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

Pull networking updates from David Miller:

 1) Fix inaccuracies in network driver interface documentation, from Ben
    Hutchings.

 2) Fix handling of negative offsets in BPF JITs, from Jan Seiffert.

 3) Compile warning, locking, and refcounting fixes in netfilter's
    xt_CT, from Pablo Neira Ayuso.

 4) phonet sendmsg needs to validate user length just like any other
    datagram protocol, fix from Sasha Levin.

 5) Ipv6 multicast code uses wrong loop index, from RongQing Li.

 6) Link handling and firmware fixes in bnx2x driver from Yaniv Rosner
    and Yuval Mintz.

 7) mlx4 erroneously allocates 4 pages at a time, regardless of page
    size, fix from Thadeu Lima de Souza Cascardo.

 8) SCTP socket option wasn't extended in a backwards compatible way,
    fix from Thomas Graf.

 9) Add missing address change event emissions to bonding, from Shlomo
    Pongratz.

10) /proc/net/dev regressed because it uses a private offset to track
    where we are in the hash table, but this doesn't track the offset
    pullback that the seq_file code does resulting in some entries being
    missed in large dumps.

    Fix from Eric Dumazet.

11) do_tcp_sendpage() unloads the send queue way too fast, because it
    invokes tcp_push() when it shouldn't.  Let the natural sequence
    generated by the splice paths, and the assosciated MSG_MORE
    settings, guide the tcp_push() calls.

    Otherwise what goes out of TCP is spaghetti and doesn't batch
    effectively into GSO/TSO clusters.

    From Eric Dumazet.

12) Once we put a SKB into either the netlink receiver's queue or a
    socket error queue, it can be consumed and freed up, therefore we
    cannot touch it after queueing it like that.

    Fixes from Eric Dumazet.

13) PPP has this annoying behavior in that for every transmit call it
    immediately stops the TX queue, then calls down into the next layer
    to transmit the PPP frame.

    But if that next layer can take it immediately, it just un-stops the
    TX queue right before returning from the transmit method.

    Besides being useless work, it makes several facilities unusable, in
    particular things like the equalizers.  Well behaved devices should
    only stop the TX queue when they really are full, and in PPP's case
    when it gets backlogged to the downstream device.

    David Woodhouse therefore fixed PPP to not stop the TX queue until
    it's downstream can't take data any more.

14) IFF_UNICAST_FLT got accidently lost in some recent stmmac driver
    changes, re-add.  From Marc Kleine-Budde.

15) Fix link flaps in ixgbe, from Eric W. Multanen.

16) Descriptor writeback fixes in e1000e from Matthew Vick.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (47 commits)
  net: fix a race in sock_queue_err_skb()
  netlink: fix races after skb queueing
  doc, net: Update ndo_start_xmit return type and values
  doc, net: Remove instruction to set net_device::trans_start
  doc, net: Update netdev operation names
  doc, net: Update documentation of synchronisation for TX multiqueue
  doc, net: Remove obsolete reference to dev->poll
  ethtool: Remove exception to the requirement of holding RTNL lock
  MAINTAINERS: update for Marvell Ethernet drivers
  bonding: properly unset current_arp_slave on slave link up
  phonet: Check input from user before allocating
  tcp: tcp_sendpages() should call tcp_push() once
  ipv6: fix array index in ip6_mc_add_src()
  mlx4: allocate just enough pages instead of always 4 pages
  stmmac: re-add IFF_UNICAST_FLT for dwmac1000
  bnx2x: Clear MDC/MDIO warning message
  bnx2x: Fix BCM57711+BCM84823 link issue
  bnx2x: Clear BCM84833 LED after fan failure
  bnx2x: Fix BCM84833 PHY FW version presentation
  bnx2x: Fix link issue for BCM8727 boards.
  ...

12 files changed, 71 insertions, 74 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 6c7dc9d..c25d453 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4028,54 +4028,41 @@ static int dev_ifconf(struct net *net, char __user *arg)
 
 #ifdef CONFIG_PROC_FS
 
-#define BUCKET_SPACE (32 - NETDEV_HASHBITS)
-
-struct dev_iter_state {
-	struct seq_net_private p;
-	unsigned int pos; /* bucket << BUCKET_SPACE + offset */
-};
+#define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1)
 
 #define get_bucket(x) ((x) >> BUCKET_SPACE)
 #define get_offset(x) ((x) & ((1 << BUCKET_SPACE) - 1))
 #define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o))
 
-static inline struct net_device *dev_from_same_bucket(struct seq_file *seq)
+static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff_t *pos)
 {
-	struct dev_iter_state *state = seq->private;
 	struct net *net = seq_file_net(seq);
 	struct net_device *dev;
 	struct hlist_node *p;
 	struct hlist_head *h;
-	unsigned int count, bucket, offset;
+	unsigned int count = 0, offset = get_offset(*pos);
 
-	bucket = get_bucket(state->pos);
-	offset = get_offset(state->pos);
-	h = &net->dev_name_head[bucket];
-	count = 0;
+	h = &net->dev_name_head[get_bucket(*pos)];
 	hlist_for_each_entry_rcu(dev, p, h, name_hlist) {
-		if (count++ == offset) {
-			state->pos = set_bucket_offset(bucket, count);
+		if (++count == offset)
 			return dev;
-		}
 	}
 
 	return NULL;
 }
 
-static inline struct net_device *dev_from_new_bucket(struct seq_file *seq)
+static inline struct net_device *dev_from_bucket(struct seq_file *seq, loff_t *pos)
 {
-	struct dev_iter_state *state = seq->private;
 	struct net_device *dev;
 	unsigned int bucket;
 
-	bucket = get_bucket(state->pos);
 	do {
-		dev = dev_from_same_bucket(seq);
+		dev = dev_from_same_bucket(seq, pos);
 		if (dev)
 			return dev;
 
-		bucket++;
-		state->pos = set_bucket_offset(bucket, 0);
+		bucket = get_bucket(*pos) + 1;
+		*pos = set_bucket_offset(bucket, 1);
 	} while (bucket < NETDEV_HASHENTRIES);
 
 	return NULL;
@@ -4088,33 +4075,20 @@ static inline struct net_device *dev_from_new_bucket(struct seq_file *seq)
 void *dev_seq_start(struct seq_file *seq, loff_t *pos)
 	__acquires(RCU)
 {
-	struct dev_iter_state *state = seq->private;
-
 	rcu_read_lock();
 	if (!*pos)
 		return SEQ_START_TOKEN;
 
-	/* check for end of the hash */
-	if (state->pos == 0 && *pos > 1)
+	if (get_bucket(*pos) >= NETDEV_HASHENTRIES)
 		return NULL;
 
-	return dev_from_new_bucket(seq);
+	return dev_from_bucket(seq, pos);
 }
 
 void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
-	struct net_device *dev;
-
 	++*pos;
-
-	if (v == SEQ_START_TOKEN)
-		return dev_from_new_bucket(seq);
-
-	dev = dev_from_same_bucket(seq);
-	if (dev)
-		return dev;
-
-	return dev_from_new_bucket(seq);
+	return dev_from_bucket(seq, pos);
 }
 
 void dev_seq_stop(struct seq_file *seq, void *v)
@@ -4213,13 +4187,7 @@ static const struct seq_operations dev_seq_ops = {
 static int dev_seq_open(struct inode *inode, struct file *file)
 {
 	return seq_open_net(inode, file, &dev_seq_ops,
-			    sizeof(struct dev_iter_state));
-}
-
-int dev_seq_open_ops(struct inode *inode, struct file *file,
-		     const struct seq_operations *ops)
-{
-	return seq_open_net(inode, file, ops, sizeof(struct dev_iter_state));
+			    sizeof(struct seq_net_private));
 }
 
 static const struct file_operations dev_seq_fops = {
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index 29c07fe..626698f 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -696,7 +696,8 @@ static const struct seq_operations dev_mc_seq_ops = {
 
 static int dev_mc_seq_open(struct inode *inode, struct file *file)
 {
-	return dev_seq_open_ops(inode, file, &dev_mc_seq_ops);
+	return seq_open_net(inode, file, &dev_mc_seq_ops,
+			    sizeof(struct seq_net_private));
 }
 
 static const struct file_operations dev_mc_seq_fops = {
diff --git a/net/core/filter.c b/net/core/filter.c
index cf4989a..6f755cc 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -39,8 +39,11 @@
 #include <linux/reciprocal_div.h>
 #include <linux/ratelimit.h>
 
-/* No hurry in this branch */
-static void *__load_pointer(const struct sk_buff *skb, int k, unsigned int size)
+/* No hurry in this branch
+ *
+ * Exported for the bpf jit load helper.
+ */
+void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size)
 {
 	u8 *ptr = NULL;
 
@@ -59,7 +62,7 @@ static inline void *load_pointer(const struct sk_buff *skb, int k,
 {
 	if (k >= 0)
 		return skb_header_pointer(skb, k, size, buffer);
-	return __load_pointer(skb, k, size);
+	return bpf_internal_load_pointer_neg_helper(skb, k, size);
 }
 
 /**
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f223cdc..baf8d28 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3161,6 +3161,8 @@ static void sock_rmem_free(struct sk_buff *skb)
  */
 int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
 {
+	int len = skb->len;
+
 	if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
 	    (unsigned)sk->sk_rcvbuf)
 		return -ENOMEM;
@@ -3175,7 +3177,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
 
 	skb_queue_tail(&sk->sk_error_queue, skb);
 	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk, skb->len);
+		sk->sk_data_ready(sk, len);
 	return 0;
 }
 EXPORT_SYMBOL(sock_queue_err_skb);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index cfd7edd..5d54ed3 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -860,7 +860,7 @@ wait_for_memory:
 	}
 
 out:
-	if (copied)
+	if (copied && !(flags & MSG_SENDPAGE_NOTLAST))
 		tcp_push(sk, flags, mss_now, tp->nonagle);
 	return copied;
 
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 16c33e3..b2869ca 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -2044,7 +2044,7 @@ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca,
 		if (!delta)
 			pmc->mca_sfcount[sfmode]--;
 		for (j=0; j<i; j++)
-			(void) ip6_mc_del1_src(pmc, sfmode, &psfsrc[i]);
+			ip6_mc_del1_src(pmc, sfmode, &psfsrc[j]);
 	} else if (isexclude != (pmc->mca_sfcount[MCAST_EXCLUDE] != 0)) {
 		struct ip6_sf_list *psf;
 
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index cbdb754..3cc4487 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -735,6 +735,7 @@ __nf_conntrack_alloc(struct net *net, u16 zone,
 
 #ifdef CONFIG_NF_CONNTRACK_ZONES
 out_free:
+	atomic_dec(&net->ct.count);
 	kmem_cache_free(net->ct.nf_conntrack_cachep, ct);
 	return ERR_PTR(-ENOMEM);
 #endif
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 0c8e438..59530e9 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -150,6 +150,17 @@ err1:
 	return ret;
 }
 
+#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
+static void __xt_ct_tg_timeout_put(struct ctnl_timeout *timeout)
+{
+	typeof(nf_ct_timeout_put_hook) timeout_put;
+
+	timeout_put = rcu_dereference(nf_ct_timeout_put_hook);
+	if (timeout_put)
+		timeout_put(timeout);
+}
+#endif
+
 static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par)
 {
 	struct xt_ct_target_info_v1 *info = par->targinfo;
@@ -158,7 +169,9 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par)
 	struct nf_conn *ct;
 	int ret = 0;
 	u8 proto;
-
+#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
+	struct ctnl_timeout *timeout;
+#endif
 	if (info->flags & ~XT_CT_NOTRACK)
 		return -EINVAL;
 
@@ -216,7 +229,6 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par)
 #ifdef CONFIG_NF_CONNTRACK_TIMEOUT
 	if (info->timeout) {
 		typeof(nf_ct_timeout_find_get_hook) timeout_find_get;
-		struct ctnl_timeout *timeout;
 		struct nf_conn_timeout *timeout_ext;
 
 		rcu_read_lock();
@@ -245,7 +257,7 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par)
 				pr_info("Timeout policy `%s' can only be "
 					"used by L3 protocol number %d\n",
 					info->timeout, timeout->l3num);
-				goto err4;
+				goto err5;
 			}
 			/* Make sure the timeout policy matches any existing
 			 * protocol tracker, otherwise default to generic.
@@ -258,13 +270,13 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par)
 					"used by L4 protocol number %d\n",
 					info->timeout,
 					timeout->l4proto->l4proto);
-				goto err4;
+				goto err5;
 			}
 			timeout_ext = nf_ct_timeout_ext_add(ct, timeout,
-							    GFP_KERNEL);
+							    GFP_ATOMIC);
 			if (timeout_ext == NULL) {
 				ret = -ENOMEM;
-				goto err4;
+				goto err5;
 			}
 		} else {
 			ret = -ENOENT;
@@ -281,8 +293,12 @@ out:
 	info->ct = ct;
 	return 0;
 
+#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
+err5:
+	__xt_ct_tg_timeout_put(timeout);
 err4:
 	rcu_read_unlock();
+#endif
 err3:
 	nf_conntrack_free(ct);
 err2:
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 32bb753..faa48f7 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -829,12 +829,19 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb,
 	return 0;
 }
 
-int netlink_sendskb(struct sock *sk, struct sk_buff *skb)
+static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb)
 {
 	int len = skb->len;
 
 	skb_queue_tail(&sk->sk_receive_queue, skb);
 	sk->sk_data_ready(sk, len);
+	return len;
+}
+
+int netlink_sendskb(struct sock *sk, struct sk_buff *skb)
+{
+	int len = __netlink_sendskb(sk, skb);
+
 	sock_put(sk);
 	return len;
 }
@@ -957,8 +964,7 @@ static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb)
 	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
 	    !test_bit(0, &nlk->state)) {
 		skb_set_owner_r(skb, sk);
-		skb_queue_tail(&sk->sk_receive_queue, skb);
-		sk->sk_data_ready(sk, skb->len);
+		__netlink_sendskb(sk, skb);
 		return atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1);
 	}
 	return -1;
@@ -1698,10 +1704,8 @@ static int netlink_dump(struct sock *sk)
 
 		if (sk_filter(sk, skb))
 			kfree_skb(skb);
-		else {
-			skb_queue_tail(&sk->sk_receive_queue, skb);
-			sk->sk_data_ready(sk, skb->len);
-		}
+		else
+			__netlink_sendskb(sk, skb);
 		return 0;
 	}
 
@@ -1715,10 +1719,8 @@ static int netlink_dump(struct sock *sk)
 
 	if (sk_filter(sk, skb))
 		kfree_skb(skb);
-	else {
-		skb_queue_tail(&sk->sk_receive_queue, skb);
-		sk->sk_data_ready(sk, skb->len);
-	}
+	else
+		__netlink_sendskb(sk, skb);
 
 	if (cb->done)
 		cb->done(cb);
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 9f60008..9726fe6 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -1130,6 +1130,9 @@ static int pep_sendmsg(struct kiocb *iocb, struct sock *sk,
 	int flags = msg->msg_flags;
 	int err, done;
 
+	if (len > USHRT_MAX)
+		return -EMSGSIZE;
+
 	if ((msg->msg_flags & ~(MSG_DONTWAIT|MSG_EOR|MSG_NOSIGNAL|
 				MSG_CMSG_COMPAT)) ||
 			!(msg->msg_flags & MSG_EOR))
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 06b42b7..92ba71d 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4133,9 +4133,10 @@ static int sctp_getsockopt_disable_fragments(struct sock *sk, int len,
 static int sctp_getsockopt_events(struct sock *sk, int len, char __user *optval,
 				  int __user *optlen)
 {
-	if (len < sizeof(struct sctp_event_subscribe))
+	if (len <= 0)
 		return -EINVAL;
-	len = sizeof(struct sctp_event_subscribe);
+	if (len > sizeof(struct sctp_event_subscribe))
+		len = sizeof(struct sctp_event_subscribe);
 	if (put_user(len, optlen))
 		return -EFAULT;
 	if (copy_to_user(optval, &sctp_sk(sk)->subscribe, len))
diff --git a/net/socket.c b/net/socket.c
index 484cc69..851edcd 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -811,9 +811,9 @@ static ssize_t sock_sendpage(struct file *file, struct page *page,
 
 	sock = file->private_data;
 
-	flags = !(file->f_flags & O_NONBLOCK) ? 0 : MSG_DONTWAIT;
-	if (more)
-		flags |= MSG_MORE;
+	flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0;
+	/* more is a combination of MSG_MORE and MSG_SENDPAGE_NOTLAST */
+	flags |= more;
 
 	return kernel_sendpage(sock, page, offset, size, flags);
 }