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

Pull networking fixes from David Miller:
 "Here are some bug fixes that have piled up during ksummit/linuxcon.

   1) Fix endian problems in ibmveth, from Anton Blanchard.

   2) IPV6 routing code does GFP_KERNEL allocation in atomic, fix from
      Benjamin Block.

   3) SCTP association fixes from Daniel Borkmann.

   4) When multiple VLAN headers are present we have to make sure the
      second and subsequent ones are pullable in the SKB otherwise we
      blindly dereference garbage.  From Jiri Benc.

   5) The argument adjustment of the signature of hlist_add_after*()
      introduced a regression in the batman-adv code, fix from Sven
      Eckelmann.

   6) Fix TX hang handling to avoid a panic in i40e, from Anjali Singhai
      Jain.

   7) PTP flag test is inverted in i40e driver, from Jesse Brandeburg.

   8) ATM LEC driver needs to hold RTNL mutex over MTU changes, from
      Chas Williams.

   9) Truncate packets larger then the TPACKET_V3 format configured
      buffers, otherwise we overwrite past the end of said buffers.
      From Eric Dumazet.

  10) Fix endianness bugs in qlcnic firmware handling, from Rajesh
      Borundia and Shahed Shaikh.

  11) CXGB4 sometimes doesn't get all of the TX completion events it
      should resulting in SKBs getting stuck in the TX queue, from
      Hariprasad Shenai.

  12) When the FEC chip's PTP clock is disabled, you can't access the
      register.  Add necessary checks to avoid the resulting hang, from
      Fugang Duan"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (37 commits)
  drivers: isdn: eicon: xdi_msg.h: Fix typo in #ifndef
  net: sctp: fix suboptimal edge-case on non-active active/retrans path selection
  net: sctp: spare unnecessary comparison in sctp_trans_elect_best
  net: ethernet: broadcom: bnx2x: Remove redundant #ifdef
  ibmveth: Fix endian issues with rx_no_buffer statistic
  net: xgene: fix possible NULL dereference in xgene_enet_free_desc_rings()
  openvswitch: fix panic with multiple vlan headers
  net: ipv6: fib: don't sleep inside atomic lock
  net: fec: ptp: avoid register access when ipg clock is disabled
  cxgb4: Free completed tx skbs promptly
  cxgb4: Fix race condition in cleanup
  sctp: not send SCTP_PEER_ADDR_CHANGE notifications with failed probe
  bnx2x: Revert UNDI flushing mechanism
  qlcnic: Fix endianess issue in firmware load from file operation
  qlcnic: Fix endianess issue in FW dump template header
  qlcnic: Fix flash access interface to application
  MAINTAINERS: Add section for MRF24J40 IEEE 802.15.4 radio driver
  macvlan: Allow setting multicast filter on all macvlan types
  packet: handle too big packets for PACKET_V3
  MAINTAINERS: add entry for ec_bhf driver
  ...

10 files changed, 51 insertions, 45 deletions

diff --git a/net/atm/lec.c b/net/atm/lec.c
index e4853b50cf40..4b98f897044a 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -410,9 +410,11 @@ static int lec_atm_send(struct atm_vcc *vcc, struct sk_buff *skb)
                 priv->lane2_ops = NULL;
                 if (priv->lane_version > 1)
                         priv->lane2_ops = &lane2_ops;
+                rtnl_lock();
                 if (dev_set_mtu(dev, mesg->content.config.mtu))
                         pr_info("%s: change_mtu to %d failed\n",
                                 dev->name, mesg->content.config.mtu);
+                rtnl_unlock();
                 priv->is_proxy = mesg->content.config.is_proxy;
                 break;
         case l_flush_tran_id:
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index 52c43f904220..fc1835c6bb40 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -188,7 +188,7 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node,
 
         /* Reached the end of the list, so insert after 'frag_entry_last'. */
         if (likely(frag_entry_last)) {
-                hlist_add_behind(&frag_entry_last->list, &frag_entry_new->list);
+                hlist_add_behind(&frag_entry_new->list, &frag_entry_last->list);
                 chain->size += skb->len - hdr_size;
                 chain->timestamp = jiffies;
                 ret = true;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index cb4459bd1d29..76b7f5ee8f4c 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -643,7 +643,7 @@ static int fib6_commit_metrics(struct dst_entry *dst,
         if (dst->flags & DST_HOST) {
                 mp = dst_metrics_write_ptr(dst);
         } else {
-                mp = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
+                mp = kzalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC);
                 if (!mp)
                         return -ENOMEM;
                 dst_init_metrics(dst, mp, 0);
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index fe5cda0deb39..5231652a95d9 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -42,6 +42,9 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 
 static int make_writable(struct sk_buff *skb, int write_len)
 {
+        if (!pskb_may_pull(skb, write_len))
+                return -ENOMEM;
+
         if (!skb_cloned(skb) || skb_clone_writable(skb, write_len))
                 return 0;
 
@@ -70,6 +73,8 @@ static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci)
 
         vlan_set_encap_proto(skb, vhdr);
         skb->mac_header += VLAN_HLEN;
+        if (skb_network_offset(skb) < ETH_HLEN)
+                skb_set_network_header(skb, ETH_HLEN);
         skb_reset_mac_len(skb);
 
         return 0;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 8d9f8042705a..93896d2092f6 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -632,6 +632,7 @@ static void init_prb_bdqc(struct packet_sock *po,
         p1->tov_in_jiffies = msecs_to_jiffies(p1->retire_blk_tov);
         p1->blk_sizeof_priv = req_u->req3.tp_sizeof_priv;
 
+        p1->max_frame_len = p1->kblk_size - BLK_PLUS_PRIV(p1->blk_sizeof_priv);
         prb_init_ft_ops(p1, req_u);
         prb_setup_retire_blk_timer(po, tx_ring);
         prb_open_block(p1, pbd);
@@ -1942,6 +1943,18 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
                         if ((int)snaplen < 0)
                                 snaplen = 0;
                 }
+        } else if (unlikely(macoff + snaplen >
+                            GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len)) {
+                u32 nval;
+
+                nval = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len - macoff;
+                pr_err_once("tpacket_rcv: packet too big, clamped from %u to %u. macoff=%u\n",
+                            snaplen, nval, macoff);
+                snaplen = nval;
+                if (unlikely((int)snaplen < 0)) {
+                        snaplen = 0;
+                        macoff = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len;
+                }
         }
         spin_lock(&sk->sk_receive_queue.lock);
         h.raw = packet_current_rx_frame(po, skb,
@@ -3783,6 +3796,10 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
                         goto out;
                 if (unlikely(req->tp_block_size & (PAGE_SIZE - 1)))
                         goto out;
+                if (po->tp_version >= TPACKET_V3 &&
+                    (int)(req->tp_block_size -
+                          BLK_PLUS_PRIV(req_u->req3.tp_sizeof_priv)) <= 0)
+                        goto out;
                 if (unlikely(req->tp_frame_size < po->tp_hdrlen +
                                         po->tp_reserve))
                         goto out;
diff --git a/net/packet/internal.h b/net/packet/internal.h
index eb9580a6b25f..cdddf6a30399 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -29,6 +29,7 @@ struct tpacket_kbdq_core {
         char            *pkblk_start;
         char            *pkblk_end;
         int             kblk_size;
+        unsigned int    max_frame_len;
         unsigned int    knum_blocks;
         uint64_t        knxt_seq_num;
         char            *prev;
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index ead526467cca..762a04bb8f6d 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -159,7 +159,6 @@ struct cbq_sched_data {
         struct cbq_class        *tx_borrowed;
         int                     tx_len;
         psched_time_t           now;            /* Cached timestamp */
-        psched_time_t           now_rt;         /* Cached real time */
         unsigned int            pmask;
 
         struct hrtimer          delay_timer;
@@ -353,12 +352,7 @@ cbq_mark_toplevel(struct cbq_sched_data *q, struct cbq_class *cl)
         int toplevel = q->toplevel;
 
         if (toplevel > cl->level && !(qdisc_is_throttled(cl->q))) {
-                psched_time_t now;
-                psched_tdiff_t incr;
-
-                now = psched_get_time();
-                incr = now - q->now_rt;
-                now = q->now + incr;
+                psched_time_t now = psched_get_time();
 
                 do {
                         if (cl->undertime < now) {
@@ -700,8 +694,13 @@ cbq_update(struct cbq_sched_data *q)
         struct cbq_class *this = q->tx_class;
         struct cbq_class *cl = this;
         int len = q->tx_len;
+        psched_time_t now;
 
         q->tx_class = NULL;
+        /* Time integrator. We calculate EOS time
+         * by adding expected packet transmission time.
+         */
+        now = q->now + L2T(&q->link, len);
 
         for ( ; cl; cl = cl->share) {
                 long avgidle = cl->avgidle;
@@ -717,7 +716,7 @@ cbq_update(struct cbq_sched_data *q)
                  *      idle = (now - last) - last_pktlen/rate
                  */
 
-                idle = q->now - cl->last;
+                idle = now - cl->last;
                 if ((unsigned long)idle > 128*1024*1024) {
                         avgidle = cl->maxidle;
                 } else {
@@ -761,7 +760,7 @@ cbq_update(struct cbq_sched_data *q)
                         idle -= L2T(&q->link, len);
                         idle += L2T(cl, len);
 
-                        cl->undertime = q->now + idle;
+                        cl->undertime = now + idle;
                 } else {
                         /* Underlimit */
 
@@ -771,7 +770,8 @@ cbq_update(struct cbq_sched_data *q)
                         else
                                 cl->avgidle = avgidle;
                 }
-                cl->last = q->now;
+                if ((s64)(now - cl->last) > 0)
+                        cl->last = now;
         }
 
         cbq_update_toplevel(q, this, q->tx_borrowed);
@@ -943,31 +943,13 @@ cbq_dequeue(struct Qdisc *sch)
         struct sk_buff *skb;
         struct cbq_sched_data *q = qdisc_priv(sch);
         psched_time_t now;
-        psched_tdiff_t incr;
 
         now = psched_get_time();
-        incr = now - q->now_rt;
-
-        if (q->tx_class) {
-                psched_tdiff_t incr2;
-                /* Time integrator. We calculate EOS time
-                 * by adding expected packet transmission time.
-                 * If real time is greater, we warp artificial clock,
-                 * so that:
-                 *
-                 * cbq_time = max(real_time, work);
-                 */
-                incr2 = L2T(&q->link, q->tx_len);
-                q->now += incr2;
+
+        if (q->tx_class)
                 cbq_update(q);
-                if ((incr -= incr2) < 0)
-                        incr = 0;
-                q->now += incr;
-        } else {
-                if (now > q->now)
-                        q->now = now;
-        }
-        q->now_rt = now;
+
+        q->now = now;
 
         for (;;) {
                 q->wd_expires = 0;
@@ -1223,7 +1205,6 @@ cbq_reset(struct Qdisc *sch)
         hrtimer_cancel(&q->delay_timer);
         q->toplevel = TC_CBQ_MAXLEVEL;
         q->now = psched_get_time();
-        q->now_rt = q->now;
 
         for (prio = 0; prio <= TC_CBQ_MAXPRIO; prio++)
                 q->active[prio] = NULL;
@@ -1407,7 +1388,6 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt)
         q->delay_timer.function = cbq_undelay;
         q->toplevel = TC_CBQ_MAXLEVEL;
         q->now = psched_get_time();
-        q->now_rt = q->now;
 
         cbq_link_class(&q->link);
 
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 06a9ee6b2d3a..a88b8524846e 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -813,6 +813,7 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
                 else {
                         dst_release(transport->dst);
                         transport->dst = NULL;
+                        ulp_notify = false;
                 }
 
                 spc_state = SCTP_ADDR_UNREACHABLE;
@@ -1244,7 +1245,7 @@ static struct sctp_transport *sctp_trans_elect_best(struct sctp_transport *curr,
 {
         u8 score_curr, score_best;
 
-        if (best == NULL)
+        if (best == NULL || curr == best)
                 return curr;
 
         score_curr = sctp_trans_score(curr);
@@ -1355,14 +1356,11 @@ static void sctp_select_active_and_retran_path(struct sctp_association *asoc)
                 trans_sec = trans_pri;
 
         /* If we failed to find a usable transport, just camp on the
-         * primary or retran, even if they are inactive, if possible
-         * pick a PF iff it's the better choice.
+         * active or pick a PF iff it's the better choice.
          */
         if (trans_pri == NULL) {
-                trans_pri = sctp_trans_elect_best(asoc->peer.primary_path,
-                                                  asoc->peer.retran_path);
-                trans_pri = sctp_trans_elect_best(trans_pri, trans_pf);
-                trans_sec = asoc->peer.primary_path;
+                trans_pri = sctp_trans_elect_best(asoc->peer.active_path, trans_pf);
+                trans_sec = trans_pri;
         }
 
         /* Set the active and retran transports. */
diff --git a/net/tipc/port.h b/net/tipc/port.h
index 3f93454592b6..3087da39ee47 100644
--- a/net/tipc/port.h
+++ b/net/tipc/port.h
@@ -179,9 +179,12 @@ static inline int tipc_port_importance(struct tipc_port *port)
         return msg_importance(&port->phdr);
 }
 
-static inline void tipc_port_set_importance(struct tipc_port *port, int imp)
+static inline int tipc_port_set_importance(struct tipc_port *port, int imp)
 {
+        if (imp > TIPC_CRITICAL_IMPORTANCE)
+                return -EINVAL;
         msg_set_importance(&port->phdr, (u32)imp);
+        return 0;
 }
 
 #endif
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 7d423ee10897..ff8c8118d56e 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1973,7 +1973,7 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt,
 
         switch (opt) {
         case TIPC_IMPORTANCE:
-                tipc_port_set_importance(port, value);
+                res = tipc_port_set_importance(port, value);
                 break;
         case TIPC_SRC_DROPPABLE:
                 if (sock->type != SOCK_STREAM)