4 files changed, 216 insertions, 73 deletions

diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 9d7f1723dd8f..f2faa779e3fe 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -88,6 +88,7 @@ struct xenvif {
 	unsigned long   credit_usec;
 	unsigned long   remaining_credit;
 	struct timer_list credit_timeout;
+	u64 credit_window_start;
 
 	/* Statistics */
 	unsigned long rx_gso_checksum_fixup;
@@ -115,6 +116,7 @@ struct xenvif *xenvif_alloc(struct device *parent,
 int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
 		   unsigned long rx_ring_ref, unsigned int evtchn);
 void xenvif_disconnect(struct xenvif *vif);
+void xenvif_free(struct xenvif *vif);
 
 void xenvif_get(struct xenvif *vif);
 void xenvif_put(struct xenvif *vif);
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index d98414168485..540a796593a3 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -275,8 +275,7 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
 	vif->credit_bytes = vif->remaining_credit = ~0UL;
 	vif->credit_usec  = 0UL;
 	init_timer(&vif->credit_timeout);
-	/* Initialize 'expires' now: it's used to track the credit window. */
-	vif->credit_timeout.expires = jiffies;
+	vif->credit_window_start = get_jiffies_64();
 
 	dev->netdev_ops	= &xenvif_netdev_ops;
 	dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO;
@@ -304,6 +303,9 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
 	}
 
 	netdev_dbg(dev, "Successfully created xenvif\n");
+
+	__module_get(THIS_MODULE);
+
 	return vif;
 }
 
@@ -363,15 +365,22 @@ void xenvif_disconnect(struct xenvif *vif)
 	if (netif_carrier_ok(vif->dev))
 		xenvif_carrier_off(vif);
 
+	if (vif->irq) {
+		unbind_from_irqhandler(vif->irq, vif);
+		vif->irq = 0;
+	}
+
+	xen_netbk_unmap_frontend_rings(vif);
+}
+
+void xenvif_free(struct xenvif *vif)
+{
 	atomic_dec(&vif->refcnt);
 	wait_event(vif->waiting_to_free, atomic_read(&vif->refcnt) == 0);
 
-	if (vif->irq)
-		unbind_from_irqhandler(vif->irq, vif);
-
 	unregister_netdev(vif->dev);
 
-	xen_netbk_unmap_frontend_rings(vif);
-
 	free_netdev(vif->dev);
+
+	module_put(THIS_MODULE);
 }
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 8c20935d72c9..70b830f6c4bf 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -347,13 +347,56 @@ static bool start_new_rx_buffer(int offset, unsigned long size, int head)
 	 * into multiple copies tend to give large frags their
 	 * own buffers as before.
 	 */
-	if ((offset + size > MAX_BUFFER_OFFSET) &&
-	    (size <= MAX_BUFFER_OFFSET) && offset && !head)
+	BUG_ON(size > MAX_BUFFER_OFFSET);
+	if ((offset + size > MAX_BUFFER_OFFSET) && offset && !head)
 		return true;
 
 	return false;
 }
 
+struct xenvif_count_slot_state {
+	unsigned long copy_off;
+	bool head;
+};
+
+unsigned int xenvif_count_frag_slots(struct xenvif *vif,
+				     unsigned long offset, unsigned long size,
+				     struct xenvif_count_slot_state *state)
+{
+	unsigned count = 0;
+
+	offset &= ~PAGE_MASK;
+
+	while (size > 0) {
+		unsigned long bytes;
+
+		bytes = PAGE_SIZE - offset;
+
+		if (bytes > size)
+			bytes = size;
+
+		if (start_new_rx_buffer(state->copy_off, bytes, state->head)) {
+			count++;
+			state->copy_off = 0;
+		}
+
+		if (state->copy_off + bytes > MAX_BUFFER_OFFSET)
+			bytes = MAX_BUFFER_OFFSET - state->copy_off;
+
+		state->copy_off += bytes;
+
+		offset += bytes;
+		size -= bytes;
+
+		if (offset == PAGE_SIZE)
+			offset = 0;
+
+		state->head = false;
+	}
+
+	return count;
+}
+
 /*
  * Figure out how many ring slots we're going to need to send @skb to
  * the guest. This function is essentially a dry run of
@@ -361,48 +404,39 @@ static bool start_new_rx_buffer(int offset, unsigned long size, int head)
  */
 unsigned int xen_netbk_count_skb_slots(struct xenvif *vif, struct sk_buff *skb)
 {
+	struct xenvif_count_slot_state state;
 	unsigned int count;
-	int i, copy_off;
+	unsigned char *data;
+	unsigned i;
 
-	count = DIV_ROUND_UP(skb_headlen(skb), PAGE_SIZE);
+	state.head = true;
+	state.copy_off = 0;
 
-	copy_off = skb_headlen(skb) % PAGE_SIZE;
+	/* Slot for the first (partial) page of data. */
+	count = 1;
 
+	/* Need a slot for the GSO prefix for GSO extra data? */
 	if (skb_shinfo(skb)->gso_size)
 		count++;
 
-	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
-		unsigned long size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
-		unsigned long offset = skb_shinfo(skb)->frags[i].page_offset;
-		unsigned long bytes;
-
-		offset &= ~PAGE_MASK;
-
-		while (size > 0) {
-			BUG_ON(offset >= PAGE_SIZE);
-			BUG_ON(copy_off > MAX_BUFFER_OFFSET);
-
-			bytes = PAGE_SIZE - offset;
-
-			if (bytes > size)
-				bytes = size;
+	data = skb->data;
+	while (data < skb_tail_pointer(skb)) {
+		unsigned long offset = offset_in_page(data);
+		unsigned long size = PAGE_SIZE - offset;
 
-			if (start_new_rx_buffer(copy_off, bytes, 0)) {
-				count++;
-				copy_off = 0;
-			}
+		if (data + size > skb_tail_pointer(skb))
+			size = skb_tail_pointer(skb) - data;
 
-			if (copy_off + bytes > MAX_BUFFER_OFFSET)
-				bytes = MAX_BUFFER_OFFSET - copy_off;
+		count += xenvif_count_frag_slots(vif, offset, size, &state);
 
-			copy_off += bytes;
+		data += size;
+	}
 
-			offset += bytes;
-			size -= bytes;
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		unsigned long size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
+		unsigned long offset = skb_shinfo(skb)->frags[i].page_offset;
 
-			if (offset == PAGE_SIZE)
-				offset = 0;
-		}
+		count += xenvif_count_frag_slots(vif, offset, size, &state);
 	}
 	return count;
 }
@@ -1389,9 +1423,8 @@ out:
 
 static bool tx_credit_exceeded(struct xenvif *vif, unsigned size)
 {
-	unsigned long now = jiffies;
-	unsigned long next_credit =
-		vif->credit_timeout.expires +
+	u64 now = get_jiffies_64();
+	u64 next_credit = vif->credit_window_start +
 		msecs_to_jiffies(vif->credit_usec / 1000);
 
 	/* Timer could already be pending in rare cases. */
@@ -1399,8 +1432,8 @@ static bool tx_credit_exceeded(struct xenvif *vif, unsigned size)
 		return true;
 
 	/* Passed the point where we can replenish credit? */
-	if (time_after_eq(now, next_credit)) {
-		vif->credit_timeout.expires = now;
+	if (time_after_eq64(now, next_credit)) {
+		vif->credit_window_start = now;
 		tx_add_credit(vif);
 	}
 
@@ -1412,6 +1445,7 @@ static bool tx_credit_exceeded(struct xenvif *vif, unsigned size)
 			tx_credit_callback;
 		mod_timer(&vif->credit_timeout,
 			  next_credit);
+		vif->credit_window_start = next_credit;
 
 		return true;
 	}
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 410018c4c528..8a9e8750703f 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -24,6 +24,12 @@
 struct backend_info {
 	struct xenbus_device *dev;
 	struct xenvif *vif;
+
+	/* This is the state that will be reflected in xenstore when any
+	 * active hotplug script completes.
+	 */
+	enum xenbus_state state;
+
 	enum xenbus_state frontend_state;
 	struct xenbus_watch hotplug_status_watch;
 	u8 have_hotplug_status_watch:1;
@@ -33,16 +39,20 @@ static int connect_rings(struct backend_info *);
 static void connect(struct backend_info *);
 static void backend_create_xenvif(struct backend_info *be);
 static void unregister_hotplug_status_watch(struct backend_info *be);
+static void set_backend_state(struct backend_info *be,
+			      enum xenbus_state state);
 
 static int netback_remove(struct xenbus_device *dev)
 {
 	struct backend_info *be = dev_get_drvdata(&dev->dev);
 
+	set_backend_state(be, XenbusStateClosed);
+
 	unregister_hotplug_status_watch(be);
 	if (be->vif) {
 		kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE);
 		xenbus_rm(XBT_NIL, dev->nodename, "hotplug-status");
-		xenvif_disconnect(be->vif);
+		xenvif_free(be->vif);
 		be->vif = NULL;
 	}
 	kfree(be);
@@ -126,6 +136,8 @@ static int netback_probe(struct xenbus_device *dev,
 	if (err)
 		goto fail;
 
+	be->state = XenbusStateInitWait;
+
 	/* This kicks hotplug scripts, so do it immediately. */
 	backend_create_xenvif(be);
 
@@ -198,15 +210,113 @@ static void backend_create_xenvif(struct backend_info *be)
 	kobject_uevent(&dev->dev.kobj, KOBJ_ONLINE);
 }
 
+static void backend_disconnect(struct backend_info *be)
+{
+	if (be->vif)
+		xenvif_disconnect(be->vif);
+}
 
-static void disconnect_backend(struct xenbus_device *dev)
+static void backend_connect(struct backend_info *be)
 {
-	struct backend_info *be = dev_get_drvdata(&dev->dev);
+	if (be->vif)
+		connect(be);
+}
 
-	if (be->vif) {
-		xenbus_rm(XBT_NIL, dev->nodename, "hotplug-status");
-		xenvif_disconnect(be->vif);
-		be->vif = NULL;
+static inline void backend_switch_state(struct backend_info *be,
+					enum xenbus_state state)
+{
+	struct xenbus_device *dev = be->dev;
+
+	pr_debug("%s -> %s\n", dev->nodename, xenbus_strstate(state));
+	be->state = state;
+
+	/* If we are waiting for a hotplug script then defer the
+	 * actual xenbus state change.
+	 */
+	if (!be->have_hotplug_status_watch)
+		xenbus_switch_state(dev, state);
+}
+
+/* Handle backend state transitions:
+ *
+ * The backend state starts in InitWait and the following transitions are
+ * allowed.
+ *
+ * InitWait -> Connected
+ *
+ *    ^    \         |
+ *    |     \        |
+ *    |      \       |
+ *    |       \      |
+ *    |        \     |
+ *    |         \    |
+ *    |          V   V
+ *
+ *  Closed  <-> Closing
+ *
+ * The state argument specifies the eventual state of the backend and the
+ * function transitions to that state via the shortest path.
+ */
+static void set_backend_state(struct backend_info *be,
+			      enum xenbus_state state)
+{
+	while (be->state != state) {
+		switch (be->state) {
+		case XenbusStateClosed:
+			switch (state) {
+			case XenbusStateInitWait:
+			case XenbusStateConnected:
+				pr_info("%s: prepare for reconnect\n",
+					be->dev->nodename);
+				backend_switch_state(be, XenbusStateInitWait);
+				break;
+			case XenbusStateClosing:
+				backend_switch_state(be, XenbusStateClosing);
+				break;
+			default:
+				BUG();
+			}
+			break;
+		case XenbusStateInitWait:
+			switch (state) {
+			case XenbusStateConnected:
+				backend_connect(be);
+				backend_switch_state(be, XenbusStateConnected);
+				break;
+			case XenbusStateClosing:
+			case XenbusStateClosed:
+				backend_switch_state(be, XenbusStateClosing);
+				break;
+			default:
+				BUG();
+			}
+			break;
+		case XenbusStateConnected:
+			switch (state) {
+			case XenbusStateInitWait:
+			case XenbusStateClosing:
+			case XenbusStateClosed:
+				backend_disconnect(be);
+				backend_switch_state(be, XenbusStateClosing);
+				break;
+			default:
+				BUG();
+			}
+			break;
+		case XenbusStateClosing:
+			switch (state) {
+			case XenbusStateInitWait:
+			case XenbusStateConnected:
+			case XenbusStateClosed:
+				backend_switch_state(be, XenbusStateClosed);
+				break;
+			default:
+				BUG();
+			}
+			break;
+		default:
+			BUG();
+		}
 	}
 }
 
@@ -218,43 +328,33 @@ static void frontend_changed(struct xenbus_device *dev,
 {
 	struct backend_info *be = dev_get_drvdata(&dev->dev);
 
-	pr_debug("frontend state %s", xenbus_strstate(frontend_state));
+	pr_debug("%s -> %s\n", dev->otherend, xenbus_strstate(frontend_state));
 
 	be->frontend_state = frontend_state;
 
 	switch (frontend_state) {
 	case XenbusStateInitialising:
-		if (dev->state == XenbusStateClosed) {
-			printk(KERN_INFO "%s: %s: prepare for reconnect\n",
-			       __func__, dev->nodename);
-			xenbus_switch_state(dev, XenbusStateInitWait);
-		}
+		set_backend_state(be, XenbusStateInitWait);
 		break;
 
 	case XenbusStateInitialised:
 		break;
 
 	case XenbusStateConnected:
-		if (dev->state == XenbusStateConnected)
-			break;
-		backend_create_xenvif(be);
-		if (be->vif)
-			connect(be);
+		set_backend_state(be, XenbusStateConnected);
 		break;
 
 	case XenbusStateClosing:
-		if (be->vif)
-			kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE);
-		disconnect_backend(dev);
-		xenbus_switch_state(dev, XenbusStateClosing);
+		set_backend_state(be, XenbusStateClosing);
 		break;
 
 	case XenbusStateClosed:
-		xenbus_switch_state(dev, XenbusStateClosed);
+		set_backend_state(be, XenbusStateClosed);
 		if (xenbus_dev_is_online(dev))
 			break;
 		/* fall through if not online */
 	case XenbusStateUnknown:
+		set_backend_state(be, XenbusStateClosed);
 		device_unregister(&dev->dev);
 		break;
 
@@ -347,7 +447,9 @@ static void hotplug_status_changed(struct xenbus_watch *watch,
 	if (IS_ERR(str))
 		return;
 	if (len == sizeof("connected")-1 && !memcmp(str, "connected", len)) {
-		xenbus_switch_state(be->dev, XenbusStateConnected);
+		/* Complete any pending state change */
+		xenbus_switch_state(be->dev, be->state);
+
 		/* Not interested in this watch anymore. */
 		unregister_hotplug_status_watch(be);
 	}
@@ -377,12 +479,8 @@ static void connect(struct backend_info *be)
 	err = xenbus_watch_pathfmt(dev, &be->hotplug_status_watch,
 				   hotplug_status_changed,
 				   "%s/%s", dev->nodename, "hotplug-status");
-	if (err) {
-		/* Switch now, since we can't do a watch. */
-		xenbus_switch_state(dev, XenbusStateConnected);
-	} else {
+	if (!err)
 		be->have_hotplug_status_watch = 1;
-	}
 
 	netif_wake_queue(be->vif->dev);
 }