10 files changed, 283 insertions, 223 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 47838509f5fd..d0cbc93fcf32 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3549,6 +3549,8 @@ static int napi_gro_complete(struct sk_buff *skb)
 	struct list_head *head = &offload_base;
 	int err = -ENOENT;
 
+	BUILD_BUG_ON(sizeof(struct napi_gro_cb) > sizeof(skb->cb));
+
 	if (NAPI_GRO_CB(skb)->count == 1) {
 		skb_shinfo(skb)->gso_size = 0;
 		goto out;
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 847c02b197b0..5e67defe2cb0 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -27,11 +27,7 @@
 
 #include <linux/fdtable.h>
 
-#define PRIOIDX_SZ 128
-
-static unsigned long prioidx_map[PRIOIDX_SZ];
-static DEFINE_SPINLOCK(prioidx_map_lock);
-static atomic_t max_prioidx = ATOMIC_INIT(0);
+#define PRIOMAP_MIN_SZ		128
 
 static inline struct cgroup_netprio_state *cgrp_netprio_state(struct cgroup *cgrp)
 {
@@ -39,136 +35,157 @@ static inline struct cgroup_netprio_state *cgrp_netprio_state(struct cgroup *cgr
 			    struct cgroup_netprio_state, css);
 }
 
-static int get_prioidx(u32 *prio)
-{
-	unsigned long flags;
-	u32 prioidx;
-
-	spin_lock_irqsave(&prioidx_map_lock, flags);
-	prioidx = find_first_zero_bit(prioidx_map, sizeof(unsigned long) * PRIOIDX_SZ);
-	if (prioidx == sizeof(unsigned long) * PRIOIDX_SZ) {
-		spin_unlock_irqrestore(&prioidx_map_lock, flags);
-		return -ENOSPC;
-	}
-	set_bit(prioidx, prioidx_map);
-	if (atomic_read(&max_prioidx) < prioidx)
-		atomic_set(&max_prioidx, prioidx);
-	spin_unlock_irqrestore(&prioidx_map_lock, flags);
-	*prio = prioidx;
-	return 0;
-}
-
-static void put_prioidx(u32 idx)
+/*
+ * Extend @dev->priomap so that it's large enough to accomodate
+ * @target_idx.  @dev->priomap.priomap_len > @target_idx after successful
+ * return.  Must be called under rtnl lock.
+ */
+static int extend_netdev_table(struct net_device *dev, u32 target_idx)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&prioidx_map_lock, flags);
-	clear_bit(idx, prioidx_map);
-	spin_unlock_irqrestore(&prioidx_map_lock, flags);
-}
+	struct netprio_map *old, *new;
+	size_t new_sz, new_len;
 
-static int extend_netdev_table(struct net_device *dev, u32 new_len)
-{
-	size_t new_size = sizeof(struct netprio_map) +
-			   ((sizeof(u32) * new_len));
-	struct netprio_map *new_priomap = kzalloc(new_size, GFP_KERNEL);
-	struct netprio_map *old_priomap;
+	/* is the existing priomap large enough? */
+	old = rtnl_dereference(dev->priomap);
+	if (old && old->priomap_len > target_idx)
+		return 0;
 
-	old_priomap  = rtnl_dereference(dev->priomap);
+	/*
+	 * Determine the new size.  Let's keep it power-of-two.  We start
+	 * from PRIOMAP_MIN_SZ and double it until it's large enough to
+	 * accommodate @target_idx.
+	 */
+	new_sz = PRIOMAP_MIN_SZ;
+	while (true) {
+		new_len = (new_sz - offsetof(struct netprio_map, priomap)) /
+			sizeof(new->priomap[0]);
+		if (new_len > target_idx)
+			break;
+		new_sz *= 2;
+		/* overflowed? */
+		if (WARN_ON(new_sz < PRIOMAP_MIN_SZ))
+			return -ENOSPC;
+	}
 
-	if (!new_priomap) {
+	/* allocate & copy */
+	new = kzalloc(new_sz, GFP_KERNEL);
+	if (!new) {
 		pr_warn("Unable to alloc new priomap!\n");
 		return -ENOMEM;
 	}
 
-	if (old_priomap)
-		memcpy(new_priomap->priomap, old_priomap->priomap,
-		       old_priomap->priomap_len *
-		       sizeof(old_priomap->priomap[0]));
+	if (old)
+		memcpy(new->priomap, old->priomap,
+		       old->priomap_len * sizeof(old->priomap[0]));
 
-	new_priomap->priomap_len = new_len;
+	new->priomap_len = new_len;
 
-	rcu_assign_pointer(dev->priomap, new_priomap);
-	if (old_priomap)
-		kfree_rcu(old_priomap, rcu);
+	/* install the new priomap */
+	rcu_assign_pointer(dev->priomap, new);
+	if (old)
+		kfree_rcu(old, rcu);
 	return 0;
 }
 
-static int write_update_netdev_table(struct net_device *dev)
+/**
+ * netprio_prio - return the effective netprio of a cgroup-net_device pair
+ * @cgrp: cgroup part of the target pair
+ * @dev: net_device part of the target pair
+ *
+ * Should be called under RCU read or rtnl lock.
+ */
+static u32 netprio_prio(struct cgroup *cgrp, struct net_device *dev)
+{
+	struct netprio_map *map = rcu_dereference_rtnl(dev->priomap);
+
+	if (map && cgrp->id < map->priomap_len)
+		return map->priomap[cgrp->id];
+	return 0;
+}
+
+/**
+ * netprio_set_prio - set netprio on a cgroup-net_device pair
+ * @cgrp: cgroup part of the target pair
+ * @dev: net_device part of the target pair
+ * @prio: prio to set
+ *
+ * Set netprio to @prio on @cgrp-@dev pair.  Should be called under rtnl
+ * lock and may fail under memory pressure for non-zero @prio.
+ */
+static int netprio_set_prio(struct cgroup *cgrp, struct net_device *dev,
+			    u32 prio)
 {
-	int ret = 0;
-	u32 max_len;
 	struct netprio_map *map;
+	int ret;
 
-	max_len = atomic_read(&max_prioidx) + 1;
+	/* avoid extending priomap for zero writes */
 	map = rtnl_dereference(dev->priomap);
-	if (!map || map->priomap_len < max_len)
-		ret = extend_netdev_table(dev, max_len);
+	if (!prio && (!map || map->priomap_len <= cgrp->id))
+		return 0;
 
-	return ret;
+	ret = extend_netdev_table(dev, cgrp->id);
+	if (ret)
+		return ret;
+
+	map = rtnl_dereference(dev->priomap);
+	map->priomap[cgrp->id] = prio;
+	return 0;
 }
 
-static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp)
+static struct cgroup_subsys_state *cgrp_css_alloc(struct cgroup *cgrp)
 {
 	struct cgroup_netprio_state *cs;
-	int ret = -EINVAL;
 
 	cs = kzalloc(sizeof(*cs), GFP_KERNEL);
 	if (!cs)
 		return ERR_PTR(-ENOMEM);
 
-	if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx)
-		goto out;
-
-	ret = get_prioidx(&cs->prioidx);
-	if (ret < 0) {
-		pr_warn("No space in priority index array\n");
-		goto out;
-	}
-
 	return &cs->css;
-out:
-	kfree(cs);
-	return ERR_PTR(ret);
 }
 
-static void cgrp_destroy(struct cgroup *cgrp)
+static int cgrp_css_online(struct cgroup *cgrp)
 {
-	struct cgroup_netprio_state *cs;
+	struct cgroup *parent = cgrp->parent;
 	struct net_device *dev;
-	struct netprio_map *map;
+	int ret = 0;
+
+	if (!parent)
+		return 0;
 
-	cs = cgrp_netprio_state(cgrp);
 	rtnl_lock();
+	/*
+	 * Inherit prios from the parent.  As all prios are set during
+	 * onlining, there is no need to clear them on offline.
+	 */
 	for_each_netdev(&init_net, dev) {
-		map = rtnl_dereference(dev->priomap);
-		if (map && cs->prioidx < map->priomap_len)
-			map->priomap[cs->prioidx] = 0;
+		u32 prio = netprio_prio(parent, dev);
+
+		ret = netprio_set_prio(cgrp, dev, prio);
+		if (ret)
+			break;
 	}
 	rtnl_unlock();
-	put_prioidx(cs->prioidx);
-	kfree(cs);
+	return ret;
+}
+
+static void cgrp_css_free(struct cgroup *cgrp)
+{
+	kfree(cgrp_netprio_state(cgrp));
 }
 
 static u64 read_prioidx(struct cgroup *cgrp, struct cftype *cft)
 {
-	return (u64)cgrp_netprio_state(cgrp)->prioidx;
+	return cgrp->id;
 }
 
 static int read_priomap(struct cgroup *cont, struct cftype *cft,
 			struct cgroup_map_cb *cb)
 {
 	struct net_device *dev;
-	u32 prioidx = cgrp_netprio_state(cont)->prioidx;
-	u32 priority;
-	struct netprio_map *map;
 
 	rcu_read_lock();
-	for_each_netdev_rcu(&init_net, dev) {
-		map = rcu_dereference(dev->priomap);
-		priority = (map && prioidx < map->priomap_len) ? map->priomap[prioidx] : 0;
-		cb->fill(cb, dev->name, priority);
-	}
+	for_each_netdev_rcu(&init_net, dev)
+		cb->fill(cb, dev->name, netprio_prio(cont, dev));
 	rcu_read_unlock();
 	return 0;
 }
@@ -176,66 +193,24 @@ static int read_priomap(struct cgroup *cont, struct cftype *cft,
 static int write_priomap(struct cgroup *cgrp, struct cftype *cft,
 			 const char *buffer)
 {
-	char *devname = kstrdup(buffer, GFP_KERNEL);
-	int ret = -EINVAL;
-	u32 prioidx = cgrp_netprio_state(cgrp)->prioidx;
-	unsigned long priority;
-	char *priostr;
+	char devname[IFNAMSIZ + 1];
 	struct net_device *dev;
-	struct netprio_map *map;
-
-	if (!devname)
-		return -ENOMEM;
-
-	/*
-	 * Minimally sized valid priomap string
-	 */
-	if (strlen(devname) < 3)
-		goto out_free_devname;
-
-	priostr = strstr(devname, " ");
-	if (!priostr)
-		goto out_free_devname;
-
-	/*
-	 *Separate the devname from the associated priority
-	 *and advance the priostr pointer to the priority value
-	 */
-	*priostr = '\0';
-	priostr++;
-
-	/*
-	 * If the priostr points to NULL, we're at the end of the passed
-	 * in string, and its not a valid write
-	 */
-	if (*priostr == '\0')
-		goto out_free_devname;
-
-	ret = kstrtoul(priostr, 10, &priority);
-	if (ret < 0)
-		goto out_free_devname;
+	u32 prio;
+	int ret;
 
-	ret = -ENODEV;
+	if (sscanf(buffer, "%"__stringify(IFNAMSIZ)"s %u", devname, &prio) != 2)
+		return -EINVAL;
 
 	dev = dev_get_by_name(&init_net, devname);
 	if (!dev)
-		goto out_free_devname;
+		return -ENODEV;
 
 	rtnl_lock();
-	ret = write_update_netdev_table(dev);
-	if (ret < 0)
-		goto out_put_dev;
 
-	map = rtnl_dereference(dev->priomap);
-	if (map)
-		map->priomap[prioidx] = priority;
+	ret = netprio_set_prio(cgrp, dev, prio);
 
-out_put_dev:
 	rtnl_unlock();
 	dev_put(dev);
-
-out_free_devname:
-	kfree(devname);
 	return ret;
 }
 
@@ -276,22 +251,13 @@ static struct cftype ss_files[] = {
 
 struct cgroup_subsys net_prio_subsys = {
 	.name		= "net_prio",
-	.create		= cgrp_create,
-	.destroy	= cgrp_destroy,
+	.css_alloc	= cgrp_css_alloc,
+	.css_online	= cgrp_css_online,
+	.css_free	= cgrp_css_free,
 	.attach		= net_prio_attach,
 	.subsys_id	= net_prio_subsys_id,
 	.base_cftypes	= ss_files,
 	.module		= THIS_MODULE,
-
-	/*
-	 * net_prio has artificial limit on the number of cgroups and
-	 * disallows nesting making it impossible to co-mount it with other
-	 * hierarchical subsystems.  Remove the artificially low PRIOIDX_SZ
-	 * limit and properly nest configuration such that children follow
-	 * their parents' configurations by default and are allowed to
-	 * override and remove the following.
-	 */
-	.broken_hierarchy = true,
 };
 
 static int netprio_device_event(struct notifier_block *unused,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index ac9e44a6ab2b..3ab989b0de42 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3032,7 +3032,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 	skb_shinfo(nskb)->gso_size = pinfo->gso_size;
 	pinfo->gso_size = 0;
 	skb_header_release(p);
-	nskb->prev = p;
+	NAPI_GRO_CB(nskb)->last = p;
 
 	nskb->data_len += p->len;
 	nskb->truesize += p->truesize;
@@ -3058,8 +3058,8 @@ merge:
 
 	__skb_pull(skb, offset);
 
-	p->prev->next = skb;
-	p->prev = skb;
+	NAPI_GRO_CB(p)->last->next = skb;
+	NAPI_GRO_CB(p)->last = skb;
 	skb_header_release(skb);
 
 done:
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index cb98cbed1973..7afa2c3c788f 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -44,6 +44,10 @@ struct inet_diag_entry {
 	u16 dport;
 	u16 family;
 	u16 userlocks;
+#if IS_ENABLED(CONFIG_IPV6)
+	struct in6_addr saddr_storage;	/* for IPv4-mapped-IPv6 addresses */
+	struct in6_addr daddr_storage;	/* for IPv4-mapped-IPv6 addresses */
+#endif
 };
 
 static DEFINE_MUTEX(inet_diag_table_mutex);
@@ -431,25 +435,31 @@ static int inet_diag_bc_run(const struct nlattr *_bc,
 				break;
 			}
 
-			if (cond->prefix_len == 0)
-				break;
-
 			if (op->code == INET_DIAG_BC_S_COND)
 				addr = entry->saddr;
 			else
 				addr = entry->daddr;
 
+			if (cond->family != AF_UNSPEC &&
+			    cond->family != entry->family) {
+				if (entry->family == AF_INET6 &&
+				    cond->family == AF_INET) {
+					if (addr[0] == 0 && addr[1] == 0 &&
+					    addr[2] == htonl(0xffff) &&
+					    bitstring_match(addr + 3,
+							    cond->addr,
+							    cond->prefix_len))
+						break;
+				}
+				yes = 0;
+				break;
+			}
+
+			if (cond->prefix_len == 0)
+				break;
 			if (bitstring_match(addr, cond->addr,
 					    cond->prefix_len))
 				break;
-			if (entry->family == AF_INET6 &&
-			    cond->family == AF_INET) {
-				if (addr[0] == 0 && addr[1] == 0 &&
-				    addr[2] == htonl(0xffff) &&
-				    bitstring_match(addr + 3, cond->addr,
-						    cond->prefix_len))
-					break;
-			}
 			yes = 0;
 			break;
 		}
@@ -512,6 +522,55 @@ static int valid_cc(const void *bc, int len, int cc)
 	return 0;
 }
 
+/* Validate an inet_diag_hostcond. */
+static bool valid_hostcond(const struct inet_diag_bc_op *op, int len,
+			   int *min_len)
+{
+	int addr_len;
+	struct inet_diag_hostcond *cond;
+
+	/* Check hostcond space. */
+	*min_len += sizeof(struct inet_diag_hostcond);
+	if (len < *min_len)
+		return false;
+	cond = (struct inet_diag_hostcond *)(op + 1);
+
+	/* Check address family and address length. */
+	switch (cond->family) {
+	case AF_UNSPEC:
+		addr_len = 0;
+		break;
+	case AF_INET:
+		addr_len = sizeof(struct in_addr);
+		break;
+	case AF_INET6:
+		addr_len = sizeof(struct in6_addr);
+		break;
+	default:
+		return false;
+	}
+	*min_len += addr_len;
+	if (len < *min_len)
+		return false;
+
+	/* Check prefix length (in bits) vs address length (in bytes). */
+	if (cond->prefix_len > 8 * addr_len)
+		return false;
+
+	return true;
+}
+
+/* Validate a port comparison operator. */
+static inline bool valid_port_comparison(const struct inet_diag_bc_op *op,
+					 int len, int *min_len)
+{
+	/* Port comparisons put the port in a follow-on inet_diag_bc_op. */
+	*min_len += sizeof(struct inet_diag_bc_op);
+	if (len < *min_len)
+		return false;
+	return true;
+}
+
 static int inet_diag_bc_audit(const void *bytecode, int bytecode_len)
 {
 	const void *bc = bytecode;
@@ -519,29 +578,39 @@ static int inet_diag_bc_audit(const void *bytecode, int bytecode_len)
 
 	while (len > 0) {
 		const struct inet_diag_bc_op *op = bc;
+		int min_len = sizeof(struct inet_diag_bc_op);
 
 //printk("BC: %d %d %d {%d} / %d\n", op->code, op->yes, op->no, op[1].no, len);
 		switch (op->code) {
-		case INET_DIAG_BC_AUTO:
 		case INET_DIAG_BC_S_COND:
 		case INET_DIAG_BC_D_COND:
+			if (!valid_hostcond(bc, len, &min_len))
+				return -EINVAL;
+			break;
 		case INET_DIAG_BC_S_GE:
 		case INET_DIAG_BC_S_LE:
 		case INET_DIAG_BC_D_GE:
 		case INET_DIAG_BC_D_LE:
-		case INET_DIAG_BC_JMP:
-			if (op->no < 4 || op->no > len + 4 || op->no & 3)
-				return -EINVAL;
-			if (op->no < len &&
-			    !valid_cc(bytecode, bytecode_len, len - op->no))
+			if (!valid_port_comparison(bc, len, &min_len))
 				return -EINVAL;
 			break;
+		case INET_DIAG_BC_AUTO:
+		case INET_DIAG_BC_JMP:
 		case INET_DIAG_BC_NOP:
 			break;
 		default:
 			return -EINVAL;
 		}
-		if (op->yes < 4 || op->yes > len + 4 || op->yes & 3)
+
+		if (op->code != INET_DIAG_BC_NOP) {
+			if (op->no < min_len || op->no > len + 4 || op->no & 3)
+				return -EINVAL;
+			if (op->no < len &&
+			    !valid_cc(bytecode, bytecode_len, len - op->no))
+				return -EINVAL;
+		}
+
+		if (op->yes < min_len || op->yes > len + 4 || op->yes & 3)
 			return -EINVAL;
 		bc  += op->yes;
 		len -= op->yes;
@@ -599,6 +668,36 @@ static int inet_twsk_diag_dump(struct inet_timewait_sock *tw,
 				   cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh);
 }
 
+/* Get the IPv4, IPv6, or IPv4-mapped-IPv6 local and remote addresses
+ * from a request_sock. For IPv4-mapped-IPv6 we must map IPv4 to IPv6.
+ */
+static inline void inet_diag_req_addrs(const struct sock *sk,
+				       const struct request_sock *req,
+				       struct inet_diag_entry *entry)
+{
+	struct inet_request_sock *ireq = inet_rsk(req);
+
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sk->sk_family == AF_INET6) {
+		if (req->rsk_ops->family == AF_INET6) {
+			entry->saddr = inet6_rsk(req)->loc_addr.s6_addr32;
+			entry->daddr = inet6_rsk(req)->rmt_addr.s6_addr32;
+		} else if (req->rsk_ops->family == AF_INET) {
+			ipv6_addr_set_v4mapped(ireq->loc_addr,
+					       &entry->saddr_storage);
+			ipv6_addr_set_v4mapped(ireq->rmt_addr,
+					       &entry->daddr_storage);
+			entry->saddr = entry->saddr_storage.s6_addr32;
+			entry->daddr = entry->daddr_storage.s6_addr32;
+		}
+	} else
+#endif
+	{
+		entry->saddr = &ireq->loc_addr;
+		entry->daddr = &ireq->rmt_addr;
+	}
+}
+
 static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk,
 			      struct request_sock *req,
 			      struct user_namespace *user_ns,
@@ -640,8 +739,10 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk,
 	r->idiag_inode = 0;
 #if IS_ENABLED(CONFIG_IPV6)
 	if (r->idiag_family == AF_INET6) {
-		*(struct in6_addr *)r->id.idiag_src = inet6_rsk(req)->loc_addr;
-		*(struct in6_addr *)r->id.idiag_dst = inet6_rsk(req)->rmt_addr;
+		struct inet_diag_entry entry;
+		inet_diag_req_addrs(sk, req, &entry);
+		memcpy(r->id.idiag_src, entry.saddr, sizeof(struct in6_addr));
+		memcpy(r->id.idiag_dst, entry.daddr, sizeof(struct in6_addr));
 	}
 #endif
 
@@ -694,18 +795,7 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk,
 				continue;
 
 			if (bc) {
-				entry.saddr =
-#if IS_ENABLED(CONFIG_IPV6)
-					(entry.family == AF_INET6) ?
-					inet6_rsk(req)->loc_addr.s6_addr32 :
-#endif
-					&ireq->loc_addr;
-				entry.daddr =
-#if IS_ENABLED(CONFIG_IPV6)
-					(entry.family == AF_INET6) ?
-					inet6_rsk(req)->rmt_addr.s6_addr32 :
-#endif
-					&ireq->rmt_addr;
+				inet_diag_req_addrs(sk, req, &entry);
 				entry.dport = ntohs(ireq->rmt_port);
 
 				if (!inet_diag_bc_run(bc, &entry))
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 1cf6a768cd53..eb9d63a570cd 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -707,28 +707,27 @@ EXPORT_SYMBOL(ip_defrag);
 
 struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user)
 {
-	const struct iphdr *iph;
+	struct iphdr iph;
 	u32 len;
 
 	if (skb->protocol != htons(ETH_P_IP))
 		return skb;
 
-	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+	if (!skb_copy_bits(skb, 0, &iph, sizeof(iph)))
 		return skb;
 
-	iph = ip_hdr(skb);
-	if (iph->ihl < 5 || iph->version != 4)
+	if (iph.ihl < 5 || iph.version != 4)
 		return skb;
-	if (!pskb_may_pull(skb, iph->ihl*4))
-		return skb;
-	iph = ip_hdr(skb);
-	len = ntohs(iph->tot_len);
-	if (skb->len < len || len < (iph->ihl * 4))
+
+	len = ntohs(iph.tot_len);
+	if (skb->len < len || len < (iph.ihl * 4))
 		return skb;
 
-	if (ip_is_fragment(ip_hdr(skb))) {
+	if (ip_is_fragment(&iph)) {
 		skb = skb_share_check(skb, GFP_ATOMIC);
 		if (skb) {
+			if (!pskb_may_pull(skb, iph.ihl*4))
+				return skb;
 			if (pskb_trim_rcsum(skb, len))
 				return skb;
 			memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 8fc5b3bd6075..1ca253635f7a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -831,8 +831,8 @@ static int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
 	return mss_now;
 }
 
-static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffset,
-			 size_t psize, int flags)
+static ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
+				size_t size, int flags)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	int mss_now, size_goal;
@@ -859,12 +859,9 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffse
 	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
 		goto out_err;
 
-	while (psize > 0) {
+	while (size > 0) {
 		struct sk_buff *skb = tcp_write_queue_tail(sk);
-		struct page *page = pages[poffset / PAGE_SIZE];
 		int copy, i;
-		int offset = poffset % PAGE_SIZE;
-		int size = min_t(size_t, psize, PAGE_SIZE - offset);
 		bool can_coalesce;
 
 		if (!tcp_send_head(sk) || (copy = size_goal - skb->len) <= 0) {
@@ -913,8 +910,8 @@ new_segment:
 			TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
 
 		copied += copy;
-		poffset += copy;
-		if (!(psize -= copy))
+		offset += copy;
+		if (!(size -= copy))
 			goto out;
 
 		if (skb->len < size_goal || (flags & MSG_OOB))
@@ -961,7 +958,7 @@ int tcp_sendpage(struct sock *sk, struct page *page, int offset,
 					flags);
 
 	lock_sock(sk);
-	res = do_tcp_sendpages(sk, &page, offset, size, flags);
+	res = do_tcp_sendpages(sk, page, offset, size, flags);
 	release_sock(sk);
 	return res;
 }
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index fc67831656e5..a13692560e63 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5652,7 +5652,11 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
 	tcp_fastopen_cache_set(sk, mss, cookie, syn_drop);
 
 	if (data) { /* Retransmit unacked data in SYN */
-		tcp_retransmit_skb(sk, data);
+		tcp_for_write_queue_from(data, sk) {
+			if (data == tcp_send_head(sk) ||
+			    __tcp_retransmit_skb(sk, data))
+				break;
+		}
 		tcp_rearm_rto(sk);
 		return true;
 	}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8ac085573217..5d451593ef16 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2309,12 +2309,11 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to,
  * state updates are done by the caller.  Returns non-zero if an
  * error occurred which prevented the send.
  */
-int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
+int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	unsigned int cur_mss;
-	int err;
 
 	/* Inconslusive MTU probe */
 	if (icsk->icsk_mtup.probe_size) {
@@ -2387,11 +2386,17 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	if (unlikely(NET_IP_ALIGN && ((unsigned long)skb->data & 3))) {
 		struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER,
 						   GFP_ATOMIC);
-		err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
-			     -ENOBUFS;
+		return nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
+			      -ENOBUFS;
 	} else {
-		err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
+		return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
 	}
+}
+
+int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	int err = __tcp_retransmit_skb(sk, skb);
 
 	if (err == 0) {
 		/* Update global TCP statistics. */
diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c
index 496ce2cebcd7..a68c88cdec6e 100644
--- a/net/irda/ircomm/ircomm_tty.c
+++ b/net/irda/ircomm/ircomm_tty.c
@@ -183,6 +183,7 @@ static void __exit __ircomm_tty_cleanup(struct ircomm_tty_cb *self)
 	ircomm_tty_shutdown(self);
 
 	self->magic = 0;
+	tty_port_destroy(&self->port);
 	kfree(self);
 }
 
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 709b0fb38a18..6db7855b9029 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -35,21 +35,25 @@ static inline struct cgroup_cls_state *task_cls_state(struct task_struct *p)
 			    struct cgroup_cls_state, css);
 }
 
-static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp)
+static struct cgroup_subsys_state *cgrp_css_alloc(struct cgroup *cgrp)
 {
 	struct cgroup_cls_state *cs;
 
 	cs = kzalloc(sizeof(*cs), GFP_KERNEL);
 	if (!cs)
 		return ERR_PTR(-ENOMEM);
+	return &cs->css;
+}
 
+static int cgrp_css_online(struct cgroup *cgrp)
+{
 	if (cgrp->parent)
-		cs->classid = cgrp_cls_state(cgrp->parent)->classid;
-
-	return &cs->css;
+		cgrp_cls_state(cgrp)->classid =
+			cgrp_cls_state(cgrp->parent)->classid;
+	return 0;
 }
 
-static void cgrp_destroy(struct cgroup *cgrp)
+static void cgrp_css_free(struct cgroup *cgrp)
 {
 	kfree(cgrp_cls_state(cgrp));
 }
@@ -98,21 +102,13 @@ static struct cftype ss_files[] = {
 
 struct cgroup_subsys net_cls_subsys = {
 	.name		= "net_cls",
-	.create		= cgrp_create,
-	.destroy	= cgrp_destroy,
+	.css_alloc	= cgrp_css_alloc,
+	.css_online	= cgrp_css_online,
+	.css_free	= cgrp_css_free,
 	.attach		= cgrp_attach,
 	.subsys_id	= net_cls_subsys_id,
 	.base_cftypes	= ss_files,
 	.module		= THIS_MODULE,
-
-	/*
-	 * While net_cls cgroup has the rudimentary hierarchy support of
-	 * inheriting the parent's classid on cgroup creation, it doesn't
-	 * properly propagates config changes in ancestors to their
-	 * descendents.  A child should follow the parent's configuration
-	 * but be allowed to override it.  Fix it and remove the following.
-	 */
-	.broken_hierarchy = true,
 };
 
 struct cls_cgroup_head {