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

Fun set of conflict resolutions here...

For the mac80211 stuff, these were fortunately just parallel
adds.  Trivially resolved.

In drivers/net/phy/phy.c we had a bug fix in 'net' that moved the
function phy_disable_interrupts() earlier in the file, whilst in
'net-next' the phy_error() call from this function was removed.

In net/ipv4/xfrm4_policy.c, David Ahern's changes to remove the
'rt_table_id' member of rtable collided with a bug fix in 'net' that
added a new struct member "rt_mtu_locked" which needs to be copied
over here.

The mlxsw driver conflict consisted of net-next separating
the span code and definitions into separate files, whilst
a 'net' bug fix made some changes to that moved code.

The mlx5 infiniband conflict resolution was quite non-trivial,
the RDMA tree's merge commit was used as a guide here, and
here are their notes:

====================

    Due to bug fixes found by the syzkaller bot and taken into the for-rc
    branch after development for the 4.17 merge window had already started
    being taken into the for-next branch, there were fairly non-trivial
    merge issues that would need to be resolved between the for-rc branch
    and the for-next branch.  This merge resolves those conflicts and
    provides a unified base upon which ongoing development for 4.17 can
    be based.

    Conflicts:
            drivers/infiniband/hw/mlx5/main.c - Commit 42cea83f9524
            (IB/mlx5: Fix cleanup order on unload) added to for-rc and
            commit b5ca15ad7e61 (IB/mlx5: Add proper representors support)
            add as part of the devel cycle both needed to modify the
            init/de-init functions used by mlx5.  To support the new
            representors, the new functions added by the cleanup patch
            needed to be made non-static, and the init/de-init list
            added by the representors patch needed to be modified to
            match the init/de-init list changes made by the cleanup
            patch.
    Updates:
            drivers/infiniband/hw/mlx5/mlx5_ib.h - Update function
            prototypes added by representors patch to reflect new function
            names as changed by cleanup patch
            drivers/infiniband/hw/mlx5/ib_rep.c - Update init/de-init
            stage list to match new order from cleanup patch
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 44 insertions, 19 deletions

diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index a383f299ce24..4e5bc4b2f14e 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -53,8 +53,7 @@ static DEFINE_MUTEX(inet_diag_table_mutex);
 static const struct inet_diag_handler *inet_diag_lock_handler(int proto)
 {
         if (!inet_diag_table[proto])
-                request_module("net-pf-%d-proto-%d-type-%d-%d", PF_NETLINK,
-                               NETLINK_SOCK_DIAG, AF_INET, proto);
+                sock_load_diag_module(AF_INET, proto);
 
         mutex_lock(&inet_diag_table_mutex);
         if (!inet_diag_table[proto])
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 26a3d0315728..e8ec28999f5c 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -119,6 +119,9 @@ out:
 
 static bool inet_fragq_should_evict(const struct inet_frag_queue *q)
 {
+        if (!hlist_unhashed(&q->list_evictor))
+                return false;
+
         return q->net->low_thresh == 0 ||
                frag_mem_limit(q->net) >= q->net->low_thresh;
 }
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index e74ee837b300..4ac5728689f5 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -635,6 +635,7 @@ static inline u32 fnhe_hashfun(__be32 daddr)
 static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe)
 {
         rt->rt_pmtu = fnhe->fnhe_pmtu;
+        rt->rt_mtu_locked = fnhe->fnhe_mtu_locked;
         rt->dst.expires = fnhe->fnhe_expires;
 
         if (fnhe->fnhe_gw) {
@@ -645,7 +646,7 @@ static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnh
 }
 
 static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
-                                  u32 pmtu, unsigned long expires)
+                                  u32 pmtu, bool lock, unsigned long expires)
 {
         struct fnhe_hash_bucket *hash;
         struct fib_nh_exception *fnhe;
@@ -682,8 +683,10 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
                         fnhe->fnhe_genid = genid;
                 if (gw)
                         fnhe->fnhe_gw = gw;
-                if (pmtu)
+                if (pmtu) {
                         fnhe->fnhe_pmtu = pmtu;
+                        fnhe->fnhe_mtu_locked = lock;
+                }
                 fnhe->fnhe_expires = max(1UL, expires);
                 /* Update all cached dsts too */
                 rt = rcu_dereference(fnhe->fnhe_rth_input);
@@ -707,6 +710,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
                 fnhe->fnhe_daddr = daddr;
                 fnhe->fnhe_gw = gw;
                 fnhe->fnhe_pmtu = pmtu;
+                fnhe->fnhe_mtu_locked = lock;
                 fnhe->fnhe_expires = expires;
 
                 /* Exception created; mark the cached routes for the nexthop
@@ -788,7 +792,8 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
                                 struct fib_nh *nh = &FIB_RES_NH(res);
 
                                 update_or_create_fnhe(nh, fl4->daddr, new_gw,
-                                                0, jiffies + ip_rt_gc_timeout);
+                                                0, false,
+                                                jiffies + ip_rt_gc_timeout);
                         }
                         if (kill_route)
                                 rt->dst.obsolete = DST_OBSOLETE_KILL;
@@ -1010,15 +1015,18 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 {
         struct dst_entry *dst = &rt->dst;
         struct fib_result res;
+        bool lock = false;
 
-        if (dst_metric_locked(dst, RTAX_MTU))
+        if (ip_mtu_locked(dst))
                 return;
 
         if (ipv4_mtu(dst) < mtu)
                 return;
 
-        if (mtu < ip_rt_min_pmtu)
+        if (mtu < ip_rt_min_pmtu) {
+                lock = true;
                 mtu = ip_rt_min_pmtu;
+        }
 
         if (rt->rt_pmtu == mtu &&
             time_before(jiffies, dst->expires - ip_rt_mtu_expires / 2))
@@ -1028,7 +1036,7 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
         if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) {
                 struct fib_nh *nh = &FIB_RES_NH(res);
 
-                update_or_create_fnhe(nh, fl4->daddr, 0, mtu,
+                update_or_create_fnhe(nh, fl4->daddr, 0, mtu, lock,
                                       jiffies + ip_rt_mtu_expires);
         }
         rcu_read_unlock();
@@ -1281,7 +1289,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
 
         mtu = READ_ONCE(dst->dev->mtu);
 
-        if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
+        if (unlikely(ip_mtu_locked(dst))) {
                 if (rt->rt_uses_gateway && mtu > 576)
                         mtu = 576;
         }
@@ -1394,7 +1402,7 @@ struct uncached_list {
 
 static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list);
 
-static void rt_add_uncached_list(struct rtable *rt)
+void rt_add_uncached_list(struct rtable *rt)
 {
         struct uncached_list *ul = raw_cpu_ptr(&rt_uncached_list);
 
@@ -1405,14 +1413,8 @@ static void rt_add_uncached_list(struct rtable *rt)
         spin_unlock_bh(&ul->lock);
 }
 
-static void ipv4_dst_destroy(struct dst_entry *dst)
+void rt_del_uncached_list(struct rtable *rt)
 {
-        struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst);
-        struct rtable *rt = (struct rtable *) dst;
-
-        if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt))
-                kfree(p);
-
         if (!list_empty(&rt->rt_uncached)) {
                 struct uncached_list *ul = rt->rt_uncached_list;
 
@@ -1422,6 +1424,17 @@ static void ipv4_dst_destroy(struct dst_entry *dst)
         }
 }
 
+static void ipv4_dst_destroy(struct dst_entry *dst)
+{
+        struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst);
+        struct rtable *rt = (struct rtable *)dst;
+
+        if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt))
+                kfree(p);
+
+        rt_del_uncached_list(rt);
+}
+
 void rt_flush_dev(struct net_device *dev)
 {
         struct net *net = dev_net(dev);
@@ -1517,6 +1530,7 @@ struct rtable *rt_dst_alloc(struct net_device *dev,
                 rt->rt_is_input = 0;
                 rt->rt_iif = 0;
                 rt->rt_pmtu = 0;
+                rt->rt_mtu_locked = 0;
                 rt->rt_gateway = 0;
                 rt->rt_uses_gateway = 0;
                 INIT_LIST_HEAD(&rt->rt_uncached);
@@ -2533,6 +2547,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
                 rt->rt_is_input = ort->rt_is_input;
                 rt->rt_iif = ort->rt_iif;
                 rt->rt_pmtu = ort->rt_pmtu;
+                rt->rt_mtu_locked = ort->rt_mtu_locked;
 
                 rt->rt_genid = rt_genid_ipv4(net);
                 rt->rt_flags = ort->rt_flags;
@@ -2635,6 +2650,8 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src, u32 table_id,
         memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics));
         if (rt->rt_pmtu && expires)
                 metrics[RTAX_MTU - 1] = rt->rt_pmtu;
+        if (rt->rt_mtu_locked && expires)
+                metrics[RTAX_LOCK - 1] |= BIT(RTAX_MTU);
         if (rtnetlink_put_metrics(skb, metrics) < 0)
                 goto nla_put_failure;
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index d763fae1b574..0c31be306572 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3545,6 +3545,7 @@ int tcp_abort(struct sock *sk, int err)
 
         bh_unlock_sock(sk);
         local_bh_enable();
+        tcp_write_queue_purge(sk);
         release_sock(sk);
         return 0;
 }
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 71fc60f1b326..f7d944855f8e 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -34,6 +34,7 @@ static void tcp_write_err(struct sock *sk)
         sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT;
         sk->sk_error_report(sk);
 
+        tcp_write_queue_purge(sk);
         tcp_done(sk);
         __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT);
 }
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index 63faeee989a9..2a9764bd1719 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -92,7 +92,8 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
 
         skb_reset_network_header(skb);
         skb_mac_header_rebuild(skb);
-        eth_hdr(skb)->h_proto = skb->protocol;
+        if (skb->mac_len)
+                eth_hdr(skb)->h_proto = skb->protocol;
 
         err = 0;
 
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 0c752dc3f93b..6c76a757fa4a 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -100,7 +100,9 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
         xdst->u.rt.rt_gateway = rt->rt_gateway;
         xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway;
         xdst->u.rt.rt_pmtu = rt->rt_pmtu;
+        xdst->u.rt.rt_mtu_locked = rt->rt_mtu_locked;
         INIT_LIST_HEAD(&xdst->u.rt.rt_uncached);
+        rt_add_uncached_list(&xdst->u.rt);
 
         return 0;
 }
@@ -240,7 +242,8 @@ static void xfrm4_dst_destroy(struct dst_entry *dst)
         struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 
         dst_destroy_metrics_generic(dst);
-
+        if (xdst->u.rt.rt_uncached_list)
+                rt_del_uncached_list(&xdst->u.rt);
         xfrm_dst_destroy(xdst);
 }