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

Pull networking updates from David Miller:

 1) New ipset extensions for matching on destination MAC addresses, from
    Stefano Brivio.

 2) Add ipv4 ttl and tos, plus ipv6 flow label and hop limit offloads to
    nfp driver. From Stefano Brivio.

 3) Implement GRO for plain UDP sockets, from Paolo Abeni.

 4) Lots of work from Michał Mirosław to eliminate the VLAN_TAG_PRESENT
    bit so that we could support the entire vlan_tci value.

 5) Rework the IPSEC policy lookups to better optimize more usecases,
    from Florian Westphal.

 6) Infrastructure changes eliminating direct manipulation of SKB lists
    wherever possible, and to always use the appropriate SKB list
    helpers. This work is still ongoing...

 7) Lots of PHY driver and state machine improvements and
    simplifications, from Heiner Kallweit.

 8) Various TSO deferral refinements, from Eric Dumazet.

 9) Add ntuple filter support to aquantia driver, from Dmitry Bogdanov.

10) Batch dropping of XDP packets in tuntap, from Jason Wang.

11) Lots of cleanups and improvements to the r8169 driver from Heiner
    Kallweit, including support for ->xmit_more. This driver has been
    getting some much needed love since he started working on it.

12) Lots of new forwarding selftests from Petr Machata.

13) Enable VXLAN learning in mlxsw driver, from Ido Schimmel.

14) Packed ring support for virtio, from Tiwei Bie.

15) Add new Aquantia AQtion USB driver, from Dmitry Bezrukov.

16) Add XDP support to dpaa2-eth driver, from Ioana Ciocoi Radulescu.

17) Implement coalescing on TCP backlog queue, from Eric Dumazet.

18) Implement carrier change in tun driver, from Nicolas Dichtel.

19) Support msg_zerocopy in UDP, from Willem de Bruijn.

20) Significantly improve garbage collection of neighbor objects when
    the table has many PERMANENT entries, from David Ahern.

21) Remove egdev usage from nfp and mlx5, and remove the facility
    completely from the tree as it no longer has any users. From Oz
    Shlomo and others.

22) Add a NETDEV_PRE_CHANGEADDR so that drivers can veto the change and
    therefore abort the operation before the commit phase (which is the
    NETDEV_CHANGEADDR event). From Petr Machata.

23) Add indirect call wrappers to avoid retpoline overhead, and use them
    in the GRO code paths. From Paolo Abeni.

24) Add support for netlink FDB get operations, from Roopa Prabhu.

25) Support bloom filter in mlxsw driver, from Nir Dotan.

26) Add SKB extension infrastructure. This consolidates the handling of
    the auxiliary SKB data used by IPSEC and bridge netfilter, and is
    designed to support the needs to MPTCP which could be integrated in
    the future.

27) Lots of XDP TX optimizations in mlx5 from Tariq Toukan.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1845 commits)
  net: dccp: fix kernel crash on module load
  drivers/net: appletalk/cops: remove redundant if statement and mask
  bnx2x: Fix NULL pointer dereference in bnx2x_del_all_vlans() on some hw
  net/net_namespace: Check the return value of register_pernet_subsys()
  net/netlink_compat: Fix a missing check of nla_parse_nested
  ieee802154: lowpan_header_create check must check daddr
  net/mlx4_core: drop useless LIST_HEAD
  mlxsw: spectrum: drop useless LIST_HEAD
  net/mlx5e: drop useless LIST_HEAD
  iptunnel: Set tun_flags in the iptunnel_metadata_reply from src
  net/mlx5e: fix semicolon.cocci warnings
  staging: octeon: fix build failure with XFRM enabled
  net: Revert recent Spectre-v1 patches.
  can: af_can: Fix Spectre v1 vulnerability
  packet: validate address length if non-zero
  nfc: af_nfc: Fix Spectre v1 vulnerability
  phonet: af_phonet: Fix Spectre v1 vulnerability
  net: core: Fix Spectre v1 vulnerability
  net: minor cleanup in skb_ext_add()
  net: drop the unused helper skb_ext_get()
  ...

1 files changed, 154 insertions, 16 deletions

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 208d940464d7..dad04e710493 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -55,6 +55,8 @@ struct fl_flow_key {
 	struct flow_dissector_key_ip ip;
 	struct flow_dissector_key_ip enc_ip;
 	struct flow_dissector_key_enc_opts enc_opts;
+	struct flow_dissector_key_ports tp_min;
+	struct flow_dissector_key_ports tp_max;
 } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
 
 struct fl_flow_mask_range {
@@ -65,6 +67,7 @@ struct fl_flow_mask_range {
 struct fl_flow_mask {
 	struct fl_flow_key key;
 	struct fl_flow_mask_range range;
+	u32 flags;
 	struct rhash_head ht_node;
 	struct rhashtable ht;
 	struct rhashtable_params filter_ht_params;
@@ -179,13 +182,89 @@ static void fl_clear_masked_range(struct fl_flow_key *key,
 	memset(fl_key_get_start(key, mask), 0, fl_mask_range(mask));
 }
 
-static struct cls_fl_filter *fl_lookup(struct fl_flow_mask *mask,
-				       struct fl_flow_key *mkey)
+static bool fl_range_port_dst_cmp(struct cls_fl_filter *filter,
+				  struct fl_flow_key *key,
+				  struct fl_flow_key *mkey)
+{
+	__be16 min_mask, max_mask, min_val, max_val;
+
+	min_mask = htons(filter->mask->key.tp_min.dst);
+	max_mask = htons(filter->mask->key.tp_max.dst);
+	min_val = htons(filter->key.tp_min.dst);
+	max_val = htons(filter->key.tp_max.dst);
+
+	if (min_mask && max_mask) {
+		if (htons(key->tp.dst) < min_val ||
+		    htons(key->tp.dst) > max_val)
+			return false;
+
+		/* skb does not have min and max values */
+		mkey->tp_min.dst = filter->mkey.tp_min.dst;
+		mkey->tp_max.dst = filter->mkey.tp_max.dst;
+	}
+	return true;
+}
+
+static bool fl_range_port_src_cmp(struct cls_fl_filter *filter,
+				  struct fl_flow_key *key,
+				  struct fl_flow_key *mkey)
+{
+	__be16 min_mask, max_mask, min_val, max_val;
+
+	min_mask = htons(filter->mask->key.tp_min.src);
+	max_mask = htons(filter->mask->key.tp_max.src);
+	min_val = htons(filter->key.tp_min.src);
+	max_val = htons(filter->key.tp_max.src);
+
+	if (min_mask && max_mask) {
+		if (htons(key->tp.src) < min_val ||
+		    htons(key->tp.src) > max_val)
+			return false;
+
+		/* skb does not have min and max values */
+		mkey->tp_min.src = filter->mkey.tp_min.src;
+		mkey->tp_max.src = filter->mkey.tp_max.src;
+	}
+	return true;
+}
+
+static struct cls_fl_filter *__fl_lookup(struct fl_flow_mask *mask,
+					 struct fl_flow_key *mkey)
 {
 	return rhashtable_lookup_fast(&mask->ht, fl_key_get_start(mkey, mask),
 				      mask->filter_ht_params);
 }
 
+static struct cls_fl_filter *fl_lookup_range(struct fl_flow_mask *mask,
+					     struct fl_flow_key *mkey,
+					     struct fl_flow_key *key)
+{
+	struct cls_fl_filter *filter, *f;
+
+	list_for_each_entry_rcu(filter, &mask->filters, list) {
+		if (!fl_range_port_dst_cmp(filter, key, mkey))
+			continue;
+
+		if (!fl_range_port_src_cmp(filter, key, mkey))
+			continue;
+
+		f = __fl_lookup(mask, mkey);
+		if (f)
+			return f;
+	}
+	return NULL;
+}
+
+static struct cls_fl_filter *fl_lookup(struct fl_flow_mask *mask,
+				       struct fl_flow_key *mkey,
+				       struct fl_flow_key *key)
+{
+	if ((mask->flags & TCA_FLOWER_MASK_FLAGS_RANGE))
+		return fl_lookup_range(mask, mkey, key);
+
+	return __fl_lookup(mask, mkey);
+}
+
 static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 		       struct tcf_result *res)
 {
@@ -208,7 +287,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 
 		fl_set_masked_key(&skb_mkey, &skb_key, mask);
 
-		f = fl_lookup(mask, &skb_mkey);
+		f = fl_lookup(mask, &skb_mkey, &skb_key);
 		if (f && !tc_skip_sw(f->flags)) {
 			*res = f->res;
 			return tcf_exts_exec(skb, &f->exts, res);
@@ -289,8 +368,7 @@ static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f,
 	cls_flower.command = TC_CLSFLOWER_DESTROY;
 	cls_flower.cookie = (unsigned long) f;
 
-	tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER,
-			 &cls_flower, false);
+	tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false);
 	tcf_block_offload_dec(block, &f->flags);
 }
 
@@ -312,8 +390,7 @@ static int fl_hw_replace_filter(struct tcf_proto *tp,
 	cls_flower.exts = &f->exts;
 	cls_flower.classid = f->res.classid;
 
-	err = tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER,
-			       &cls_flower, skip_sw);
+	err = tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, skip_sw);
 	if (err < 0) {
 		fl_hw_destroy_filter(tp, f, NULL);
 		return err;
@@ -339,8 +416,7 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f)
 	cls_flower.exts = &f->exts;
 	cls_flower.classid = f->res.classid;
 
-	tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER,
-			 &cls_flower, false);
+	tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false);
 }
 
 static bool __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f,
@@ -514,6 +590,31 @@ static void fl_set_key_val(struct nlattr **tb,
 		memcpy(mask, nla_data(tb[mask_type]), len);
 }
 
+static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key,
+				 struct fl_flow_key *mask)
+{
+	fl_set_key_val(tb, &key->tp_min.dst,
+		       TCA_FLOWER_KEY_PORT_DST_MIN, &mask->tp_min.dst,
+		       TCA_FLOWER_UNSPEC, sizeof(key->tp_min.dst));
+	fl_set_key_val(tb, &key->tp_max.dst,
+		       TCA_FLOWER_KEY_PORT_DST_MAX, &mask->tp_max.dst,
+		       TCA_FLOWER_UNSPEC, sizeof(key->tp_max.dst));
+	fl_set_key_val(tb, &key->tp_min.src,
+		       TCA_FLOWER_KEY_PORT_SRC_MIN, &mask->tp_min.src,
+		       TCA_FLOWER_UNSPEC, sizeof(key->tp_min.src));
+	fl_set_key_val(tb, &key->tp_max.src,
+		       TCA_FLOWER_KEY_PORT_SRC_MAX, &mask->tp_max.src,
+		       TCA_FLOWER_UNSPEC, sizeof(key->tp_max.src));
+
+	if ((mask->tp_min.dst && mask->tp_max.dst &&
+	     htons(key->tp_max.dst) <= htons(key->tp_min.dst)) ||
+	     (mask->tp_min.src && mask->tp_max.src &&
+	      htons(key->tp_max.src) <= htons(key->tp_min.src)))
+		return -EINVAL;
+
+	return 0;
+}
+
 static int fl_set_key_mpls(struct nlattr **tb,
 			   struct flow_dissector_key_mpls *key_val,
 			   struct flow_dissector_key_mpls *key_mask)
@@ -921,6 +1022,14 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 			       sizeof(key->arp.tha));
 	}
 
+	if (key->basic.ip_proto == IPPROTO_TCP ||
+	    key->basic.ip_proto == IPPROTO_UDP ||
+	    key->basic.ip_proto == IPPROTO_SCTP) {
+		ret = fl_set_key_port_range(tb, key, mask);
+		if (ret)
+			return ret;
+	}
+
 	if (tb[TCA_FLOWER_KEY_ENC_IPV4_SRC] ||
 	    tb[TCA_FLOWER_KEY_ENC_IPV4_DST]) {
 		key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
@@ -1038,8 +1147,9 @@ static void fl_init_dissector(struct flow_dissector *dissector,
 			     FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4);
 	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6);
-	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
-			     FLOW_DISSECTOR_KEY_PORTS, tp);
+	if (FL_KEY_IS_MASKED(mask, tp) ||
+	    FL_KEY_IS_MASKED(mask, tp_min) || FL_KEY_IS_MASKED(mask, tp_max))
+		FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_PORTS, tp);
 	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_IP, ip);
 	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
@@ -1086,6 +1196,10 @@ static struct fl_flow_mask *fl_create_new_mask(struct cls_fl_head *head,
 
 	fl_mask_copy(newmask, mask);
 
+	if ((newmask->key.tp_min.dst && newmask->key.tp_max.dst) ||
+	    (newmask->key.tp_min.src && newmask->key.tp_max.src))
+		newmask->flags |= TCA_FLOWER_MASK_FLAGS_RANGE;
+
 	err = fl_init_mask_hashtable(newmask);
 	if (err)
 		goto errout_free;
@@ -1238,7 +1352,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 	if (err)
 		goto errout_idr;
 
-	if (!fold && fl_lookup(fnew->mask, &fnew->mkey)) {
+	if (!fold && __fl_lookup(fnew->mask, &fnew->mkey)) {
 		err = -EEXIST;
 		goto errout_mask;
 	}
@@ -1384,8 +1498,7 @@ static void fl_hw_create_tmplt(struct tcf_chain *chain,
 	/* We don't care if driver (any of them) fails to handle this
 	 * call. It serves just as a hint for it.
 	 */
-	tc_setup_cb_call(block, NULL, TC_SETUP_CLSFLOWER,
-			 &cls_flower, false);
+	tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false);
 }
 
 static void fl_hw_destroy_tmplt(struct tcf_chain *chain,
@@ -1398,8 +1511,7 @@ static void fl_hw_destroy_tmplt(struct tcf_chain *chain,
 	cls_flower.command = TC_CLSFLOWER_TMPLT_DESTROY;
 	cls_flower.cookie = (unsigned long) tmplt;
 
-	tc_setup_cb_call(block, NULL, TC_SETUP_CLSFLOWER,
-			 &cls_flower, false);
+	tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false);
 }
 
 static void *fl_tmplt_create(struct net *net, struct tcf_chain *chain,
@@ -1472,6 +1584,26 @@ static int fl_dump_key_val(struct sk_buff *skb,
 	return 0;
 }
 
+static int fl_dump_key_port_range(struct sk_buff *skb, struct fl_flow_key *key,
+				  struct fl_flow_key *mask)
+{
+	if (fl_dump_key_val(skb, &key->tp_min.dst, TCA_FLOWER_KEY_PORT_DST_MIN,
+			    &mask->tp_min.dst, TCA_FLOWER_UNSPEC,
+			    sizeof(key->tp_min.dst)) ||
+	    fl_dump_key_val(skb, &key->tp_max.dst, TCA_FLOWER_KEY_PORT_DST_MAX,
+			    &mask->tp_max.dst, TCA_FLOWER_UNSPEC,
+			    sizeof(key->tp_max.dst)) ||
+	    fl_dump_key_val(skb, &key->tp_min.src, TCA_FLOWER_KEY_PORT_SRC_MIN,
+			    &mask->tp_min.src, TCA_FLOWER_UNSPEC,
+			    sizeof(key->tp_min.src)) ||
+	    fl_dump_key_val(skb, &key->tp_max.src, TCA_FLOWER_KEY_PORT_SRC_MAX,
+			    &mask->tp_max.src, TCA_FLOWER_UNSPEC,
+			    sizeof(key->tp_max.src)))
+		return -1;
+
+	return 0;
+}
+
 static int fl_dump_key_mpls(struct sk_buff *skb,
 			    struct flow_dissector_key_mpls *mpls_key,
 			    struct flow_dissector_key_mpls *mpls_mask)
@@ -1808,6 +1940,12 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net,
 				  sizeof(key->arp.tha))))
 		goto nla_put_failure;
 
+	if ((key->basic.ip_proto == IPPROTO_TCP ||
+	     key->basic.ip_proto == IPPROTO_UDP ||
+	     key->basic.ip_proto == IPPROTO_SCTP) &&
+	     fl_dump_key_port_range(skb, key, mask))
+		goto nla_put_failure;
+
 	if (key->enc_control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS &&
 	    (fl_dump_key_val(skb, &key->enc_ipv4.src,
 			    TCA_FLOWER_KEY_ENC_IPV4_SRC, &mask->enc_ipv4.src,