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

Pull networking updates from David Miller:
 "Some highlights from this development cycle:

   1) Big refactoring of ipv6 route and neigh handling to support
      nexthop objects configurable as units from userspace. From David
      Ahern.

   2) Convert explored_states in BPF verifier into a hash table,
      significantly decreased state held for programs with bpf2bpf
      calls, from Alexei Starovoitov.

   3) Implement bpf_send_signal() helper, from Yonghong Song.

   4) Various classifier enhancements to mvpp2 driver, from Maxime
      Chevallier.

   5) Add aRFS support to hns3 driver, from Jian Shen.

   6) Fix use after free in inet frags by allocating fqdirs dynamically
      and reworking how rhashtable dismantle occurs, from Eric Dumazet.

   7) Add act_ctinfo packet classifier action, from Kevin
      Darbyshire-Bryant.

   8) Add TFO key backup infrastructure, from Jason Baron.

   9) Remove several old and unused ISDN drivers, from Arnd Bergmann.

  10) Add devlink notifications for flash update status to mlxsw driver,
      from Jiri Pirko.

  11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski.

  12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes.

  13) Various enhancements to ipv6 flow label handling, from Eric
      Dumazet and Willem de Bruijn.

  14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van
      der Merwe, and others.

  15) Various improvements to axienet driver including converting it to
      phylink, from Robert Hancock.

  16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean.

  17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana
      Radulescu.

  18) Add devlink health reporting to mlx5, from Moshe Shemesh.

  19) Convert stmmac over to phylink, from Jose Abreu.

  20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from
      Shalom Toledo.

  21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera.

  22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel.

  23) Track spill/fill of constants in BPF verifier, from Alexei
      Starovoitov.

  24) Support bounded loops in BPF, from Alexei Starovoitov.

  25) Various page_pool API fixes and improvements, from Jesper Dangaard
      Brouer.

  26) Just like ipv4, support ref-countless ipv6 route handling. From
      Wei Wang.

  27) Support VLAN offloading in aquantia driver, from Igor Russkikh.

  28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy.

  29) Add flower GRE encap/decap support to nfp driver, from Pieter
      Jansen van Vuuren.

  30) Protect against stack overflow when using act_mirred, from John
      Hurley.

  31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen.

  32) Use page_pool API in netsec driver, Ilias Apalodimas.

  33) Add Google gve network driver, from Catherine Sullivan.

  34) More indirect call avoidance, from Paolo Abeni.

  35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan.

  36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek.

  37) Add MPLS manipulation actions to TC, from John Hurley.

  38) Add sending a packet to connection tracking from TC actions, and
      then allow flower classifier matching on conntrack state. From
      Paul Blakey.

  39) Netfilter hw offload support, from Pablo Neira Ayuso"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits)
  net/mlx5e: Return in default case statement in tx_post_resync_params
  mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync().
  net: dsa: add support for BRIDGE_MROUTER attribute
  pkt_sched: Include const.h
  net: netsec: remove static declaration for netsec_set_tx_de()
  net: netsec: remove superfluous if statement
  netfilter: nf_tables: add hardware offload support
  net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload
  net: flow_offload: add flow_block_cb_is_busy() and use it
  net: sched: remove tcf block API
  drivers: net: use flow block API
  net: sched: use flow block API
  net: flow_offload: add flow_block_cb_{priv, incref, decref}()
  net: flow_offload: add list handling functions
  net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free()
  net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*
  net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND
  net: flow_offload: add flow_block_cb_setup_simple()
  net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC
  net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC
  ...

1 files changed, 216 insertions, 134 deletions

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 8c2ec35b6512..cc7ef0d05bbd 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -287,16 +287,9 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk,
 	return ret;
 }
 
-static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+static int __ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	unsigned int mtu;
-	int ret;
-
-	ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
-	if (ret) {
-		kfree_skb(skb);
-		return ret;
-	}
 
 #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
 	/* Policy lookup after SNAT yielded a new policy */
@@ -315,14 +308,37 @@ static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *sk
 	return ip_finish_output2(net, sk, skb);
 }
 
+static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	int ret;
+
+	ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
+	switch (ret) {
+	case NET_XMIT_SUCCESS:
+		return __ip_finish_output(net, sk, skb);
+	case NET_XMIT_CN:
+		return __ip_finish_output(net, sk, skb) ? : ret;
+	default:
+		kfree_skb(skb);
+		return ret;
+	}
+}
+
 static int ip_mc_finish_output(struct net *net, struct sock *sk,
 			       struct sk_buff *skb)
 {
 	struct rtable *new_rt;
-	int ret;
+	bool do_cn = false;
+	int ret, err;
 
 	ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb);
-	if (ret) {
+	switch (ret) {
+	case NET_XMIT_CN:
+		do_cn = true;
+		/* fall through */
+	case NET_XMIT_SUCCESS:
+		break;
+	default:
 		kfree_skb(skb);
 		return ret;
 	}
@@ -338,7 +354,8 @@ static int ip_mc_finish_output(struct net *net, struct sock *sk,
 		skb_dst_set(skb, &new_rt->dst);
 	}
 
-	return dev_loopback_xmit(net, sk, skb);
+	err = dev_loopback_xmit(net, sk, skb);
+	return (do_cn && err) ? ret : err;
 }
 
 int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb)
@@ -537,9 +554,6 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 
 	skb_copy_hash(to, from);
 
-	/* Copy the flags to each fragment. */
-	IPCB(to)->flags = IPCB(from)->flags;
-
 #ifdef CONFIG_NET_SCHED
 	to->tc_index = from->tc_index;
 #endif
@@ -573,6 +587,175 @@ static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 	return ip_do_fragment(net, sk, skb, output);
 }
 
+void ip_fraglist_init(struct sk_buff *skb, struct iphdr *iph,
+		      unsigned int hlen, struct ip_fraglist_iter *iter)
+{
+	unsigned int first_len = skb_pagelen(skb);
+
+	iter->frag = skb_shinfo(skb)->frag_list;
+	skb_frag_list_init(skb);
+
+	iter->offset = 0;
+	iter->iph = iph;
+	iter->hlen = hlen;
+
+	skb->data_len = first_len - skb_headlen(skb);
+	skb->len = first_len;
+	iph->tot_len = htons(first_len);
+	iph->frag_off = htons(IP_MF);
+	ip_send_check(iph);
+}
+EXPORT_SYMBOL(ip_fraglist_init);
+
+static void ip_fraglist_ipcb_prepare(struct sk_buff *skb,
+				     struct ip_fraglist_iter *iter)
+{
+	struct sk_buff *to = iter->frag;
+
+	/* Copy the flags to each fragment. */
+	IPCB(to)->flags = IPCB(skb)->flags;
+
+	if (iter->offset == 0)
+		ip_options_fragment(to);
+}
+
+void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter)
+{
+	unsigned int hlen = iter->hlen;
+	struct iphdr *iph = iter->iph;
+	struct sk_buff *frag;
+
+	frag = iter->frag;
+	frag->ip_summed = CHECKSUM_NONE;
+	skb_reset_transport_header(frag);
+	__skb_push(frag, hlen);
+	skb_reset_network_header(frag);
+	memcpy(skb_network_header(frag), iph, hlen);
+	iter->iph = ip_hdr(frag);
+	iph = iter->iph;
+	iph->tot_len = htons(frag->len);
+	ip_copy_metadata(frag, skb);
+	iter->offset += skb->len - hlen;
+	iph->frag_off = htons(iter->offset >> 3);
+	if (frag->next)
+		iph->frag_off |= htons(IP_MF);
+	/* Ready, complete checksum */
+	ip_send_check(iph);
+}
+EXPORT_SYMBOL(ip_fraglist_prepare);
+
+void ip_frag_init(struct sk_buff *skb, unsigned int hlen,
+		  unsigned int ll_rs, unsigned int mtu,
+		  struct ip_frag_state *state)
+{
+	struct iphdr *iph = ip_hdr(skb);
+
+	state->hlen = hlen;
+	state->ll_rs = ll_rs;
+	state->mtu = mtu;
+
+	state->left = skb->len - hlen;	/* Space per frame */
+	state->ptr = hlen;		/* Where to start from */
+
+	state->offset = (ntohs(iph->frag_off) & IP_OFFSET) << 3;
+	state->not_last_frag = iph->frag_off & htons(IP_MF);
+}
+EXPORT_SYMBOL(ip_frag_init);
+
+static void ip_frag_ipcb(struct sk_buff *from, struct sk_buff *to,
+			 bool first_frag, struct ip_frag_state *state)
+{
+	/* Copy the flags to each fragment. */
+	IPCB(to)->flags = IPCB(from)->flags;
+
+	if (IPCB(from)->flags & IPSKB_FRAG_PMTU)
+		state->iph->frag_off |= htons(IP_DF);
+
+	/* ANK: dirty, but effective trick. Upgrade options only if
+	 * the segment to be fragmented was THE FIRST (otherwise,
+	 * options are already fixed) and make it ONCE
+	 * on the initial skb, so that all the following fragments
+	 * will inherit fixed options.
+	 */
+	if (first_frag)
+		ip_options_fragment(from);
+}
+
+struct sk_buff *ip_frag_next(struct sk_buff *skb, struct ip_frag_state *state)
+{
+	unsigned int len = state->left;
+	struct sk_buff *skb2;
+	struct iphdr *iph;
+
+	len = state->left;
+	/* IF: it doesn't fit, use 'mtu' - the data space left */
+	if (len > state->mtu)
+		len = state->mtu;
+	/* IF: we are not sending up to and including the packet end
+	   then align the next start on an eight byte boundary */
+	if (len < state->left)	{
+		len &= ~7;
+	}
+
+	/* Allocate buffer */
+	skb2 = alloc_skb(len + state->hlen + state->ll_rs, GFP_ATOMIC);
+	if (!skb2)
+		return ERR_PTR(-ENOMEM);
+
+	/*
+	 *	Set up data on packet
+	 */
+
+	ip_copy_metadata(skb2, skb);
+	skb_reserve(skb2, state->ll_rs);
+	skb_put(skb2, len + state->hlen);
+	skb_reset_network_header(skb2);
+	skb2->transport_header = skb2->network_header + state->hlen;
+
+	/*
+	 *	Charge the memory for the fragment to any owner
+	 *	it might possess
+	 */
+
+	if (skb->sk)
+		skb_set_owner_w(skb2, skb->sk);
+
+	/*
+	 *	Copy the packet header into the new buffer.
+	 */
+
+	skb_copy_from_linear_data(skb, skb_network_header(skb2), state->hlen);
+
+	/*
+	 *	Copy a block of the IP datagram.
+	 */
+	if (skb_copy_bits(skb, state->ptr, skb_transport_header(skb2), len))
+		BUG();
+	state->left -= len;
+
+	/*
+	 *	Fill in the new header fields.
+	 */
+	iph = ip_hdr(skb2);
+	iph->frag_off = htons((state->offset >> 3));
+
+	/*
+	 *	Added AC : If we are fragmenting a fragment that's not the
+	 *		   last fragment then keep MF on each bit
+	 */
+	if (state->left > 0 || state->not_last_frag)
+		iph->frag_off |= htons(IP_MF);
+	state->ptr += len;
+	state->offset += len;
+
+	iph->tot_len = htons(len + state->hlen);
+
+	ip_send_check(iph);
+
+	return skb2;
+}
+EXPORT_SYMBOL(ip_frag_next);
+
 /*
  *	This IP datagram is too large to be sent in one piece.  Break it up into
  *	smaller pieces (each of size equal to IP header plus
@@ -584,12 +767,11 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		   int (*output)(struct net *, struct sock *, struct sk_buff *))
 {
 	struct iphdr *iph;
-	int ptr;
 	struct sk_buff *skb2;
-	unsigned int mtu, hlen, left, len, ll_rs;
-	int offset;
-	__be16 not_last_frag;
 	struct rtable *rt = skb_rtable(skb);
+	unsigned int mtu, hlen, ll_rs;
+	struct ip_fraglist_iter iter;
+	struct ip_frag_state state;
 	int err = 0;
 
 	/* for offloaded checksums cleanup checksum before fragmentation */
@@ -654,49 +836,24 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		}
 
 		/* Everything is OK. Generate! */
-
-		err = 0;
-		offset = 0;
-		frag = skb_shinfo(skb)->frag_list;
-		skb_frag_list_init(skb);
-		skb->data_len = first_len - skb_headlen(skb);
-		skb->len = first_len;
-		iph->tot_len = htons(first_len);
-		iph->frag_off = htons(IP_MF);
-		ip_send_check(iph);
+		ip_fraglist_init(skb, iph, hlen, &iter);
 
 		for (;;) {
 			/* Prepare header of the next frame,
 			 * before previous one went down. */
-			if (frag) {
-				frag->ip_summed = CHECKSUM_NONE;
-				skb_reset_transport_header(frag);
-				__skb_push(frag, hlen);
-				skb_reset_network_header(frag);
-				memcpy(skb_network_header(frag), iph, hlen);
-				iph = ip_hdr(frag);
-				iph->tot_len = htons(frag->len);
-				ip_copy_metadata(frag, skb);
-				if (offset == 0)
-					ip_options_fragment(frag);
-				offset += skb->len - hlen;
-				iph->frag_off = htons(offset>>3);
-				if (frag->next)
-					iph->frag_off |= htons(IP_MF);
-				/* Ready, complete checksum */
-				ip_send_check(iph);
+			if (iter.frag) {
+				ip_fraglist_ipcb_prepare(skb, &iter);
+				ip_fraglist_prepare(skb, &iter);
 			}
 
 			err = output(net, sk, skb);
 
 			if (!err)
 				IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES);
-			if (err || !frag)
+			if (err || !iter.frag)
 				break;
 
-			skb = frag;
-			frag = skb->next;
-			skb_mark_not_on_list(skb);
+			skb = ip_fraglist_next(&iter);
 		}
 
 		if (err == 0) {
@@ -704,7 +861,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 			return 0;
 		}
 
-		kfree_skb_list(frag);
+		kfree_skb_list(iter.frag);
 
 		IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS);
 		return err;
@@ -720,105 +877,29 @@ slow_path_clean:
 	}
 
 slow_path:
-	iph = ip_hdr(skb);
-
-	left = skb->len - hlen;		/* Space per frame */
-	ptr = hlen;		/* Where to start from */
-
 	/*
 	 *	Fragment the datagram.
 	 */
 
-	offset = (ntohs(iph->frag_off) & IP_OFFSET) << 3;
-	not_last_frag = iph->frag_off & htons(IP_MF);
+	ip_frag_init(skb, hlen, ll_rs, mtu, &state);
 
 	/*
 	 *	Keep copying data until we run out.
 	 */
 
-	while (left > 0) {
-		len = left;
-		/* IF: it doesn't fit, use 'mtu' - the data space left */
-		if (len > mtu)
-			len = mtu;
-		/* IF: we are not sending up to and including the packet end
-		   then align the next start on an eight byte boundary */
-		if (len < left)	{
-			len &= ~7;
-		}
+	while (state.left > 0) {
+		bool first_frag = (state.offset == 0);
 
-		/* Allocate buffer */
-		skb2 = alloc_skb(len + hlen + ll_rs, GFP_ATOMIC);
-		if (!skb2) {
-			err = -ENOMEM;
+		skb2 = ip_frag_next(skb, &state);
+		if (IS_ERR(skb2)) {
+			err = PTR_ERR(skb2);
 			goto fail;
 		}
-
-		/*
-		 *	Set up data on packet
-		 */
-
-		ip_copy_metadata(skb2, skb);
-		skb_reserve(skb2, ll_rs);
-		skb_put(skb2, len + hlen);
-		skb_reset_network_header(skb2);
-		skb2->transport_header = skb2->network_header + hlen;
-
-		/*
-		 *	Charge the memory for the fragment to any owner
-		 *	it might possess
-		 */
-
-		if (skb->sk)
-			skb_set_owner_w(skb2, skb->sk);
-
-		/*
-		 *	Copy the packet header into the new buffer.
-		 */
-
-		skb_copy_from_linear_data(skb, skb_network_header(skb2), hlen);
-
-		/*
-		 *	Copy a block of the IP datagram.
-		 */
-		if (skb_copy_bits(skb, ptr, skb_transport_header(skb2), len))
-			BUG();
-		left -= len;
-
-		/*
-		 *	Fill in the new header fields.
-		 */
-		iph = ip_hdr(skb2);
-		iph->frag_off = htons((offset >> 3));
-
-		if (IPCB(skb)->flags & IPSKB_FRAG_PMTU)
-			iph->frag_off |= htons(IP_DF);
-
-		/* ANK: dirty, but effective trick. Upgrade options only if
-		 * the segment to be fragmented was THE FIRST (otherwise,
-		 * options are already fixed) and make it ONCE
-		 * on the initial skb, so that all the following fragments
-		 * will inherit fixed options.
-		 */
-		if (offset == 0)
-			ip_options_fragment(skb);
-
-		/*
-		 *	Added AC : If we are fragmenting a fragment that's not the
-		 *		   last fragment then keep MF on each bit
-		 */
-		if (left > 0 || not_last_frag)
-			iph->frag_off |= htons(IP_MF);
-		ptr += len;
-		offset += len;
+		ip_frag_ipcb(skb, skb2, first_frag, &state);
 
 		/*
 		 *	Put this fragment into the sending queue.
 		 */
-		iph->tot_len = htons(len + hlen);
-
-		ip_send_check(iph);
-
 		err = output(net, sk, skb2);
 		if (err)
 			goto fail;
@@ -1568,7 +1649,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 			   const struct ip_options *sopt,
 			   __be32 daddr, __be32 saddr,
 			   const struct ip_reply_arg *arg,
-			   unsigned int len)
+			   unsigned int len, u64 transmit_time)
 {
 	struct ip_options_data replyopts;
 	struct ipcm_cookie ipc;
@@ -1584,6 +1665,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 
 	ipcm_init(&ipc);
 	ipc.addr = daddr;
+	ipc.sockc.transmit_time = transmit_time;
 
 	if (replyopts.opt.opt.optlen) {
 		ipc.opt = &replyopts.opt;