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

Pull networking updates from David Miller:
 "Most notable changes in here:

   1) By far the biggest accomplishment, thanks to a large range of
      contributors, is the addition of multi-send for transmit.  This is
      the result of discussions back in Chicago, and the hard work of
      several individuals.

      Now, when the ->ndo_start_xmit() method of a driver sees
      skb->xmit_more as true, it can choose to defer the doorbell
      telling the driver to start processing the new TX queue entires.

      skb->xmit_more means that the generic networking is guaranteed to
      call the driver immediately with another SKB to send.

      There is logic added to the qdisc layer to dequeue multiple
      packets at a time, and the handling mis-predicted offloads in
      software is now done with no locks held.

      Finally, pktgen is extended to have a "burst" parameter that can
      be used to test a multi-send implementation.

      Several drivers have xmit_more support: i40e, igb, ixgbe, mlx4,
      virtio_net

      Adding support is almost trivial, so export more drivers to
      support this optimization soon.

      I want to thank, in no particular or implied order, Jesper
      Dangaard Brouer, Eric Dumazet, Alexander Duyck, Tom Herbert, Jamal
      Hadi Salim, John Fastabend, Florian Westphal, Daniel Borkmann,
      David Tat, Hannes Frederic Sowa, and Rusty Russell.

   2) PTP and timestamping support in bnx2x, from Michal Kalderon.

   3) Allow adjusting the rx_copybreak threshold for a driver via
      ethtool, and add rx_copybreak support to enic driver.  From
      Govindarajulu Varadarajan.

   4) Significant enhancements to the generic PHY layer and the bcm7xxx
      driver in particular (EEE support, auto power down, etc.) from
      Florian Fainelli.

   5) Allow raw buffers to be used for flow dissection, allowing drivers
      to determine the optimal "linear pull" size for devices that DMA
      into pools of pages.  The objective is to get exactly the
      necessary amount of headers into the linear SKB area pre-pulled,
      but no more.  The new interface drivers use is eth_get_headlen().
      From WANG Cong, with driver conversions (several had their own
      by-hand duplicated implementations) by Alexander Duyck and Eric
      Dumazet.

   6) Support checksumming more smoothly and efficiently for
      encapsulations, and add "foo over UDP" facility.  From Tom
      Herbert.

   7) Add Broadcom SF2 switch driver to DSA layer, from Florian
      Fainelli.

   8) eBPF now can load programs via a system call and has an extensive
      testsuite.  Alexei Starovoitov and Daniel Borkmann.

   9) Major overhaul of the packet scheduler to use RCU in several major
      areas such as the classifiers and rate estimators.  From John
      Fastabend.

  10) Add driver for Intel FM10000 Ethernet Switch, from Alexander
      Duyck.

  11) Rearrange TCP_SKB_CB() to reduce cache line misses, from Eric
      Dumazet.

  12) Add Datacenter TCP congestion control algorithm support, From
      Florian Westphal.

  13) Reorganize sk_buff so that __copy_skb_header() is significantly
      faster.  From Eric Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1558 commits)
  netlabel: directly return netlbl_unlabel_genl_init()
  net: add netdev_txq_bql_{enqueue, complete}_prefetchw() helpers
  net: description of dma_cookie cause make xmldocs warning
  cxgb4: clean up a type issue
  cxgb4: potential shift wrapping bug
  i40e: skb->xmit_more support
  net: fs_enet: Add NAPI TX
  net: fs_enet: Remove non NAPI RX
  r8169:add support for RTL8168EP
  net_sched: copy exts->type in tcf_exts_change()
  wimax: convert printk to pr_foo()
  af_unix: remove 0 assignment on static
  ipv6: Do not warn for informational ICMP messages, regardless of type.
  Update Intel Ethernet Driver maintainers list
  bridge: Save frag_max_size between PRE_ROUTING and POST_ROUTING
  tipc: fix bug in multicast congestion handling
  net: better IFF_XMIT_DST_RELEASE support
  net/mlx4_en: remove NETDEV_TX_BUSY
  3c59x: fix bad split of cpu_to_le32(pci_map_single())
  net: bcmgenet: fix Tx ring priority programming
  ...

1 files changed, 74 insertions, 68 deletions

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 97b9fa8de377..b2d1838897c9 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -46,20 +46,11 @@
 
 static struct kmem_cache *fib6_node_kmem __read_mostly;
 
-enum fib_walk_state_t {
-#ifdef CONFIG_IPV6_SUBTREES
-	FWS_S,
-#endif
-	FWS_L,
-	FWS_R,
-	FWS_C,
-	FWS_U
-};
-
-struct fib6_cleaner_t {
-	struct fib6_walker_t w;
+struct fib6_cleaner {
+	struct fib6_walker w;
 	struct net *net;
 	int (*func)(struct rt6_info *, void *arg);
+	int sernum;
 	void *arg;
 };
 
@@ -74,8 +65,8 @@ static DEFINE_RWLOCK(fib6_walker_lock);
 static void fib6_prune_clones(struct net *net, struct fib6_node *fn);
 static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn);
 static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_node *fn);
-static int fib6_walk(struct fib6_walker_t *w);
-static int fib6_walk_continue(struct fib6_walker_t *w);
+static int fib6_walk(struct fib6_walker *w);
+static int fib6_walk_continue(struct fib6_walker *w);
 
 /*
  *	A routing update causes an increase of the serial number on the
@@ -84,34 +75,41 @@ static int fib6_walk_continue(struct fib6_walker_t *w);
  *	result of redirects, path MTU changes, etc.
  */
 
-static __u32 rt_sernum;
-
 static void fib6_gc_timer_cb(unsigned long arg);
 
 static LIST_HEAD(fib6_walkers);
 #define FOR_WALKERS(w) list_for_each_entry(w, &fib6_walkers, lh)
 
-static inline void fib6_walker_link(struct fib6_walker_t *w)
+static void fib6_walker_link(struct fib6_walker *w)
 {
 	write_lock_bh(&fib6_walker_lock);
 	list_add(&w->lh, &fib6_walkers);
 	write_unlock_bh(&fib6_walker_lock);
 }
 
-static inline void fib6_walker_unlink(struct fib6_walker_t *w)
+static void fib6_walker_unlink(struct fib6_walker *w)
 {
 	write_lock_bh(&fib6_walker_lock);
 	list_del(&w->lh);
 	write_unlock_bh(&fib6_walker_lock);
 }
-static __inline__ u32 fib6_new_sernum(void)
+
+static int fib6_new_sernum(struct net *net)
 {
-	u32 n = ++rt_sernum;
-	if ((__s32)n <= 0)
-		rt_sernum = n = 1;
-	return n;
+	int new, old;
+
+	do {
+		old = atomic_read(&net->ipv6.fib6_sernum);
+		new = old < INT_MAX ? old + 1 : 1;
+	} while (atomic_cmpxchg(&net->ipv6.fib6_sernum,
+				old, new) != old);
+	return new;
 }
 
+enum {
+	FIB6_NO_SERNUM_CHANGE = 0,
+};
+
 /*
  *	Auxiliary address test functions for the radix tree.
  *
@@ -128,7 +126,7 @@ static __inline__ u32 fib6_new_sernum(void)
 # define BITOP_BE32_SWIZZLE	0
 #endif
 
-static __inline__ __be32 addr_bit_set(const void *token, int fn_bit)
+static __be32 addr_bit_set(const void *token, int fn_bit)
 {
 	const __be32 *addr = token;
 	/*
@@ -142,7 +140,7 @@ static __inline__ __be32 addr_bit_set(const void *token, int fn_bit)
 	       addr[fn_bit >> 5];
 }
 
-static __inline__ struct fib6_node *node_alloc(void)
+static struct fib6_node *node_alloc(void)
 {
 	struct fib6_node *fn;
 
@@ -151,12 +149,12 @@ static __inline__ struct fib6_node *node_alloc(void)
 	return fn;
 }
 
-static __inline__ void node_free(struct fib6_node *fn)
+static void node_free(struct fib6_node *fn)
 {
 	kmem_cache_free(fib6_node_kmem, fn);
 }
 
-static __inline__ void rt6_release(struct rt6_info *rt)
+static void rt6_release(struct rt6_info *rt)
 {
 	if (atomic_dec_and_test(&rt->rt6i_ref))
 		dst_free(&rt->dst);
@@ -267,7 +265,7 @@ static void __net_init fib6_tables_init(struct net *net)
 
 #endif
 
-static int fib6_dump_node(struct fib6_walker_t *w)
+static int fib6_dump_node(struct fib6_walker *w)
 {
 	int res;
 	struct rt6_info *rt;
@@ -287,7 +285,7 @@ static int fib6_dump_node(struct fib6_walker_t *w)
 
 static void fib6_dump_end(struct netlink_callback *cb)
 {
-	struct fib6_walker_t *w = (void *)cb->args[2];
+	struct fib6_walker *w = (void *)cb->args[2];
 
 	if (w) {
 		if (cb->args[4]) {
@@ -310,7 +308,7 @@ static int fib6_dump_done(struct netlink_callback *cb)
 static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb,
 			   struct netlink_callback *cb)
 {
-	struct fib6_walker_t *w;
+	struct fib6_walker *w;
 	int res;
 
 	w = (void *)cb->args[2];
@@ -355,7 +353,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 	unsigned int h, s_h;
 	unsigned int e = 0, s_e;
 	struct rt6_rtnl_dump_arg arg;
-	struct fib6_walker_t *w;
+	struct fib6_walker *w;
 	struct fib6_table *tb;
 	struct hlist_head *head;
 	int res = 0;
@@ -423,14 +421,13 @@ out:
 static struct fib6_node *fib6_add_1(struct fib6_node *root,
 				     struct in6_addr *addr, int plen,
 				     int offset, int allow_create,
-				     int replace_required)
+				     int replace_required, int sernum)
 {
 	struct fib6_node *fn, *in, *ln;
 	struct fib6_node *pn = NULL;
 	struct rt6key *key;
 	int	bit;
 	__be32	dir = 0;
-	__u32	sernum = fib6_new_sernum();
 
 	RT6_TRACE("fib6_add_1\n");
 
@@ -627,7 +624,7 @@ insert_above:
 	return ln;
 }
 
-static inline bool rt6_qualify_for_ecmp(struct rt6_info *rt)
+static bool rt6_qualify_for_ecmp(struct rt6_info *rt)
 {
 	return (rt->rt6i_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) ==
 	       RTF_GATEWAY;
@@ -820,7 +817,7 @@ add:
 	return 0;
 }
 
-static __inline__ void fib6_start_gc(struct net *net, struct rt6_info *rt)
+static void fib6_start_gc(struct net *net, struct rt6_info *rt)
 {
 	if (!timer_pending(&net->ipv6.ip6_fib_timer) &&
 	    (rt->rt6i_flags & (RTF_EXPIRES | RTF_CACHE)))
@@ -848,6 +845,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
 	int err = -ENOMEM;
 	int allow_create = 1;
 	int replace_required = 0;
+	int sernum = fib6_new_sernum(info->nl_net);
 
 	if (info->nlh) {
 		if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
@@ -860,7 +858,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
 
 	fn = fib6_add_1(root, &rt->rt6i_dst.addr, rt->rt6i_dst.plen,
 			offsetof(struct rt6_info, rt6i_dst), allow_create,
-			replace_required);
+			replace_required, sernum);
 	if (IS_ERR(fn)) {
 		err = PTR_ERR(fn);
 		fn = NULL;
@@ -894,14 +892,14 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
 			sfn->leaf = info->nl_net->ipv6.ip6_null_entry;
 			atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref);
 			sfn->fn_flags = RTN_ROOT;
-			sfn->fn_sernum = fib6_new_sernum();
+			sfn->fn_sernum = sernum;
 
 			/* Now add the first leaf node to new subtree */
 
 			sn = fib6_add_1(sfn, &rt->rt6i_src.addr,
 					rt->rt6i_src.plen,
 					offsetof(struct rt6_info, rt6i_src),
-					allow_create, replace_required);
+					allow_create, replace_required, sernum);
 
 			if (IS_ERR(sn)) {
 				/* If it is failed, discard just allocated
@@ -920,7 +918,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
 			sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr,
 					rt->rt6i_src.plen,
 					offsetof(struct rt6_info, rt6i_src),
-					allow_create, replace_required);
+					allow_create, replace_required, sernum);
 
 			if (IS_ERR(sn)) {
 				err = PTR_ERR(sn);
@@ -1174,7 +1172,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 	int children;
 	int nstate;
 	struct fib6_node *child, *pn;
-	struct fib6_walker_t *w;
+	struct fib6_walker *w;
 	int iter = 0;
 
 	for (;;) {
@@ -1276,7 +1274,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
 			   struct nl_info *info)
 {
-	struct fib6_walker_t *w;
+	struct fib6_walker *w;
 	struct rt6_info *rt = *rtp;
 	struct net *net = info->nl_net;
 
@@ -1414,7 +1412,7 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info)
  *	<0  -> walk is terminated by an error.
  */
 
-static int fib6_walk_continue(struct fib6_walker_t *w)
+static int fib6_walk_continue(struct fib6_walker *w)
 {
 	struct fib6_node *fn, *pn;
 
@@ -1498,7 +1496,7 @@ skip:
 	}
 }
 
-static int fib6_walk(struct fib6_walker_t *w)
+static int fib6_walk(struct fib6_walker *w)
 {
 	int res;
 
@@ -1512,15 +1510,25 @@ static int fib6_walk(struct fib6_walker_t *w)
 	return res;
 }
 
-static int fib6_clean_node(struct fib6_walker_t *w)
+static int fib6_clean_node(struct fib6_walker *w)
 {
 	int res;
 	struct rt6_info *rt;
-	struct fib6_cleaner_t *c = container_of(w, struct fib6_cleaner_t, w);
+	struct fib6_cleaner *c = container_of(w, struct fib6_cleaner, w);
 	struct nl_info info = {
 		.nl_net = c->net,
 	};
 
+	if (c->sernum != FIB6_NO_SERNUM_CHANGE &&
+	    w->node->fn_sernum != c->sernum)
+		w->node->fn_sernum = c->sernum;
+
+	if (!c->func) {
+		WARN_ON_ONCE(c->sernum == FIB6_NO_SERNUM_CHANGE);
+		w->leaf = NULL;
+		return 0;
+	}
+
 	for (rt = w->leaf; rt; rt = rt->dst.rt6_next) {
 		res = c->func(rt, c->arg);
 		if (res < 0) {
@@ -1554,9 +1562,9 @@ static int fib6_clean_node(struct fib6_walker_t *w)
 
 static void fib6_clean_tree(struct net *net, struct fib6_node *root,
 			    int (*func)(struct rt6_info *, void *arg),
-			    int prune, void *arg)
+			    bool prune, int sernum, void *arg)
 {
-	struct fib6_cleaner_t c;
+	struct fib6_cleaner c;
 
 	c.w.root = root;
 	c.w.func = fib6_clean_node;
@@ -1564,14 +1572,16 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root,
 	c.w.count = 0;
 	c.w.skip = 0;
 	c.func = func;
+	c.sernum = sernum;
 	c.arg = arg;
 	c.net = net;
 
 	fib6_walk(&c.w);
 }
 
-void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
-		    void *arg)
+static void __fib6_clean_all(struct net *net,
+			     int (*func)(struct rt6_info *, void *),
+			     int sernum, void *arg)
 {
 	struct fib6_table *table;
 	struct hlist_head *head;
@@ -1583,13 +1593,19 @@ void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
 		hlist_for_each_entry_rcu(table, head, tb6_hlist) {
 			write_lock_bh(&table->tb6_lock);
 			fib6_clean_tree(net, &table->tb6_root,
-					func, 0, arg);
+					func, false, sernum, arg);
 			write_unlock_bh(&table->tb6_lock);
 		}
 	}
 	rcu_read_unlock();
 }
 
+void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *),
+		    void *arg)
+{
+	__fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg);
+}
+
 static int fib6_prune_clone(struct rt6_info *rt, void *arg)
 {
 	if (rt->rt6i_flags & RTF_CACHE) {
@@ -1602,25 +1618,15 @@ static int fib6_prune_clone(struct rt6_info *rt, void *arg)
 
 static void fib6_prune_clones(struct net *net, struct fib6_node *fn)
 {
-	fib6_clean_tree(net, fn, fib6_prune_clone, 1, NULL);
-}
-
-static int fib6_update_sernum(struct rt6_info *rt, void *arg)
-{
-	__u32 sernum = *(__u32 *)arg;
-
-	if (rt->rt6i_node &&
-	    rt->rt6i_node->fn_sernum != sernum)
-		rt->rt6i_node->fn_sernum = sernum;
-
-	return 0;
+	fib6_clean_tree(net, fn, fib6_prune_clone, true,
+			FIB6_NO_SERNUM_CHANGE, NULL);
 }
 
 static void fib6_flush_trees(struct net *net)
 {
-	__u32 new_sernum = fib6_new_sernum();
+	int new_sernum = fib6_new_sernum(net);
 
-	fib6_clean_all(net, fib6_update_sernum, &new_sernum);
+	__fib6_clean_all(net, NULL, new_sernum, NULL);
 }
 
 /*
@@ -1828,10 +1834,10 @@ void fib6_gc_cleanup(void)
 
 struct ipv6_route_iter {
 	struct seq_net_private p;
-	struct fib6_walker_t w;
+	struct fib6_walker w;
 	loff_t skip;
 	struct fib6_table *tbl;
-	__u32 sernum;
+	int sernum;
 };
 
 static int ipv6_route_seq_show(struct seq_file *seq, void *v)
@@ -1859,7 +1865,7 @@ static int ipv6_route_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static int ipv6_route_yield(struct fib6_walker_t *w)
+static int ipv6_route_yield(struct fib6_walker *w)
 {
 	struct ipv6_route_iter *iter = w->args;
 
@@ -1980,7 +1986,7 @@ static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos)
 
 static bool ipv6_route_iter_active(struct ipv6_route_iter *iter)
 {
-	struct fib6_walker_t *w = &iter->w;
+	struct fib6_walker *w = &iter->w;
 	return w->node && !(w->state == FWS_U && w->node == w->root);
 }