Merge branch 'netback'

Ian Campbell says:

====================
The Xen netback implementation contains a couple of flaws which can
allow a guest to cause a DoS in the backend domain, potentially
affecting other domains in the system.

CVE-2013-0216 is a failure to sanity check the ring producer/consumer
pointers which can allow a guest to cause netback to loop for an
extended period preventing other work from occurring.

CVE-2013-0217 is a memory leak on an error path which is guest
triggerable.

The following series contains the fixes for these issues, as previously
included in Xen Security Advisory 39:
http://lists.xen.org/archives/html/xen-announce/2013-02/msg00001.html

Changes in v2:
 - Typo and block comment format fixes
 - Added stable Cc
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/xen-netback/common.h

@@ -151,6 +151,9 @@ void xen_netbk_queue_tx_skb(struct xenvif *vif, struct sk_buff *skb);
 /* Notify xenvif that ring now has space to send an skb to the frontend */
 void xenvif_notify_tx_completion(struct xenvif *vif);
 
+/* Prevent the device from generating any further traffic. */
+void xenvif_carrier_off(struct xenvif *vif);
+
 /* Returns number of ring slots required to send an skb to the frontend */
 unsigned int xen_netbk_count_skb_slots(struct xenvif *vif, struct sk_buff *skb);
 

drivers/net/xen-netback/interface.c

@@ -343,17 +343,22 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
 	return err;
 }
 
-void xenvif_disconnect(struct xenvif *vif)
+void xenvif_carrier_off(struct xenvif *vif)
 {
 	struct net_device *dev = vif->dev;
-	if (netif_carrier_ok(dev)) {
-		rtnl_lock();
-		netif_carrier_off(dev); /* discard queued packets */
-		if (netif_running(dev))
-			xenvif_down(vif);
-		rtnl_unlock();
-		xenvif_put(vif);
-	}
+
+	rtnl_lock();
+	netif_carrier_off(dev); /* discard queued packets */
+	if (netif_running(dev))
+		xenvif_down(vif);
+	rtnl_unlock();
+	xenvif_put(vif);
+}
+
+void xenvif_disconnect(struct xenvif *vif)
+{
+	if (netif_carrier_ok(vif->dev))
+		xenvif_carrier_off(vif);
 
 	atomic_dec(&vif->refcnt);
 	wait_event(vif->waiting_to_free, atomic_read(&vif->refcnt) == 0);

drivers/net/xen-netback/netback.c

@@ -147,7 +147,8 @@ void xen_netbk_remove_xenvif(struct xenvif *vif)
 	atomic_dec(&netbk->netfront_count);
 }
 
-static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx);
+static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx,
+				  u8 status);
 static void make_tx_response(struct xenvif *vif,
 			     struct xen_netif_tx_request *txp,
 			     s8       st);
@@ -879,7 +880,7 @@ static void netbk_tx_err(struct xenvif *vif,
 
 	do {
 		make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR);
-		if (cons >= end)
+		if (cons == end)
 			break;
 		txp = RING_GET_REQUEST(&vif->tx, cons++);
 	} while (1);
@@ -888,6 +889,13 @@ static void netbk_tx_err(struct xenvif *vif,
 	xenvif_put(vif);
 }
 
+static void netbk_fatal_tx_err(struct xenvif *vif)
+{
+	netdev_err(vif->dev, "fatal error; disabling device\n");
+	xenvif_carrier_off(vif);
+	xenvif_put(vif);
+}
+
 static int netbk_count_requests(struct xenvif *vif,
 				struct xen_netif_tx_request *first,
 				struct xen_netif_tx_request *txp,
@@ -901,19 +909,22 @@ static int netbk_count_requests(struct xenvif *vif,
 
 	do {
 		if (frags >= work_to_do) {
-			netdev_dbg(vif->dev, "Need more frags\n");
+			netdev_err(vif->dev, "Need more frags\n");
+			netbk_fatal_tx_err(vif);
 			return -frags;
 		}
 
 		if (unlikely(frags >= MAX_SKB_FRAGS)) {
-			netdev_dbg(vif->dev, "Too many frags\n");
+			netdev_err(vif->dev, "Too many frags\n");
+			netbk_fatal_tx_err(vif);
 			return -frags;
 		}
 
 		memcpy(txp, RING_GET_REQUEST(&vif->tx, cons + frags),
 		       sizeof(*txp));
 		if (txp->size > first->size) {
-			netdev_dbg(vif->dev, "Frags galore\n");
+			netdev_err(vif->dev, "Frag is bigger than frame.\n");
+			netbk_fatal_tx_err(vif);
 			return -frags;
 		}
 
@@ -921,8 +932,9 @@ static int netbk_count_requests(struct xenvif *vif,
 		frags++;
 
 		if (unlikely((txp->offset + txp->size) > PAGE_SIZE)) {
-			netdev_dbg(vif->dev, "txp->offset: %x, size: %u\n",
+			netdev_err(vif->dev, "txp->offset: %x, size: %u\n",
 				 txp->offset, txp->size);
+			netbk_fatal_tx_err(vif);
 			return -frags;
 		}
 	} while ((txp++)->flags & XEN_NETTXF_more_data);
@@ -966,7 +978,7 @@ static struct gnttab_copy *xen_netbk_get_requests(struct xen_netbk *netbk,
 		pending_idx = netbk->pending_ring[index];
 		page = xen_netbk_alloc_page(netbk, skb, pending_idx);
 		if (!page)
-			return NULL;
+			goto err;
 
 		gop->source.u.ref = txp->gref;
 		gop->source.domid = vif->domid;
@@ -988,6 +1000,17 @@ static struct gnttab_copy *xen_netbk_get_requests(struct xen_netbk *netbk,
 	}
 
 	return gop;
+err:
+	/* Unwind, freeing all pages and sending error responses. */
+	while (i-- > start) {
+		xen_netbk_idx_release(netbk, frag_get_pending_idx(&frags[i]),
+				      XEN_NETIF_RSP_ERROR);
+	}
+	/* The head too, if necessary. */
+	if (start)
+		xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_ERROR);
+
+	return NULL;
 }
 
 static int xen_netbk_tx_check_gop(struct xen_netbk *netbk,
@@ -996,30 +1019,20 @@ static int xen_netbk_tx_check_gop(struct xen_netbk *netbk,
 {
 	struct gnttab_copy *gop = *gopp;
 	u16 pending_idx = *((u16 *)skb->data);
-	struct pending_tx_info *pending_tx_info = netbk->pending_tx_info;
-	struct xenvif *vif = pending_tx_info[pending_idx].vif;
-	struct xen_netif_tx_request *txp;
 	struct skb_shared_info *shinfo = skb_shinfo(skb);
 	int nr_frags = shinfo->nr_frags;
 	int i, err, start;
 
 	/* Check status of header. */
 	err = gop->status;
-	if (unlikely(err)) {
-		pending_ring_idx_t index;
-		index = pending_index(netbk->pending_prod++);
-		txp = &pending_tx_info[pending_idx].req;
-		make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR);
-		netbk->pending_ring[index] = pending_idx;
-		xenvif_put(vif);
-	}
+	if (unlikely(err))
+		xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_ERROR);
 
 	/* Skip first skb fragment if it is on same page as header fragment. */
 	start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx);
 
 	for (i = start; i < nr_frags; i++) {
 		int j, newerr;
-		pending_ring_idx_t index;
 
 		pending_idx = frag_get_pending_idx(&shinfo->frags[i]);
 
@@ -1028,16 +1041,12 @@ static int xen_netbk_tx_check_gop(struct xen_netbk *netbk,
 		if (likely(!newerr)) {
 			/* Had a previous error? Invalidate this fragment. */
 			if (unlikely(err))
-				xen_netbk_idx_release(netbk, pending_idx);
+				xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY);
 			continue;
 		}
 
 		/* Error on this fragment: respond to client with an error. */
-		txp = &netbk->pending_tx_info[pending_idx].req;
-		make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR);
-		index = pending_index(netbk->pending_prod++);
-		netbk->pending_ring[index] = pending_idx;
-		xenvif_put(vif);
+		xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_ERROR);
 
 		/* Not the first error? Preceding frags already invalidated. */
 		if (err)
@@ -1045,10 +1054,10 @@ static int xen_netbk_tx_check_gop(struct xen_netbk *netbk,
 
 		/* First error: invalidate header and preceding fragments. */
 		pending_idx = *((u16 *)skb->data);
-		xen_netbk_idx_release(netbk, pending_idx);
+		xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY);
 		for (j = start; j < i; j++) {
 			pending_idx = frag_get_pending_idx(&shinfo->frags[j]);
-			xen_netbk_idx_release(netbk, pending_idx);
+			xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY);
 		}
 
 		/* Remember the error: invalidate all subsequent fragments. */
@@ -1082,7 +1091,7 @@ static void xen_netbk_fill_frags(struct xen_netbk *netbk, struct sk_buff *skb)
 
 		/* Take an extra reference to offset xen_netbk_idx_release */
 		get_page(netbk->mmap_pages[pending_idx]);
-		xen_netbk_idx_release(netbk, pending_idx);
+		xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY);
 	}
 }
 
@@ -1095,7 +1104,8 @@ static int xen_netbk_get_extras(struct xenvif *vif,
 
 	do {
 		if (unlikely(work_to_do-- <= 0)) {
-			netdev_dbg(vif->dev, "Missing extra info\n");
+			netdev_err(vif->dev, "Missing extra info\n");
+			netbk_fatal_tx_err(vif);
 			return -EBADR;
 		}
 
@@ -1104,8 +1114,9 @@ static int xen_netbk_get_extras(struct xenvif *vif,
 		if (unlikely(!extra.type ||
 			     extra.type >= XEN_NETIF_EXTRA_TYPE_MAX)) {
 			vif->tx.req_cons = ++cons;
-			netdev_dbg(vif->dev,
+			netdev_err(vif->dev,
 				   "Invalid extra type: %d\n", extra.type);
+			netbk_fatal_tx_err(vif);
 			return -EINVAL;
 		}
 
@@ -1121,13 +1132,15 @@ static int netbk_set_skb_gso(struct xenvif *vif,
 			     struct xen_netif_extra_info *gso)
 {
 	if (!gso->u.gso.size) {
-		netdev_dbg(vif->dev, "GSO size must not be zero.\n");
+		netdev_err(vif->dev, "GSO size must not be zero.\n");
+		netbk_fatal_tx_err(vif);
 		return -EINVAL;
 	}
 
 	/* Currently only TCPv4 S.O. is supported. */
 	if (gso->u.gso.type != XEN_NETIF_GSO_TYPE_TCPV4) {
-		netdev_dbg(vif->dev, "Bad GSO type %d.\n", gso->u.gso.type);
+		netdev_err(vif->dev, "Bad GSO type %d.\n", gso->u.gso.type);
+		netbk_fatal_tx_err(vif);
 		return -EINVAL;
 	}
 
@@ -1264,9 +1277,25 @@ static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk)
 
 		/* Get a netif from the list with work to do. */
 		vif = poll_net_schedule_list(netbk);
+		/* This can sometimes happen because the test of
+		 * list_empty(net_schedule_list) at the top of the
+		 * loop is unlocked.  Just go back and have another
+		 * look.
+		 */
 		if (!vif)
 			continue;
 
+		if (vif->tx.sring->req_prod - vif->tx.req_cons >
+		    XEN_NETIF_TX_RING_SIZE) {
+			netdev_err(vif->dev,
+				   "Impossible number of requests. "
+				   "req_prod %d, req_cons %d, size %ld\n",
+				   vif->tx.sring->req_prod, vif->tx.req_cons,
+				   XEN_NETIF_TX_RING_SIZE);
+			netbk_fatal_tx_err(vif);
+			continue;
+		}
+
 		RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, work_to_do);
 		if (!work_to_do) {
 			xenvif_put(vif);
@@ -1294,17 +1323,14 @@ static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk)
 			work_to_do = xen_netbk_get_extras(vif, extras,
 							  work_to_do);
 			idx = vif->tx.req_cons;
-			if (unlikely(work_to_do < 0)) {
-				netbk_tx_err(vif, &txreq, idx);
+			if (unlikely(work_to_do < 0))
 				continue;
-			}
 		}
 
 		ret = netbk_count_requests(vif, &txreq, txfrags, work_to_do);
-		if (unlikely(ret < 0)) {
-			netbk_tx_err(vif, &txreq, idx - ret);
+		if (unlikely(ret < 0))
 			continue;
-		}
+
 		idx += ret;
 
 		if (unlikely(txreq.size < ETH_HLEN)) {
@@ -1316,11 +1342,11 @@ static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk)
 
 		/* No crossing a page as the payload mustn't fragment. */
 		if (unlikely((txreq.offset + txreq.size) > PAGE_SIZE)) {
-			netdev_dbg(vif->dev,
+			netdev_err(vif->dev,
 				   "txreq.offset: %x, size: %u, end: %lu\n",
 				   txreq.offset, txreq.size,
 				   (txreq.offset&~PAGE_MASK) + txreq.size);
-			netbk_tx_err(vif, &txreq, idx);
+			netbk_fatal_tx_err(vif);
 			continue;
 		}
 
@@ -1348,8 +1374,8 @@ static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk)
 			gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1];
 
 			if (netbk_set_skb_gso(vif, skb, gso)) {
+				/* Failure in netbk_set_skb_gso is fatal. */
 				kfree_skb(skb);
-				netbk_tx_err(vif, &txreq, idx);
 				continue;
 			}
 		}
@@ -1448,7 +1474,7 @@ static void xen_netbk_tx_submit(struct xen_netbk *netbk)
 			txp->size -= data_len;
 		} else {
 			/* Schedule a response immediately. */
-			xen_netbk_idx_release(netbk, pending_idx);
+			xen_netbk_idx_release(netbk, pending_idx, XEN_NETIF_RSP_OKAY);
 		}
 
 		if (txp->flags & XEN_NETTXF_csum_blank)
@@ -1500,7 +1526,8 @@ static void xen_netbk_tx_action(struct xen_netbk *netbk)
 	xen_netbk_tx_submit(netbk);
 }
 
-static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx)
+static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx,
+				  u8 status)
 {
 	struct xenvif *vif;
 	struct pending_tx_info *pending_tx_info;
@@ -1514,7 +1541,7 @@ static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx)
 
 	vif = pending_tx_info->vif;
 
-	make_tx_response(vif, &pending_tx_info->req, XEN_NETIF_RSP_OKAY);
+	make_tx_response(vif, &pending_tx_info->req, status);
 
 	index = pending_index(netbk->pending_prod++);
 	netbk->pending_ring[index] = pending_idx;