Merge branch 'linux-4.14.y_for_4.14-2.0.x-imx' into 4.14-2.0.x-imx

20 files changed, 528 insertions, 332 deletions

diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 777fa3b7fb13..f0165c5f376b 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -667,7 +667,8 @@ static int cipso_v4_map_lvl_valid(const struct cipso_v4_doi *doi_def, u8 level)
 	case CIPSO_V4_MAP_PASS:
 		return 0;
 	case CIPSO_V4_MAP_TRANS:
-		if (doi_def->map.std->lvl.cipso[level] < CIPSO_V4_INV_LVL)
+		if ((level < doi_def->map.std->lvl.cipso_size) &&
+		    (doi_def->map.std->lvl.cipso[level] < CIPSO_V4_INV_LVL))
 			return 0;
 		break;
 	}
@@ -1735,13 +1736,26 @@ validate_return:
  */
 void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway)
 {
+	unsigned char optbuf[sizeof(struct ip_options) + 40];
+	struct ip_options *opt = (struct ip_options *)optbuf;
+
 	if (ip_hdr(skb)->protocol == IPPROTO_ICMP || error != -EACCES)
 		return;
 
+	/*
+	 * We might be called above the IP layer,
+	 * so we can not use icmp_send and IPCB here.
+	 */
+
+	memset(opt, 0, sizeof(struct ip_options));
+	opt->optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr);
+	if (__ip_options_compile(dev_net(skb->dev), opt, skb, NULL))
+		return;
+
 	if (gateway)
-		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_NET_ANO, 0);
+		__icmp_send(skb, ICMP_DEST_UNREACH, ICMP_NET_ANO, 0, opt);
 	else
-		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_ANO, 0);
+		__icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_ANO, 0, opt);
 }
 
 /**
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index b00e4a43b4dc..d30285c5d52d 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -307,7 +307,7 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 			skb->len += tailen;
 			skb->data_len += tailen;
 			skb->truesize += tailen;
-			if (sk)
+			if (sk && sk_fullsock(sk))
 				refcount_add(tailen, &sk->sk_wmem_alloc);
 
 			goto out;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index b5317b2b191d..ff499000f6cd 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -675,6 +675,10 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 		case RTA_GATEWAY:
 			cfg->fc_gw = nla_get_be32(attr);
 			break;
+		case RTA_VIA:
+			NL_SET_ERR_MSG(extack, "IPv4 does not support RTA_VIA attribute");
+			err = -EINVAL;
+			goto errout;
 		case RTA_PRIORITY:
 			cfg->fc_priority = nla_get_u32(attr);
 			break;
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index c9ec1603666b..665f11d7388e 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -120,6 +120,7 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
 	struct guehdr *guehdr;
 	void *data;
 	u16 doffset = 0;
+	u8 proto_ctype;
 
 	if (!fou)
 		return 1;
@@ -211,13 +212,14 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
 	if (unlikely(guehdr->control))
 		return gue_control_message(skb, guehdr);
 
+	proto_ctype = guehdr->proto_ctype;
 	__skb_pull(skb, sizeof(struct udphdr) + hdrlen);
 	skb_reset_transport_header(skb);
 
 	if (iptunnel_pull_offloads(skb))
 		goto drop;
 
-	return -guehdr->proto_ctype;
+	return -proto_ctype;
 
 drop:
 	kfree_skb(skb);
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 3c1570d3e22f..f9d790b058d2 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -573,7 +573,8 @@ relookup_failed:
  *			MUST reply to only the first fragment.
  */
 
-void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
+void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
+		 const struct ip_options *opt)
 {
 	struct iphdr *iph;
 	int room;
@@ -694,7 +695,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 					  iph->tos;
 	mark = IP4_REPLY_MARK(net, skb_in->mark);
 
-	if (ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in))
+	if (__ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in, opt))
 		goto out_unlock;
 
 
@@ -747,7 +748,7 @@ out_bh_enable:
 	local_bh_enable();
 out:;
 }
-EXPORT_SYMBOL(icmp_send);
+EXPORT_SYMBOL(__icmp_send);
 
 
 static void icmp_socket_deliver(struct sk_buff *skb, u32 info)
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 857ec3dbb742..33edccfebc30 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -109,6 +109,7 @@ static size_t inet_sk_attr_size(struct sock *sk,
 		+ nla_total_size(1) /* INET_DIAG_TOS */
 		+ nla_total_size(1) /* INET_DIAG_TCLASS */
 		+ nla_total_size(4) /* INET_DIAG_MARK */
+		+ nla_total_size(4) /* INET_DIAG_CLASS_ID */
 		+ nla_total_size(sizeof(struct inet_diag_meminfo))
 		+ nla_total_size(sizeof(struct inet_diag_msg))
 		+ nla_total_size(SK_MEMINFO_VARS * sizeof(u32))
@@ -288,12 +289,19 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 			goto errout;
 	}
 
-	if (ext & (1 << (INET_DIAG_CLASS_ID - 1))) {
+	if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) ||
+	    ext & (1 << (INET_DIAG_TCLASS - 1))) {
 		u32 classid = 0;
 
 #ifdef CONFIG_SOCK_CGROUP_DATA
 		classid = sock_cgroup_classid(&sk->sk_cgrp_data);
 #endif
+		/* Fallback to socket priority if class id isn't set.
+		 * Classful qdiscs use it as direct reference to class.
+		 * For cgroup2 classid is always zero.
+		 */
+		if (!classid)
+			classid = sk->sk_priority;
 
 		if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid))
 			goto errout;
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 6ffee9d2b0e5..481cded81b2d 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -24,6 +24,62 @@
 #include <net/sock.h>
 #include <net/inet_frag.h>
 #include <net/inet_ecn.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+
+/* Use skb->cb to track consecutive/adjacent fragments coming at
+ * the end of the queue. Nodes in the rb-tree queue will
+ * contain "runs" of one or more adjacent fragments.
+ *
+ * Invariants:
+ * - next_frag is NULL at the tail of a "run";
+ * - the head of a "run" has the sum of all fragment lengths in frag_run_len.
+ */
+struct ipfrag_skb_cb {
+	union {
+		struct inet_skb_parm	h4;
+		struct inet6_skb_parm	h6;
+	};
+	struct sk_buff		*next_frag;
+	int			frag_run_len;
+};
+
+#define FRAG_CB(skb)		((struct ipfrag_skb_cb *)((skb)->cb))
+
+static void fragcb_clear(struct sk_buff *skb)
+{
+	RB_CLEAR_NODE(&skb->rbnode);
+	FRAG_CB(skb)->next_frag = NULL;
+	FRAG_CB(skb)->frag_run_len = skb->len;
+}
+
+/* Append skb to the last "run". */
+static void fragrun_append_to_last(struct inet_frag_queue *q,
+				   struct sk_buff *skb)
+{
+	fragcb_clear(skb);
+
+	FRAG_CB(q->last_run_head)->frag_run_len += skb->len;
+	FRAG_CB(q->fragments_tail)->next_frag = skb;
+	q->fragments_tail = skb;
+}
+
+/* Create a new "run" with the skb. */
+static void fragrun_create(struct inet_frag_queue *q, struct sk_buff *skb)
+{
+	BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb));
+	fragcb_clear(skb);
+
+	if (q->last_run_head)
+		rb_link_node(&skb->rbnode, &q->last_run_head->rbnode,
+			     &q->last_run_head->rbnode.rb_right);
+	else
+		rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node);
+	rb_insert_color(&skb->rbnode, &q->rb_fragments);
+
+	q->fragments_tail = skb;
+	q->last_run_head = skb;
+}
 
 /* Given the OR values of all fragments, apply RFC 3168 5.3 requirements
  * Value : 0xff if frame should be dropped.
@@ -122,6 +178,28 @@ static void inet_frag_destroy_rcu(struct rcu_head *head)
 	kmem_cache_free(f->frags_cachep, q);
 }
 
+unsigned int inet_frag_rbtree_purge(struct rb_root *root)
+{
+	struct rb_node *p = rb_first(root);
+	unsigned int sum = 0;
+
+	while (p) {
+		struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode);
+
+		p = rb_next(p);
+		rb_erase(&skb->rbnode, root);
+		while (skb) {
+			struct sk_buff *next = FRAG_CB(skb)->next_frag;
+
+			sum += skb->truesize;
+			kfree_skb(skb);
+			skb = next;
+		}
+	}
+	return sum;
+}
+EXPORT_SYMBOL(inet_frag_rbtree_purge);
+
 void inet_frag_destroy(struct inet_frag_queue *q)
 {
 	struct sk_buff *fp;
@@ -224,3 +302,218 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key)
 	return fq;
 }
 EXPORT_SYMBOL(inet_frag_find);
+
+int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb,
+			   int offset, int end)
+{
+	struct sk_buff *last = q->fragments_tail;
+
+	/* RFC5722, Section 4, amended by Errata ID : 3089
+	 *                          When reassembling an IPv6 datagram, if
+	 *   one or more its constituent fragments is determined to be an
+	 *   overlapping fragment, the entire datagram (and any constituent
+	 *   fragments) MUST be silently discarded.
+	 *
+	 * Duplicates, however, should be ignored (i.e. skb dropped, but the
+	 * queue/fragments kept for later reassembly).
+	 */
+	if (!last)
+		fragrun_create(q, skb);  /* First fragment. */
+	else if (last->ip_defrag_offset + last->len < end) {
+		/* This is the common case: skb goes to the end. */
+		/* Detect and discard overlaps. */
+		if (offset < last->ip_defrag_offset + last->len)
+			return IPFRAG_OVERLAP;
+		if (offset == last->ip_defrag_offset + last->len)
+			fragrun_append_to_last(q, skb);
+		else
+			fragrun_create(q, skb);
+	} else {
+		/* Binary search. Note that skb can become the first fragment,
+		 * but not the last (covered above).
+		 */
+		struct rb_node **rbn, *parent;
+
+		rbn = &q->rb_fragments.rb_node;
+		do {
+			struct sk_buff *curr;
+			int curr_run_end;
+
+			parent = *rbn;
+			curr = rb_to_skb(parent);
+			curr_run_end = curr->ip_defrag_offset +
+					FRAG_CB(curr)->frag_run_len;
+			if (end <= curr->ip_defrag_offset)
+				rbn = &parent->rb_left;
+			else if (offset >= curr_run_end)
+				rbn = &parent->rb_right;
+			else if (offset >= curr->ip_defrag_offset &&
+				 end <= curr_run_end)
+				return IPFRAG_DUP;
+			else
+				return IPFRAG_OVERLAP;
+		} while (*rbn);
+		/* Here we have parent properly set, and rbn pointing to
+		 * one of its NULL left/right children. Insert skb.
+		 */
+		fragcb_clear(skb);
+		rb_link_node(&skb->rbnode, parent, rbn);
+		rb_insert_color(&skb->rbnode, &q->rb_fragments);
+	}
+
+	skb->ip_defrag_offset = offset;
+
+	return IPFRAG_OK;
+}
+EXPORT_SYMBOL(inet_frag_queue_insert);
+
+void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
+			      struct sk_buff *parent)
+{
+	struct sk_buff *fp, *head = skb_rb_first(&q->rb_fragments);
+	struct sk_buff **nextp;
+	int delta;
+
+	if (head != skb) {
+		fp = skb_clone(skb, GFP_ATOMIC);
+		if (!fp)
+			return NULL;
+		FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag;
+		if (RB_EMPTY_NODE(&skb->rbnode))
+			FRAG_CB(parent)->next_frag = fp;
+		else
+			rb_replace_node(&skb->rbnode, &fp->rbnode,
+					&q->rb_fragments);
+		if (q->fragments_tail == skb)
+			q->fragments_tail = fp;
+		skb_morph(skb, head);
+		FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag;
+		rb_replace_node(&head->rbnode, &skb->rbnode,
+				&q->rb_fragments);
+		consume_skb(head);
+		head = skb;
+	}
+	WARN_ON(head->ip_defrag_offset != 0);
+
+	delta = -head->truesize;
+
+	/* Head of list must not be cloned. */
+	if (skb_unclone(head, GFP_ATOMIC))
+		return NULL;
+
+	delta += head->truesize;
+	if (delta)
+		add_frag_mem_limit(q->net, delta);
+
+	/* If the first fragment is fragmented itself, we split
+	 * it to two chunks: the first with data and paged part
+	 * and the second, holding only fragments.
+	 */
+	if (skb_has_frag_list(head)) {
+		struct sk_buff *clone;
+		int i, plen = 0;
+
+		clone = alloc_skb(0, GFP_ATOMIC);
+		if (!clone)
+			return NULL;
+		skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
+		skb_frag_list_init(head);
+		for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
+			plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
+		clone->data_len = head->data_len - plen;
+		clone->len = clone->data_len;
+		head->truesize += clone->truesize;
+		clone->csum = 0;
+		clone->ip_summed = head->ip_summed;
+		add_frag_mem_limit(q->net, clone->truesize);
+		skb_shinfo(head)->frag_list = clone;
+		nextp = &clone->next;
+	} else {
+		nextp = &skb_shinfo(head)->frag_list;
+	}
+
+	return nextp;
+}
+EXPORT_SYMBOL(inet_frag_reasm_prepare);
+
+void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
+			    void *reasm_data)
+{
+	struct sk_buff **nextp = (struct sk_buff **)reasm_data;
+	struct rb_node *rbn;
+	struct sk_buff *fp;
+
+	skb_push(head, head->data - skb_network_header(head));
+
+	/* Traverse the tree in order, to build frag_list. */
+	fp = FRAG_CB(head)->next_frag;
+	rbn = rb_next(&head->rbnode);
+	rb_erase(&head->rbnode, &q->rb_fragments);
+	while (rbn || fp) {
+		/* fp points to the next sk_buff in the current run;
+		 * rbn points to the next run.
+		 */
+		/* Go through the current run. */
+		while (fp) {
+			*nextp = fp;
+			nextp = &fp->next;
+			fp->prev = NULL;
+			memset(&fp->rbnode, 0, sizeof(fp->rbnode));
+			fp->sk = NULL;
+			head->data_len += fp->len;
+			head->len += fp->len;
+			if (head->ip_summed != fp->ip_summed)
+				head->ip_summed = CHECKSUM_NONE;
+			else if (head->ip_summed == CHECKSUM_COMPLETE)
+				head->csum = csum_add(head->csum, fp->csum);
+			head->truesize += fp->truesize;
+			fp = FRAG_CB(fp)->next_frag;
+		}
+		/* Move to the next run. */
+		if (rbn) {
+			struct rb_node *rbnext = rb_next(rbn);
+
+			fp = rb_to_skb(rbn);
+			rb_erase(rbn, &q->rb_fragments);
+			rbn = rbnext;
+		}
+	}
+	sub_frag_mem_limit(q->net, head->truesize);
+
+	*nextp = NULL;
+	head->next = NULL;
+	head->prev = NULL;
+	head->tstamp = q->stamp;
+}
+EXPORT_SYMBOL(inet_frag_reasm_finish);
+
+struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q)
+{
+	struct sk_buff *head;
+
+	if (q->fragments) {
+		head = q->fragments;
+		q->fragments = head->next;
+	} else {
+		struct sk_buff *skb;
+
+		head = skb_rb_first(&q->rb_fragments);
+		if (!head)
+			return NULL;
+		skb = FRAG_CB(head)->next_frag;
+		if (skb)
+			rb_replace_node(&head->rbnode, &skb->rbnode,
+					&q->rb_fragments);
+		else
+			rb_erase(&head->rbnode, &q->rb_fragments);
+		memset(&head->rbnode, 0, sizeof(head->rbnode));
+		barrier();
+	}
+	if (head == q->fragments_tail)
+		q->fragments_tail = NULL;
+
+	sub_frag_mem_limit(q->net, head->truesize);
+
+	return head;
+}
+EXPORT_SYMBOL(inet_frag_pull_head);
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index 64007ce87273..f9cef27907ed 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -215,6 +215,7 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base,
 			atomic_set(&p->rid, 0);
 			p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
 			p->rate_tokens = 0;
+			p->n_redirects = 0;
 			/* 60*HZ is arbitrary, but chosen enough high so that the first
 			 * calculation of tokens is at its maximum.
 			 */
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index d95b32af4a0e..5a1d39e32196 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -57,57 +57,6 @@
  */
 static const char ip_frag_cache_name[] = "ip4-frags";
 
-/* Use skb->cb to track consecutive/adjacent fragments coming at
- * the end of the queue. Nodes in the rb-tree queue will
- * contain "runs" of one or more adjacent fragments.
- *
- * Invariants:
- * - next_frag is NULL at the tail of a "run";
- * - the head of a "run" has the sum of all fragment lengths in frag_run_len.
- */
-struct ipfrag_skb_cb {
-	struct inet_skb_parm	h;
-	struct sk_buff		*next_frag;
-	int			frag_run_len;
-};
-
-#define FRAG_CB(skb)		((struct ipfrag_skb_cb *)((skb)->cb))
-
-static void ip4_frag_init_run(struct sk_buff *skb)
-{
-	BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb));
-
-	FRAG_CB(skb)->next_frag = NULL;
-	FRAG_CB(skb)->frag_run_len = skb->len;
-}
-
-/* Append skb to the last "run". */
-static void ip4_frag_append_to_last_run(struct inet_frag_queue *q,
-					struct sk_buff *skb)
-{
-	RB_CLEAR_NODE(&skb->rbnode);
-	FRAG_CB(skb)->next_frag = NULL;
-
-	FRAG_CB(q->last_run_head)->frag_run_len += skb->len;
-	FRAG_CB(q->fragments_tail)->next_frag = skb;
-	q->fragments_tail = skb;
-}
-
-/* Create a new "run" with the skb. */
-static void ip4_frag_create_run(struct inet_frag_queue *q, struct sk_buff *skb)
-{
-	if (q->last_run_head)
-		rb_link_node(&skb->rbnode, &q->last_run_head->rbnode,
-			     &q->last_run_head->rbnode.rb_right);
-	else
-		rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node);
-	rb_insert_color(&skb->rbnode, &q->rb_fragments);
-
-	ip4_frag_init_run(skb);
-	q->fragments_tail = skb;
-	q->last_run_head = skb;
-}
-
 /* Describe an entry in the "incomplete datagrams" queue. */
 struct ipq {
 	struct inet_frag_queue q;
@@ -212,27 +161,9 @@ static void ip_expire(struct timer_list *t)
 	 * pull the head out of the tree in order to be able to
 	 * deal with head->dev.
 	 */
-	if (qp->q.fragments) {
-		head = qp->q.fragments;
-		qp->q.fragments = head->next;
-	} else {
-		head = skb_rb_first(&qp->q.rb_fragments);
-		if (!head)
-			goto out;
-		if (FRAG_CB(head)->next_frag)
-			rb_replace_node(&head->rbnode,
-					&FRAG_CB(head)->next_frag->rbnode,
-					&qp->q.rb_fragments);
-		else
-			rb_erase(&head->rbnode, &qp->q.rb_fragments);
-		memset(&head->rbnode, 0, sizeof(head->rbnode));
-		barrier();
-	}
-	if (head == qp->q.fragments_tail)
-		qp->q.fragments_tail = NULL;
-
-	sub_frag_mem_limit(qp->q.net, head->truesize);
-
+	head = inet_frag_pull_head(&qp->q);
+	if (!head)
+		goto out;
 	head->dev = dev_get_by_index_rcu(net, qp->iif);
 	if (!head->dev)
 		goto out;
@@ -345,12 +276,10 @@ static int ip_frag_reinit(struct ipq *qp)
 static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 {
 	struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
-	struct rb_node **rbn, *parent;
-	struct sk_buff *skb1, *prev_tail;
-	int ihl, end, skb1_run_end;
+	int ihl, end, flags, offset;
+	struct sk_buff *prev_tail;
 	struct net_device *dev;
 	unsigned int fragsize;
-	int flags, offset;
 	int err = -ENOENT;
 	u8 ecn;
 
@@ -382,7 +311,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 		 */
 		if (end < qp->q.len ||
 		    ((qp->q.flags & INET_FRAG_LAST_IN) && end != qp->q.len))
-			goto err;
+			goto discard_qp;
 		qp->q.flags |= INET_FRAG_LAST_IN;
 		qp->q.len = end;
 	} else {
@@ -394,82 +323,33 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 		if (end > qp->q.len) {
 			/* Some bits beyond end -> corruption. */
 			if (qp->q.flags & INET_FRAG_LAST_IN)
-				goto err;
+				goto discard_qp;
 			qp->q.len = end;
 		}
 	}
 	if (end == offset)
-		goto err;
+		goto discard_qp;
 
 	err = -ENOMEM;
 	if (!pskb_pull(skb, skb_network_offset(skb) + ihl))
-		goto err;
+		goto discard_qp;
 
 	err = pskb_trim_rcsum(skb, end - offset);
 	if (err)
-		goto err;
+		goto discard_qp;
 
 	/* Note : skb->rbnode and skb->dev share the same location. */
 	dev = skb->dev;
 	/* Makes sure compiler wont do silly aliasing games */
 	barrier();
 
-	/* RFC5722, Section 4, amended by Errata ID : 3089
-	 *                          When reassembling an IPv6 datagram, if
-	 *   one or more its constituent fragments is determined to be an
-	 *   overlapping fragment, the entire datagram (and any constituent
-	 *   fragments) MUST be silently discarded.
-	 *
-	 * We do the same here for IPv4 (and increment an snmp counter) but
-	 * we do not want to drop the whole queue in response to a duplicate
-	 * fragment.
-	 */
-
-	err = -EINVAL;
-	/* Find out where to put this fragment.  */
 	prev_tail = qp->q.fragments_tail;
-	if (!prev_tail)
-		ip4_frag_create_run(&qp->q, skb);  /* First fragment. */
-	else if (prev_tail->ip_defrag_offset + prev_tail->len < end) {
-		/* This is the common case: skb goes to the end. */
-		/* Detect and discard overlaps. */
-		if (offset < prev_tail->ip_defrag_offset + prev_tail->len)
-			goto discard_qp;
-		if (offset == prev_tail->ip_defrag_offset + prev_tail->len)
-			ip4_frag_append_to_last_run(&qp->q, skb);
-		else
-			ip4_frag_create_run(&qp->q, skb);
-	} else {
-		/* Binary search. Note that skb can become the first fragment,
-		 * but not the last (covered above).
-		 */
-		rbn = &qp->q.rb_fragments.rb_node;
-		do {
-			parent = *rbn;
-			skb1 = rb_to_skb(parent);
-			skb1_run_end = skb1->ip_defrag_offset +
-				       FRAG_CB(skb1)->frag_run_len;
-			if (end <= skb1->ip_defrag_offset)
-				rbn = &parent->rb_left;
-			else if (offset >= skb1_run_end)
-				rbn = &parent->rb_right;
-			else if (offset >= skb1->ip_defrag_offset &&
-				 end <= skb1_run_end)
-				goto err; /* No new data, potential duplicate */
-			else
-				goto discard_qp; /* Found an overlap */
-		} while (*rbn);
-		/* Here we have parent properly set, and rbn pointing to
-		 * one of its NULL left/right children. Insert skb.
-		 */
-		ip4_frag_init_run(skb);
-		rb_link_node(&skb->rbnode, parent, rbn);
-		rb_insert_color(&skb->rbnode, &qp->q.rb_fragments);
-	}
+	err = inet_frag_queue_insert(&qp->q, skb, offset, end);
+	if (err)
+		goto insert_error;
 
 	if (dev)
 		qp->iif = dev->ifindex;
-	skb->ip_defrag_offset = offset;
 
 	qp->q.stamp = skb->tstamp;
 	qp->q.meat += skb->len;
@@ -494,15 +374,24 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 		skb->_skb_refdst = 0UL;
 		err = ip_frag_reasm(qp, skb, prev_tail, dev);
 		skb->_skb_refdst = orefdst;
+		if (err)
+			inet_frag_kill(&qp->q);
 		return err;
 	}
 
 	skb_dst_drop(skb);
 	return -EINPROGRESS;
 
+insert_error:
+	if (err == IPFRAG_DUP) {
+		kfree_skb(skb);
+		return -EINVAL;
+	}
+	err = -EINVAL;
+	__IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS);
 discard_qp:
 	inet_frag_kill(&qp->q);
-	__IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS);
+	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
 err:
 	kfree_skb(skb);
 	return err;
@@ -514,13 +403,8 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
 {
 	struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
 	struct iphdr *iph;
-	struct sk_buff *fp, *head = skb_rb_first(&qp->q.rb_fragments);
-	struct sk_buff **nextp; /* To build frag_list. */
-	struct rb_node *rbn;
-	int len;
-	int ihlen;
-	int delta;
-	int err;
+	void *reasm_data;
+	int len, err;
 	u8 ecn;
 
 	ipq_kill(qp);
@@ -530,117 +414,23 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
 		err = -EINVAL;
 		goto out_fail;
 	}
-	/* Make the one we just received the head. */
-	if (head != skb) {
-		fp = skb_clone(skb, GFP_ATOMIC);
-		if (!fp)
-			goto out_nomem;
-		FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag;
-		if (RB_EMPTY_NODE(&skb->rbnode))
-			FRAG_CB(prev_tail)->next_frag = fp;
-		else
-			rb_replace_node(&skb->rbnode, &fp->rbnode,
-					&qp->q.rb_fragments);
-		if (qp->q.fragments_tail == skb)
-			qp->q.fragments_tail = fp;
-		skb_morph(skb, head);
-		FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag;
-		rb_replace_node(&head->rbnode, &skb->rbnode,
-				&qp->q.rb_fragments);
-		consume_skb(head);
-		head = skb;
-	}
 
-	WARN_ON(head->ip_defrag_offset != 0);
-
-	/* Allocate a new buffer for the datagram. */
-	ihlen = ip_hdrlen(head);
-	len = ihlen + qp->q.len;
+	/* Make the one we just received the head. */
+	reasm_data = inet_frag_reasm_prepare(&qp->q, skb, prev_tail);
+	if (!reasm_data)
+		goto out_nomem;
 
+	len = ip_hdrlen(skb) + qp->q.len;
 	err = -E2BIG;
 	if (len > 65535)
 		goto out_oversize;
 
-	delta = - head->truesize;
-
-	/* Head of list must not be cloned. */
-	if (skb_unclone(head, GFP_ATOMIC))
-		goto out_nomem;
-
-	delta += head->truesize;
-	if (delta)
-		add_frag_mem_limit(qp->q.net, delta);
-
-	/* If the first fragment is fragmented itself, we split
-	 * it to two chunks: the first with data and paged part
-	 * and the second, holding only fragments. */
-	if (skb_has_frag_list(head)) {
-		struct sk_buff *clone;
-		int i, plen = 0;
-
-		clone = alloc_skb(0, GFP_ATOMIC);
-		if (!clone)
-			goto out_nomem;
-		skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
-		skb_frag_list_init(head);
-		for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
-			plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
-		clone->len = clone->data_len = head->data_len - plen;
-		head->truesize += clone->truesize;
-		clone->csum = 0;
-		clone->ip_summed = head->ip_summed;
-		add_frag_mem_limit(qp->q.net, clone->truesize);
-		skb_shinfo(head)->frag_list = clone;
-		nextp = &clone->next;
-	} else {
-		nextp = &skb_shinfo(head)->frag_list;
-	}
+	inet_frag_reasm_finish(&qp->q, skb, reasm_data);
 
-	skb_push(head, head->data - skb_network_header(head));
+	skb->dev = dev;
+	IPCB(skb)->frag_max_size = max(qp->max_df_size, qp->q.max_size);
 
-	/* Traverse the tree in order, to build frag_list. */
-	fp = FRAG_CB(head)->next_frag;
-	rbn = rb_next(&head->rbnode);
-	rb_erase(&head->rbnode, &qp->q.rb_fragments);
-	while (rbn || fp) {
-		/* fp points to the next sk_buff in the current run;
-		 * rbn points to the next run.
-		 */
-		/* Go through the current run. */
-		while (fp) {
-			*nextp = fp;
-			nextp = &fp->next;
-			fp->prev = NULL;
-			memset(&fp->rbnode, 0, sizeof(fp->rbnode));
-			fp->sk = NULL;
-			head->data_len += fp->len;
-			head->len += fp->len;
-			if (head->ip_summed != fp->ip_summed)
-				head->ip_summed = CHECKSUM_NONE;
-			else if (head->ip_summed == CHECKSUM_COMPLETE)
-				head->csum = csum_add(head->csum, fp->csum);
-			head->truesize += fp->truesize;
-			fp = FRAG_CB(fp)->next_frag;
-		}
-		/* Move to the next run. */
-		if (rbn) {
-			struct rb_node *rbnext = rb_next(rbn);
-
-			fp = rb_to_skb(rbn);
-			rb_erase(rbn, &qp->q.rb_fragments);
-			rbn = rbnext;
-		}
-	}
-	sub_frag_mem_limit(qp->q.net, head->truesize);
-
-	*nextp = NULL;
-	head->next = NULL;
-	head->prev = NULL;
-	head->dev = dev;
-	head->tstamp = qp->q.stamp;
-	IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size);
-
-	iph = ip_hdr(head);
+	iph = ip_hdr(skb);
 	iph->tot_len = htons(len);
 	iph->tos |= ecn;
 
@@ -653,7 +443,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
 	 * from one very small df-fragment and one large non-df frag.
 	 */
 	if (qp->max_df_size == qp->q.max_size) {
-		IPCB(head)->flags |= IPSKB_FRAG_PMTU;
+		IPCB(skb)->flags |= IPSKB_FRAG_PMTU;
 		iph->frag_off = htons(IP_DF);
 	} else {
 		iph->frag_off = 0;
@@ -751,28 +541,6 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
 }
 EXPORT_SYMBOL(ip_check_defrag);
 
-unsigned int inet_frag_rbtree_purge(struct rb_root *root)
-{
-	struct rb_node *p = rb_first(root);
-	unsigned int sum = 0;
-
-	while (p) {
-		struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode);
-
-		p = rb_next(p);
-		rb_erase(&skb->rbnode, root);
-		while (skb) {
-			struct sk_buff *next = FRAG_CB(skb)->next_frag;
-
-			sum += skb->truesize;
-			kfree_skb(skb);
-			skb = next;
-		}
-	}
-	return sum;
-}
-EXPORT_SYMBOL(inet_frag_rbtree_purge);
-
 #ifdef CONFIG_SYSCTL
 static int dist_min;
 
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 1b160378ea9c..6fc45d3a1f8a 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -259,11 +259,10 @@ int ip_local_deliver(struct sk_buff *skb)
 		       ip_local_deliver_finish);
 }
 
-static inline bool ip_rcv_options(struct sk_buff *skb)
+static inline bool ip_rcv_options(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip_options *opt;
 	const struct iphdr *iph;
-	struct net_device *dev = skb->dev;
 
 	/* It looks as overkill, because not all
 	   IP options require packet mangling.
@@ -299,7 +298,7 @@ static inline bool ip_rcv_options(struct sk_buff *skb)
 			}
 		}
 
-		if (ip_options_rcv_srr(skb))
+		if (ip_options_rcv_srr(skb, dev))
 			goto drop;
 	}
 
@@ -362,7 +361,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 	}
 #endif
 
-	if (iph->ihl > 5 && ip_rcv_options(skb))
+	if (iph->ihl > 5 && ip_rcv_options(skb, dev))
 		goto drop;
 
 	rt = skb_rtable(skb);
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index ed194d46c00e..3db31bb9df50 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -251,8 +251,9 @@ static void spec_dst_fill(__be32 *spec_dst, struct sk_buff *skb)
  * If opt == NULL, then skb->data should point to IP header.
  */
 
-int ip_options_compile(struct net *net,
-		       struct ip_options *opt, struct sk_buff *skb)
+int __ip_options_compile(struct net *net,
+			 struct ip_options *opt, struct sk_buff *skb,
+			 __be32 *info)
 {
 	__be32 spec_dst = htonl(INADDR_ANY);
 	unsigned char *pp_ptr = NULL;
@@ -468,11 +469,22 @@ eol:
 		return 0;
 
 error:
-	if (skb) {
-		icmp_send(skb, ICMP_PARAMETERPROB, 0, htonl((pp_ptr-iph)<<24));
-	}
+	if (info)
+		*info = htonl((pp_ptr-iph)<<24);
 	return -EINVAL;
 }
+
+int ip_options_compile(struct net *net,
+		       struct ip_options *opt, struct sk_buff *skb)
+{
+	int ret;
+	__be32 info;
+
+	ret = __ip_options_compile(net, opt, skb, &info);
+	if (ret != 0 && skb)
+		icmp_send(skb, ICMP_PARAMETERPROB, 0, info);
+	return ret;
+}
 EXPORT_SYMBOL(ip_options_compile);
 
 /*
@@ -600,7 +612,7 @@ void ip_forward_options(struct sk_buff *skb)
 	}
 }
 
-int ip_options_rcv_srr(struct sk_buff *skb)
+int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip_options *opt = &(IPCB(skb)->opt);
 	int srrspace, srrptr;
@@ -635,7 +647,7 @@ int ip_options_rcv_srr(struct sk_buff *skb)
 
 		orefdst = skb->_skb_refdst;
 		skb_dst_set(skb, NULL);
-		err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, skb->dev);
+		err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, dev);
 		rt2 = skb_rtable(skb);
 		if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) {
 			skb_dst_drop(skb);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index e2dd325bed9b..34d49f76d1a7 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -518,6 +518,7 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	to->pkt_type = from->pkt_type;
 	to->priority = from->priority;
 	to->protocol = from->protocol;
+	to->skb_iif = from->skb_iif;
 	skb_dst_drop(to);
 	skb_dst_copy(to, from);
 	to->dev = from->dev;
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 00d4371d4573..306603a7f351 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -74,6 +74,33 @@ drop:
 	return 0;
 }
 
+static int vti_input_ipip(struct sk_buff *skb, int nexthdr, __be32 spi,
+		     int encap_type)
+{
+	struct ip_tunnel *tunnel;
+	const struct iphdr *iph = ip_hdr(skb);
+	struct net *net = dev_net(skb->dev);
+	struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
+
+	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+				  iph->saddr, iph->daddr, 0);
+	if (tunnel) {
+		if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+			goto drop;
+
+		XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;
+
+		skb->dev = tunnel->dev;
+
+		return xfrm_input(skb, nexthdr, spi, encap_type);
+	}
+
+	return -EINVAL;
+drop:
+	kfree_skb(skb);
+	return 0;
+}
+
 static int vti_rcv(struct sk_buff *skb)
 {
 	XFRM_SPI_SKB_CB(skb)->family = AF_INET;
@@ -82,6 +109,14 @@ static int vti_rcv(struct sk_buff *skb)
 	return vti_input(skb, ip_hdr(skb)->protocol, 0, 0);
 }
 
+static int vti_rcv_ipip(struct sk_buff *skb)
+{
+	XFRM_SPI_SKB_CB(skb)->family = AF_INET;
+	XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
+
+	return vti_input_ipip(skb, ip_hdr(skb)->protocol, ip_hdr(skb)->saddr, 0);
+}
+
 static int vti_rcv_cb(struct sk_buff *skb, int err)
 {
 	unsigned short family;
@@ -439,6 +474,12 @@ static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = {
 	.priority	=	100,
 };
 
+static struct xfrm_tunnel ipip_handler __read_mostly = {
+	.handler	=	vti_rcv_ipip,
+	.err_handler	=	vti4_err,
+	.priority	=	0,
+};
+
 static int __net_init vti_init_net(struct net *net)
 {
 	int err;
@@ -607,6 +648,13 @@ static int __init vti_init(void)
 	if (err < 0)
 		goto xfrm_proto_comp_failed;
 
+	msg = "ipip tunnel";
+	err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
+	if (err < 0) {
+		pr_info("%s: cant't register tunnel\n",__func__);
+		goto xfrm_tunnel_failed;
+	}
+
 	msg = "netlink interface";
 	err = rtnl_link_register(&vti_link_ops);
 	if (err < 0)
@@ -616,6 +664,8 @@ static int __init vti_init(void)
 
 rtnl_link_failed:
 	xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
+xfrm_tunnel_failed:
+	xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
 xfrm_proto_comp_failed:
 	xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
 xfrm_proto_ah_failed:
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 7afa8d2463d8..6a7e187dd0a9 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -904,13 +904,15 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 	/* No redirected packets during ip_rt_redirect_silence;
 	 * reset the algorithm.
 	 */
-	if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence))
+	if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) {
 		peer->rate_tokens = 0;
+		peer->n_redirects = 0;
+	}
 
 	/* Too many ignored redirects; do not send anything
 	 * set dst.rate_last to the last seen redirected packet.
 	 */
-	if (peer->rate_tokens >= ip_rt_redirect_number) {
+	if (peer->n_redirects >= ip_rt_redirect_number) {
 		peer->rate_last = jiffies;
 		goto out_put_peer;
 	}
@@ -927,6 +929,7 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 		icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw);
 		peer->rate_last = jiffies;
 		++peer->rate_tokens;
+		++peer->n_redirects;
 #ifdef CONFIG_IP_ROUTE_VERBOSE
 		if (log_martians &&
 		    peer->rate_tokens == ip_rt_redirect_number)
@@ -1189,11 +1192,39 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
 	return dst;
 }
 
+static void ipv4_send_dest_unreach(struct sk_buff *skb)
+{
+	struct ip_options opt;
+	int res;
+
+	/* Recompile ip options since IPCB may not be valid anymore.
+	 * Also check we have a reasonable ipv4 header.
+	 */
+	if (!pskb_network_may_pull(skb, sizeof(struct iphdr)) ||
+	    ip_hdr(skb)->version != 4 || ip_hdr(skb)->ihl < 5)
+		return;
+
+	memset(&opt, 0, sizeof(opt));
+	if (ip_hdr(skb)->ihl > 5) {
+		if (!pskb_network_may_pull(skb, ip_hdr(skb)->ihl * 4))
+			return;
+		opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr);
+
+		rcu_read_lock();
+		res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL);
+		rcu_read_unlock();
+
+		if (res)
+			return;
+	}
+	__icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt);
+}
+
 static void ipv4_link_failure(struct sk_buff *skb)
 {
 	struct rtable *rt;
 
-	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
+	ipv4_send_dest_unreach(skb);
 
 	rt = skb_rtable(skb);
 	if (rt)
@@ -1312,6 +1343,10 @@ static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
 		if (fnhe->fnhe_daddr == daddr) {
 			rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
 				fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
+			/* set fnhe_daddr to 0 to ensure it won't bind with
+			 * new dsts in rt_bind_exception().
+			 */
+			fnhe->fnhe_daddr = 0;
 			fnhe_flush_routes(fnhe);
 			kfree_rcu(fnhe, rcu);
 			break;
@@ -2120,12 +2155,13 @@ int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 		int our = 0;
 		int err = -EINVAL;
 
-		if (in_dev)
-			our = ip_check_mc_rcu(in_dev, daddr, saddr,
-					      ip_hdr(skb)->protocol);
+		if (!in_dev)
+			return err;
+		our = ip_check_mc_rcu(in_dev, daddr, saddr,
+				      ip_hdr(skb)->protocol);
 
 		/* check l3 master if no match yet */
-		if ((!in_dev || !our) && netif_is_l3_slave(dev)) {
+		if (!our && netif_is_l3_slave(dev)) {
 			struct in_device *l3_in_dev;
 
 			l3_in_dev = __in_dev_get_rcu(skb->dev);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 77cf32a80952..2f871424925e 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -216,7 +216,12 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 		refcount_set(&req->rsk_refcnt, 1);
 		tcp_sk(child)->tsoffset = tsoff;
 		sock_rps_save_rxhash(child, skb);
-		inet_csk_reqsk_queue_add(sk, req, child);
+		if (!inet_csk_reqsk_queue_add(sk, req, child)) {
+			bh_unlock_sock(child);
+			sock_put(child);
+			child = NULL;
+			reqsk_put(req);
+		}
 	} else {
 		reqsk_free(req);
 	}
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index d82e8344fc54..e8caab8e2f5c 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -45,6 +45,7 @@ static int tcp_syn_retries_min = 1;
 static int tcp_syn_retries_max = MAX_TCP_SYNCNT;
 static int ip_ping_group_range_min[] = { 0, 0 };
 static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
+static int one_day_secs = 24 * 3600;
 
 /* obsolete */
 static int sysctl_tcp_low_latency __read_mostly;
@@ -552,7 +553,9 @@ static struct ctl_table ipv4_table[] = {
 		.data		= &sysctl_tcp_min_rtt_wlen,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one_day_secs
 	},
 	{
 		.procname	= "tcp_low_latency",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index fd14501ac3af..00ae9a1d44ed 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2347,7 +2347,6 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->write_seq += tp->max_window + 2;
 	if (tp->write_seq == 0)
 		tp->write_seq = 1;
-	icsk->icsk_backoff = 0;
 	tp->snd_cwnd = 2;
 	icsk->icsk_probes_out = 0;
 	tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 8b637f9f23a2..f0de9fb92f0d 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -66,11 +66,6 @@ static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA;
 module_param(dctcp_alpha_on_init, uint, 0644);
 MODULE_PARM_DESC(dctcp_alpha_on_init, "parameter for initial alpha value");
 
-static unsigned int dctcp_clamp_alpha_on_loss __read_mostly;
-module_param(dctcp_clamp_alpha_on_loss, uint, 0644);
-MODULE_PARM_DESC(dctcp_clamp_alpha_on_loss,
-		 "parameter for clamping alpha on loss");
-
 static struct tcp_congestion_ops dctcp_reno;
 
 static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca)
@@ -211,21 +206,23 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags)
 	}
 }
 
-static void dctcp_state(struct sock *sk, u8 new_state)
+static void dctcp_react_to_loss(struct sock *sk)
 {
-	if (dctcp_clamp_alpha_on_loss && new_state == TCP_CA_Loss) {
-		struct dctcp *ca = inet_csk_ca(sk);
+	struct dctcp *ca = inet_csk_ca(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
 
-		/* If this extension is enabled, we clamp dctcp_alpha to
-		 * max on packet loss; the motivation is that dctcp_alpha
-		 * is an indicator to the extend of congestion and packet
-		 * loss is an indicator of extreme congestion; setting
-		 * this in practice turned out to be beneficial, and
-		 * effectively assumes total congestion which reduces the
-		 * window by half.
-		 */
-		ca->dctcp_alpha = DCTCP_MAX_ALPHA;
-	}
+	ca->loss_cwnd = tp->snd_cwnd;
+	tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U);
+}
+
+static void dctcp_state(struct sock *sk, u8 new_state)
+{
+	if (new_state == TCP_CA_Recovery &&
+	    new_state != inet_csk(sk)->icsk_ca_state)
+		dctcp_react_to_loss(sk);
+	/* We handle RTO in dctcp_cwnd_event to ensure that we perform only
+	 * one loss-adjustment per RTT.
+	 */
 }
 
 static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
@@ -237,6 +234,9 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
 	case CA_EVENT_ECN_NO_CE:
 		dctcp_ce_state_1_to_0(sk);
 		break;
+	case CA_EVENT_LOSS:
+		dctcp_react_to_loss(sk);
+		break;
 	default:
 		/* Don't care for the rest. */
 		break;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e24c0d7adf65..657d33e2ff6a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -389,11 +389,12 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb)
 static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	int room;
+
+	room = min_t(int, tp->window_clamp, tcp_space(sk)) - tp->rcv_ssthresh;
 
 	/* Check #1 */
-	if (tp->rcv_ssthresh < tp->window_clamp &&
-	    (int)tp->rcv_ssthresh < tcp_space(sk) &&
-	    !tcp_under_memory_pressure(sk)) {
+	if (room > 0 && !tcp_under_memory_pressure(sk)) {
 		int incr;
 
 		/* Check #2. Increase window, if skb with such overhead
@@ -406,8 +407,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
 
 		if (incr) {
 			incr = max_t(int, incr, 2 * skb->len);
-			tp->rcv_ssthresh = min(tp->rcv_ssthresh + incr,
-					       tp->window_clamp);
+			tp->rcv_ssthresh += min(room, incr);
 			inet_csk(sk)->icsk_ack.quick |= 1;
 		}
 	}
@@ -6406,7 +6406,13 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		af_ops->send_synack(fastopen_sk, dst, &fl, req,
 				    &foc, TCP_SYNACK_FASTOPEN);
 		/* Add the child socket directly into the accept queue */
-		inet_csk_reqsk_queue_add(sk, req, fastopen_sk);
+		if (!inet_csk_reqsk_queue_add(sk, req, fastopen_sk)) {
+			reqsk_fastopen_remove(fastopen_sk, req, false);
+			bh_unlock_sock(fastopen_sk);
+			sock_put(fastopen_sk);
+			reqsk_put(req);
+			goto drop;
+		}
 		sk->sk_data_ready(sk);
 		bh_unlock_sock(fastopen_sk);
 		sock_put(fastopen_sk);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 31b34c0c2d5f..97a414dbdaf4 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -475,14 +475,15 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 		if (sock_owned_by_user(sk))
 			break;
 
+		skb = tcp_write_queue_head(sk);
+		if (WARN_ON_ONCE(!skb))
+			break;
+
 		icsk->icsk_backoff--;
 		icsk->icsk_rto = tp->srtt_us ? __tcp_set_rto(tp) :
 					       TCP_TIMEOUT_INIT;
 		icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX);
 
-		skb = tcp_write_queue_head(sk);
-		BUG_ON(!skb);
-
 		tcp_mstamp_refresh(tp);
 		delta_us = (u32)(tp->tcp_mstamp - skb->skb_mstamp);
 		remaining = icsk->icsk_rto -
@@ -1577,15 +1578,8 @@ EXPORT_SYMBOL(tcp_add_backlog);
 int tcp_filter(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcphdr *th = (struct tcphdr *)skb->data;
-	unsigned int eaten = skb->len;
-	int err;
 
-	err = sk_filter_trim_cap(sk, skb, th->doff * 4);
-	if (!err) {
-		eaten -= skb->len;
-		TCP_SKB_CB(skb)->end_seq -= eaten;
-	}
-	return err;
+	return sk_filter_trim_cap(sk, skb, th->doff * 4);
 }
 EXPORT_SYMBOL(tcp_filter);