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

Pull networking updates from David Miller:
 "Highlights:

   1) Support SPI based w5100 devices, from Akinobu Mita.

   2) Partial Segmentation Offload, from Alexander Duyck.

   3) Add GMAC4 support to stmmac driver, from Alexandre TORGUE.

   4) Allow cls_flower stats offload, from Amir Vadai.

   5) Implement bpf blinding, from Daniel Borkmann.

   6) Optimize _ASYNC_ bit twiddling on sockets, unless the socket is
      actually using FASYNC these atomics are superfluous.  From Eric
      Dumazet.

   7) Run TCP more preemptibly, also from Eric Dumazet.

   8) Support LED blinking, EEPROM dumps, and rxvlan offloading in mlx5e
      driver, from Gal Pressman.

   9) Allow creating ppp devices via rtnetlink, from Guillaume Nault.

  10) Improve BPF usage documentation, from Jesper Dangaard Brouer.

  11) Support tunneling offloads in qed, from Manish Chopra.

  12) aRFS offloading in mlx5e, from Maor Gottlieb.

  13) Add RFS and RPS support to SCTP protocol, from Marcelo Ricardo
      Leitner.

  14) Add MSG_EOR support to TCP, this allows controlling packet
      coalescing on application record boundaries for more accurate
      socket timestamp sampling.  From Martin KaFai Lau.

  15) Fix alignment of 64-bit netlink attributes across the board, from
      Nicolas Dichtel.

  16) Per-vlan stats in bridging, from Nikolay Aleksandrov.

  17) Several conversions of drivers to ethtool ksettings, from Philippe
      Reynes.

  18) Checksum neutral ILA in ipv6, from Tom Herbert.

  19) Factorize all of the various marvell dsa drivers into one, from
      Vivien Didelot

  20) Add VF support to qed driver, from Yuval Mintz"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1649 commits)
  Revert "phy dp83867: Fix compilation with CONFIG_OF_MDIO=m"
  Revert "phy dp83867: Make rgmii parameters optional"
  r8169: default to 64-bit DMA on recent PCIe chips
  phy dp83867: Make rgmii parameters optional
  phy dp83867: Fix compilation with CONFIG_OF_MDIO=m
  bpf: arm64: remove callee-save registers use for tmp registers
  asix: Fix offset calculation in asix_rx_fixup() causing slow transmissions
  switchdev: pass pointer to fib_info instead of copy
  net_sched: close another race condition in tcf_mirred_release()
  tipc: fix nametable publication field in nl compat
  drivers: net: Don't print unpopulated net_device name
  qed: add support for dcbx.
  ravb: Add missing free_irq() calls to ravb_close()
  qed: Remove a stray tab
  net: ethernet: fec-mpc52xx: use phy_ethtool_{get|set}_link_ksettings
  net: ethernet: fec-mpc52xx: use phydev from struct net_device
  bpf, doc: fix typo on bpf_asm descriptions
  stmmac: hardware TX COE doesn't work when force_thresh_dma_mode is set
  net: ethernet: fs-enet: use phy_ethtool_{get|set}_link_ksettings
  net: ethernet: fs-enet: use phydev from struct net_device
  ...

1 files changed, 59 insertions, 39 deletions

diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 5fdb02f5598e..25af1243649b 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -66,7 +66,7 @@ static void inet_diag_unlock_handler(const struct inet_diag_handler *handler)
 	mutex_unlock(&inet_diag_table_mutex);
 }
 
-static void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk)
+void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk)
 {
 	r->idiag_family = sk->sk_family;
 
@@ -89,6 +89,7 @@ static void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk)
 	r->id.idiag_dst[0] = sk->sk_daddr;
 	}
 }
+EXPORT_SYMBOL_GPL(inet_diag_msg_common_fill);
 
 static size_t inet_sk_attr_size(void)
 {
@@ -104,13 +105,50 @@ static size_t inet_sk_attr_size(void)
 		+ 64;
 }
 
+int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
+			     struct inet_diag_msg *r, int ext,
+			     struct user_namespace *user_ns)
+{
+	const struct inet_sock *inet = inet_sk(sk);
+
+	if (nla_put_u8(skb, INET_DIAG_SHUTDOWN, sk->sk_shutdown))
+		goto errout;
+
+	/* IPv6 dual-stack sockets use inet->tos for IPv4 connections,
+	 * hence this needs to be included regardless of socket family.
+	 */
+	if (ext & (1 << (INET_DIAG_TOS - 1)))
+		if (nla_put_u8(skb, INET_DIAG_TOS, inet->tos) < 0)
+			goto errout;
+
+#if IS_ENABLED(CONFIG_IPV6)
+	if (r->idiag_family == AF_INET6) {
+		if (ext & (1 << (INET_DIAG_TCLASS - 1)))
+			if (nla_put_u8(skb, INET_DIAG_TCLASS,
+				       inet6_sk(sk)->tclass) < 0)
+				goto errout;
+
+		if (((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) &&
+		    nla_put_u8(skb, INET_DIAG_SKV6ONLY, ipv6_only_sock(sk)))
+			goto errout;
+	}
+#endif
+
+	r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk));
+	r->idiag_inode = sock_i_ino(sk);
+
+	return 0;
+errout:
+	return 1;
+}
+EXPORT_SYMBOL_GPL(inet_diag_msg_attrs_fill);
+
 int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 		      struct sk_buff *skb, const struct inet_diag_req_v2 *req,
 		      struct user_namespace *user_ns,
 		      u32 portid, u32 seq, u16 nlmsg_flags,
 		      const struct nlmsghdr *unlh)
 {
-	const struct inet_sock *inet = inet_sk(sk);
 	const struct tcp_congestion_ops *ca_ops;
 	const struct inet_diag_handler *handler;
 	int ext = req->idiag_ext;
@@ -135,32 +173,9 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 	r->idiag_timer = 0;
 	r->idiag_retrans = 0;
 
-	if (nla_put_u8(skb, INET_DIAG_SHUTDOWN, sk->sk_shutdown))
+	if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns))
 		goto errout;
 
-	/* IPv6 dual-stack sockets use inet->tos for IPv4 connections,
-	 * hence this needs to be included regardless of socket family.
-	 */
-	if (ext & (1 << (INET_DIAG_TOS - 1)))
-		if (nla_put_u8(skb, INET_DIAG_TOS, inet->tos) < 0)
-			goto errout;
-
-#if IS_ENABLED(CONFIG_IPV6)
-	if (r->idiag_family == AF_INET6) {
-		if (ext & (1 << (INET_DIAG_TCLASS - 1)))
-			if (nla_put_u8(skb, INET_DIAG_TCLASS,
-				       inet6_sk(sk)->tclass) < 0)
-				goto errout;
-
-		if (((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) &&
-		    nla_put_u8(skb, INET_DIAG_SKV6ONLY, ipv6_only_sock(sk)))
-			goto errout;
-	}
-#endif
-
-	r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk));
-	r->idiag_inode = sock_i_ino(sk);
-
 	if (ext & (1 << (INET_DIAG_MEMINFO - 1))) {
 		struct inet_diag_meminfo minfo = {
 			.idiag_rmem = sk_rmem_alloc_get(sk),
@@ -182,31 +197,32 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 		goto out;
 	}
 
-#define EXPIRES_IN_MS(tmo)  DIV_ROUND_UP((tmo - jiffies) * 1000, HZ)
-
 	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
 	    icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
 	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		r->idiag_timer = 1;
 		r->idiag_retrans = icsk->icsk_retransmits;
-		r->idiag_expires = EXPIRES_IN_MS(icsk->icsk_timeout);
+		r->idiag_expires =
+			jiffies_to_msecs(icsk->icsk_timeout - jiffies);
 	} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
 		r->idiag_timer = 4;
 		r->idiag_retrans = icsk->icsk_probes_out;
-		r->idiag_expires = EXPIRES_IN_MS(icsk->icsk_timeout);
+		r->idiag_expires =
+			jiffies_to_msecs(icsk->icsk_timeout - jiffies);
 	} else if (timer_pending(&sk->sk_timer)) {
 		r->idiag_timer = 2;
 		r->idiag_retrans = icsk->icsk_probes_out;
-		r->idiag_expires = EXPIRES_IN_MS(sk->sk_timer.expires);
+		r->idiag_expires =
+			jiffies_to_msecs(sk->sk_timer.expires - jiffies);
 	} else {
 		r->idiag_timer = 0;
 		r->idiag_expires = 0;
 	}
-#undef EXPIRES_IN_MS
 
 	if ((ext & (1 << (INET_DIAG_INFO - 1))) && handler->idiag_info_size) {
-		attr = nla_reserve(skb, INET_DIAG_INFO,
-				   handler->idiag_info_size);
+		attr = nla_reserve_64bit(skb, INET_DIAG_INFO,
+					 handler->idiag_info_size,
+					 INET_DIAG_PAD);
 		if (!attr)
 			goto errout;
 
@@ -356,6 +372,7 @@ struct sock *inet_diag_find_one_icsk(struct net *net,
 {
 	struct sock *sk;
 
+	rcu_read_lock();
 	if (req->sdiag_family == AF_INET)
 		sk = inet_lookup(net, hashinfo, NULL, 0, req->id.idiag_dst[0],
 				 req->id.idiag_dport, req->id.idiag_src[0],
@@ -376,9 +393,11 @@ struct sock *inet_diag_find_one_icsk(struct net *net,
 					  req->id.idiag_if);
 	}
 #endif
-	else
+	else {
+		rcu_read_unlock();
 		return ERR_PTR(-EINVAL);
-
+	}
+	rcu_read_unlock();
 	if (!sk)
 		return ERR_PTR(-ENOENT);
 
@@ -772,13 +791,12 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
 
 		for (i = s_i; i < INET_LHTABLE_SIZE; i++) {
 			struct inet_listen_hashbucket *ilb;
-			struct hlist_nulls_node *node;
 			struct sock *sk;
 
 			num = 0;
 			ilb = &hashinfo->listening_hash[i];
 			spin_lock_bh(&ilb->lock);
-			sk_nulls_for_each(sk, node, &ilb->head) {
+			sk_for_each(sk, &ilb->head) {
 				struct inet_sock *inet = inet_sk(sk);
 
 				if (!net_eq(sock_net(sk), net))
@@ -1061,7 +1079,9 @@ int inet_diag_handler_get_info(struct sk_buff *skb, struct sock *sk)
 	}
 
 	attr = handler->idiag_info_size
-		? nla_reserve(skb, INET_DIAG_INFO, handler->idiag_info_size)
+		? nla_reserve_64bit(skb, INET_DIAG_INFO,
+				    handler->idiag_info_size,
+				    INET_DIAG_PAD)
 		: NULL;
 	if (attr)
 		info = nla_data(attr);