3.10.23-stable review

@@ -85,7 +85,7 @@ static struct sk_buff *udp6_ufo_fragment
 
 	/* Check if there is enough headroom to insert fragment header. */
 	tnl_hlen = skb_tnl_header_len(skb);
-	if (skb_headroom(skb) < (tnl_hlen + frag_hdr_sz)) {
+	if (skb->mac_header < (tnl_hlen + frag_hdr_sz)) {
 		if (gso_pskb_expand_head(skb, tnl_hlen + frag_hdr_sz))
 			goto out;
 	}

@@ -264,6 +264,10 @@ static void *mlx4_en_add(struct mlx4_dev
 	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH)
 		mdev->port_cnt++;
 
+	/* Initialize time stamp mechanism */
+	if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)
+		mlx4_en_init_timestamp(mdev);
+
 	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) {
 		if (!dev->caps.comp_pool) {
 			mdev->profile.prof[i].rx_ring_num =

@@ -301,10 +305,6 @@ static void *mlx4_en_add(struct mlx4_dev
 			mdev->pndev[i] = NULL;
 	}
 
-	/* Initialize time stamp mechanism */
-	if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)
-		mlx4_en_init_timestamp(mdev);
-
 	return mdev;
 
 err_mr:

@@ -445,7 +445,8 @@ static int fib_nl_delrule(struct sk_buff
 		if (frh->action && (frh->action != rule->action))
 			continue;
 
-		if (frh->table && (frh_get_table(frh, tb) != rule->table))
+		if (frh_get_table(frh, tb) &&
+		    (frh_get_table(frh, tb) != rule->table))
 			continue;
 
 		if (tb[FRA_PRIORITY] &&

@@ -728,8 +728,11 @@ int rt6_route_rcv(struct net_device *dev
 		prefix = &prefix_buf;
 	}
 
-	rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, gwaddr,
-				dev->ifindex);
+	if (rinfo->prefix_len == 0)
+		rt = rt6_get_dflt_router(gwaddr, dev);
+	else
+		rt = rt6_get_route_info(net, prefix, rinfo->prefix_len,
+					gwaddr, dev->ifindex);
 
 	if (rt && !lifetime) {
 		ip6_del_rt(rt);

@@ -453,8 +453,10 @@ static int mem_check(struct sock *sk)
 	if (room > FL_MAX_SIZE - FL_MAX_PER_SOCK)
 		return 0;
 
+	rcu_read_lock_bh();
 	for_each_sk_fl_rcu(np, sfl)
 		count++;
+	rcu_read_unlock_bh();
 
 	if (room <= 0 ||
 	    ((count >= FL_MAX_PER_SOCK ||

@@ -50,9 +50,9 @@ static inline void prandom_seed_state(st
 {
 	u32 i = (seed >> 32) ^ (seed << 10) ^ seed;
 
-	state->s1 = __seed(i, 1);
-	state->s2 = __seed(i, 7);
-	state->s3 = __seed(i, 15);
+	state->s1 = __seed(i, 2);
+	state->s2 = __seed(i, 8);
+	state->s3 = __seed(i, 16);
 }
 
 #ifdef CONFIG_ARCH_RANDOM

@@ -141,7 +141,7 @@ void prandom_seed(u32 entropy)
 	 */
 	for_each_possible_cpu (i) {
 		struct rnd_state *state = &per_cpu(net_rand_state, i);
-		state->s1 = __seed(state->s1 ^ entropy, 1);
+		state->s1 = __seed(state->s1 ^ entropy, 2);
 	}
 }
 EXPORT_SYMBOL(prandom_seed);

@@ -158,9 +158,9 @@ static int __init prandom_init(void)
 		struct rnd_state *state = &per_cpu(net_rand_state,i);
 
 #define LCG(x)	((x) * 69069)	/* super-duper LCG */
-		state->s1 = __seed(LCG(i + jiffies), 1);
-		state->s2 = __seed(LCG(state->s1), 7);
-		state->s3 = __seed(LCG(state->s2), 15);
+		state->s1 = __seed(LCG(i + jiffies), 2);
+		state->s2 = __seed(LCG(state->s1), 8);
+		state->s3 = __seed(LCG(state->s2), 16);
 
 		/* "warm it up" */
 		prandom_u32_state(state);

@@ -187,9 +187,9 @@ static int __init prandom_reseed(void)
 		u32 seeds[3];
 
 		get_random_bytes(&seeds, sizeof(seeds));
-		state->s1 = __seed(seeds[0], 1);
-		state->s2 = __seed(seeds[1], 7);
-		state->s3 = __seed(seeds[2], 15);
+		state->s1 = __seed(seeds[0], 2);
+		state->s2 = __seed(seeds[1], 8);
+		state->s3 = __seed(seeds[2], 16);
 
 		/* mix it in */
 		prandom_u32_state(state);

@@ -537,8 +537,9 @@ static ssize_t bonding_store_arp_interva
 		goto out;
 	}
 	if (bond->params.mode == BOND_MODE_ALB ||
-	    bond->params.mode == BOND_MODE_TLB) {
-		pr_info("%s: ARP monitoring cannot be used with ALB/TLB. Only MII monitoring is supported on %s.\n",
+	    bond->params.mode == BOND_MODE_TLB ||
+	    bond->params.mode == BOND_MODE_8023AD) {
+		pr_info("%s: ARP monitoring cannot be used with ALB/TLB/802.3ad. Only MII monitoring is supported on %s.\n",
 			bond->dev->name, bond->dev->name);
 		ret = -EINVAL;
 		goto out;

@@ -206,9 +206,6 @@ static void intr_complete (struct urb *u
 		break;
 	}
 
-	if (!netif_running (dev->net))
-		return;
-
 	status = usb_submit_urb (urb, GFP_ATOMIC);
 	if (status != 0)
 		netif_err(dev, timer, dev->net,

@@ -862,7 +862,7 @@ lowpan_process_data(struct sk_buff *skb)
 	 * Traffic class carried in-line
 	 * ECN + DSCP (1 byte), Flow Label is elided
 	 */
-	case 1: /* 10b */
+	case 2: /* 10b */
 		if (lowpan_fetch_skb_u8(skb, &tmp))
 			goto drop;
 

@@ -875,7 +875,7 @@ lowpan_process_data(struct sk_buff *skb)
 	 * Flow Label carried in-line
 	 * ECN + 2-bit Pad + Flow Label (3 bytes), DSCP is elided
 	 */
-	case 2: /* 01b */
+	case 1: /* 01b */
 		if (lowpan_fetch_skb_u8(skb, &tmp))
 			goto drop;
 

@@ -1069,6 +1069,7 @@ static ssize_t tun_get_user(struct tun_s
 	struct sk_buff *skb;
 	size_t len = total_len, align = NET_SKB_PAD, linear;
 	struct virtio_net_hdr gso = { 0 };
+	int good_linear;
 	int offset = 0;
 	int copylen;
 	bool zerocopy = false;

@@ -1109,12 +1110,16 @@ static ssize_t tun_get_user(struct tun_s
 			return -EINVAL;
 	}
 
+	good_linear = SKB_MAX_HEAD(align);
+
 	if (msg_control) {
 		/* There are 256 bytes to be copied in skb, so there is
 		 * enough room for skb expand head in case it is used.
 		 * The rest of the buffer is mapped from userspace.
 		 */
 		copylen = gso.hdr_len ? gso.hdr_len : GOODCOPY_LEN;
+		if (copylen > good_linear)
+			copylen = good_linear;
 		linear = copylen;
 		if (iov_pages(iv, offset + copylen, count) <= MAX_SKB_FRAGS)
 			zerocopy = true;

@@ -1122,7 +1127,10 @@ static ssize_t tun_get_user(struct tun_s
 
 	if (!zerocopy) {
 		copylen = len;
-		linear = gso.hdr_len;
+		if (gso.hdr_len > good_linear)
+			linear = good_linear;
+		else
+			linear = gso.hdr_len;
 	}
 
 	skb = tun_alloc_skb(tfile, align, copylen, linear, noblock);

@@ -661,6 +661,7 @@ static ssize_t macvtap_get_user(struct m
 				const struct iovec *iv, unsigned long total_len,
 				size_t count, int noblock)
 {
+	int good_linear = SKB_MAX_HEAD(NET_IP_ALIGN);
 	struct sk_buff *skb;
 	struct macvlan_dev *vlan;
 	unsigned long len = total_len;

@@ -703,6 +704,8 @@ static ssize_t macvtap_get_user(struct m
 
 	if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) {
 		copylen = vnet_hdr.hdr_len ? vnet_hdr.hdr_len : GOODCOPY_LEN;
+		if (copylen > good_linear)
+			copylen = good_linear;
 		linear = copylen;
 		if (iov_pages(iv, vnet_hdr_len + copylen, count)
 		    <= MAX_SKB_FRAGS)

@@ -711,7 +714,10 @@ static ssize_t macvtap_get_user(struct m
 
 	if (!zerocopy) {
 		copylen = len;
-		linear = vnet_hdr.hdr_len;
+		if (vnet_hdr.hdr_len > good_linear)
+			linear = good_linear;
+		else
+			linear = vnet_hdr.hdr_len;
 	}
 
 	skb = macvtap_alloc_skb(&q->sk, NET_IP_ALIGN, copylen,

@@ -807,12 +807,6 @@ static unsigned int tcp_xmit_size_goal(s
 		xmit_size_goal = min_t(u32, gso_size,
 				       sk->sk_gso_max_size - 1 - hlen);
 
-		/* TSQ : try to have at least two segments in flight
-		 * (one in NIC TX ring, another in Qdisc)
-		 */
-		xmit_size_goal = min_t(u32, xmit_size_goal,
-				       sysctl_tcp_limit_output_bytes >> 1);
-
 		xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal);
 
 		/* We try hard to avoid divides here */

@@ -1866,8 +1866,12 @@ static bool tcp_write_xmit(struct sock *
 		 *  - better RTT estimation and ACK scheduling
 		 *  - faster recovery
 		 *  - high rates
+		 * Alas, some drivers / subsystems require a fair amount
+		 * of queued bytes to ensure line rate.
+		 * One example is wifi aggregation (802.11 AMPDU)
 		 */
-		limit = max(skb->truesize, sk->sk_pacing_rate >> 10);
+		limit = max_t(unsigned int, sysctl_tcp_limit_output_bytes,
+			      sk->sk_pacing_rate >> 10);
 
 		if (atomic_read(&sk->sk_wmem_alloc) > limit) {
 			set_bit(TSQ_THROTTLED, &tp->tsq_flags);

@@ -697,6 +697,8 @@ static ssize_t bonding_store_downdelay(s
 	int new_value, ret = count;
 	struct bonding *bond = to_bond(d);
 
+	if (!rtnl_trylock())
+		return restart_syscall();
 	if (!(bond->params.miimon)) {
 		pr_err("%s: Unable to set down delay as MII monitoring is disabled\n",
 		       bond->dev->name);

@@ -730,6 +732,7 @@ static ssize_t bonding_store_downdelay(s
 	}
 
 out:
+	rtnl_unlock();
 	return ret;
 }
 static DEVICE_ATTR(downdelay, S_IRUGO | S_IWUSR,

@@ -752,6 +755,8 @@ static ssize_t bonding_store_updelay(str
 	int new_value, ret = count;
 	struct bonding *bond = to_bond(d);
 
+	if (!rtnl_trylock())
+		return restart_syscall();
 	if (!(bond->params.miimon)) {
 		pr_err("%s: Unable to set up delay as MII monitoring is disabled\n",
 		       bond->dev->name);

@@ -785,6 +790,7 @@ static ssize_t bonding_store_updelay(str
 	}
 
 out:
+	rtnl_unlock();
 	return ret;
 }
 static DEVICE_ATTR(updelay, S_IRUGO | S_IWUSR,

@@ -665,10 +665,13 @@ void tcp_fastopen_cache_get(struct sock
 void tcp_fastopen_cache_set(struct sock *sk, u16 mss,
 			    struct tcp_fastopen_cookie *cookie, bool syn_lost)
 {
+	struct dst_entry *dst = __sk_dst_get(sk);
 	struct tcp_metrics_block *tm;
 
+	if (!dst)
+		return;
 	rcu_read_lock();
-	tm = tcp_get_metrics(sk, __sk_dst_get(sk), true);
+	tm = tcp_get_metrics(sk, dst, true);
 	if (tm) {
 		struct tcp_fastopen_metrics *tfom = &tm->tcpm_fastopen;
 

@@ -1083,8 +1083,10 @@ isdnloop_start(isdnloop_card *card, isdn
 			spin_unlock_irqrestore(&card->isdnloop_lock, flags);
 			return -ENOMEM;
 		}
-		for (i = 0; i < 3; i++)
-			strcpy(card->s0num[i], sdef.num[i]);
+		for (i = 0; i < 3; i++) {
+			strlcpy(card->s0num[i], sdef.num[i],
+				sizeof(card->s0num[0]));
+		}
 		break;
 	case ISDN_PTYPE_1TR6:
 		if (isdnloop_fake(card, "DRV1.04TC-1TR6-CAPI-CNS-BASIS-29.11.95",

@@ -1097,7 +1099,7 @@ isdnloop_start(isdnloop_card *card, isdn
 			spin_unlock_irqrestore(&card->isdnloop_lock, flags);
 			return -ENOMEM;
 		}
-		strcpy(card->s0num[0], sdef.num[0]);
+		strlcpy(card->s0num[0], sdef.num[0], sizeof(card->s0num[0]));
 		card->s0num[1][0] = '\0';
 		card->s0num[2][0] = '\0';
 		break;

@@ -32,11 +32,23 @@
 #include <linux/atomic.h>
 #include <linux/pid_namespace.h>
 
-#include <asm/unaligned.h>
-
 #include <linux/cn_proc.h>
 
-#define CN_PROC_MSG_SIZE (sizeof(struct cn_msg) + sizeof(struct proc_event))
+/*
+ * Size of a cn_msg followed by a proc_event structure.  Since the
+ * sizeof struct cn_msg is a multiple of 4 bytes, but not 8 bytes, we
+ * add one 4-byte word to the size here, and then start the actual
+ * cn_msg structure 4 bytes into the stack buffer.  The result is that
+ * the immediately following proc_event structure is aligned to 8 bytes.
+ */
+#define CN_PROC_MSG_SIZE (sizeof(struct cn_msg) + sizeof(struct proc_event) + 4)
+
+/* See comment above; we test our assumption about sizeof struct cn_msg here. */
+static inline struct cn_msg *buffer_to_cn_msg(__u8 *buffer)
+{
+	BUILD_BUG_ON(sizeof(struct cn_msg) != 20);
+	return (struct cn_msg *)(buffer + 4);
+}
 
 static atomic_t proc_event_num_listeners = ATOMIC_INIT(0);
 static struct cb_id cn_proc_event_id = { CN_IDX_PROC, CN_VAL_PROC };

@@ -56,19 +68,19 @@ void proc_fork_connector(struct task_str
 {
 	struct cn_msg *msg;
 	struct proc_event *ev;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 	struct timespec ts;
 	struct task_struct *parent;
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg *)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 	ev->what = PROC_EVENT_FORK;
 	rcu_read_lock();
 	parent = rcu_dereference(task->real_parent);

@@ -91,17 +103,17 @@ void proc_exec_connector(struct task_str
 	struct cn_msg *msg;
 	struct proc_event *ev;
 	struct timespec ts;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg *)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 	ev->what = PROC_EVENT_EXEC;
 	ev->event_data.exec.process_pid = task->pid;
 	ev->event_data.exec.process_tgid = task->tgid;

@@ -117,14 +129,14 @@ void proc_id_connector(struct task_struc
 {
 	struct cn_msg *msg;
 	struct proc_event *ev;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 	struct timespec ts;
 	const struct cred *cred;
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg *)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	ev->what = which_id;

@@ -145,7 +157,7 @@ void proc_id_connector(struct task_struc
 	rcu_read_unlock();
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 
 	memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
 	msg->ack = 0; /* not used */

@@ -159,17 +171,17 @@ void proc_sid_connector(struct task_stru
 	struct cn_msg *msg;
 	struct proc_event *ev;
 	struct timespec ts;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg *)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 	ev->what = PROC_EVENT_SID;
 	ev->event_data.sid.process_pid = task->pid;
 	ev->event_data.sid.process_tgid = task->tgid;

@@ -186,17 +198,17 @@ void proc_ptrace_connector(struct task_s
 	struct cn_msg *msg;
 	struct proc_event *ev;
 	struct timespec ts;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg *)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 	ev->what = PROC_EVENT_PTRACE;
 	ev->event_data.ptrace.process_pid  = task->pid;
 	ev->event_data.ptrace.process_tgid = task->tgid;

@@ -221,17 +233,17 @@ void proc_comm_connector(struct task_str
 	struct cn_msg *msg;
 	struct proc_event *ev;
 	struct timespec ts;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg *)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 	ev->what = PROC_EVENT_COMM;
 	ev->event_data.comm.process_pid  = task->pid;
 	ev->event_data.comm.process_tgid = task->tgid;

@@ -248,18 +260,18 @@ void proc_coredump_connector(struct task
 {
 	struct cn_msg *msg;
 	struct proc_event *ev;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 	struct timespec ts;
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg *)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 	ev->what = PROC_EVENT_COREDUMP;
 	ev->event_data.coredump.process_pid = task->pid;
 	ev->event_data.coredump.process_tgid = task->tgid;

@@ -275,18 +287,18 @@ void proc_exit_connector(struct task_str
 {
 	struct cn_msg *msg;
 	struct proc_event *ev;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 	struct timespec ts;
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg *)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 	ev->what = PROC_EVENT_EXIT;
 	ev->event_data.exit.process_pid = task->pid;
 	ev->event_data.exit.process_tgid = task->tgid;

@@ -312,18 +324,18 @@ static void cn_proc_ack(int err, int rcv
 {
 	struct cn_msg *msg;
 	struct proc_event *ev;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 	struct timespec ts;
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg *)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	msg->seq = rcvd_seq;
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 	ev->cpu = -1;
 	ev->what = PROC_EVENT_NONE;
 	ev->event_data.ack.err = err;

@@ -57,7 +57,7 @@ int ip4_datagram_connect(struct sock *sk
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);
 		if (err == -ENETUNREACH)
-			IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
+			IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
 		goto out;
 	}
 

@@ -315,9 +315,8 @@ static int dgram_recvmsg(struct kiocb *i
 	if (saddr) {
 		saddr->family = AF_IEEE802154;
 		saddr->addr = mac_cb(skb)->sa;
-	}
-	if (addr_len)
 		*addr_len = sizeof(*saddr);
+	}
 
 	if (flags & MSG_TRUNC)
 		copied = skb->len;

@@ -626,7 +626,6 @@ static int ping_recvmsg(struct kiocb *io
 			size_t len, int noblock, int flags, int *addr_len)
 {
 	struct inet_sock *isk = inet_sk(sk);
-	struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
 	struct sk_buff *skb;
 	int copied, err;
 

@@ -636,9 +635,6 @@ static int ping_recvmsg(struct kiocb *io
 	if (flags & MSG_OOB)
 		goto out;
 
-	if (addr_len)
-		*addr_len = sizeof(*sin);
-
 	if (flags & MSG_ERRQUEUE)
 		return ip_recv_error(sk, msg, len);
 

@@ -660,11 +656,14 @@ static int ping_recvmsg(struct kiocb *io
 	sock_recv_timestamp(msg, sk, skb);
 
 	/* Copy the address. */
-	if (sin) {
+	if (msg->msg_name) {
+		struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
+
 		sin->sin_family = AF_INET;
 		sin->sin_port = 0 /* skb->h.uh->source */;
 		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
 		memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+		*addr_len = sizeof(*sin);
 	}
 	if (isk->cmsg_flags)
 		ip_cmsg_recv(msg, skb);

@@ -692,9 +692,6 @@ static int raw_recvmsg(struct kiocb *ioc
 	if (flags & MSG_OOB)
 		goto out;
 
-	if (addr_len)
-		*addr_len = sizeof(*sin);
-
 	if (flags & MSG_ERRQUEUE) {
 		err = ip_recv_error(sk, msg, len);
 		goto out;

@@ -722,6 +719,7 @@ static int raw_recvmsg(struct kiocb *ioc
 		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
 		sin->sin_port = 0;
 		memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
+		*addr_len = sizeof(*sin);
 	}
 	if (inet->cmsg_flags)
 		ip_cmsg_recv(msg, skb);

@@ -1207,12 +1207,6 @@ int udp_recvmsg(struct kiocb *iocb, stru
 	int is_udplite = IS_UDPLITE(sk);
 	bool slow;
 
-	/*
-	 *	Check any passed addresses
-	 */
-	if (addr_len)
-		*addr_len = sizeof(*sin);
-
 	if (flags & MSG_ERRQUEUE)
 		return ip_recv_error(sk, msg, len);
 

@@ -1274,6 +1268,7 @@ try_again:
 		sin->sin_port = udp_hdr(skb)->source;
 		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
 		memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+		*addr_len = sizeof(*sin);
 	}
 	if (inet->cmsg_flags)
 		ip_cmsg_recv(msg, skb);

@@ -459,9 +459,6 @@ static int rawv6_recvmsg(struct kiocb *i
 	if (flags & MSG_OOB)
 		return -EOPNOTSUPP;
 
-	if (addr_len)
-		*addr_len=sizeof(*sin6);
-
 	if (flags & MSG_ERRQUEUE)
 		return ipv6_recv_error(sk, msg, len);
 

@@ -500,6 +497,7 @@ static int rawv6_recvmsg(struct kiocb *i
 		sin6->sin6_flowinfo = 0;
 		sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr,
 							  IP6CB(skb)->iif);
+		*addr_len = sizeof(*sin6);
 	}
 
 	sock_recv_ts_and_drops(msg, sk, skb);

@@ -373,9 +373,6 @@ int udpv6_recvmsg(struct kiocb *iocb, st
 	int is_udp4;
 	bool slow;
 
-	if (addr_len)
-		*addr_len = sizeof(struct sockaddr_in6);
-
 	if (flags & MSG_ERRQUEUE)
 		return ipv6_recv_error(sk, msg, len);
 

@@ -461,7 +458,7 @@ try_again:
 				ipv6_iface_scope_id(&sin6->sin6_addr,
 						    IP6CB(skb)->iif);
 		}
-
+		*addr_len = sizeof(*sin6);
 	}
 	if (is_udp4) {
 		if (inet->cmsg_flags)

@@ -518,9 +518,6 @@ static int l2tp_ip_recvmsg(struct kiocb
 	if (flags & MSG_OOB)
 		goto out;
 
-	if (addr_len)
-		*addr_len = sizeof(*sin);
-
 	skb = skb_recv_datagram(sk, flags, noblock, &err);
 	if (!skb)
 		goto out;

@@ -543,6 +540,7 @@ static int l2tp_ip_recvmsg(struct kiocb
 		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
 		sin->sin_port = 0;
 		memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
+		*addr_len = sizeof(*sin);
 	}
 	if (inet->cmsg_flags)
 		ip_cmsg_recv(msg, skb);

@@ -139,9 +139,6 @@ static int pn_recvmsg(struct kiocb *iocb
 			MSG_CMSG_COMPAT))
 		goto out_nofree;
 
-	if (addr_len)
-		*addr_len = sizeof(sa);
-
 	skb = skb_recv_datagram(sk, flags, noblock, &rval);
 	if (skb == NULL)
 		goto out_nofree;

@@ -162,8 +159,10 @@ static int pn_recvmsg(struct kiocb *iocb
 
 	rval = (flags & MSG_TRUNC) ? skb->len : copylen;
 
-	if (msg->msg_name != NULL)
-		memcpy(msg->msg_name, &sa, sizeof(struct sockaddr_pn));
+	if (msg->msg_name != NULL) {
+		memcpy(msg->msg_name, &sa, sizeof(sa));
+		*addr_len = sizeof(sa);
+	}
 
 out:
 	skb_free_datagram(sk, skb);

@@ -161,8 +161,6 @@ static int hash_recvmsg(struct kiocb *un
 	else if (len < ds)
 		msg->msg_flags |= MSG_TRUNC;
 
-	msg->msg_namelen = 0;
-
 	lock_sock(sk);
 	if (ctx->more) {
 		ctx->more = 0;

@@ -432,7 +432,6 @@ static int skcipher_recvmsg(struct kiocb
 	long copied = 0;
 
 	lock_sock(sk);
-	msg->msg_namelen = 0;
 	for (iov = msg->msg_iov, iovlen = msg->msg_iovlen; iovlen > 0;
 	     iovlen--, iov++) {
 		unsigned long seglen = iov->iov_len;

@@ -117,7 +117,6 @@ mISDN_sock_recvmsg(struct kiocb *iocb, s
 {
 	struct sk_buff		*skb;
 	struct sock		*sk = sock->sk;
-	struct sockaddr_mISDN	*maddr;
 
 	int		copied, err;
 

@@ -135,9 +134,9 @@ mISDN_sock_recvmsg(struct kiocb *iocb, s
 	if (!skb)
 		return err;
 
-	if (msg->msg_namelen >= sizeof(struct sockaddr_mISDN)) {
-		msg->msg_namelen = sizeof(struct sockaddr_mISDN);
-		maddr = (struct sockaddr_mISDN *)msg->msg_name;
+	if (msg->msg_name) {
+		struct sockaddr_mISDN *maddr = msg->msg_name;
+
 		maddr->family = AF_ISDN;
 		maddr->dev = _pms(sk)->dev->id;
 		if ((sk->sk_protocol == ISDN_P_LAPD_TE) ||

@@ -150,11 +149,7 @@ mISDN_sock_recvmsg(struct kiocb *iocb, s
 			maddr->sapi = _pms(sk)->ch.addr & 0xFF;
 			maddr->tei =  (_pms(sk)->ch.addr >> 8) & 0xFF;
 		}
-	} else {
-		if (msg->msg_namelen)
-			printk(KERN_WARNING "%s: too small namelen %d\n",
-			       __func__, msg->msg_namelen);
-		msg->msg_namelen = 0;
+		msg->msg_namelen = sizeof(*maddr);
 	}
 
 	copied = skb->len + MISDN_HEADER_LEN;

@@ -979,8 +979,6 @@ static int pppoe_recvmsg(struct kiocb *i
 	if (error < 0)
 		goto end;
 
-	m->msg_namelen = 0;
-
 	if (skb) {
 		total_len = min_t(size_t, total_len, skb->len);
 		error = skb_copy_datagram_iovec(skb, 0, m->msg_iov, total_len);

@@ -163,6 +163,14 @@ struct proto_ops {
 #endif
 	int		(*sendmsg)   (struct kiocb *iocb, struct socket *sock,
 				      struct msghdr *m, size_t total_len);
+	/* Notes for implementing recvmsg:
+	 * ===============================
+	 * msg->msg_namelen should get updated by the recvmsg handlers
+	 * iff msg_name != NULL. It is by default 0 to prevent
+	 * returning uninitialized memory to user space.  The recvfrom
+	 * handlers can assume that msg.msg_name is either NULL or has
+	 * a minimum size of sizeof(struct sockaddr_storage).
+	 */
 	int		(*recvmsg)   (struct kiocb *iocb, struct socket *sock,
 				      struct msghdr *m, size_t total_len,
 				      int flags);

@@ -1735,7 +1735,6 @@ static int atalk_recvmsg(struct kiocb *i
 			 size_t size, int flags)
 {
 	struct sock *sk = sock->sk;
-	struct sockaddr_at *sat = (struct sockaddr_at *)msg->msg_name;
 	struct ddpehdr *ddp;
 	int copied = 0;
 	int offset = 0;

@@ -1764,14 +1763,13 @@ static int atalk_recvmsg(struct kiocb *i
 	}
 	err = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copied);
 
-	if (!err) {
-		if (sat) {
-			sat->sat_family      = AF_APPLETALK;
-			sat->sat_port        = ddp->deh_sport;
-			sat->sat_addr.s_node = ddp->deh_snode;
-			sat->sat_addr.s_net  = ddp->deh_snet;
-		}
-		msg->msg_namelen = sizeof(*sat);
+	if (!err && msg->msg_name) {
+		struct sockaddr_at *sat = msg->msg_name;
+		sat->sat_family      = AF_APPLETALK;
+		sat->sat_port        = ddp->deh_sport;
+		sat->sat_addr.s_node = ddp->deh_snode;
+		sat->sat_addr.s_net  = ddp->deh_snet;
+		msg->msg_namelen     = sizeof(*sat);
 	}
 
 	skb_free_datagram(sk, skb);	/* Free the datagram. */

@@ -531,8 +531,6 @@ int vcc_recvmsg(struct kiocb *iocb, stru
 	struct sk_buff *skb;
 	int copied, error = -EINVAL;
 
-	msg->msg_namelen = 0;
-
 	if (sock->state != SS_CONNECTED)
 		return -ENOTCONN;
 

@@ -1636,11 +1636,11 @@ static int ax25_recvmsg(struct kiocb *io
 
 	skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
 
-	if (msg->msg_namelen != 0) {
-		struct sockaddr_ax25 *sax = (struct sockaddr_ax25 *)msg->msg_name;
+	if (msg->msg_name) {
 		ax25_digi digi;
 		ax25_address src;
 		const unsigned char *mac = skb_mac_header(skb);
+		struct sockaddr_ax25 *sax = msg->msg_name;
 
 		memset(sax, 0, sizeof(struct full_sockaddr_ax25));
 		ax25_addr_parse(mac + 1, skb->data - mac - 1, &src, NULL,

@@ -221,8 +221,6 @@ int bt_sock_recvmsg(struct kiocb *iocb,
 	if (flags & (MSG_OOB))
 		return -EOPNOTSUPP;
 
-	msg->msg_namelen = 0;
-
 	skb = skb_recv_datagram(sk, flags, noblock, &err);
 	if (!skb) {
 		if (sk->sk_shutdown & RCV_SHUTDOWN)

@@ -287,8 +285,6 @@ int bt_sock_stream_recvmsg(struct kiocb
 	if (flags & MSG_OOB)
 		return -EOPNOTSUPP;
 
-	msg->msg_namelen = 0;
-
 	BT_DBG("sk %p size %zu", sk, size);
 
 	lock_sock(sk);

@@ -752,8 +752,6 @@ static int hci_sock_recvmsg(struct kiocb
 	if (!skb)
 		return err;
 
-	msg->msg_namelen = 0;
-
 	copied = skb->len;
 	if (len < copied) {
 		msg->msg_flags |= MSG_TRUNC;

@@ -608,7 +608,6 @@ static int rfcomm_sock_recvmsg(struct ki
 
 	if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) {
 		rfcomm_dlc_accept(d);
-		msg->msg_namelen = 0;
 		return 0;
 	}
 

@@ -700,7 +700,6 @@ static int sco_sock_recvmsg(struct kiocb
 	    test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) {
 		sco_conn_defer_accept(pi->conn->hcon, 0);
 		sk->sk_state = BT_CONFIG;
-		msg->msg_namelen = 0;
 
 		release_sock(sk);
 		return 0;

@@ -286,8 +286,6 @@ static int caif_seqpkt_recvmsg(struct ki
 	if (m->msg_flags&MSG_OOB)
 		goto read_error;
 
-	m->msg_namelen = 0;
-
 	skb = skb_recv_datagram(sk, flags, 0 , &ret);
 	if (!skb)
 		goto read_error;

@@ -361,8 +359,6 @@ static int caif_stream_recvmsg(struct ki
 	if (flags&MSG_OOB)
 		goto out;
 
-	msg->msg_namelen = 0;
-
 	/*
 	 * Lock the socket to prevent queue disordering
 	 * while sleeps in memcpy_tomsg

@@ -93,7 +93,8 @@ int verify_compat_iovec(struct msghdr *k
 			if (err < 0)
 				return err;
 		}
-		kern_msg->msg_name = kern_address;
+		if (kern_msg->msg_name)
+			kern_msg->msg_name = kern_address;
 	} else
 		kern_msg->msg_name = NULL;
 

@@ -48,7 +48,8 @@ int verify_iovec(struct msghdr *m, struc
 			if (err < 0)
 				return err;
 		}
-		m->msg_name = address;
+		if (m->msg_name)
+			m->msg_name = address;
 	} else {
 		m->msg_name = NULL;
 	}

@@ -1823,8 +1823,6 @@ static int ipx_recvmsg(struct kiocb *ioc
 	if (skb->tstamp.tv64)
 		sk->sk_stamp = skb->tstamp;
 
-	msg->msg_namelen = sizeof(*sipx);
-
 	if (sipx) {
 		sipx->sipx_family	= AF_IPX;
 		sipx->sipx_port		= ipx->ipx_source.sock;

@@ -1832,6 +1830,7 @@ static int ipx_recvmsg(struct kiocb *ioc
 		sipx->sipx_network	= IPX_SKB_CB(skb)->ipx_source_net;
 		sipx->sipx_type 	= ipx->ipx_type;
 		sipx->sipx_zero		= 0;
+		msg->msg_namelen	= sizeof(*sipx);
 	}
 	rc = copied;
 

@@ -1385,8 +1385,6 @@ static int irda_recvmsg_dgram(struct kio
 
 	IRDA_DEBUG(4, "%s()\n", __func__);
 
-	msg->msg_namelen = 0;
-
 	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
 				flags & MSG_DONTWAIT, &err);
 	if (!skb)

@@ -1451,8 +1449,6 @@ static int irda_recvmsg_stream(struct ki
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, size);
 	timeo = sock_rcvtimeo(sk, noblock);
 
-	msg->msg_namelen = 0;
-
 	do {
 		int chunk;
 		struct sk_buff *skb = skb_dequeue(&sk->sk_receive_queue);

@@ -1324,8 +1324,6 @@ static int iucv_sock_recvmsg(struct kioc
 	int err = 0;
 	u32 offset;
 
-	msg->msg_namelen = 0;
-
 	if ((sk->sk_state == IUCV_DISCONN) &&
 	    skb_queue_empty(&iucv->backlog_skb_q) &&
 	    skb_queue_empty(&sk->sk_receive_queue) &&

@@ -3623,7 +3623,6 @@ static int pfkey_recvmsg(struct kiocb *k
 	if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT))
 		goto out;
 
-	msg->msg_namelen = 0;
 	skb = skb_recv_datagram(sk, flags, flags & MSG_DONTWAIT, &err);
 	if (skb == NULL)
 		goto out;

@@ -197,8 +197,6 @@ static int pppol2tp_recvmsg(struct kiocb
 	if (sk->sk_state & PPPOX_BOUND)
 		goto end;
 
-	msg->msg_namelen = 0;
-
 	err = 0;
 	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
 				flags & MSG_DONTWAIT, &err);

@@ -720,8 +720,6 @@ static int llc_ui_recvmsg(struct kiocb *
 	int target;	/* Read at least this many bytes */
 	long timeo;
 
-	msg->msg_namelen = 0;
-
 	lock_sock(sk);
 	copied = -ENOTCONN;
 	if (unlikely(sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN))

@@ -2168,8 +2168,6 @@ static int netlink_recvmsg(struct kiocb
 	}
 #endif
 
-	msg->msg_namelen = 0;
-
 	copied = data_skb->len;
 	if (len < copied) {
 		msg->msg_flags |= MSG_TRUNC;

@@ -1179,10 +1179,9 @@ static int nr_recvmsg(struct kiocb *iocb
 		sax->sax25_family = AF_NETROM;
 		skb_copy_from_linear_data_offset(skb, 7, sax->sax25_call.ax25_call,
 			      AX25_ADDR_LEN);
+		msg->msg_namelen = sizeof(*sax);
 	}
 
-	msg->msg_namelen = sizeof(*sax);
-
 	skb_free_datagram(sk, skb);
 
 	release_sock(sk);

@@ -800,8 +800,6 @@ static int llcp_sock_recvmsg(struct kioc
 
 	pr_debug("%p %zu\n", sk, len);
 
-	msg->msg_namelen = 0;
-
 	lock_sock(sk);
 
 	if (sk->sk_state == LLCP_CLOSED &&

@@ -241,8 +241,6 @@ static int rawsock_recvmsg(struct kiocb
 	if (!skb)
 		return rc;
 
-	msg->msg_namelen = 0;
-
 	copied = skb->len;
 	if (len < copied) {
 		msg->msg_flags |= MSG_TRUNC;

@@ -2694,7 +2694,6 @@ static int packet_recvmsg(struct kiocb *
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb;
 	int copied, err;
-	struct sockaddr_ll *sll;
 	int vnet_hdr_len = 0;
 
 	err = -EINVAL;

@@ -2777,22 +2776,10 @@ static int packet_recvmsg(struct kiocb *
 			goto out_free;
 	}
 
-	/*
-	 *	If the address length field is there to be filled in, we fill
-	 *	it in now.
+	/* You lose any data beyond the buffer you gave. If it worries
+	 * a user program they can ask the device for its MTU
+	 * anyway.
 	 */
-
-	sll = &PACKET_SKB_CB(skb)->sa.ll;
-	if (sock->type == SOCK_PACKET)
-		msg->msg_namelen = sizeof(struct sockaddr_pkt);
-	else
-		msg->msg_namelen = sll->sll_halen + offsetof(struct sockaddr_ll, sll_addr);
-
-	/*
-	 *	You lose any data beyond the buffer you gave. If it worries a
-	 *	user program they can ask the device for its MTU anyway.
-	 */
-
 	copied = skb->len;
 	if (copied > len) {
 		copied = len;

@@ -2805,9 +2792,20 @@ static int packet_recvmsg(struct kiocb *
 
 	sock_recv_ts_and_drops(msg, sk, skb);
 
-	if (msg->msg_name)
+	if (msg->msg_name) {
+		/* If the address length field is there to be filled
+		 * in, we fill it in now.
+		 */
+		if (sock->type == SOCK_PACKET) {
+			msg->msg_namelen = sizeof(struct sockaddr_pkt);
+		} else {
+			struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll;
+			msg->msg_namelen = sll->sll_halen +
+				offsetof(struct sockaddr_ll, sll_addr);
+		}
 		memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa,
 		       msg->msg_namelen);
+	}
 
 	if (pkt_sk(sk)->auxdata) {
 		struct tpacket_auxdata aux;

@@ -410,8 +410,6 @@ int rds_recvmsg(struct kiocb *iocb, stru
 
 	rdsdebug("size %zu flags 0x%x timeo %ld\n", size, msg_flags, timeo);
 
-	msg->msg_namelen = 0;
-
 	if (msg_flags & MSG_OOB)
 		goto out;
 

@@ -1216,7 +1216,6 @@ static int rose_recvmsg(struct kiocb *io
 {
 	struct sock *sk = sock->sk;
 	struct rose_sock *rose = rose_sk(sk);
-	struct sockaddr_rose *srose = (struct sockaddr_rose *)msg->msg_name;
 	size_t copied;
 	unsigned char *asmptr;
 	struct sk_buff *skb;

@@ -1252,8 +1251,11 @@ static int rose_recvmsg(struct kiocb *io
 
 	skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
 
-	if (srose != NULL) {
-		memset(srose, 0, msg->msg_namelen);
+	if (msg->msg_name) {
+		struct sockaddr_rose *srose;
+
+		memset(msg->msg_name, 0, sizeof(struct full_sockaddr_rose));
+		srose = msg->msg_name;
 		srose->srose_family = AF_ROSE;
 		srose->srose_addr   = rose->dest_addr;
 		srose->srose_call   = rose->dest_call;

@@ -143,10 +143,13 @@ int rxrpc_recvmsg(struct kiocb *iocb, st
 
 		/* copy the peer address and timestamp */
 		if (!continue_call) {
-			if (msg->msg_name && msg->msg_namelen > 0)
+			if (msg->msg_name) {
+				size_t len =
+					sizeof(call->conn->trans->peer->srx);
 				memcpy(msg->msg_name,
-				       &call->conn->trans->peer->srx,
-				       sizeof(call->conn->trans->peer->srx));
+				       &call->conn->trans->peer->srx, len);
+				msg->msg_namelen = len;
+			}
 			sock_recv_ts_and_drops(msg, &rx->sk, skb);
 		}
 

@@ -1832,8 +1832,10 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void
 	msg.msg_iov = &iov;
 	iov.iov_len = size;
 	iov.iov_base = ubuf;
-	msg.msg_name = (struct sockaddr *)&address;
-	msg.msg_namelen = sizeof(address);
+	/* Save some cycles and don't copy the address if not needed */
+	msg.msg_name = addr ? (struct sockaddr *)&address : NULL;
+	/* We assume all kernel code knows the size of sockaddr_storage */
+	msg.msg_namelen = 0;
 	if (sock->file->f_flags & O_NONBLOCK)
 		flags |= MSG_DONTWAIT;
 	err = sock_recvmsg(sock, &msg, size, flags);

@@ -2213,16 +2215,14 @@ static int ___sys_recvmsg(struct socket
 			goto out;
 	}
 
-	/*
-	 *      Save the user-mode address (verify_iovec will change the
-	 *      kernel msghdr to use the kernel address space)
+	/* Save the user-mode address (verify_iovec will change the
+	 * kernel msghdr to use the kernel address space)
 	 */
-
 	uaddr = (__force void __user *)msg_sys->msg_name;
 	uaddr_len = COMPAT_NAMELEN(msg);
-	if (MSG_CMSG_COMPAT & flags) {
+	if (MSG_CMSG_COMPAT & flags)
 		err = verify_compat_iovec(msg_sys, iov, &addr, VERIFY_WRITE);
-	} else
+	else
 		err = verify_iovec(msg_sys, iov, &addr, VERIFY_WRITE);
 	if (err < 0)
 		goto out_freeiov;

@@ -2231,6 +2231,9 @@ static int ___sys_recvmsg(struct socket
 	cmsg_ptr = (unsigned long)msg_sys->msg_control;
 	msg_sys->msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT);
 
+	/* We assume all kernel code knows the size of sockaddr_storage */
+	msg_sys->msg_namelen = 0;
+
 	if (sock->file->f_flags & O_NONBLOCK)
 		flags |= MSG_DONTWAIT;
 	err = (nosec ? sock_recvmsg_nosec : sock_recvmsg)(sock, msg_sys,

@@ -905,9 +905,6 @@ static int recv_msg(struct kiocb *iocb,
 		goto exit;
 	}
 
-	/* will be updated in set_orig_addr() if needed */
-	m->msg_namelen = 0;
-
 	timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 restart:
 

@@ -1017,9 +1014,6 @@ static int recv_stream(struct kiocb *ioc
 		goto exit;
 	}
 
-	/* will be updated in set_orig_addr() if needed */
-	m->msg_namelen = 0;
-
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, buf_len);
 	timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 

@@ -1761,7 +1761,6 @@ static void unix_copy_addr(struct msghdr
 {
 	struct unix_sock *u = unix_sk(sk);
 
-	msg->msg_namelen = 0;
 	if (u->addr) {
 		msg->msg_namelen = u->addr->len;
 		memcpy(msg->msg_name, u->addr->name, u->addr->len);

@@ -1785,8 +1784,6 @@ static int unix_dgram_recvmsg(struct kio
 	if (flags&MSG_OOB)
 		goto out;
 
-	msg->msg_namelen = 0;
-
 	err = mutex_lock_interruptible(&u->readlock);
 	if (err) {
 		err = sock_intr_errno(sock_rcvtimeo(sk, noblock));

@@ -1926,8 +1923,6 @@ static int unix_stream_recvmsg(struct ki
 	target = sock_rcvlowat(sk, flags&MSG_WAITALL, size);
 	timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT);
 
-	msg->msg_namelen = 0;
-
 	/* Lock the socket to prevent queue disordering
 	 * while sleeps in memcpy_tomsg
 	 */

@@ -1670,8 +1670,6 @@ vsock_stream_recvmsg(struct kiocb *kiocb
 	vsk = vsock_sk(sk);
 	err = 0;
 
-	msg->msg_namelen = 0;
-
 	lock_sock(sk);
 
 	if (sk->sk_state != SS_CONNECTED) {

@@ -1746,8 +1746,6 @@ static int vmci_transport_dgram_dequeue(
 	if (flags & MSG_OOB || flags & MSG_ERRQUEUE)
 		return -EOPNOTSUPP;
 
-	msg->msg_namelen = 0;
-
 	/* Retrieve the head sk_buff from the socket's receive queue. */
 	err = 0;
 	skb = skb_recv_datagram(&vsk->sk, flags, noblock, &err);

@@ -1340,10 +1340,9 @@ static int x25_recvmsg(struct kiocb *ioc
 	if (sx25) {
 		sx25->sx25_family = AF_X25;
 		sx25->sx25_addr   = x25->dest_addr;
+		msg->msg_namelen = sizeof(*sx25);
 	}
 
-	msg->msg_namelen = sizeof(struct sockaddr_x25);
-
 	x25_check_rbuf(sk);
 	rc = copied;
 out_free_dgram:

@@ -215,12 +215,13 @@ static int move_addr_to_user(struct sock
 	int err;
 	int len;
 
+	BUG_ON(klen > sizeof(struct sockaddr_storage));
 	err = get_user(len, ulen);
 	if (err)
 		return err;
 	if (len > klen)
 		len = klen;
-	if (len < 0 || len > sizeof(struct sockaddr_storage))
+	if (len < 0)
 		return -EINVAL;
 	if (len) {
 		if (audit_sockaddr(klen, kaddr))

@@ -454,7 +454,7 @@ extern int	compat_ip_getsockopt(struct s
 			int optname, char __user *optval, int __user *optlen);
 extern int	ip_ra_control(struct sock *sk, unsigned char on, void (*destructor)(struct sock *));
 
-extern int 	ip_recv_error(struct sock *sk, struct msghdr *msg, int len);
+extern int 	ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len);
 extern void	ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, 
 			      __be16 port, u32 info, u8 *payload);
 extern void	ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport,

@@ -793,8 +793,10 @@ extern int			compat_ipv6_getsockopt(stru
 extern int			ip6_datagram_connect(struct sock *sk, 
 						     struct sockaddr *addr, int addr_len);
 
-extern int 			ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len);
-extern int 			ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len);
+extern int 			ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len,
+						int *addr_len);
+extern int 			ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len,
+						 int *addr_len);
 extern void			ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port,
 						u32 info, u8 *payload);
 extern void			ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info);

@@ -368,7 +368,7 @@ void ip_local_error(struct sock *sk, int
 /*
  *	Handle MSG_ERRQUEUE
  */
-int ip_recv_error(struct sock *sk, struct msghdr *msg, int len)
+int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 {
 	struct sock_exterr_skb *serr;
 	struct sk_buff *skb, *skb2;

@@ -405,6 +405,7 @@ int ip_recv_error(struct sock *sk, struc
 						   serr->addr_offset);
 		sin->sin_port = serr->port;
 		memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
+		*addr_len = sizeof(*sin);
 	}
 
 	memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));

@@ -636,7 +636,7 @@ static int ping_recvmsg(struct kiocb *io
 		goto out;
 
 	if (flags & MSG_ERRQUEUE)
-		return ip_recv_error(sk, msg, len);
+		return ip_recv_error(sk, msg, len, addr_len);
 
 	skb = skb_recv_datagram(sk, flags, noblock, &err);
 	if (!skb)

@@ -693,7 +693,7 @@ static int raw_recvmsg(struct kiocb *ioc
 		goto out;
 
 	if (flags & MSG_ERRQUEUE) {
-		err = ip_recv_error(sk, msg, len);
+		err = ip_recv_error(sk, msg, len, addr_len);
 		goto out;
 	}
 

@@ -1208,7 +1208,7 @@ int udp_recvmsg(struct kiocb *iocb, stru
 	bool slow;
 
 	if (flags & MSG_ERRQUEUE)
-		return ip_recv_error(sk, msg, len);
+		return ip_recv_error(sk, msg, len, addr_len);
 
 try_again:
 	skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),

@@ -318,7 +318,7 @@ void ipv6_local_rxpmtu(struct sock *sk,
 /*
  *	Handle MSG_ERRQUEUE
  */
-int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
+int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sock_exterr_skb *serr;

@@ -369,6 +369,7 @@ int ipv6_recv_error(struct sock *sk, str
 					       &sin->sin6_addr);
 			sin->sin6_scope_id = 0;
 		}
+		*addr_len = sizeof(*sin);
 	}
 
 	memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));

@@ -423,7 +424,8 @@ EXPORT_SYMBOL_GPL(ipv6_recv_error);
 /*
  *	Handle IPV6_RECVPATHMTU
  */
-int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len)
+int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len,
+		     int *addr_len)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sk_buff *skb;

@@ -457,6 +459,7 @@ int ipv6_recv_rxpmtu(struct sock *sk, st
 		sin->sin6_port = 0;
 		sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id;
 		sin->sin6_addr = mtu_info.ip6m_addr.sin6_addr;
+		*addr_len = sizeof(*sin);
 	}
 
 	put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info);

@@ -460,10 +460,10 @@ static int rawv6_recvmsg(struct kiocb *i
 		return -EOPNOTSUPP;
 
 	if (flags & MSG_ERRQUEUE)
-		return ipv6_recv_error(sk, msg, len);
+		return ipv6_recv_error(sk, msg, len, addr_len);
 
 	if (np->rxpmtu && np->rxopt.bits.rxpmtu)
-		return ipv6_recv_rxpmtu(sk, msg, len);
+		return ipv6_recv_rxpmtu(sk, msg, len, addr_len);
 
 	skb = skb_recv_datagram(sk, flags, noblock, &err);
 	if (!skb)

@@ -374,10 +374,10 @@ int udpv6_recvmsg(struct kiocb *iocb, st
 	bool slow;
 
 	if (flags & MSG_ERRQUEUE)
-		return ipv6_recv_error(sk, msg, len);
+		return ipv6_recv_error(sk, msg, len, addr_len);
 
 	if (np->rxpmtu && np->rxopt.bits.rxpmtu)
-		return ipv6_recv_rxpmtu(sk, msg, len);
+		return ipv6_recv_rxpmtu(sk, msg, len, addr_len);
 
 try_again:
 	skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),

@@ -665,7 +665,7 @@ static int l2tp_ip6_recvmsg(struct kiocb
 		*addr_len = sizeof(*lsa);
 
 	if (flags & MSG_ERRQUEUE)
-		return ipv6_recv_error(sk, msg, len);
+		return ipv6_recv_error(sk, msg, len, addr_len);
 
 	skb = skb_recv_datagram(sk, flags, noblock, &err);
 	if (!skb)

@@ -72,7 +72,7 @@ int get_compat_msghdr(struct msghdr *kms
 	    __get_user(kmsg->msg_flags, &umsg->msg_flags))
 		return -EFAULT;
 	if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
-		return -EINVAL;
+		kmsg->msg_namelen = sizeof(struct sockaddr_storage);
 	kmsg->msg_name = compat_ptr(tmp1);
 	kmsg->msg_iov = compat_ptr(tmp2);
 	kmsg->msg_control = compat_ptr(tmp3);

@@ -1965,7 +1965,7 @@ static int copy_msghdr_from_user(struct
 	if (copy_from_user(kmsg, umsg, sizeof(struct msghdr)))
 		return -EFAULT;
 	if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
-		return -EINVAL;
+		kmsg->msg_namelen = sizeof(struct sockaddr_storage);
 	return 0;
 }
 

@@ -378,6 +378,7 @@ int ipv6_recv_error(struct sock *sk, str
 	if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) {
 		sin->sin6_family = AF_INET6;
 		sin->sin6_flowinfo = 0;
+		sin->sin6_port = 0;
 		if (skb->protocol == htons(ETH_P_IPV6)) {
 			sin->sin6_addr = ipv6_hdr(skb)->saddr;
 			if (np->rxopt.all)

@@ -150,7 +150,8 @@ static int ip6_finish_output2(struct sk_
 static int ip6_finish_output(struct sk_buff *skb)
 {
 	if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
-	    dst_allfrag(skb_dst(skb)))
+	    dst_allfrag(skb_dst(skb)) ||
+	    (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
 		return ip6_fragment(skb, ip6_finish_output2);
 	else
 		return ip6_finish_output2(skb);

@@ -331,11 +331,6 @@ typedef unsigned int sk_buff_data_t;
 typedef unsigned char *sk_buff_data_t;
 #endif
 
-#if defined(CONFIG_NF_DEFRAG_IPV4) || defined(CONFIG_NF_DEFRAG_IPV4_MODULE) || \
-    defined(CONFIG_NF_DEFRAG_IPV6) || defined(CONFIG_NF_DEFRAG_IPV6_MODULE)
-#define NET_SKBUFF_NF_DEFRAG_NEEDED 1
-#endif
-
 /** 
  *	struct sk_buff - socket buffer
  *	@next: Next buffer in list

@@ -368,7 +363,6 @@ typedef unsigned char *sk_buff_data_t;
  *	@protocol: Packet protocol from driver
  *	@destructor: Destruct function
  *	@nfct: Associated connection, if any
- *	@nfct_reasm: netfilter conntrack re-assembly pointer
  *	@nf_bridge: Saved data about a bridged frame - see br_netfilter.c
  *	@skb_iif: ifindex of device we arrived on
  *	@tc_index: Traffic control index

@@ -455,9 +449,6 @@ struct sk_buff {
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	struct nf_conntrack	*nfct;
 #endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-	struct sk_buff		*nfct_reasm;
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 	struct nf_bridge_info	*nf_bridge;
 #endif

@@ -2700,18 +2691,6 @@ static inline void nf_conntrack_get(stru
 		atomic_inc(&nfct->use);
 }
 #endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-static inline void nf_conntrack_get_reasm(struct sk_buff *skb)
-{
-	if (skb)
-		atomic_inc(&skb->users);
-}
-static inline void nf_conntrack_put_reasm(struct sk_buff *skb)
-{
-	if (skb)
-		kfree_skb(skb);
-}
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 static inline void nf_bridge_put(struct nf_bridge_info *nf_bridge)
 {

@@ -2730,10 +2709,6 @@ static inline void nf_reset(struct sk_bu
 	nf_conntrack_put(skb->nfct);
 	skb->nfct = NULL;
 #endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-	nf_conntrack_put_reasm(skb->nfct_reasm);
-	skb->nfct_reasm = NULL;
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 	nf_bridge_put(skb->nf_bridge);
 	skb->nf_bridge = NULL;

@@ -2755,10 +2730,6 @@ static inline void __nf_copy(struct sk_b
 	nf_conntrack_get(src->nfct);
 	dst->nfctinfo = src->nfctinfo;
 #endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-	dst->nfct_reasm = src->nfct_reasm;
-	nf_conntrack_get_reasm(src->nfct_reasm);
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 	dst->nf_bridge  = src->nf_bridge;
 	nf_bridge_get(src->nf_bridge);

@@ -2770,9 +2741,6 @@ static inline void nf_copy(struct sk_buf
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	nf_conntrack_put(dst->nfct);
 #endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-	nf_conntrack_put_reasm(dst->nfct_reasm);
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 	nf_bridge_put(dst->nf_bridge);
 #endif

@@ -109,7 +109,6 @@ extern int ip_vs_conn_tab_size;
 struct ip_vs_iphdr {
 	__u32 len;	/* IPv4 simply where L4 starts
 			   IPv6 where L4 Transport Header starts */
-	__u32 thoff_reasm; /* Transport Header Offset in nfct_reasm skb */
 	__u16 fragoffs; /* IPv6 fragment offset, 0 if first frag (or not frag)*/
 	__s16 protocol;
 	__s32 flags;

@@ -117,34 +116,12 @@ struct ip_vs_iphdr {
 	union nf_inet_addr daddr;
 };
 
-/* Dependency to module: nf_defrag_ipv6 */
-#if defined(CONFIG_NF_DEFRAG_IPV6) || defined(CONFIG_NF_DEFRAG_IPV6_MODULE)
-static inline struct sk_buff *skb_nfct_reasm(const struct sk_buff *skb)
-{
-	return skb->nfct_reasm;
-}
 static inline void *frag_safe_skb_hp(const struct sk_buff *skb, int offset,
 				      int len, void *buffer,
 				      const struct ip_vs_iphdr *ipvsh)
 {
-	if (unlikely(ipvsh->fragoffs && skb_nfct_reasm(skb)))
-		return skb_header_pointer(skb_nfct_reasm(skb),
-					  ipvsh->thoff_reasm, len, buffer);
-
 	return skb_header_pointer(skb, offset, len, buffer);
 }
-#else
-static inline struct sk_buff *skb_nfct_reasm(const struct sk_buff *skb)
-{
-	return NULL;
-}
-static inline void *frag_safe_skb_hp(const struct sk_buff *skb, int offset,
-				      int len, void *buffer,
-				      const struct ip_vs_iphdr *ipvsh)
-{
-	return skb_header_pointer(skb, offset, len, buffer);
-}
-#endif
 
 static inline void
 ip_vs_fill_ip4hdr(const void *nh, struct ip_vs_iphdr *iphdr)

@@ -171,19 +148,12 @@ ip_vs_fill_iph_skb(int af, const struct
 			(struct ipv6hdr *)skb_network_header(skb);
 		iphdr->saddr.in6 = iph->saddr;
 		iphdr->daddr.in6 = iph->daddr;
-		/* ipv6_find_hdr() updates len, flags, thoff_reasm */
-		iphdr->thoff_reasm = 0;
+		/* ipv6_find_hdr() updates len, flags */
 		iphdr->len	 = 0;
 		iphdr->flags	 = 0;
 		iphdr->protocol  = ipv6_find_hdr(skb, &iphdr->len, -1,
 						 &iphdr->fragoffs,
 						 &iphdr->flags);
-		/* get proto from re-assembled packet and it's offset */
-		if (skb_nfct_reasm(skb))
-			iphdr->protocol = ipv6_find_hdr(skb_nfct_reasm(skb),
-							&iphdr->thoff_reasm,
-							-1, NULL, NULL);
-
 	} else
 #endif
 	{

@@ -6,10 +6,7 @@ extern void nf_defrag_ipv6_enable(void);
 extern int nf_ct_frag6_init(void);
 extern void nf_ct_frag6_cleanup(void);
 extern struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user);
-extern void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
-			       struct net_device *in,
-			       struct net_device *out,
-			       int (*okfn)(struct sk_buff *));
+extern void nf_ct_frag6_consume_orig(struct sk_buff *skb);
 
 struct inet_frags_ctl;
 

@@ -585,9 +585,6 @@ static void skb_release_head_state(struc
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 	nf_conntrack_put(skb->nfct);
 #endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-	nf_conntrack_put_reasm(skb->nfct_reasm);
-#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 	nf_bridge_put(skb->nf_bridge);
 #endif

72 lines not on this page · raw message

@@ -621,31 +621,16 @@ ret_orig:
 	return skb;
 }
 
-void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
-			struct net_device *in, struct net_device *out,
-			int (*okfn)(struct sk_buff *))
+void nf_ct_frag6_consume_orig(struct sk_buff *skb)
 {
 	struct sk_buff *s, *s2;
-	unsigned int ret = 0;
 
 	for (s = NFCT_FRAG6_CB(skb)->orig; s;) {
-		nf_conntrack_put_reasm(s->nfct_reasm);
-		nf_conntrack_get_reasm(skb);
-		s->nfct_reasm = skb;
-
 		s2 = s->next;
 		s->next = NULL;
-
-		if (ret != -ECANCELED)
-			ret = NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, s,
-					     in, out, okfn,
-					     NF_IP6_PRI_CONNTRACK_DEFRAG + 1);
-		else
-			kfree_skb(s);
-
+		consume_skb(s);
 		s = s2;
 	}
-	nf_conntrack_put_reasm(skb);
 }
 
 static int nf_ct_net_init(struct net *net)

@@ -75,8 +75,11 @@ static unsigned int ipv6_defrag(unsigned
 	if (reasm == skb)
 		return NF_ACCEPT;
 
-	nf_ct_frag6_output(hooknum, reasm, (struct net_device *)in,
-			   (struct net_device *)out, okfn);
+	nf_ct_frag6_consume_orig(reasm);
+
+	NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, reasm,
+		       (struct net_device *) in, (struct net_device *) out,
+		       okfn, NF_IP6_PRI_CONNTRACK_DEFRAG + 1);
 
 	return NF_STOLEN;
 }

86 lines not on this page · raw message

@@ -65,7 +65,6 @@ static int get_callid(const char *dptr,
 static int
 ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
 {
-	struct sk_buff *reasm = skb_nfct_reasm(skb);
 	struct ip_vs_iphdr iph;
 	unsigned int dataoff, datalen, matchoff, matchlen;
 	const char *dptr;

@@ -79,15 +78,10 @@ ip_vs_sip_fill_param(struct ip_vs_conn_p
 	/* todo: IPv6 fragments:
 	 *       I think this only should be done for the first fragment. /HS
 	 */
-	if (reasm) {
-		skb = reasm;
-		dataoff = iph.thoff_reasm + sizeof(struct udphdr);
-	} else
-		dataoff = iph.len + sizeof(struct udphdr);
+	dataoff = iph.len + sizeof(struct udphdr);
 
 	if (dataoff >= skb->len)
 		return -EINVAL;
-	/* todo: Check if this will mess-up the reasm skb !!! /HS */
 	retc = skb_linearize(skb);
 	if (retc < 0)
 		return retc;

@@ -350,6 +350,7 @@ static netdev_tx_t vti_tunnel_xmit(struc
 	if (!rt->dst.xfrm ||
 	    rt->dst.xfrm->props.mode != XFRM_MODE_TUNNEL) {
 		dev->stats.tx_carrier_errors++;
+		ip_rt_put(rt);
 		goto tx_error_icmp;
 	}
 	tdev = rt->dst.dev;

@@ -3511,7 +3511,7 @@ static int init_card(struct atm_dev *dev
 	tmp = dev_get_by_name(&init_net, tname);	/* jhs: was "tmp = dev_get(tname);" */
 	if (tmp) {
 		memcpy(card->atmdev->esi, tmp->dev_addr, 6);
-
+		dev_put(tmp);
 		printk("%s: ESI %pM\n", card->name, card->atmdev->esi);
 	}
 	/*

@@ -3102,7 +3102,6 @@ void tcp_send_window_probe(struct sock *
 {
 	if (sk->sk_state == TCP_ESTABLISHED) {
 		tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1;
-		tcp_sk(sk)->snd_nxt = tcp_sk(sk)->write_seq;
 		tcp_xmit_probe_skb(sk, 0);
 	}
 }

@@ -1720,8 +1720,12 @@ local_input:
 		rth->dst.error= -err;
 		rth->rt_flags 	&= ~RTCF_LOCAL;
 	}
-	if (do_cache)
-		rt_cache_route(&FIB_RES_NH(res), rth);
+	if (do_cache) {
+		if (unlikely(!rt_cache_route(&FIB_RES_NH(res), rth))) {
+			rth->dst.flags |= DST_NOCACHE;
+			rt_add_uncached_list(rth);
+		}
+	}
 	skb_dst_set(skb, &rth->dst);
 	err = 0;
 	goto out;

@@ -4478,7 +4478,7 @@ static void dev_change_rx_flags(struct n
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 
-	if ((dev->flags & IFF_UP) && ops->ndo_change_rx_flags)
+	if (ops->ndo_change_rx_flags)
 		ops->ndo_change_rx_flags(dev, flags);
 }
 

@@ -172,6 +172,8 @@ void br_dev_delete(struct net_device *de
 		del_nbp(p);
 	}
 
+	br_fdb_delete_by_port(br, NULL, 1);
+
 	del_timer_sync(&br->gc_timer);
 
 	br_sysfs_delbr(br->dev);

@@ -244,11 +244,15 @@ static void __fanout_link(struct sock *s
 static void register_prot_hook(struct sock *sk)
 {
 	struct packet_sock *po = pkt_sk(sk);
+
 	if (!po->running) {
-		if (po->fanout)
+		if (po->fanout) {
 			__fanout_link(sk, po);
-		else
+		} else {
 			dev_add_pack(&po->prot_hook);
+			rcu_assign_pointer(po->cached_dev, po->prot_hook.dev);
+		}
+
 		sock_hold(sk);
 		po->running = 1;
 	}

@@ -266,10 +270,13 @@ static void __unregister_prot_hook(struc
 	struct packet_sock *po = pkt_sk(sk);
 
 	po->running = 0;
-	if (po->fanout)
+	if (po->fanout) {
 		__fanout_unlink(sk, po);
-	else
+	} else {
 		__dev_remove_pack(&po->prot_hook);
+		RCU_INIT_POINTER(po->cached_dev, NULL);
+	}
+
 	__sock_put(sk);
 
 	if (sync) {

@@ -2041,12 +2048,24 @@ static int tpacket_fill_skb(struct packe
 	return tp_len;
 }
 
+static struct net_device *packet_cached_dev_get(struct packet_sock *po)
+{
+	struct net_device *dev;
+
+	rcu_read_lock();
+	dev = rcu_dereference(po->cached_dev);
+	if (dev)
+		dev_hold(dev);
+	rcu_read_unlock();
+
+	return dev;
+}
+
 static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 {
 	struct sk_buff *skb;
 	struct net_device *dev;
 	__be16 proto;
-	bool need_rls_dev = false;
 	int err, reserve = 0;
 	void *ph;
 	struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name;

@@ -2059,7 +2078,7 @@ static int tpacket_snd(struct packet_soc
 	mutex_lock(&po->pg_vec_lock);
 
 	if (saddr == NULL) {
-		dev = po->prot_hook.dev;
+		dev	= packet_cached_dev_get(po);
 		proto	= po->num;
 		addr	= NULL;
 	} else {

@@ -2073,19 +2092,17 @@ static int tpacket_snd(struct packet_soc
 		proto	= saddr->sll_protocol;
 		addr	= saddr->sll_addr;
 		dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
-		need_rls_dev = true;
 	}
 
 	err = -ENXIO;
 	if (unlikely(dev == NULL))
 		goto out;
-
-	reserve = dev->hard_header_len;
-
 	err = -ENETDOWN;
 	if (unlikely(!(dev->flags & IFF_UP)))
 		goto out_put;
 
+	reserve = dev->hard_header_len;
+
 	size_max = po->tx_ring.frame_size
 		- (po->tp_hdrlen - sizeof(struct sockaddr_ll));
 

@@ -2162,8 +2179,7 @@ out_status:
 	__packet_set_status(po, ph, status);
 	kfree_skb(skb);
 out_put:
-	if (need_rls_dev)
-		dev_put(dev);
+	dev_put(dev);
 out:
 	mutex_unlock(&po->pg_vec_lock);
 	return err;

@@ -2201,7 +2217,6 @@ static int packet_snd(struct socket *soc
 	struct sk_buff *skb;
 	struct net_device *dev;
 	__be16 proto;
-	bool need_rls_dev = false;
 	unsigned char *addr;
 	int err, reserve = 0;
 	struct virtio_net_hdr vnet_hdr = { 0 };

@@ -2217,7 +2232,7 @@ static int packet_snd(struct socket *soc
 	 */
 
 	if (saddr == NULL) {
-		dev = po->prot_hook.dev;
+		dev	= packet_cached_dev_get(po);
 		proto	= po->num;
 		addr	= NULL;
 	} else {

@@ -2229,19 +2244,17 @@ static int packet_snd(struct socket *soc
 		proto	= saddr->sll_protocol;
 		addr	= saddr->sll_addr;
 		dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex);
-		need_rls_dev = true;
 	}
 
 	err = -ENXIO;
-	if (dev == NULL)
+	if (unlikely(dev == NULL))
 		goto out_unlock;
-	if (sock->type == SOCK_RAW)
-		reserve = dev->hard_header_len;
-
 	err = -ENETDOWN;
-	if (!(dev->flags & IFF_UP))
+	if (unlikely(!(dev->flags & IFF_UP)))
 		goto out_unlock;
 
+	if (sock->type == SOCK_RAW)
+		reserve = dev->hard_header_len;
 	if (po->has_vnet_hdr) {
 		vnet_hdr_len = sizeof(vnet_hdr);
 

@@ -2375,15 +2388,14 @@ static int packet_snd(struct socket *soc
 	if (err > 0 && (err = net_xmit_errno(err)) != 0)
 		goto out_unlock;
 
-	if (need_rls_dev)
-		dev_put(dev);
+	dev_put(dev);
 
 	return len;
 
 out_free:
 	kfree_skb(skb);
 out_unlock:
-	if (dev && need_rls_dev)
+	if (dev)
 		dev_put(dev);
 out:
 	return err;

@@ -2603,6 +2615,7 @@ static int packet_create(struct net *net
 	po = pkt_sk(sk);
 	sk->sk_family = PF_PACKET;
 	po->num = proto;
+	RCU_INIT_POINTER(po->cached_dev, NULL);
 
 	sk->sk_destruct = packet_sock_destruct;
 	sk_refcnt_debug_inc(sk);

@@ -113,6 +113,7 @@ struct packet_sock {
 	unsigned int		tp_loss:1;
 	unsigned int		tp_tx_has_off:1;
 	unsigned int		tp_tstamp;
+	struct net_device __rcu	*cached_dev;
 	struct packet_type	prot_hook ____cacheline_aligned_in_smp;
 };
 

@@ -439,9 +439,9 @@ static void prb_shutdown_retire_blk_time
 
 	pkc = tx_ring ? &po->tx_ring.prb_bdqc : &po->rx_ring.prb_bdqc;
 
-	spin_lock(&rb_queue->lock);
+	spin_lock_bh(&rb_queue->lock);
 	pkc->delete_blk_timer = 1;
-	spin_unlock(&rb_queue->lock);
+	spin_unlock_bh(&rb_queue->lock);
 
 	prb_del_retire_blk_timer(pkc);
 }

@@ -3456,6 +3456,11 @@ static void rtl8168g_1_hw_phy_config(str
 	rtl_writephy(tp, 0x14, 0x9065);
 	rtl_writephy(tp, 0x14, 0x1065);
 
+	/* Check ALDPS bit, disable it if enabled */
+	rtl_writephy(tp, 0x1f, 0x0a43);
+	if (rtl_readphy(tp, 0x10) & 0x0004)
+		rtl_w1w0_phy(tp, 0x10, 0x0000, 0x0004);
+
 	rtl_writephy(tp, 0x1f, 0x0000);
 }
 

@@ -678,9 +678,6 @@ static void cp_tx (struct cp_private *cp
 				 le32_to_cpu(txd->opts1) & 0xffff,
 				 PCI_DMA_TODEVICE);
 
-		bytes_compl += skb->len;
-		pkts_compl++;
-
 		if (status & LastFrag) {
 			if (status & (TxError | TxFIFOUnder)) {
 				netif_dbg(cp, tx_err, cp->dev,

@@ -702,6 +699,8 @@ static void cp_tx (struct cp_private *cp
 				netif_dbg(cp, tx_done, cp->dev,
 					  "tx done, slot %d\n", tx_tail);
 			}
+			bytes_compl += skb->len;
+			pkts_compl++;
 			dev_kfree_skb_irq(skb);
 		}
 

@@ -114,6 +114,9 @@ static ssize_t hash_sendpage(struct sock
 	struct hash_ctx *ctx = ask->private;
 	int err;
 
+	if (flags & MSG_SENDPAGE_NOTLAST)
+		flags |= MSG_MORE;
+
 	lock_sock(sk);
 	sg_init_table(ctx->sgl.sg, 1);
 	sg_set_page(ctx->sgl.sg, page, size, offset);

@@ -378,6 +378,9 @@ static ssize_t skcipher_sendpage(struct
 	struct skcipher_sg_list *sgl;
 	int err = -EINVAL;
 
+	if (flags & MSG_SENDPAGE_NOTLAST)
+		flags |= MSG_MORE;
+
 	lock_sock(sk);
 	if (!ctx->more && ctx->used)
 		goto unlock;

@@ -1070,6 +1070,9 @@ int udp_sendpage(struct sock *sk, struct
 	struct udp_sock *up = udp_sk(sk);
 	int ret;
 
+	if (flags & MSG_SENDPAGE_NOTLAST)
+		flags |= MSG_MORE;
+
 	if (!up->pending) {
 		struct msghdr msg = {	.msg_flags = flags|MSG_MORE };
 

@@ -1217,6 +1217,8 @@ static int team_user_linkup_option_get(s
 	return 0;
 }
 
+static void __team_carrier_check(struct team *team);
+
 static int team_user_linkup_option_set(struct team *team,
 				       struct team_gsetter_ctx *ctx)
 {

@@ -1224,6 +1226,7 @@ static int team_user_linkup_option_set(s
 
 	port->user.linkup = ctx->data.bool_val;
 	team_refresh_port_linkup(port);
+	__team_carrier_check(port->team);
 	return 0;
 }
 

@@ -1243,6 +1246,7 @@ static int team_user_linkup_en_option_se
 
 	port->user.linkup_enabled = ctx->data.bool_val;
 	team_refresh_port_linkup(port);
+	__team_carrier_check(port->team);
 	return 0;
 }
 

@@ -570,7 +570,7 @@ static int ping_sendmsg(struct kiocb *io
 		err = PTR_ERR(rt);
 		rt = NULL;
 		if (err == -ENETUNREACH)
-			IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
+			IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
 		goto out;
 	}
 

@@ -176,7 +176,7 @@ int tcp_v4_connect(struct sock *sk, stru
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);
 		if (err == -ENETUNREACH)
-			IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
+			IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
 		return err;
 	}
 

@@ -971,7 +971,7 @@ int udp_sendmsg(struct kiocb *iocb, stru
 			err = PTR_ERR(rt);
 			rt = NULL;
 			if (err == -ENETUNREACH)
-				IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
+				IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
 			goto out;
 		}
 

@@ -141,8 +141,8 @@ static int ip6_finish_output2(struct sk_
 	}
 	rcu_read_unlock_bh();
 
-	IP6_INC_STATS_BH(dev_net(dst->dev),
-			 ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
+	IP6_INC_STATS(dev_net(dst->dev),
+		      ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
 	kfree_skb(skb);
 	return -EINVAL;
 }

@@ -2515,6 +2515,8 @@ static int process_ipsec(struct pktgen_d
 		if (x) {
 			int ret;
 			__u8 *eth;
+			struct iphdr *iph;
+
 			nhead = x->props.header_len - skb_headroom(skb);
 			if (nhead > 0) {
 				ret = pskb_expand_head(skb, nhead, 0, GFP_ATOMIC);

@@ -2536,6 +2538,11 @@ static int process_ipsec(struct pktgen_d
 			eth = (__u8 *) skb_push(skb, ETH_HLEN);
 			memcpy(eth, pkt_dev->hh, 12);
 			*(u16 *) &eth[12] = protocol;
+
+			/* Update IPv4 header len as well as checksum value */
+			iph = ip_hdr(skb);
+			iph->tot_len = htons(skb->len - ETH_HLEN);
+			ip_send_check(iph);
 		}
 	}
 	return 1;