Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:

 1) Revert iwlwifi reclaimed packet tracking, it causes problems for a
    bunch of folks.  From Emmanuel Grumbach.

 2) Work limiting code in brcmsmac wifi driver can clear tx status
    without processing the event.  From Arend van Spriel.

 3) rtlwifi USB driver processes wrong SKB, fix from Larry Finger.

 4) l2tp tunnel delete can race with close, fix from Tom Parkin.

 5) pktgen_add_device() failures are not checked at all, fix from Cong
    Wang.

 6) Fix unintentional removal of carrier off from tun_detach(),
    otherwise we confuse userspace, from Michael S.  Tsirkin.

 7) Don't leak socket reference counts and ubufs in vhost-net driver,
    from Jason Wang.

 8) vmxnet3 driver gets it's initial carrier state wrong, fix from Neil
    Horman.

 9) Protect against USB networking devices which spam the host with 0
    length frames, from Bjørn Mork.

10) Prevent neighbour overflows in ipv6 for locally destined routes,
    from Marcelo Ricardo.  This is the best short-term fix for this, a
    longer term fix has been implemented in net-next.

11) L2TP uses ipv4 datagram routines in it's ipv6 code, whoops.  This
    mistake is largely because the ipv6 functions don't even have some
    kind of prefix in their names to suggest they are ipv6 specific.
    From Tom Parkin.

12) Check SYN packet drops properly in tcp_rcv_fastopen_synack(), from
    Yuchung Cheng.

13) Fix races and TX skb freeing bugs in via-rhine's NAPI support, from
    Francois Romieu and your's truly.

14) Fix infinite loops and divides by zero in TCP congestion window
    handling, from Eric Dumazet, Neal Cardwell, and Ilpo Järvinen.

15) AF_PACKET tx ring handling can leak kernel memory to userspace, fix
    from Phil Sutter.

16) Fix error handling in ipv6 GRE tunnel transmit, from Tommi Rantala.

17) Protect XEN netback driver against hostile frontend putting garbage
    into the rings, don't leak pages in TX GOP checking, and add proper
    resource releasing in error path of xen_netbk_get_requests().  From
    Ian Campbell.

18) SCTP authentication keys should be cleared out and released with
    kzfree(), from Daniel Borkmann.

19) L2TP is a bit too clever trying to maintain skb->truesize, and ends
    up corrupting socket memory accounting to the point where packet
    sending is halted indefinitely.  Just remove the adjustments
    entirely, they aren't really needed.  From Eric Dumazet.

20) ATM Iphase driver uses a data type with the same name as the S390
    headers, rename to fix the build.  From Heiko Carstens.

21) Fix a typo in copying the inner network header offset from one SKB
    to another, from Pravin B Shelar.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (56 commits)
  net: sctp: sctp_endpoint_free: zero out secret key data
  net: sctp: sctp_setsockopt_auth_key: use kzfree instead of kfree
  atm/iphase: rename fregt_t -> ffreg_t
  net: usb: fix regression from FLAG_NOARP code
  l2tp: dont play with skb->truesize
  net: sctp: sctp_auth_key_put: use kzfree instead of kfree
  netback: correct netbk_tx_err to handle wrap around.
  xen/netback: free already allocated memory on failure in xen_netbk_get_requests
  xen/netback: don't leak pages on failure in xen_netbk_tx_check_gop.
  xen/netback: shutdown the ring if it contains garbage.
  net: qmi_wwan: add more Huawei devices, including E320
  net: cdc_ncm: add another Huawei vendor specific device
  ipv6/ip6_gre: fix error case handling in ip6gre_tunnel_xmit()
  tcp: fix for zero packets_in_flight was too broad
  brcmsmac: rework of mac80211 .flush() callback operation
  ssb: unregister gpios before unloading ssb
  bcma: unregister gpios before unloading bcma
  rtlwifi: Fix scheduling while atomic bug
  net: usbnet: fix tx_dropped statistics
  tcp: ipv6: Update MIB counters for drops
  ...

1 files changed, 71 insertions, 44 deletions

diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index f2d6b78d901..2b9520c46e9 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/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;