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

Pull networking fixes from David Miller:

 1) The value choosen for the new SO_MAX_PACING_RATE socket option on
    parisc was very poorly choosen, let's fix it while we still can.
    From Eric Dumazet.

 2) Our generic reciprocal divide was found to handle some edge cases
    incorrectly, part of this is encoded into the BPF as deep as the JIT
    engines themselves.  Just use a real divide throughout for now.
    From Eric Dumazet.

 3) Because the initial lookup is lockless, the TCP metrics engine can
    end up creating two entries for the same lookup key.  Fix this by
    doing a second lookup under the lock before we actually create the
    new entry.  From Christoph Paasch.

 4) Fix scatter-gather list init in usbnet driver, from Bjørn Mork.

 5) Fix unintended 32-bit truncation in cxgb4 driver's bit shifting.
    From Dan Carpenter.

 6) Netlink socket dumping uses the wrong socket state for timewait
    sockets.  Fix from Neal Cardwell.

 7) Fix netlink memory leak in ieee802154_add_iface(), from Christian
    Engelmayer.

 8) Multicast forwarding in ipv4 can overflow the per-rule reference
    counts, causing all multicast traffic to cease.  Fix from Hannes
    Frederic Sowa.

 9) via-rhine needs to stop all TX queues when it resets the device,
    from Richard Weinberger.

10) Fix RDS per-cpu accesses broken by the this_cpu_* conversions.  From
    Gerald Schaefer.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:
  s390/bpf,jit: fix 32 bit divisions, use unsigned divide instructions
  parisc: fix SO_MAX_PACING_RATE typo
  ipv6: simplify detection of first operational link-local address on interface
  tcp: metrics: Avoid duplicate entries with the same destination-IP
  net: rds: fix per-cpu helper usage
  e1000e: Fix compilation warning when !CONFIG_PM_SLEEP
  bpf: do not use reciprocal divide
  be2net: add dma_mapping_error() check for dma_map_page()
  bnx2x: Don't release PCI bars on shutdown
  net,via-rhine: Fix tx_timeout handling
  batman-adv: fix batman-adv header overhead calculation
  qlge: Fix vlan netdev features.
  net: avoid reference counter overflows on fib_rules in multicast forwarding
  dm9601: add USB IDs for new dm96xx variants
  MAINTAINERS: add virtio-dev ML for virtio
  ieee802154: Fix memory leak in ieee802154_add_iface()
  net: usbnet: fix SG initialisation
  inet_diag: fix inet_diag_dump_icsk() to use correct state for timewait sockets
  cxgb4: silence shift wrapping static checker warning

9 files changed, 73 insertions, 80 deletions

diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index 1511f64a6ce..faba0f61ad5 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -277,7 +277,7 @@ int batadv_max_header_len(void)
 			   sizeof(struct batadv_coded_packet));
 #endif
 
-	return header_len;
+	return header_len + ETH_HLEN;
 }
 
 /**
diff --git a/net/core/filter.c b/net/core/filter.c
index 01b780856db..ad30d626a5b 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -36,7 +36,6 @@
 #include <asm/uaccess.h>
 #include <asm/unaligned.h>
 #include <linux/filter.h>
-#include <linux/reciprocal_div.h>
 #include <linux/ratelimit.h>
 #include <linux/seccomp.h>
 #include <linux/if_vlan.h>
@@ -166,7 +165,7 @@ unsigned int sk_run_filter(const struct sk_buff *skb,
 			A /= X;
 			continue;
 		case BPF_S_ALU_DIV_K:
-			A = reciprocal_divide(A, K);
+			A /= K;
 			continue;
 		case BPF_S_ALU_MOD_X:
 			if (X == 0)
@@ -553,11 +552,6 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen)
 		/* Some instructions need special checks */
 		switch (code) {
 		case BPF_S_ALU_DIV_K:
-			/* check for division by zero */
-			if (ftest->k == 0)
-				return -EINVAL;
-			ftest->k = reciprocal_value(ftest->k);
-			break;
 		case BPF_S_ALU_MOD_K:
 			/* check for division by zero */
 			if (ftest->k == 0)
@@ -853,27 +847,7 @@ void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to)
 	to->code = decodes[code];
 	to->jt = filt->jt;
 	to->jf = filt->jf;
-
-	if (code == BPF_S_ALU_DIV_K) {
-		/*
-		 * When loaded this rule user gave us X, which was
-		 * translated into R = r(X). Now we calculate the
-		 * RR = r(R) and report it back. If next time this
-		 * value is loaded and RRR = r(RR) is calculated
-		 * then the R == RRR will be true.
-		 *
-		 * One exception. X == 1 translates into R == 0 and
-		 * we can't calculate RR out of it with r().
-		 */
-
-		if (filt->k == 0)
-			to->k = 1;
-		else
-			to->k = reciprocal_value(filt->k);
-
-		BUG_ON(reciprocal_value(to->k) != filt->k);
-	} else
-		to->k = filt->k;
+	to->k = filt->k;
 }
 
 int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, unsigned int len)
diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c
index d08c7a43dcd..89b265aea15 100644
--- a/net/ieee802154/nl-phy.c
+++ b/net/ieee802154/nl-phy.c
@@ -221,8 +221,10 @@ int ieee802154_add_iface(struct sk_buff *skb, struct genl_info *info)
 
 	if (info->attrs[IEEE802154_ATTR_DEV_TYPE]) {
 		type = nla_get_u8(info->attrs[IEEE802154_ATTR_DEV_TYPE]);
-		if (type >= __IEEE802154_DEV_MAX)
-			return -EINVAL;
+		if (type >= __IEEE802154_DEV_MAX) {
+			rc = -EINVAL;
+			goto nla_put_failure;
+		}
 	}
 
 	dev = phy->add_iface(phy, devname, type);
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index a0f52dac894..e34dccbc4d7 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -930,12 +930,15 @@ skip_listen_ht:
 		spin_lock_bh(lock);
 		sk_nulls_for_each(sk, node, &head->chain) {
 			int res;
+			int state;
 
 			if (!net_eq(sock_net(sk), net))
 				continue;
 			if (num < s_num)
 				goto next_normal;
-			if (!(r->idiag_states & (1 << sk->sk_state)))
+			state = (sk->sk_state == TCP_TIME_WAIT) ?
+				inet_twsk(sk)->tw_substate : sk->sk_state;
+			if (!(r->idiag_states & (1 << state)))
 				goto next_normal;
 			if (r->sdiag_family != AF_UNSPEC &&
 			    sk->sk_family != r->sdiag_family)
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 62212c772a4..1672409f5ba 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -157,9 +157,12 @@ static struct mr_table *ipmr_get_table(struct net *net, u32 id)
 static int ipmr_fib_lookup(struct net *net, struct flowi4 *flp4,
 			   struct mr_table **mrt)
 {
-	struct ipmr_result res;
-	struct fib_lookup_arg arg = { .result = &res, };
 	int err;
+	struct ipmr_result res;
+	struct fib_lookup_arg arg = {
+		.result = &res,
+		.flags = FIB_LOOKUP_NOREF,
+	};
 
 	err = fib_rules_lookup(net->ipv4.mr_rules_ops,
 			       flowi4_to_flowi(flp4), 0, &arg);
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 06493736fbc..098b3a29f6f 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -22,6 +22,9 @@
 
 int sysctl_tcp_nometrics_save __read_mostly;
 
+static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *addr,
+						   struct net *net, unsigned int hash);
+
 struct tcp_fastopen_metrics {
 	u16	mss;
 	u16	syn_loss:10;		/* Recurring Fast Open SYN losses */
@@ -130,16 +133,41 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst,
 	}
 }
 
+#define TCP_METRICS_TIMEOUT		(60 * 60 * HZ)
+
+static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst)
+{
+	if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT)))
+		tcpm_suck_dst(tm, dst, false);
+}
+
+#define TCP_METRICS_RECLAIM_DEPTH	5
+#define TCP_METRICS_RECLAIM_PTR		(struct tcp_metrics_block *) 0x1UL
+
 static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst,
 					  struct inetpeer_addr *addr,
-					  unsigned int hash,
-					  bool reclaim)
+					  unsigned int hash)
 {
 	struct tcp_metrics_block *tm;
 	struct net *net;
+	bool reclaim = false;
 
 	spin_lock_bh(&tcp_metrics_lock);
 	net = dev_net(dst->dev);
+
+	/* While waiting for the spin-lock the cache might have been populated
+	 * with this entry and so we have to check again.
+	 */
+	tm = __tcp_get_metrics(addr, net, hash);
+	if (tm == TCP_METRICS_RECLAIM_PTR) {
+		reclaim = true;
+		tm = NULL;
+	}
+	if (tm) {
+		tcpm_check_stamp(tm, dst);
+		goto out_unlock;
+	}
+
 	if (unlikely(reclaim)) {
 		struct tcp_metrics_block *oldest;
 
@@ -169,17 +197,6 @@ out_unlock:
 	return tm;
 }
 
-#define TCP_METRICS_TIMEOUT		(60 * 60 * HZ)
-
-static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst)
-{
-	if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT)))
-		tcpm_suck_dst(tm, dst, false);
-}
-
-#define TCP_METRICS_RECLAIM_DEPTH	5
-#define TCP_METRICS_RECLAIM_PTR		(struct tcp_metrics_block *) 0x1UL
-
 static struct tcp_metrics_block *tcp_get_encode(struct tcp_metrics_block *tm, int depth)
 {
 	if (tm)
@@ -282,7 +299,6 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
 	struct inetpeer_addr addr;
 	unsigned int hash;
 	struct net *net;
-	bool reclaim;
 
 	addr.family = sk->sk_family;
 	switch (addr.family) {
@@ -304,13 +320,10 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
 	hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log);
 
 	tm = __tcp_get_metrics(&addr, net, hash);
-	reclaim = false;
-	if (tm == TCP_METRICS_RECLAIM_PTR) {
-		reclaim = true;
+	if (tm == TCP_METRICS_RECLAIM_PTR)
 		tm = NULL;
-	}
 	if (!tm && create)
-		tm = tcpm_new(dst, &addr, hash, reclaim);
+		tm = tcpm_new(dst, &addr, hash);
 	else
 		tcpm_check_stamp(tm, dst);
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index abe46a4228c..4b6b720971b 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3189,6 +3189,22 @@ out:
 	in6_ifa_put(ifp);
 }
 
+/* ifp->idev must be at least read locked */
+static bool ipv6_lonely_lladdr(struct inet6_ifaddr *ifp)
+{
+	struct inet6_ifaddr *ifpiter;
+	struct inet6_dev *idev = ifp->idev;
+
+	list_for_each_entry(ifpiter, &idev->addr_list, if_list) {
+		if (ifp != ifpiter && ifpiter->scope == IFA_LINK &&
+		    (ifpiter->flags & (IFA_F_PERMANENT|IFA_F_TENTATIVE|
+				       IFA_F_OPTIMISTIC|IFA_F_DADFAILED)) ==
+		    IFA_F_PERMANENT)
+			return false;
+	}
+	return true;
+}
+
 static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
 {
 	struct net_device *dev = ifp->idev->dev;
@@ -3208,14 +3224,11 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
 	 */
 
 	read_lock_bh(&ifp->idev->lock);
-	spin_lock(&ifp->lock);
-	send_mld = ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL &&
-		   ifp->idev->valid_ll_addr_cnt == 1;
+	send_mld = ifp->scope == IFA_LINK && ipv6_lonely_lladdr(ifp);
 	send_rs = send_mld &&
 		  ipv6_accept_ra(ifp->idev) &&
 		  ifp->idev->cnf.rtr_solicits > 0 &&
 		  (dev->flags&IFF_LOOPBACK) == 0;
-	spin_unlock(&ifp->lock);
 	read_unlock_bh(&ifp->idev->lock);
 
 	/* While dad is in progress mld report's source address is in6_addrany.
@@ -4512,19 +4525,6 @@ errout:
 		rtnl_set_sk_err(net, RTNLGRP_IPV6_PREFIX, err);
 }
 
-static void update_valid_ll_addr_cnt(struct inet6_ifaddr *ifp, int count)
-{
-	write_lock_bh(&ifp->idev->lock);
-	spin_lock(&ifp->lock);
-	if (((ifp->flags & (IFA_F_PERMANENT|IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|
-			    IFA_F_DADFAILED)) == IFA_F_PERMANENT) &&
-	    (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL))
-		ifp->idev->valid_ll_addr_cnt += count;
-	WARN_ON(ifp->idev->valid_ll_addr_cnt < 0);
-	spin_unlock(&ifp->lock);
-	write_unlock_bh(&ifp->idev->lock);
-}
-
 static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 {
 	struct net *net = dev_net(ifp->idev->dev);
@@ -4533,8 +4533,6 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 
 	switch (event) {
 	case RTM_NEWADDR:
-		update_valid_ll_addr_cnt(ifp, 1);
-
 		/*
 		 * If the address was optimistic
 		 * we inserted the route at the start of
@@ -4550,8 +4548,6 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 					      ifp->idev->dev, 0, 0);
 		break;
 	case RTM_DELADDR:
-		update_valid_ll_addr_cnt(ifp, -1);
-
 		if (ifp->idev->cnf.forwarding)
 			addrconf_leave_anycast(ifp);
 		addrconf_leave_solict(ifp->idev, &ifp->addr);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index f365310bfcc..0eb4038a4d6 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -141,9 +141,12 @@ static struct mr6_table *ip6mr_get_table(struct net *net, u32 id)
 static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6,
 			    struct mr6_table **mrt)
 {
-	struct ip6mr_result res;
-	struct fib_lookup_arg arg = { .result = &res, };
 	int err;
+	struct ip6mr_result res;
+	struct fib_lookup_arg arg = {
+		.result = &res,
+		.flags = FIB_LOOKUP_NOREF,
+	};
 
 	err = fib_rules_lookup(net->ipv6.mr6_rules_ops,
 			       flowi6_to_flowi(flp6), 0, &arg);
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index 8eb9501e3d6..b7ebe23cded 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -421,8 +421,7 @@ static void rds_ib_recv_cache_put(struct list_head *new_item,
 				 struct rds_ib_refill_cache *cache)
 {
 	unsigned long flags;
-	struct list_head *old;
-	struct list_head __percpu *chpfirst;
+	struct list_head *old, *chpfirst;
 
 	local_irq_save(flags);
 
@@ -432,7 +431,7 @@ static void rds_ib_recv_cache_put(struct list_head *new_item,
 	else /* put on front */
 		list_add_tail(new_item, chpfirst);
 
-	__this_cpu_write(chpfirst, new_item);
+	__this_cpu_write(cache->percpu->first, new_item);
 	__this_cpu_inc(cache->percpu->count);
 
 	if (__this_cpu_read(cache->percpu->count) < RDS_IB_RECYCLE_BATCH_COUNT)
@@ -452,7 +451,7 @@ static void rds_ib_recv_cache_put(struct list_head *new_item,
 	} while (old);
 
 
-	__this_cpu_write(chpfirst, NULL);
+	__this_cpu_write(cache->percpu->first, NULL);
 	__this_cpu_write(cache->percpu->count, 0);
 end:
 	local_irq_restore(flags);