4 files changed, 179 insertions, 35 deletions

diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 8a495b318b6f..6dc76c1e807b 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -210,12 +210,22 @@ enum state_bit_shift {
 	VIF_STATUS_CONNECTED,
 };
 
+struct xenvif_mcast_addr {
+	struct list_head entry;
+	struct rcu_head rcu;
+	u8 addr[6];
+};
+
+#define XEN_NETBK_MCAST_MAX 64
+
 struct xenvif {
 	/* Unique identifier for this interface. */
 	domid_t          domid;
 	unsigned int     handle;
 
 	u8               fe_dev_addr[6];
+	struct list_head fe_mcast_addr;
+	unsigned int     fe_mcast_count;
 
 	/* Frontend feature information. */
 	int gso_mask;
@@ -224,6 +234,7 @@ struct xenvif {
 	u8 can_sg:1;
 	u8 ip_csum:1;
 	u8 ipv6_csum:1;
+	u8 multicast_control:1;
 
 	/* Is this interface disabled? True when backend discovers
 	 * frontend is rogue.
@@ -325,9 +336,6 @@ static inline pending_ring_idx_t nr_pending_reqs(struct xenvif_queue *queue)
 		queue->pending_prod + queue->pending_cons;
 }
 
-/* Callback from stack when TX packet can be released */
-void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success);
-
 irqreturn_t xenvif_interrupt(int irq, void *dev_id);
 
 extern bool separate_tx_rx_irq;
@@ -344,4 +352,8 @@ void xenvif_skb_zerocopy_prepare(struct xenvif_queue *queue,
 				 struct sk_buff *skb);
 void xenvif_skb_zerocopy_complete(struct xenvif_queue *queue);
 
+/* Multicast control */
+bool xenvif_mcast_match(struct xenvif *vif, const u8 *addr);
+void xenvif_mcast_addr_list_free(struct xenvif *vif);
+
 #endif /* __XEN_NETBACK__COMMON_H__ */
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 1a83e190fc15..e7bd63eb2876 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -61,6 +61,12 @@ void xenvif_skb_zerocopy_prepare(struct xenvif_queue *queue,
 void xenvif_skb_zerocopy_complete(struct xenvif_queue *queue)
 {
 	atomic_dec(&queue->inflight_packets);
+
+	/* Wake the dealloc thread _after_ decrementing inflight_packets so
+	 * that if kthread_stop() has already been called, the dealloc thread
+	 * does not wait forever with nothing to wake it.
+	 */
+	wake_up(&queue->dealloc_wq);
 }
 
 int xenvif_schedulable(struct xenvif *vif)
@@ -165,6 +171,13 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	    !xenvif_schedulable(vif))
 		goto drop;
 
+	if (vif->multicast_control && skb->pkt_type == PACKET_MULTICAST) {
+		struct ethhdr *eth = (struct ethhdr *)skb->data;
+
+		if (!xenvif_mcast_match(vif, eth->h_dest))
+			goto drop;
+	}
+
 	cb = XENVIF_RX_CB(skb);
 	cb->expires = jiffies + vif->drain_timeout;
 
@@ -421,6 +434,7 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
 	vif->num_queues = 0;
 
 	spin_lock_init(&vif->lock);
+	INIT_LIST_HEAD(&vif->fe_mcast_addr);
 
 	dev->netdev_ops	= &xenvif_netdev_ops;
 	dev->hw_features = NETIF_F_SG |
@@ -655,6 +669,8 @@ void xenvif_disconnect(struct xenvif *vif)
 
 		xenvif_unmap_frontend_rings(queue);
 	}
+
+	xenvif_mcast_addr_list_free(vif);
 }
 
 /* Reverse the relevant parts of xenvif_init_queue().
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 880d0d63e872..42569b994ea8 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -810,23 +810,17 @@ static inline struct sk_buff *xenvif_alloc_skb(unsigned int size)
 static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif_queue *queue,
 							struct sk_buff *skb,
 							struct xen_netif_tx_request *txp,
-							struct gnttab_map_grant_ref *gop)
+							struct gnttab_map_grant_ref *gop,
+							unsigned int frag_overflow,
+							struct sk_buff *nskb)
 {
 	struct skb_shared_info *shinfo = skb_shinfo(skb);
 	skb_frag_t *frags = shinfo->frags;
 	u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx;
 	int start;
 	pending_ring_idx_t index;
-	unsigned int nr_slots, frag_overflow = 0;
+	unsigned int nr_slots;
 
-	/* At this point shinfo->nr_frags is in fact the number of
-	 * slots, which can be as large as XEN_NETBK_LEGACY_SLOTS_MAX.
-	 */
-	if (shinfo->nr_frags > MAX_SKB_FRAGS) {
-		frag_overflow = shinfo->nr_frags - MAX_SKB_FRAGS;
-		BUG_ON(frag_overflow > MAX_SKB_FRAGS);
-		shinfo->nr_frags = MAX_SKB_FRAGS;
-	}
 	nr_slots = shinfo->nr_frags;
 
 	/* Skip first skb fragment if it is on same page as header fragment. */
@@ -841,13 +835,6 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif_queue *que
 	}
 
 	if (frag_overflow) {
-		struct sk_buff *nskb = xenvif_alloc_skb(0);
-		if (unlikely(nskb == NULL)) {
-			if (net_ratelimit())
-				netdev_err(queue->vif->dev,
-					   "Can't allocate the frag_list skb.\n");
-			return NULL;
-		}
 
 		shinfo = skb_shinfo(nskb);
 		frags = shinfo->frags;
@@ -1170,14 +1157,89 @@ static bool tx_credit_exceeded(struct xenvif_queue *queue, unsigned size)
 	return false;
 }
 
+/* No locking is required in xenvif_mcast_add/del() as they are
+ * only ever invoked from NAPI poll. An RCU list is used because
+ * xenvif_mcast_match() is called asynchronously, during start_xmit.
+ */
+
+static int xenvif_mcast_add(struct xenvif *vif, const u8 *addr)
+{
+	struct xenvif_mcast_addr *mcast;
+
+	if (vif->fe_mcast_count == XEN_NETBK_MCAST_MAX) {
+		if (net_ratelimit())
+			netdev_err(vif->dev,
+				   "Too many multicast addresses\n");
+		return -ENOSPC;
+	}
+
+	mcast = kzalloc(sizeof(*mcast), GFP_ATOMIC);
+	if (!mcast)
+		return -ENOMEM;
+
+	ether_addr_copy(mcast->addr, addr);
+	list_add_tail_rcu(&mcast->entry, &vif->fe_mcast_addr);
+	vif->fe_mcast_count++;
+
+	return 0;
+}
+
+static void xenvif_mcast_del(struct xenvif *vif, const u8 *addr)
+{
+	struct xenvif_mcast_addr *mcast;
+
+	list_for_each_entry_rcu(mcast, &vif->fe_mcast_addr, entry) {
+		if (ether_addr_equal(addr, mcast->addr)) {
+			--vif->fe_mcast_count;
+			list_del_rcu(&mcast->entry);
+			kfree_rcu(mcast, rcu);
+			break;
+		}
+	}
+}
+
+bool xenvif_mcast_match(struct xenvif *vif, const u8 *addr)
+{
+	struct xenvif_mcast_addr *mcast;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(mcast, &vif->fe_mcast_addr, entry) {
+		if (ether_addr_equal(addr, mcast->addr)) {
+			rcu_read_unlock();
+			return true;
+		}
+	}
+	rcu_read_unlock();
+
+	return false;
+}
+
+void xenvif_mcast_addr_list_free(struct xenvif *vif)
+{
+	/* No need for locking or RCU here. NAPI poll and TX queue
+	 * are stopped.
+	 */
+	while (!list_empty(&vif->fe_mcast_addr)) {
+		struct xenvif_mcast_addr *mcast;
+
+		mcast = list_first_entry(&vif->fe_mcast_addr,
+					 struct xenvif_mcast_addr,
+					 entry);
+		--vif->fe_mcast_count;
+		list_del(&mcast->entry);
+		kfree(mcast);
+	}
+}
+
 static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 				     int budget,
 				     unsigned *copy_ops,
 				     unsigned *map_ops)
 {
-	struct gnttab_map_grant_ref *gop = queue->tx_map_ops, *request_gop;
-	struct sk_buff *skb;
+	struct gnttab_map_grant_ref *gop = queue->tx_map_ops;
+	struct sk_buff *skb, *nskb;
 	int ret;
+	unsigned int frag_overflow;
 
 	while (skb_queue_len(&queue->tx_queue) < budget) {
 		struct xen_netif_tx_request txreq;
@@ -1227,6 +1289,31 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 				break;
 		}
 
+		if (extras[XEN_NETIF_EXTRA_TYPE_MCAST_ADD - 1].type) {
+			struct xen_netif_extra_info *extra;
+
+			extra = &extras[XEN_NETIF_EXTRA_TYPE_MCAST_ADD - 1];
+			ret = xenvif_mcast_add(queue->vif, extra->u.mcast.addr);
+
+			make_tx_response(queue, &txreq,
+					 (ret == 0) ?
+					 XEN_NETIF_RSP_OKAY :
+					 XEN_NETIF_RSP_ERROR);
+			push_tx_responses(queue);
+			continue;
+		}
+
+		if (extras[XEN_NETIF_EXTRA_TYPE_MCAST_DEL - 1].type) {
+			struct xen_netif_extra_info *extra;
+
+			extra = &extras[XEN_NETIF_EXTRA_TYPE_MCAST_DEL - 1];
+			xenvif_mcast_del(queue->vif, extra->u.mcast.addr);
+
+			make_tx_response(queue, &txreq, XEN_NETIF_RSP_OKAY);
+			push_tx_responses(queue);
+			continue;
+		}
+
 		ret = xenvif_count_requests(queue, &txreq, txfrags, work_to_do);
 		if (unlikely(ret < 0))
 			break;
@@ -1265,6 +1352,29 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 			break;
 		}
 
+		skb_shinfo(skb)->nr_frags = ret;
+		if (data_len < txreq.size)
+			skb_shinfo(skb)->nr_frags++;
+		/* At this point shinfo->nr_frags is in fact the number of
+		 * slots, which can be as large as XEN_NETBK_LEGACY_SLOTS_MAX.
+		 */
+		frag_overflow = 0;
+		nskb = NULL;
+		if (skb_shinfo(skb)->nr_frags > MAX_SKB_FRAGS) {
+			frag_overflow = skb_shinfo(skb)->nr_frags - MAX_SKB_FRAGS;
+			BUG_ON(frag_overflow > MAX_SKB_FRAGS);
+			skb_shinfo(skb)->nr_frags = MAX_SKB_FRAGS;
+			nskb = xenvif_alloc_skb(0);
+			if (unlikely(nskb == NULL)) {
+				kfree_skb(skb);
+				xenvif_tx_err(queue, &txreq, idx);
+				if (net_ratelimit())
+					netdev_err(queue->vif->dev,
+						   "Can't allocate the frag_list skb.\n");
+				break;
+			}
+		}
+
 		if (extras[XEN_NETIF_EXTRA_TYPE_GSO - 1].type) {
 			struct xen_netif_extra_info *gso;
 			gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1];
@@ -1272,6 +1382,7 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 			if (xenvif_set_skb_gso(queue->vif, skb, gso)) {
 				/* Failure in xenvif_set_skb_gso is fatal. */
 				kfree_skb(skb);
+				kfree_skb(nskb);
 				break;
 			}
 		}
@@ -1294,9 +1405,7 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 
 		(*copy_ops)++;
 
-		skb_shinfo(skb)->nr_frags = ret;
 		if (data_len < txreq.size) {
-			skb_shinfo(skb)->nr_frags++;
 			frag_set_pending_idx(&skb_shinfo(skb)->frags[0],
 					     pending_idx);
 			xenvif_tx_create_map_op(queue, pending_idx, &txreq, gop);
@@ -1310,13 +1419,8 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 
 		queue->pending_cons++;
 
-		request_gop = xenvif_get_requests(queue, skb, txfrags, gop);
-		if (request_gop == NULL) {
-			kfree_skb(skb);
-			xenvif_tx_err(queue, &txreq, idx);
-			break;
-		}
-		gop = request_gop;
+		gop = xenvif_get_requests(queue, skb, txfrags, gop,
+				          frag_overflow, nskb);
 
 		__skb_queue_tail(&queue->tx_queue, skb);
 
@@ -1536,7 +1640,6 @@ void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success)
 		smp_wmb();
 		queue->dealloc_prod++;
 	} while (ubuf);
-	wake_up(&queue->dealloc_wq);
 	spin_unlock_irqrestore(&queue->callback_lock, flags);
 
 	if (likely(zerocopy_success))
@@ -1566,13 +1669,13 @@ static inline void xenvif_tx_dealloc_action(struct xenvif_queue *queue)
 		smp_rmb();
 
 		while (dc != dp) {
-			BUG_ON(gop - queue->tx_unmap_ops > MAX_PENDING_REQS);
+			BUG_ON(gop - queue->tx_unmap_ops >= MAX_PENDING_REQS);
 			pending_idx =
 				queue->dealloc_ring[pending_index(dc++)];
 
-			pending_idx_release[gop-queue->tx_unmap_ops] =
+			pending_idx_release[gop - queue->tx_unmap_ops] =
 				pending_idx;
-			queue->pages_to_unmap[gop-queue->tx_unmap_ops] =
+			queue->pages_to_unmap[gop - queue->tx_unmap_ops] =
 				queue->mmap_pages[pending_idx];
 			gnttab_set_unmap_op(gop,
 					    idx_to_kaddr(queue, pending_idx),
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index ec383b0f5443..929a6e7e5ecf 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -327,6 +327,14 @@ static int netback_probe(struct xenbus_device *dev,
 			goto abort_transaction;
 		}
 
+		/* We support multicast-control. */
+		err = xenbus_printf(xbt, dev->nodename,
+				    "feature-multicast-control", "%d", 1);
+		if (err) {
+			message = "writing feature-multicast-control";
+			goto abort_transaction;
+		}
+
 		err = xenbus_transaction_end(xbt, 0);
 	} while (err == -EAGAIN);
 
@@ -1016,6 +1024,11 @@ static int read_xenbus_vif_flags(struct backend_info *be)
 		val = 0;
 	vif->ipv6_csum = !!val;
 
+	if (xenbus_scanf(XBT_NIL, dev->otherend, "request-multicast-control",
+			 "%d", &val) < 0)
+		val = 0;
+	vif->multicast_control = !!val;
+
 	return 0;
 }