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

Pull networking fixes from David Miller:

 1) Fix list tests in netfilter ingress support, from Florian Westphal.

 2) Fix reversal of input and output interfaces in ingress hook
    invocation, from Pablo Neira Ayuso.

 3) We have a use after free in r8169, caught by Dave Jones, fixed by
    Francois Romieu.

 4) Splice use-after-free fix in AF_UNIX frmo Hannes Frederic Sowa.

 5) Three ipv6 route handling bug fixes from Martin KaFai Lau:
    a) Don't create clone routes not managed by the fib6 tree
    b) Don't forget to check expiration of DST_NOCACHE routes.
    c) Handle rt->dst.from == NULL properly.

 6) Several AF_PACKET fixes wrt transport header setting and SKB
    protocol setting, from Daniel Borkmann.

 7) Fix thunder driver crash on shutdown, from Pavel Fedin.

 8) Several Mellanox driver fixes (max MTU calculations, use of correct
    DMA unmap in TX path, etc.) from Saeed Mahameed, Tariq Toukan, Doron
    Tsur, Achiad Shochat, Eran Ben Elisha, and Noa Osherovich.

 9) Several mv88e6060 DSA driver fixes (wrong bit definitions for
    certain registers, etc.) from Neil Armstrong.

10) Make sure to disable preemption while updating per-cpu stats of ip
    tunnels, from Jason A.  Donenfeld.

11) Various ARM64 bpf JIT fixes, from Yang Shi.

12) Flush icache properly in ARM JITs, from Daniel Borkmann.

13) Fix masking of RX and TX interrupts in ravb driver, from Masaru
    Nagai.

14) Fix netdev feature propagation for devices not implementing
    ->ndo_set_features().  From Nikolay Aleksandrov.

15) Big endian fix in vmxnet3 driver, from Shrikrishna Khare.

16) RAW socket code increments incorrect SNMP counters, fix from Ben
    Cartwright-Cox.

17) IPv6 multicast SNMP counters are bumped twice, fix from Neil Horman.

18) Fix handling of VLAN headers on stacked devices when REORDER is
    disabled.  From Vlad Yasevich.

19) Fix SKB leaks and use-after-free in ipvlan and macvlan drivers, from
    Sabrina Dubroca.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (83 commits)
  MAINTAINERS: Update Mellanox's Eth NIC driver entries
  net/core: revert "net: fix __netdev_update_features return.." and add comment
  af_unix: take receive queue lock while appending new skb
  rtnetlink: fix frame size warning in rtnl_fill_ifinfo
  net: use skb_clone to avoid alloc_pages failure.
  packet: Use PAGE_ALIGNED macro
  packet: Don't check frames_per_block against negative values
  net: phy: Use interrupts when available in NOLINK state
  phy: marvell: Add support for 88E1540 PHY
  arm64: bpf: make BPF prologue and epilogue align with ARM64 AAPCS
  macvlan: fix leak in macvlan_handle_frame
  ipvlan: fix use after free of skb
  ipvlan: fix leak in ipvlan_rcv_frame
  vlan: Do not put vlan headers back on bridge and macvlan ports
  vlan: Fix untag operations of stacked vlans with REORDER_HEADER off
  via-velocity: unconditionally drop frames with bad l2 length
  ipg: Remove ipg driver
  dl2k: Add support for IP1000A-based cards
  snmp: Remove duplicate OUTMCAST stat increment
  net: thunder: Check for driver data in nicvf_remove()
  ...

11 files changed, 90 insertions, 34 deletions

diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h
index e6982ac3200d..a57f0dfb6db7 100644
--- a/include/linux/marvell_phy.h
+++ b/include/linux/marvell_phy.h
@@ -16,6 +16,7 @@
 #define MARVELL_PHY_ID_88E1318S         0x01410e90
 #define MARVELL_PHY_ID_88E1116R         0x01410e40
 #define MARVELL_PHY_ID_88E1510          0x01410dd0
+#define MARVELL_PHY_ID_88E1540          0x01410eb0
 #define MARVELL_PHY_ID_88E3016          0x01410e60
 
 /* struct phy_device dev_flags definitions */
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index dd2097455a2e..1565324eb620 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -453,26 +453,28 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits {
         u8         lro_cap[0x1];
         u8         lro_psh_flag[0x1];
         u8         lro_time_stamp[0x1];
-        u8         reserved_0[0x6];
+        u8         reserved_0[0x3];
+        u8         self_lb_en_modifiable[0x1];
+        u8         reserved_1[0x2];
         u8         max_lso_cap[0x5];
-        u8         reserved_1[0x4];
+        u8         reserved_2[0x4];
         u8         rss_ind_tbl_cap[0x4];
-        u8         reserved_2[0x3];
+        u8         reserved_3[0x3];
         u8         tunnel_lso_const_out_ip_id[0x1];
-        u8         reserved_3[0x2];
+        u8         reserved_4[0x2];
         u8         tunnel_statless_gre[0x1];
         u8         tunnel_stateless_vxlan[0x1];
 
-        u8         reserved_4[0x20];
+        u8         reserved_5[0x20];
 
-        u8         reserved_5[0x10];
+        u8         reserved_6[0x10];
         u8         lro_min_mss_size[0x10];
 
-        u8         reserved_6[0x120];
+        u8         reserved_7[0x120];
 
         u8         lro_timer_supported_periods[4][0x20];
 
-        u8         reserved_7[0x600];
+        u8         reserved_8[0x600];
 };
 
 struct mlx5_ifc_roce_cap_bits {
@@ -4051,9 +4053,11 @@ struct mlx5_ifc_modify_tis_in_bits {
 };
 
 struct mlx5_ifc_modify_tir_bitmask_bits {
-        u8         reserved[0x20];
+        u8         reserved_0[0x20];
 
-        u8         reserved1[0x1f];
+        u8         reserved_1[0x1b];
+        u8         self_lb_en[0x1];
+        u8         reserved_2[0x3];
         u8         lro[0x1];
 };
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d20891465247..67bfac1abfc1 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2068,20 +2068,23 @@ struct pcpu_sw_netstats {
         struct u64_stats_sync   syncp;
 };
 
-#define netdev_alloc_pcpu_stats(type)                           \
-({                                                              \
-        typeof(type) __percpu *pcpu_stats = alloc_percpu(type); \
-        if (pcpu_stats) {                                       \
-                int __cpu;                                      \
-                for_each_possible_cpu(__cpu) {                  \
-                        typeof(type) *stat;                     \
-                        stat = per_cpu_ptr(pcpu_stats, __cpu);  \
-                        u64_stats_init(&stat->syncp);           \
-                }                                               \
-        }                                                       \
-        pcpu_stats;                                             \
+#define __netdev_alloc_pcpu_stats(type, gfp)                            \
+({                                                                      \
+        typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\
+        if (pcpu_stats) {                                               \
+                int __cpu;                                              \
+                for_each_possible_cpu(__cpu) {                          \
+                        typeof(type) *stat;                             \
+                        stat = per_cpu_ptr(pcpu_stats, __cpu);          \
+                        u64_stats_init(&stat->syncp);                   \
+                }                                                       \
+        }                                                               \
+        pcpu_stats;                                                     \
 })
 
+#define netdev_alloc_pcpu_stats(type)                                   \
+        __netdev_alloc_pcpu_stats(type, GFP_KERNEL);
+
 #include <linux/notifier.h>
 
 /* netdevice notifier chain. Please remember to update the rtnetlink
@@ -3854,6 +3857,11 @@ static inline bool netif_is_bridge_master(const struct net_device *dev)
         return dev->priv_flags & IFF_EBRIDGE;
 }
 
+static inline bool netif_is_bridge_port(const struct net_device *dev)
+{
+        return dev->priv_flags & IFF_BRIDGE_PORT;
+}
+
 static inline bool netif_is_ovs_master(const struct net_device *dev)
 {
         return dev->priv_flags & IFF_OPENVSWITCH;
diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index 48bb01edcf30..0e1f433cc4b7 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -421,7 +421,7 @@ extern void ip_set_free(void *members);
 extern int ip_set_get_ipaddr4(struct nlattr *nla,  __be32 *ipaddr);
 extern int ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr);
 extern size_t ip_set_elem_len(struct ip_set *set, struct nlattr *tb[],
-                              size_t len);
+                              size_t len, size_t align);
 extern int ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[],
                                  struct ip_set_ext *ext);
 
diff --git a/include/linux/netfilter_ingress.h b/include/linux/netfilter_ingress.h
index 187feabe557c..5fcd375ef175 100644
--- a/include/linux/netfilter_ingress.h
+++ b/include/linux/netfilter_ingress.h
@@ -5,10 +5,13 @@
 #include <linux/netdevice.h>
 
 #ifdef CONFIG_NETFILTER_INGRESS
-static inline int nf_hook_ingress_active(struct sk_buff *skb)
+static inline bool nf_hook_ingress_active(const struct sk_buff *skb)
 {
-        return nf_hook_list_active(&skb->dev->nf_hooks_ingress,
-                                   NFPROTO_NETDEV, NF_NETDEV_INGRESS);
+#ifdef HAVE_JUMP_LABEL
+        if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_INGRESS]))
+                return false;
+#endif
+        return !list_empty(&skb->dev->nf_hooks_ingress);
 }
 
 static inline int nf_hook_ingress(struct sk_buff *skb)
@@ -16,8 +19,8 @@ static inline int nf_hook_ingress(struct sk_buff *skb)
         struct nf_hook_state state;
 
         nf_hook_state_init(&state, &skb->dev->nf_hooks_ingress,
-                           NF_NETDEV_INGRESS, INT_MIN, NFPROTO_NETDEV, NULL,
-                           skb->dev, NULL, dev_net(skb->dev), NULL);
+                           NF_NETDEV_INGRESS, INT_MIN, NFPROTO_NETDEV,
+                           skb->dev, NULL, NULL, dev_net(skb->dev), NULL);
         return nf_hook_slow(skb, &state);
 }
 
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index aaf9700fc9e5..fb961a576abe 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -167,7 +167,8 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout)
 
 static inline u32 rt6_get_cookie(const struct rt6_info *rt)
 {
-        if (rt->rt6i_flags & RTF_PCPU || unlikely(rt->dst.flags & DST_NOCACHE))
+        if (rt->rt6i_flags & RTF_PCPU ||
+            (unlikely(rt->dst.flags & DST_NOCACHE) && rt->dst.from))
                 rt = (struct rt6_info *)(rt->dst.from);
 
         return rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index aaee6fa02cf1..ff788b665277 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -90,11 +90,12 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
         err = ip6_local_out(dev_net(skb_dst(skb)->dev), sk, skb);
 
         if (net_xmit_eval(err) == 0) {
-                struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
+                struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats);
                 u64_stats_update_begin(&tstats->syncp);
                 tstats->tx_bytes += pkt_len;
                 tstats->tx_packets++;
                 u64_stats_update_end(&tstats->syncp);
+                put_cpu_ptr(tstats);
         } else {
                 stats->tx_errors++;
                 stats->tx_aborted_errors++;
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index f6dafec9102c..62a750a6a8f8 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -287,12 +287,13 @@ static inline void iptunnel_xmit_stats(int err,
                                        struct pcpu_sw_netstats __percpu *stats)
 {
         if (err > 0) {
-                struct pcpu_sw_netstats *tstats = this_cpu_ptr(stats);
+                struct pcpu_sw_netstats *tstats = get_cpu_ptr(stats);
 
                 u64_stats_update_begin(&tstats->syncp);
                 tstats->tx_bytes += err;
                 tstats->tx_packets++;
                 u64_stats_update_end(&tstats->syncp);
+                put_cpu_ptr(tstats);
         } else if (err < 0) {
                 err_stats->tx_errors++;
                 err_stats->tx_aborted_errors++;
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index c9149cc0a02d..4bd7508bedc9 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -618,6 +618,8 @@ struct nft_expr_ops {
         void                            (*eval)(const struct nft_expr *expr,
                                                 struct nft_regs *regs,
                                                 const struct nft_pktinfo *pkt);
+        int                             (*clone)(struct nft_expr *dst,
+                                                 const struct nft_expr *src);
         unsigned int                    size;
 
         int                             (*init)(const struct nft_ctx *ctx,
@@ -660,10 +662,20 @@ void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr);
 int nft_expr_dump(struct sk_buff *skb, unsigned int attr,
                   const struct nft_expr *expr);
 
-static inline void nft_expr_clone(struct nft_expr *dst, struct nft_expr *src)
+static inline int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src)
 {
+        int err;
+
         __module_get(src->ops->type->owner);
-        memcpy(dst, src, src->ops->size);
+        if (src->ops->clone) {
+                dst->ops = src->ops;
+                err = src->ops->clone(dst, src);
+                if (err < 0)
+                        return err;
+        } else {
+                memcpy(dst, src, src->ops->size);
+        }
+        return 0;
 }
 
 /**
diff --git a/include/net/sock.h b/include/net/sock.h
index bbf7c2cf15b4..7f89e4ba18d1 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2226,6 +2226,31 @@ static inline bool sk_listener(const struct sock *sk)
         return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV);
 }
 
+/**
+ * sk_state_load - read sk->sk_state for lockless contexts
+ * @sk: socket pointer
+ *
+ * Paired with sk_state_store(). Used in places we do not hold socket lock :
+ * tcp_diag_get_info(), tcp_get_info(), tcp_poll(), get_tcp4_sock() ...
+ */
+static inline int sk_state_load(const struct sock *sk)
+{
+        return smp_load_acquire(&sk->sk_state);
+}
+
+/**
+ * sk_state_store - update sk->sk_state
+ * @sk: socket pointer
+ * @newstate: new state
+ *
+ * Paired with sk_state_load(). Should be used in contexts where
+ * state change might impact lockless readers.
+ */
+static inline void sk_state_store(struct sock *sk, int newstate)
+{
+        smp_store_release(&sk->sk_state, newstate);
+}
+
 void sock_enable_timestamp(struct sock *sk, int flag);
 int sock_get_timestamp(struct sock *, struct timeval __user *);
 int sock_get_timestampns(struct sock *, struct timespec __user *);
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index bc865e244efe..1d22ce9f352e 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -323,7 +323,7 @@ static inline int switchdev_port_fdb_dump(struct sk_buff *skb,
                                           struct net_device *filter_dev,
                                           int idx)
 {
-        return -EOPNOTSUPP;
+       return idx;
 }
 
 static inline void switchdev_port_fwd_mark_set(struct net_device *dev,