dcbfb8 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -31,6 +31,7 @@
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#define dev_fmt pr_fmt
 
 #define DPRINTK(fmt, args...)				\
 	pr_debug("xenbus_probe (%s:%d) " fmt ".\n",	\
@@ -51,7 +52,6 @@
 #include <linux/module.h>
 
 #include <asm/page.h>
-#include <asm/pgtable.h>
 #include <asm/xen/hypervisor.h>
 
 #include <xen/xen.h>
@@ -65,6 +65,7 @@
 #include "xenbus.h"
 
 
+static int xs_init_irq;
 int xen_store_evtchn;
 EXPORT_SYMBOL_GPL(xen_store_evtchn);
 
@@ -136,6 +137,7 @@ 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");
 }
@@ -205,6 +207,64 @@ void xenbus_otherend_changed(struct xenbus_watch *watch,
 }
 EXPORT_SYMBOL_GPL(xenbus_otherend_changed);
 
+#define XENBUS_SHOW_STAT(name)						\
+static ssize_t name##_show(struct device *_dev,				\
+			   struct device_attribute *attr,		\
+			   char *buf)					\
+{									\
+	struct xenbus_device *dev = to_xenbus_device(_dev);		\
+									\
+	return sprintf(buf, "%d\n", atomic_read(&dev->name));		\
+}									\
+static DEVICE_ATTR_RO(name)
+
+XENBUS_SHOW_STAT(event_channels);
+XENBUS_SHOW_STAT(events);
+XENBUS_SHOW_STAT(spurious_events);
+XENBUS_SHOW_STAT(jiffies_eoi_delayed);
+
+static ssize_t spurious_threshold_show(struct device *_dev,
+				       struct device_attribute *attr,
+				       char *buf)
+{
+	struct xenbus_device *dev = to_xenbus_device(_dev);
+
+	return sprintf(buf, "%d\n", dev->spurious_threshold);
+}
+
+static ssize_t spurious_threshold_store(struct device *_dev,
+					struct device_attribute *attr,
+					const char *buf, size_t count)
+{
+	struct xenbus_device *dev = to_xenbus_device(_dev);
+	unsigned int val;
+	ssize_t ret;
+
+	ret = kstrtouint(buf, 0, &val);
+	if (ret)
+		return ret;
+
+	dev->spurious_threshold = val;
+
+	return count;
+}
+
+static DEVICE_ATTR_RW(spurious_threshold);
+
+static struct attribute *xenbus_attrs[] = {
+	&dev_attr_event_channels.attr,
+	&dev_attr_events.attr,
+	&dev_attr_spurious_events.attr,
+	&dev_attr_jiffies_eoi_delayed.attr,
+	&dev_attr_spurious_threshold.attr,
+	NULL
+};
+
+static const struct attribute_group xenbus_group = {
+	.name = "xenbus",
+	.attrs = xenbus_attrs,
+};
+
 int xenbus_dev_probe(struct device *_dev)
 {
 	struct xenbus_device *dev = to_xenbus_device(_dev);
@@ -252,6 +312,11 @@ int xenbus_dev_probe(struct device *_dev)
 		return err;
 	}
 
+	dev->spurious_threshold = 1;
+	if (sysfs_create_group(&dev->dev.kobj, &xenbus_group))
+		dev_warn(&dev->dev, "sysfs_create_group on %s failed.\n",
+			 dev->nodename);
+
 	return 0;
 fail_put:
 	module_put(drv->driver.owner);
@@ -261,13 +326,15 @@ fail:
 }
 EXPORT_SYMBOL_GPL(xenbus_dev_probe);
 
-int xenbus_dev_remove(struct device *_dev)
+void xenbus_dev_remove(struct device *_dev)
 {
 	struct xenbus_device *dev = to_xenbus_device(_dev);
 	struct xenbus_driver *drv = to_xenbus_driver(_dev->driver);
 
 	DPRINTK("%s", dev->nodename);
 
+	sysfs_remove_group(&dev->dev.kobj, &xenbus_group);
+
 	free_otherend_watch(dev);
 
 	if (drv->remove) {
@@ -289,8 +356,6 @@ int xenbus_dev_remove(struct device *_dev)
 	if (!drv->allow_rebind ||
 	    xenbus_read_driver_state(dev->nodename) == XenbusStateClosing)
 		xenbus_switch_state(dev, XenbusStateClosed);
-
-	return 0;
 }
 EXPORT_SYMBOL_GPL(xenbus_dev_remove);
 
@@ -608,7 +673,7 @@ int xenbus_dev_suspend(struct device *dev)
 	if (drv->suspend)
 		err = drv->suspend(xdev);
 	if (err)
-		pr_warn("suspend %s failed: %i\n", dev_name(dev), err);
+		dev_warn(dev, "suspend failed: %i\n", err);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(xenbus_dev_suspend);
@@ -627,8 +692,7 @@ int xenbus_dev_resume(struct device *dev)
 	drv = to_xenbus_driver(dev->driver);
 	err = talk_to_otherend(xdev);
 	if (err) {
-		pr_warn("resume (talk_to_otherend) %s failed: %i\n",
-			dev_name(dev), err);
+		dev_warn(dev, "resume (talk_to_otherend) failed: %i\n", err);
 		return err;
 	}
 
@@ -637,15 +701,14 @@ int xenbus_dev_resume(struct device *dev)
 	if (drv->resume) {
 		err = drv->resume(xdev);
 		if (err) {
-			pr_warn("resume %s failed: %i\n", dev_name(dev), err);
+			dev_warn(dev, "resume failed: %i\n", err);
 			return err;
 		}
 	}
 
 	err = watch_otherend(xdev);
 	if (err) {
-		pr_warn("resume (watch_otherend) %s failed: %d.\n",
-			dev_name(dev), err);
+		dev_warn(dev, "resume (watch_otherend) failed: %d\n", err);
 		return err;
 	}
 
@@ -684,29 +747,123 @@ 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;
 
+	if (!xen_store_interface) {
+		xen_store_interface = memremap(xen_store_gfn << XEN_PAGE_SHIFT,
+					       XEN_PAGE_SIZE, MEMREMAP_WB);
+		/*
+		 * Now it is safe to free the IRQ used for xenstore late
+		 * initialization. No need to unbind: it is about to be
+		 * bound again from xb_init_comms. Note that calling
+		 * unbind_from_irqhandler now would result in xen_evtchn_close()
+		 * being called and the event channel not being enabled again
+		 * afterwards, resulting in missed event notifications.
+		 */
+		free_irq(xs_init_irq, &xb_waitq);
+	}
+
+	/*
+	 * 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);
+
+	/*
+	 * 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);
 
-	xenbus_probe(NULL);
+	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 or
+	 * xen_store_interface is not ready.
+	 */
+	if (xen_store_domain_type == XS_PV ||
+	    (xen_store_domain_type == XS_HVM &&
+	     !xs_hvm_defer_init_for_callback() &&
+	     xen_store_interface != NULL))
+		xenbus_probe();
+
+	/*
+	 * For XS_LOCAL or when xen_store_interface is not ready, 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 || xen_store_interface == NULL) {
+		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)
  */
@@ -767,10 +924,25 @@ static struct notifier_block xenbus_resume_nb = {
 	.notifier_call = xenbus_resume_cb,
 };
 
+static irqreturn_t xenbus_late_init(int irq, void *unused)
+{
+	int err;
+	uint64_t v = 0;
+
+	err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v);
+	if (err || !v || !~v)
+		return IRQ_HANDLED;
+	xen_store_gfn = (unsigned long)v;
+
+	wake_up(&xb_waitq);
+	return IRQ_HANDLED;
+}
+
 static int __init xenbus_init(void)
 {
-	int err = 0;
+	int err;
 	uint64_t v = 0;
+	bool wait = false;
 	xen_store_domain_type = XS_UNKNOWN;
 
 	if (!xen_domain())
@@ -809,21 +981,69 @@ static int __init xenbus_init(void)
 		err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v);
 		if (err)
 			goto out_error;
-		xen_store_gfn = (unsigned long)v;
-		xen_store_interface =
-			xen_remap(xen_store_gfn << XEN_PAGE_SHIFT,
-				  XEN_PAGE_SIZE);
+		/*
+		 * 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/uninitialized value.
+		 */
+		if (!v) {
+			err = -ENOENT;
+			goto out_error;
+		}
+		if (v == ~0ULL) {
+			wait = true;
+		} else {
+			/* 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 =
+				memremap(xen_store_gfn << XEN_PAGE_SHIFT,
+					 XEN_PAGE_SIZE, MEMREMAP_WB);
+			if (xen_store_interface->connection != XENSTORE_CONNECTED)
+				wait = true;
+		}
+		if (wait) {
+			err = bind_evtchn_to_irqhandler(xen_store_evtchn,
+							xenbus_late_init,
+							0, "xenstore_late_init",
+							&xb_waitq);
+			if (err < 0) {
+				pr_err("xenstore_late_init couldn't bind irq err=%d\n",
+				       err);
+				return err;
+			}
+
+			xs_init_irq = err;
+		}
 		break;
 	default:
 		pr_warn("Xenstore state unknown\n");
 		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) &&
@@ -837,8 +1057,10 @@ static int __init xenbus_init(void)
 	 */
 	proc_create_mount_point("xen");
 #endif
+	return 0;
 
 out_error:
+	xen_store_domain_type = XS_UNKNOWN;
 	return err;
 }