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

Pull networking updates from David Miller:

 1) New offloading infrastructure and example 'rocker' driver for
    offloading of switching and routing to hardware.

    This work was done by a large group of dedicated individuals, not
    limited to: Scott Feldman, Jiri Pirko, Thomas Graf, John Fastabend,
    Jamal Hadi Salim, Andy Gospodarek, Florian Fainelli, Roopa Prabhu

 2) Start making the networking operate on IOV iterators instead of
    modifying iov objects in-situ during transfers.  Thanks to Al Viro
    and Herbert Xu.

 3) A set of new netlink interfaces for the TIPC stack, from Richard
    Alpe.

 4) Remove unnecessary looping during ipv6 routing lookups, from Martin
    KaFai Lau.

 5) Add PAUSE frame generation support to gianfar driver, from Matei
    Pavaluca.

 6) Allow for larger reordering levels in TCP, which are easily
    achievable in the real world right now, from Eric Dumazet.

 7) Add a variable of napi_schedule that doesn't need to disable cpu
    interrupts, from Eric Dumazet.

 8) Use a doubly linked list to optimize neigh_parms_release(), from
    Nicolas Dichtel.

 9) Various enhancements to the kernel BPF verifier, and allow eBPF
    programs to actually be attached to sockets.  From Alexei
    Starovoitov.

10) Support TSO/LSO in sunvnet driver, from David L Stevens.

11) Allow controlling ECN usage via routing metrics, from Florian
    Westphal.

12) Remote checksum offload, from Tom Herbert.

13) Add split-header receive, BQL, and xmit_more support to amd-xgbe
    driver, from Thomas Lendacky.

14) Add MPLS support to openvswitch, from Simon Horman.

15) Support wildcard tunnel endpoints in ipv6 tunnels, from Steffen
    Klassert.

16) Do gro flushes on a per-device basis using a timer, from Eric
    Dumazet.  This tries to resolve the conflicting goals between the
    desired handling of bulk vs.  RPC-like traffic.

17) Allow userspace to ask for the CPU upon what a packet was
    received/steered, via SO_INCOMING_CPU.  From Eric Dumazet.

18) Limit GSO packets to half the current congestion window, from Eric
    Dumazet.

19) Add a generic helper so that all drivers set their RSS keys in a
    consistent way, from Eric Dumazet.

20) Add xmit_more support to enic driver, from Govindarajulu
    Varadarajan.

21) Add VLAN packet scheduler action, from Jiri Pirko.

22) Support configurable RSS hash functions via ethtool, from Eyal
    Perry.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1820 commits)
  Fix race condition between vxlan_sock_add and vxlan_sock_release
  net/macb: fix compilation warning for print_hex_dump() called with skb->mac_header
  net/mlx4: Add support for A0 steering
  net/mlx4: Refactor QUERY_PORT
  net/mlx4_core: Add explicit error message when rule doesn't meet configuration
  net/mlx4: Add A0 hybrid steering
  net/mlx4: Add mlx4_bitmap zone allocator
  net/mlx4: Add a check if there are too many reserved QPs
  net/mlx4: Change QP allocation scheme
  net/mlx4_core: Use tasklet for user-space CQ completion events
  net/mlx4_core: Mask out host side virtualization features for guests
  net/mlx4_en: Set csum level for encapsulated packets
  be2net: Export tunnel offloads only when a VxLAN tunnel is created
  gianfar: Fix dma check map error when DMA_API_DEBUG is enabled
  cxgb4/csiostor: Don't use MASTER_MUST for fw_hello call
  net: fec: only enable mdio interrupt before phy device link up
  net: fec: clear all interrupt events to support i.MX6SX
  net: fec: reset fep link status in suspend function
  net: sock: fix access via invalid file descriptor
  net: introduce helper macro for_each_cmsghdr
  ...

1 files changed, 53 insertions, 41 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a318dd89b6d9..c91083156edb 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -772,23 +772,22 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
 }
 #endif
 
-#define BACKTRACK(__net, saddr)			\
-do { \
-	if (rt == __net->ipv6.ip6_null_entry) {	\
-		struct fib6_node *pn; \
-		while (1) { \
-			if (fn->fn_flags & RTN_TL_ROOT) \
-				goto out; \
-			pn = fn->parent; \
-			if (FIB6_SUBTREE(pn) && FIB6_SUBTREE(pn) != fn) \
-				fn = fib6_lookup(FIB6_SUBTREE(pn), NULL, saddr); \
-			else \
-				fn = pn; \
-			if (fn->fn_flags & RTN_RTINFO) \
-				goto restart; \
-		} \
-	} \
-} while (0)
+static struct fib6_node* fib6_backtrack(struct fib6_node *fn,
+					struct in6_addr *saddr)
+{
+	struct fib6_node *pn;
+	while (1) {
+		if (fn->fn_flags & RTN_TL_ROOT)
+			return NULL;
+		pn = fn->parent;
+		if (FIB6_SUBTREE(pn) && FIB6_SUBTREE(pn) != fn)
+			fn = fib6_lookup(FIB6_SUBTREE(pn), NULL, saddr);
+		else
+			fn = pn;
+		if (fn->fn_flags & RTN_RTINFO)
+			return fn;
+	}
+}
 
 static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 					     struct fib6_table *table,
@@ -804,8 +803,11 @@ restart:
 	rt = rt6_device_match(net, rt, &fl6->saddr, fl6->flowi6_oif, flags);
 	if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0)
 		rt = rt6_multipath_select(rt, fl6, fl6->flowi6_oif, flags);
-	BACKTRACK(net, &fl6->saddr);
-out:
+	if (rt == net->ipv6.ip6_null_entry) {
+		fn = fib6_backtrack(fn, &fl6->saddr);
+		if (fn)
+			goto restart;
+	}
 	dst_use(&rt->dst, jiffies);
 	read_unlock_bh(&table->tb6_lock);
 	return rt;
@@ -915,33 +917,48 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort,
 static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif,
 				      struct flowi6 *fl6, int flags)
 {
-	struct fib6_node *fn;
+	struct fib6_node *fn, *saved_fn;
 	struct rt6_info *rt, *nrt;
 	int strict = 0;
 	int attempts = 3;
 	int err;
-	int reachable = net->ipv6.devconf_all->forwarding ? 0 : RT6_LOOKUP_F_REACHABLE;
 
 	strict |= flags & RT6_LOOKUP_F_IFACE;
+	if (net->ipv6.devconf_all->forwarding == 0)
+		strict |= RT6_LOOKUP_F_REACHABLE;
 
-relookup:
+redo_fib6_lookup_lock:
 	read_lock_bh(&table->tb6_lock);
 
-restart_2:
 	fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
+	saved_fn = fn;
 
-restart:
-	rt = rt6_select(fn, oif, strict | reachable);
+redo_rt6_select:
+	rt = rt6_select(fn, oif, strict);
 	if (rt->rt6i_nsiblings)
-		rt = rt6_multipath_select(rt, fl6, oif, strict | reachable);
-	BACKTRACK(net, &fl6->saddr);
-	if (rt == net->ipv6.ip6_null_entry ||
-	    rt->rt6i_flags & RTF_CACHE)
-		goto out;
+		rt = rt6_multipath_select(rt, fl6, oif, strict);
+	if (rt == net->ipv6.ip6_null_entry) {
+		fn = fib6_backtrack(fn, &fl6->saddr);
+		if (fn)
+			goto redo_rt6_select;
+		else if (strict & RT6_LOOKUP_F_REACHABLE) {
+			/* also consider unreachable route */
+			strict &= ~RT6_LOOKUP_F_REACHABLE;
+			fn = saved_fn;
+			goto redo_rt6_select;
+		} else {
+			dst_hold(&rt->dst);
+			read_unlock_bh(&table->tb6_lock);
+			goto out2;
+		}
+	}
 
 	dst_hold(&rt->dst);
 	read_unlock_bh(&table->tb6_lock);
 
+	if (rt->rt6i_flags & RTF_CACHE)
+		goto out2;
+
 	if (!(rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY)))
 		nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr);
 	else if (!(rt->dst.flags & DST_HOST))
@@ -967,15 +984,8 @@ restart:
 	 * released someone could insert this route.  Relookup.
 	 */
 	ip6_rt_put(rt);
-	goto relookup;
+	goto redo_fib6_lookup_lock;
 
-out:
-	if (reachable) {
-		reachable = 0;
-		goto restart_2;
-	}
-	dst_hold(&rt->dst);
-	read_unlock_bh(&table->tb6_lock);
 out2:
 	rt->dst.lastuse = jiffies;
 	rt->dst.__use++;
@@ -1235,10 +1245,12 @@ restart:
 		rt = net->ipv6.ip6_null_entry;
 	else if (rt->dst.error) {
 		rt = net->ipv6.ip6_null_entry;
-		goto out;
+	} else if (rt == net->ipv6.ip6_null_entry) {
+		fn = fib6_backtrack(fn, &fl6->saddr);
+		if (fn)
+			goto restart;
 	}
-	BACKTRACK(net, &fl6->saddr);
-out:
+
 	dst_hold(&rt->dst);
 
 	read_unlock_bh(&table->tb6_lock);