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

Pull networking fixes from David Miller:
 "I've been traveling so this accumulates more than week or so of bug
  fixing.  It perhaps looks a little worse than it really is.

   1) Fix deadlock in ath10k driver, from Ben Greear.

   2) Increase scan timeout in iwlwifi, from Luca Coelho.

   3) Unbreak STP by properly reinjecting STP packets back into the
      stack.  Regression fix from Ido Schimmel.

   4) Mediatek driver fixes (missing malloc failure checks, leaking of
      scratch memory, wrong indexing when mapping TX buffers, etc.) from
      John Crispin.

   5) Fix endianness bug in icmpv6_err() handler, from Hannes Frederic
      Sowa.

   6) Fix hashing of flows in UDP in the ruseport case, from Xuemin Su.

   7) Fix netlink notifications in ovs for tunnels, delete link messages
      are never emitted because of how the device registry state is
      handled.  From Nicolas Dichtel.

   8) Conntrack module leaks kmemcache on unload, from Florian Westphal.

   9) Prevent endless jump loops in nft rules, from Liping Zhang and
      Pablo Neira Ayuso.

  10) Not early enough spinlock initialization in mlx4, from Eric
      Dumazet.

  11) Bind refcount leak in act_ipt, from Cong WANG.

  12) Missing RCU locking in HTB scheduler, from Florian Westphal.

  13) Several small MACSEC bug fixes from Sabrina Dubroca (missing RCU
      barrier, using heap for SG and IV, and erroneous use of async flag
      when allocating AEAD conext.)

  14) RCU handling fix in TIPC, from Ying Xue.

  15) Pass correct protocol down into ipv4_{update_pmtu,redirect}() in
      SIT driver, from Simon Horman.

  16) Socket timer deadlock fix in TIPC from Jon Paul Maloy.

  17) Fix potential deadlock in team enslave, from Ido Schimmel.

  18) Memory leak in KCM procfs handling, from Jiri Slaby.

  19) ESN generation fix in ipv4 ESP, from Herbert Xu.

  20) Fix GFP_KERNEL allocations with locks held in act_ife, from Cong
      WANG.

  21) Use after free in netem, from Eric Dumazet.

  22) Uninitialized last assert time in multicast router code, from Tom
      Goff.

  23) Skip raw sockets in sock_diag destruction broadcast, from Willem
      de Bruijn.

  24) Fix link status reporting in thunderx, from Sunil Goutham.

  25) Limit resegmentation of retransmit queue so that we do not
      retransmit too large GSO frames.  From Eric Dumazet.

  26) Delay bpf program release after grace period, from Daniel
      Borkmann"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (141 commits)
  openvswitch: fix conntrack netlink event delivery
  qed: Protect the doorbell BAR with the write barriers.
  neigh: Explicitly declare RCU-bh read side critical section in neigh_xmit()
  e1000e: keep VLAN interfaces functional after rxvlan off
  cfg80211: fix proto in ieee80211_data_to_8023 for frames without LLC header
  qlcnic: use the correct ring in qlcnic_83xx_process_rcv_ring_diag()
  bpf, perf: delay release of BPF prog after grace period
  net: bridge: fix vlan stats continue counter
  tcp: do not send too big packets at retransmit time
  ibmvnic: fix to use list_for_each_safe() when delete items
  net: thunderx: Fix TL4 configuration for secondary Qsets
  net: thunderx: Fix link status reporting
  net/mlx5e: Reorganize ethtool statistics
  net/mlx5e: Fix number of PFC counters reported to ethtool
  net/mlx5e: Prevent adding the same vxlan port
  net/mlx5e: Check for BlueFlame capability before allocating SQ uar
  net/mlx5e: Change enum to better reflect usage
  net/mlx5: Add ConnectX-5 PCIe 4.0 to list of supported devices
  net/mlx5: Update command strings
  net: marvell: Add separate config ANEG function for Marvell 88E1111
  ...

7 files changed, 85 insertions, 98 deletions

diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 477937465a20..d95631d09248 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -23,6 +23,11 @@ struct esp_skb_cb {
 	void *tmp;
 };
 
+struct esp_output_extra {
+	__be32 seqhi;
+	u32 esphoff;
+};
+
 #define ESP_SKB_CB(__skb) ((struct esp_skb_cb *)&((__skb)->cb[0]))
 
 static u32 esp4_get_mtu(struct xfrm_state *x, int mtu);
@@ -35,11 +40,11 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu);
  *
  * TODO: Use spare space in skb for this where possible.
  */
-static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqhilen)
+static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int extralen)
 {
 	unsigned int len;
 
-	len = seqhilen;
+	len = extralen;
 
 	len += crypto_aead_ivsize(aead);
 
@@ -57,15 +62,16 @@ static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqhilen)
 	return kmalloc(len, GFP_ATOMIC);
 }
 
-static inline __be32 *esp_tmp_seqhi(void *tmp)
+static inline void *esp_tmp_extra(void *tmp)
 {
-	return PTR_ALIGN((__be32 *)tmp, __alignof__(__be32));
+	return PTR_ALIGN(tmp, __alignof__(struct esp_output_extra));
 }
-static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int seqhilen)
+
+static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int extralen)
 {
 	return crypto_aead_ivsize(aead) ?
-	       PTR_ALIGN((u8 *)tmp + seqhilen,
-			 crypto_aead_alignmask(aead) + 1) : tmp + seqhilen;
+	       PTR_ALIGN((u8 *)tmp + extralen,
+			 crypto_aead_alignmask(aead) + 1) : tmp + extralen;
 }
 
 static inline struct aead_request *esp_tmp_req(struct crypto_aead *aead, u8 *iv)
@@ -99,7 +105,7 @@ static void esp_restore_header(struct sk_buff *skb, unsigned int offset)
 {
 	struct ip_esp_hdr *esph = (void *)(skb->data + offset);
 	void *tmp = ESP_SKB_CB(skb)->tmp;
-	__be32 *seqhi = esp_tmp_seqhi(tmp);
+	__be32 *seqhi = esp_tmp_extra(tmp);
 
 	esph->seq_no = esph->spi;
 	esph->spi = *seqhi;
@@ -107,7 +113,11 @@ static void esp_restore_header(struct sk_buff *skb, unsigned int offset)
 
 static void esp_output_restore_header(struct sk_buff *skb)
 {
-	esp_restore_header(skb, skb_transport_offset(skb) - sizeof(__be32));
+	void *tmp = ESP_SKB_CB(skb)->tmp;
+	struct esp_output_extra *extra = esp_tmp_extra(tmp);
+
+	esp_restore_header(skb, skb_transport_offset(skb) + extra->esphoff -
+				sizeof(__be32));
 }
 
 static void esp_output_done_esn(struct crypto_async_request *base, int err)
@@ -121,6 +131,7 @@ static void esp_output_done_esn(struct crypto_async_request *base, int err)
 static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 {
 	int err;
+	struct esp_output_extra *extra;
 	struct ip_esp_hdr *esph;
 	struct crypto_aead *aead;
 	struct aead_request *req;
@@ -137,8 +148,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	int tfclen;
 	int nfrags;
 	int assoclen;
-	int seqhilen;
-	__be32 *seqhi;
+	int extralen;
 	__be64 seqno;
 
 	/* skb is pure payload to encrypt */
@@ -166,21 +176,21 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	nfrags = err;
 
 	assoclen = sizeof(*esph);
-	seqhilen = 0;
+	extralen = 0;
 
 	if (x->props.flags & XFRM_STATE_ESN) {
-		seqhilen += sizeof(__be32);
-		assoclen += seqhilen;
+		extralen += sizeof(*extra);
+		assoclen += sizeof(__be32);
 	}
 
-	tmp = esp_alloc_tmp(aead, nfrags, seqhilen);
+	tmp = esp_alloc_tmp(aead, nfrags, extralen);
 	if (!tmp) {
 		err = -ENOMEM;
 		goto error;
 	}
 
-	seqhi = esp_tmp_seqhi(tmp);
-	iv = esp_tmp_iv(aead, tmp, seqhilen);
+	extra = esp_tmp_extra(tmp);
+	iv = esp_tmp_iv(aead, tmp, extralen);
 	req = esp_tmp_req(aead, iv);
 	sg = esp_req_sg(aead, req);
 
@@ -247,8 +257,10 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	 * encryption.
 	 */
 	if ((x->props.flags & XFRM_STATE_ESN)) {
-		esph = (void *)(skb_transport_header(skb) - sizeof(__be32));
-		*seqhi = esph->spi;
+		extra->esphoff = (unsigned char *)esph -
+				 skb_transport_header(skb);
+		esph = (struct ip_esp_hdr *)((unsigned char *)esph - 4);
+		extra->seqhi = esph->spi;
 		esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
 		aead_request_set_callback(req, 0, esp_output_done_esn, skb);
 	}
@@ -445,7 +457,7 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
 		goto out;
 
 	ESP_SKB_CB(skb)->tmp = tmp;
-	seqhi = esp_tmp_seqhi(tmp);
+	seqhi = esp_tmp_extra(tmp);
 	iv = esp_tmp_iv(aead, tmp, seqhilen);
 	req = esp_tmp_req(aead, iv);
 	sg = esp_req_sg(aead, req);
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 4c39f4fd332a..de1d119a4497 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -62,26 +62,26 @@ EXPORT_SYMBOL_GPL(gre_del_protocol);
 
 /* Fills in tpi and returns header length to be pulled. */
 int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
-		     bool *csum_err, __be16 proto)
+		     bool *csum_err, __be16 proto, int nhs)
 {
 	const struct gre_base_hdr *greh;
 	__be32 *options;
 	int hdr_len;
 
-	if (unlikely(!pskb_may_pull(skb, sizeof(struct gre_base_hdr))))
+	if (unlikely(!pskb_may_pull(skb, nhs + sizeof(struct gre_base_hdr))))
 		return -EINVAL;
 
-	greh = (struct gre_base_hdr *)skb_transport_header(skb);
+	greh = (struct gre_base_hdr *)(skb->data + nhs);
 	if (unlikely(greh->flags & (GRE_VERSION | GRE_ROUTING)))
 		return -EINVAL;
 
 	tpi->flags = gre_flags_to_tnl_flags(greh->flags);
 	hdr_len = gre_calc_hlen(tpi->flags);
 
-	if (!pskb_may_pull(skb, hdr_len))
+	if (!pskb_may_pull(skb, nhs + hdr_len))
 		return -EINVAL;
 
-	greh = (struct gre_base_hdr *)skb_transport_header(skb);
+	greh = (struct gre_base_hdr *)(skb->data + nhs);
 	tpi->proto = greh->protocol;
 
 	options = (__be32 *)(greh + 1);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 4d2025f7ec57..1d000af7f561 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -49,12 +49,6 @@
 #include <net/gre.h>
 #include <net/dst_metadata.h>
 
-#if IS_ENABLED(CONFIG_IPV6)
-#include <net/ipv6.h>
-#include <net/ip6_fib.h>
-#include <net/ip6_route.h>
-#endif
-
 /*
    Problems & solutions
    --------------------
@@ -217,12 +211,14 @@ static void gre_err(struct sk_buff *skb, u32 info)
 	 * by themselves???
 	 */
 
+	const struct iphdr *iph = (struct iphdr *)skb->data;
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
 	struct tnl_ptk_info tpi;
 	bool csum_err = false;
 
-	if (gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP)) < 0) {
+	if (gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP),
+			     iph->ihl * 4) < 0) {
 		if (!csum_err)		/* ignore csum errors. */
 			return;
 	}
@@ -338,7 +334,7 @@ static int gre_rcv(struct sk_buff *skb)
 	}
 #endif
 
-	hdr_len = gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP));
+	hdr_len = gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP), 0);
 	if (hdr_len < 0)
 		goto drop;
 
@@ -1121,6 +1117,7 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
 {
 	struct nlattr *tb[IFLA_MAX + 1];
 	struct net_device *dev;
+	LIST_HEAD(list_kill);
 	struct ip_tunnel *t;
 	int err;
 
@@ -1136,8 +1133,10 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
 	t->collect_md = true;
 
 	err = ipgre_newlink(net, dev, tb, NULL);
-	if (err < 0)
-		goto out;
+	if (err < 0) {
+		free_netdev(dev);
+		return ERR_PTR(err);
+	}
 
 	/* openvswitch users expect packet sizes to be unrestricted,
 	 * so set the largest MTU we can.
@@ -1146,9 +1145,14 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
 	if (err)
 		goto out;
 
+	err = rtnl_configure_link(dev, NULL);
+	if (err < 0)
+		goto out;
+
 	return dev;
 out:
-	free_netdev(dev);
+	ip_tunnel_dellink(dev, &list_kill);
+	unregister_netdevice_many(&list_kill);
 	return ERR_PTR(err);
 }
 EXPORT_SYMBOL_GPL(gretap_fb_dev_create);
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 2ed9dd2b5f2f..1d71c40eaaf3 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -127,7 +127,9 @@ __be32 ic_myaddr = NONE;		/* My IP address */
 static __be32 ic_netmask = NONE;	/* Netmask for local subnet */
 __be32 ic_gateway = NONE;	/* Gateway IP address */
 
-__be32 ic_addrservaddr = NONE;	/* IP Address of the IP addresses'server */
+#ifdef IPCONFIG_DYNAMIC
+static __be32 ic_addrservaddr = NONE;	/* IP Address of the IP addresses'server */
+#endif
 
 __be32 ic_servaddr = NONE;	/* Boot server IP address */
 
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 21a38e296fe2..5ad48ec77710 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -891,8 +891,10 @@ static struct mfc_cache *ipmr_cache_alloc(void)
 {
 	struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL);
 
-	if (c)
+	if (c) {
+		c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
 		c->mfc_un.res.minvif = MAXVIFS;
+	}
 	return c;
 }
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8bd9911fdd16..e00e972c4e6a 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2751,7 +2751,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
 	struct sk_buff *hole = NULL;
-	u32 last_lost;
+	u32 max_segs, last_lost;
 	int mib_idx;
 	int fwd_rexmitting = 0;
 
@@ -2771,6 +2771,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
 		last_lost = tp->snd_una;
 	}
 
+	max_segs = tcp_tso_autosize(sk, tcp_current_mss(sk));
 	tcp_for_write_queue_from(skb, sk) {
 		__u8 sacked = TCP_SKB_CB(skb)->sacked;
 		int segs;
@@ -2784,6 +2785,10 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
 		segs = tp->snd_cwnd - tcp_packets_in_flight(tp);
 		if (segs <= 0)
 			return;
+		/* In case tcp_shift_skb_data() have aggregated large skbs,
+		 * we need to make sure not sending too bigs TSO packets
+		 */
+		segs = min_t(int, segs, max_segs);
 
 		if (fwd_rexmitting) {
 begin_fwd:
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 0ff31d97d485..ca5e8ea29538 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -391,9 +391,9 @@ int udp_v4_get_port(struct sock *sk, unsigned short snum)
 	return udp_lib_get_port(sk, snum, ipv4_rcv_saddr_equal, hash2_nulladdr);
 }
 
-static inline int compute_score(struct sock *sk, struct net *net,
-				__be32 saddr, unsigned short hnum, __be16 sport,
-				__be32 daddr, __be16 dport, int dif)
+static int compute_score(struct sock *sk, struct net *net,
+			 __be32 saddr, __be16 sport,
+			 __be32 daddr, unsigned short hnum, int dif)
 {
 	int score;
 	struct inet_sock *inet;
@@ -434,52 +434,6 @@ static inline int compute_score(struct sock *sk, struct net *net,
 	return score;
 }
 
-/*
- * In this second variant, we check (daddr, dport) matches (inet_rcv_sadd, inet_num)
- */
-static inline int compute_score2(struct sock *sk, struct net *net,
-				 __be32 saddr, __be16 sport,
-				 __be32 daddr, unsigned int hnum, int dif)
-{
-	int score;
-	struct inet_sock *inet;
-
-	if (!net_eq(sock_net(sk), net) ||
-	    ipv6_only_sock(sk))
-		return -1;
-
-	inet = inet_sk(sk);
-
-	if (inet->inet_rcv_saddr != daddr ||
-	    inet->inet_num != hnum)
-		return -1;
-
-	score = (sk->sk_family == PF_INET) ? 2 : 1;
-
-	if (inet->inet_daddr) {
-		if (inet->inet_daddr != saddr)
-			return -1;
-		score += 4;
-	}
-
-	if (inet->inet_dport) {
-		if (inet->inet_dport != sport)
-			return -1;
-		score += 4;
-	}
-
-	if (sk->sk_bound_dev_if) {
-		if (sk->sk_bound_dev_if != dif)
-			return -1;
-		score += 4;
-	}
-
-	if (sk->sk_incoming_cpu == raw_smp_processor_id())
-		score++;
-
-	return score;
-}
-
 static u32 udp_ehashfn(const struct net *net, const __be32 laddr,
 		       const __u16 lport, const __be32 faddr,
 		       const __be16 fport)
@@ -492,11 +446,11 @@ static u32 udp_ehashfn(const struct net *net, const __be32 laddr,
 			      udp_ehash_secret + net_hash_mix(net));
 }
 
-/* called with read_rcu_lock() */
+/* called with rcu_read_lock() */
 static struct sock *udp4_lib_lookup2(struct net *net,
 		__be32 saddr, __be16 sport,
 		__be32 daddr, unsigned int hnum, int dif,
-		struct udp_hslot *hslot2, unsigned int slot2,
+		struct udp_hslot *hslot2,
 		struct sk_buff *skb)
 {
 	struct sock *sk, *result;
@@ -506,7 +460,7 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 	result = NULL;
 	badness = 0;
 	udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
-		score = compute_score2(sk, net, saddr, sport,
+		score = compute_score(sk, net, saddr, sport,
 				      daddr, hnum, dif);
 		if (score > badness) {
 			reuseport = sk->sk_reuseport;
@@ -554,17 +508,22 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
 
 		result = udp4_lib_lookup2(net, saddr, sport,
 					  daddr, hnum, dif,
-					  hslot2, slot2, skb);
+					  hslot2, skb);
 		if (!result) {
+			unsigned int old_slot2 = slot2;
 			hash2 = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
 			slot2 = hash2 & udptable->mask;
+			/* avoid searching the same slot again. */
+			if (unlikely(slot2 == old_slot2))
+				return result;
+
 			hslot2 = &udptable->hash2[slot2];
 			if (hslot->count < hslot2->count)
 				goto begin;
 
 			result = udp4_lib_lookup2(net, saddr, sport,
-						  htonl(INADDR_ANY), hnum, dif,
-						  hslot2, slot2, skb);
+						  daddr, hnum, dif,
+						  hslot2, skb);
 		}
 		return result;
 	}
@@ -572,8 +531,8 @@ begin:
 	result = NULL;
 	badness = 0;
 	sk_for_each_rcu(sk, &hslot->head) {
-		score = compute_score(sk, net, saddr, hnum, sport,
-				      daddr, dport, dif);
+		score = compute_score(sk, net, saddr, sport,
+				      daddr, hnum, dif);
 		if (score > badness) {
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
@@ -1755,8 +1714,11 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
 			return err;
 	}
 
-	return skb_checksum_init_zero_check(skb, proto, uh->check,
-					    inet_compute_pseudo);
+	/* Note, we are only interested in != 0 or == 0, thus the
+	 * force to int.
+	 */
+	return (__force int)skb_checksum_init_zero_check(skb, proto, uh->check,
+							 inet_compute_pseudo);
 }
 
 /*