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, 135 insertions, 9 deletions

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index fdde51f..4c4e457 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -349,12 +349,39 @@ static inline unsigned int idx_hash(struct net *net, u32 index)
 	return __idx_hash(index, net->xfrm.policy_idx_hmask);
 }
 
+/* calculate policy hash thresholds */
+static void __get_hash_thresh(struct net *net,
+			      unsigned short family, int dir,
+			      u8 *dbits, u8 *sbits)
+{
+	switch (family) {
+	case AF_INET:
+		*dbits = net->xfrm.policy_bydst[dir].dbits4;
+		*sbits = net->xfrm.policy_bydst[dir].sbits4;
+		break;
+
+	case AF_INET6:
+		*dbits = net->xfrm.policy_bydst[dir].dbits6;
+		*sbits = net->xfrm.policy_bydst[dir].sbits6;
+		break;
+
+	default:
+		*dbits = 0;
+		*sbits = 0;
+	}
+}
+
 static struct hlist_head *policy_hash_bysel(struct net *net,
 					    const struct xfrm_selector *sel,
 					    unsigned short family, int dir)
 {
 	unsigned int hmask = net->xfrm.policy_bydst[dir].hmask;
-	unsigned int hash = __sel_hash(sel, family, hmask);
+	unsigned int hash;
+	u8 dbits;
+	u8 sbits;
+
+	__get_hash_thresh(net, family, dir, &dbits, &sbits);
+	hash = __sel_hash(sel, family, hmask, dbits, sbits);
 
 	return (hash == hmask + 1 ?
 		&net->xfrm.policy_inexact[dir] :
@@ -367,25 +394,35 @@ static struct hlist_head *policy_hash_direct(struct net *net,
 					     unsigned short family, int dir)
 {
 	unsigned int hmask = net->xfrm.policy_bydst[dir].hmask;
-	unsigned int hash = __addr_hash(daddr, saddr, family, hmask);
+	unsigned int hash;
+	u8 dbits;
+	u8 sbits;
+
+	__get_hash_thresh(net, family, dir, &dbits, &sbits);
+	hash = __addr_hash(daddr, saddr, family, hmask, dbits, sbits);
 
 	return net->xfrm.policy_bydst[dir].table + hash;
 }
 
-static void xfrm_dst_hash_transfer(struct hlist_head *list,
+static void xfrm_dst_hash_transfer(struct net *net,
+				   struct hlist_head *list,
 				   struct hlist_head *ndsttable,
-				   unsigned int nhashmask)
+				   unsigned int nhashmask,
+				   int dir)
 {
 	struct hlist_node *tmp, *entry0 = NULL;
 	struct xfrm_policy *pol;
 	unsigned int h0 = 0;
+	u8 dbits;
+	u8 sbits;
 
 redo:
 	hlist_for_each_entry_safe(pol, tmp, list, bydst) {
 		unsigned int h;
 
+		__get_hash_thresh(net, pol->family, dir, &dbits, &sbits);
 		h = __addr_hash(&pol->selector.daddr, &pol->selector.saddr,
-				pol->family, nhashmask);
+				pol->family, nhashmask, dbits, sbits);
 		if (!entry0) {
 			hlist_del(&pol->bydst);
 			hlist_add_head(&pol->bydst, ndsttable+h);
@@ -439,7 +476,7 @@ static void xfrm_bydst_resize(struct net *net, int dir)
 	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 
 	for (i = hmask; i >= 0; i--)
-		xfrm_dst_hash_transfer(odst + i, ndst, nhashmask);
+		xfrm_dst_hash_transfer(net, odst + i, ndst, nhashmask, dir);
 
 	net->xfrm.policy_bydst[dir].table = ndst;
 	net->xfrm.policy_bydst[dir].hmask = nhashmask;
@@ -534,6 +571,86 @@ static void xfrm_hash_resize(struct work_struct *work)
 	mutex_unlock(&hash_resize_mutex);
 }
 
+static void xfrm_hash_rebuild(struct work_struct *work)
+{
+	struct net *net = container_of(work, struct net,
+				       xfrm.policy_hthresh.work);
+	unsigned int hmask;
+	struct xfrm_policy *pol;
+	struct xfrm_policy *policy;
+	struct hlist_head *chain;
+	struct hlist_head *odst;
+	struct hlist_node *newpos;
+	int i;
+	int dir;
+	unsigned seq;
+	u8 lbits4, rbits4, lbits6, rbits6;
+
+	mutex_lock(&hash_resize_mutex);
+
+	/* read selector prefixlen thresholds */
+	do {
+		seq = read_seqbegin(&net->xfrm.policy_hthresh.lock);
+
+		lbits4 = net->xfrm.policy_hthresh.lbits4;
+		rbits4 = net->xfrm.policy_hthresh.rbits4;
+		lbits6 = net->xfrm.policy_hthresh.lbits6;
+		rbits6 = net->xfrm.policy_hthresh.rbits6;
+	} while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq));
+
+	write_lock_bh(&net->xfrm.xfrm_policy_lock);
+
+	/* reset the bydst and inexact table in all directions */
+	for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) {
+		INIT_HLIST_HEAD(&net->xfrm.policy_inexact[dir]);
+		hmask = net->xfrm.policy_bydst[dir].hmask;
+		odst = net->xfrm.policy_bydst[dir].table;
+		for (i = hmask; i >= 0; i--)
+			INIT_HLIST_HEAD(odst + i);
+		if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) {
+			/* dir out => dst = remote, src = local */
+			net->xfrm.policy_bydst[dir].dbits4 = rbits4;
+			net->xfrm.policy_bydst[dir].sbits4 = lbits4;
+			net->xfrm.policy_bydst[dir].dbits6 = rbits6;
+			net->xfrm.policy_bydst[dir].sbits6 = lbits6;
+		} else {
+			/* dir in/fwd => dst = local, src = remote */
+			net->xfrm.policy_bydst[dir].dbits4 = lbits4;
+			net->xfrm.policy_bydst[dir].sbits4 = rbits4;
+			net->xfrm.policy_bydst[dir].dbits6 = lbits6;
+			net->xfrm.policy_bydst[dir].sbits6 = rbits6;
+		}
+	}
+
+	/* re-insert all policies by order of creation */
+	list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) {
+		newpos = NULL;
+		chain = policy_hash_bysel(net, &policy->selector,
+					  policy->family,
+					  xfrm_policy_id2dir(policy->index));
+		hlist_for_each_entry(pol, chain, bydst) {
+			if (policy->priority >= pol->priority)
+				newpos = &pol->bydst;
+			else
+				break;
+		}
+		if (newpos)
+			hlist_add_behind(&policy->bydst, newpos);
+		else
+			hlist_add_head(&policy->bydst, chain);
+	}
+
+	write_unlock_bh(&net->xfrm.xfrm_policy_lock);
+
+	mutex_unlock(&hash_resize_mutex);
+}
+
+void xfrm_policy_hash_rebuild(struct net *net)
+{
+	schedule_work(&net->xfrm.policy_hthresh.work);
+}
+EXPORT_SYMBOL(xfrm_policy_hash_rebuild);
+
 /* Generate new index... KAME seems to generate them ordered by cost
  * of an absolute inpredictability of ordering of rules. This will not pass. */
 static u32 xfrm_gen_index(struct net *net, int dir, u32 index)
@@ -1844,10 +1961,8 @@ static int xdst_queue_output(struct sock *sk, struct sk_buff *skb)
 	struct xfrm_dst *xdst = (struct xfrm_dst *) dst;
 	struct xfrm_policy *pol = xdst->pols[0];
 	struct xfrm_policy_queue *pq = &pol->polq;
-	const struct sk_buff *fclone = skb + 1;
 
-	if (unlikely(skb->fclone == SKB_FCLONE_ORIG &&
-		     fclone->fclone == SKB_FCLONE_CLONE)) {
+	if (unlikely(skb_fclone_busy(skb))) {
 		kfree_skb(skb);
 		return 0;
 	}
@@ -2862,10 +2977,21 @@ static int __net_init xfrm_policy_init(struct net *net)
 		if (!htab->table)
 			goto out_bydst;
 		htab->hmask = hmask;
+		htab->dbits4 = 32;
+		htab->sbits4 = 32;
+		htab->dbits6 = 128;
+		htab->sbits6 = 128;
 	}
+	net->xfrm.policy_hthresh.lbits4 = 32;
+	net->xfrm.policy_hthresh.rbits4 = 32;
+	net->xfrm.policy_hthresh.lbits6 = 128;
+	net->xfrm.policy_hthresh.rbits6 = 128;
+
+	seqlock_init(&net->xfrm.policy_hthresh.lock);
 
 	INIT_LIST_HEAD(&net->xfrm.policy_all);
 	INIT_WORK(&net->xfrm.policy_hash_work, xfrm_hash_resize);
+	INIT_WORK(&net->xfrm.policy_hthresh.work, xfrm_hash_rebuild);
 	if (net_eq(net, &init_net))
 		register_netdevice_notifier(&xfrm_dev_notifier);
 	return 0;