3 files changed, 218 insertions, 121 deletions

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 1d6793dbfba..dd5cd49b0e0 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -158,10 +158,16 @@ struct packet_mreq_max {
 	unsigned char	mr_address[MAX_ADDR_LEN];
 };
 
+union tpacket_uhdr {
+	struct tpacket_hdr  *h1;
+	struct tpacket2_hdr *h2;
+	struct tpacket3_hdr *h3;
+	void *raw;
+};
+
 static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		int closing, int tx_ring);
 
-
 #define V3_ALIGNMENT	(8)
 
 #define BLK_HDR_LEN	(ALIGN(sizeof(struct tpacket_block_desc), V3_ALIGNMENT))
@@ -181,6 +187,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 
 struct packet_sock;
 static int tpacket_snd(struct packet_sock *po, struct msghdr *msg);
+static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
+		       struct packet_type *pt, struct net_device *orig_dev);
 
 static void *packet_previous_frame(struct packet_sock *po,
 		struct packet_ring_buffer *rb,
@@ -288,11 +296,7 @@ static inline __pure struct page *pgv_to_page(void *addr)
 
 static void __packet_set_status(struct packet_sock *po, void *frame, int status)
 {
-	union {
-		struct tpacket_hdr *h1;
-		struct tpacket2_hdr *h2;
-		void *raw;
-	} h;
+	union tpacket_uhdr h;
 
 	h.raw = frame;
 	switch (po->tp_version) {
@@ -315,11 +319,7 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status)
 
 static int __packet_get_status(struct packet_sock *po, void *frame)
 {
-	union {
-		struct tpacket_hdr *h1;
-		struct tpacket2_hdr *h2;
-		void *raw;
-	} h;
+	union tpacket_uhdr h;
 
 	smp_rmb();
 
@@ -339,17 +339,66 @@ static int __packet_get_status(struct packet_sock *po, void *frame)
 	}
 }
 
+static __u32 tpacket_get_timestamp(struct sk_buff *skb, struct timespec *ts,
+				   unsigned int flags)
+{
+	struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb);
+
+	if (shhwtstamps) {
+		if ((flags & SOF_TIMESTAMPING_SYS_HARDWARE) &&
+		    ktime_to_timespec_cond(shhwtstamps->syststamp, ts))
+			return TP_STATUS_TS_SYS_HARDWARE;
+		if ((flags & SOF_TIMESTAMPING_RAW_HARDWARE) &&
+		    ktime_to_timespec_cond(shhwtstamps->hwtstamp, ts))
+			return TP_STATUS_TS_RAW_HARDWARE;
+	}
+
+	if (ktime_to_timespec_cond(skb->tstamp, ts))
+		return TP_STATUS_TS_SOFTWARE;
+
+	return 0;
+}
+
+static __u32 __packet_set_timestamp(struct packet_sock *po, void *frame,
+				    struct sk_buff *skb)
+{
+	union tpacket_uhdr h;
+	struct timespec ts;
+	__u32 ts_status;
+
+	if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp)))
+		return 0;
+
+	h.raw = frame;
+	switch (po->tp_version) {
+	case TPACKET_V1:
+		h.h1->tp_sec = ts.tv_sec;
+		h.h1->tp_usec = ts.tv_nsec / NSEC_PER_USEC;
+		break;
+	case TPACKET_V2:
+		h.h2->tp_sec = ts.tv_sec;
+		h.h2->tp_nsec = ts.tv_nsec;
+		break;
+	case TPACKET_V3:
+	default:
+		WARN(1, "TPACKET version not supported.\n");
+		BUG();
+	}
+
+	/* one flush is safe, as both fields always lie on the same cacheline */
+	flush_dcache_page(pgv_to_page(&h.h1->tp_sec));
+	smp_wmb();
+
+	return ts_status;
+}
+
 static void *packet_lookup_frame(struct packet_sock *po,
 		struct packet_ring_buffer *rb,
 		unsigned int position,
 		int status)
 {
 	unsigned int pg_vec_pos, frame_offset;
-	union {
-		struct tpacket_hdr *h1;
-		struct tpacket2_hdr *h2;
-		void *raw;
-	} h;
+	union tpacket_uhdr h;
 
 	pg_vec_pos = position / rb->frames_per_block;
 	frame_offset = position % rb->frames_per_block;
@@ -479,7 +528,7 @@ static void init_prb_bdqc(struct packet_sock *po,
 	p1->hdrlen = po->tp_hdrlen;
 	p1->version = po->tp_version;
 	p1->last_kactive_blk_num = 0;
-	po->stats_u.stats3.tp_freeze_q_cnt = 0;
+	po->stats.stats3.tp_freeze_q_cnt = 0;
 	if (req_u->req3.tp_retire_blk_tov)
 		p1->retire_blk_tov = req_u->req3.tp_retire_blk_tov;
 	else
@@ -647,7 +696,7 @@ static void prb_close_block(struct tpacket_kbdq_core *pkc1,
 	struct tpacket3_hdr *last_pkt;
 	struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1;
 
-	if (po->stats.tp_drops)
+	if (po->stats.stats3.tp_drops)
 		status |= TP_STATUS_LOSING;
 
 	last_pkt = (struct tpacket3_hdr *)pkc1->prev;
@@ -752,7 +801,7 @@ static void prb_freeze_queue(struct tpacket_kbdq_core *pkc,
 				  struct packet_sock *po)
 {
 	pkc->reset_pending_on_curr_blk = 1;
-	po->stats_u.stats3.tp_freeze_q_cnt++;
+	po->stats.stats3.tp_freeze_q_cnt++;
 }
 
 #define TOTAL_PKT_LEN_INCL_ALIGN(length) (ALIGN((length), V3_ALIGNMENT))
@@ -973,11 +1022,11 @@ static void *packet_current_rx_frame(struct packet_sock *po,
 
 static void *prb_lookup_block(struct packet_sock *po,
 				     struct packet_ring_buffer *rb,
-				     unsigned int previous,
+				     unsigned int idx,
 				     int status)
 {
 	struct tpacket_kbdq_core *pkc  = GET_PBDQC_FROM_RB(rb);
-	struct tpacket_block_desc *pbd = GET_PBLOCK_DESC(pkc, previous);
+	struct tpacket_block_desc *pbd = GET_PBLOCK_DESC(pkc, idx);
 
 	if (status != BLOCK_STATUS(pbd))
 		return NULL;
@@ -1041,6 +1090,29 @@ static void packet_increment_head(struct packet_ring_buffer *buff)
 	buff->head = buff->head != buff->frame_max ? buff->head+1 : 0;
 }
 
+static bool packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb)
+{
+	struct sock *sk = &po->sk;
+	bool has_room;
+
+	if (po->prot_hook.func != tpacket_rcv)
+		return (atomic_read(&sk->sk_rmem_alloc) + skb->truesize)
+			<= sk->sk_rcvbuf;
+
+	spin_lock(&sk->sk_receive_queue.lock);
+	if (po->tp_version == TPACKET_V3)
+		has_room = prb_lookup_block(po, &po->rx_ring,
+					    po->rx_ring.prb_bdqc.kactive_blk_num,
+					    TP_STATUS_KERNEL);
+	else
+		has_room = packet_lookup_frame(po, &po->rx_ring,
+					       po->rx_ring.head,
+					       TP_STATUS_KERNEL);
+	spin_unlock(&sk->sk_receive_queue.lock);
+
+	return has_room;
+}
+
 static void packet_sock_destruct(struct sock *sk)
 {
 	skb_queue_purge(&sk->sk_error_queue);
@@ -1066,16 +1138,16 @@ static int fanout_rr_next(struct packet_fanout *f, unsigned int num)
 	return x;
 }
 
-static struct sock *fanout_demux_hash(struct packet_fanout *f, struct sk_buff *skb, unsigned int num)
+static unsigned int fanout_demux_hash(struct packet_fanout *f,
+				      struct sk_buff *skb,
+				      unsigned int num)
 {
-	u32 idx, hash = skb->rxhash;
-
-	idx = ((u64)hash * num) >> 32;
-
-	return f->arr[idx];
+	return (((u64)skb->rxhash) * num) >> 32;
 }
 
-static struct sock *fanout_demux_lb(struct packet_fanout *f, struct sk_buff *skb, unsigned int num)
+static unsigned int fanout_demux_lb(struct packet_fanout *f,
+				    struct sk_buff *skb,
+				    unsigned int num)
 {
 	int cur, old;
 
@@ -1083,14 +1155,40 @@ static struct sock *fanout_demux_lb(struct packet_fanout *f, struct sk_buff *skb
 	while ((old = atomic_cmpxchg(&f->rr_cur, cur,
 				     fanout_rr_next(f, num))) != cur)
 		cur = old;
-	return f->arr[cur];
+	return cur;
 }
 
-static struct sock *fanout_demux_cpu(struct packet_fanout *f, struct sk_buff *skb, unsigned int num)
+static unsigned int fanout_demux_cpu(struct packet_fanout *f,
+				     struct sk_buff *skb,
+				     unsigned int num)
 {
-	unsigned int cpu = smp_processor_id();
+	return smp_processor_id() % num;
+}
 
-	return f->arr[cpu % num];
+static unsigned int fanout_demux_rollover(struct packet_fanout *f,
+					  struct sk_buff *skb,
+					  unsigned int idx, unsigned int skip,
+					  unsigned int num)
+{
+	unsigned int i, j;
+
+	i = j = min_t(int, f->next[idx], num - 1);
+	do {
+		if (i != skip && packet_rcv_has_room(pkt_sk(f->arr[i]), skb)) {
+			if (i != j)
+				f->next[idx] = i;
+			return i;
+		}
+		if (++i == num)
+			i = 0;
+	} while (i != j);
+
+	return idx;
+}
+
+static bool fanout_has_flag(struct packet_fanout *f, u16 flag)
+{
+	return f->flags & (flag >> 8);
 }
 
 static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
@@ -1099,7 +1197,7 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 	struct packet_fanout *f = pt->af_packet_priv;
 	unsigned int num = f->num_members;
 	struct packet_sock *po;
-	struct sock *sk;
+	unsigned int idx;
 
 	if (!net_eq(dev_net(dev), read_pnet(&f->net)) ||
 	    !num) {
@@ -1110,23 +1208,31 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 	switch (f->type) {
 	case PACKET_FANOUT_HASH:
 	default:
-		if (f->defrag) {
+		if (fanout_has_flag(f, PACKET_FANOUT_FLAG_DEFRAG)) {
 			skb = ip_check_defrag(skb, IP_DEFRAG_AF_PACKET);
 			if (!skb)
 				return 0;
 		}
 		skb_get_rxhash(skb);
-		sk = fanout_demux_hash(f, skb, num);
+		idx = fanout_demux_hash(f, skb, num);
 		break;
 	case PACKET_FANOUT_LB:
-		sk = fanout_demux_lb(f, skb, num);
+		idx = fanout_demux_lb(f, skb, num);
 		break;
 	case PACKET_FANOUT_CPU:
-		sk = fanout_demux_cpu(f, skb, num);
+		idx = fanout_demux_cpu(f, skb, num);
+		break;
+	case PACKET_FANOUT_ROLLOVER:
+		idx = fanout_demux_rollover(f, skb, 0, (unsigned int) -1, num);
 		break;
 	}
 
-	po = pkt_sk(sk);
+	po = pkt_sk(f->arr[idx]);
+	if (fanout_has_flag(f, PACKET_FANOUT_FLAG_ROLLOVER) &&
+	    unlikely(!packet_rcv_has_room(po, skb))) {
+		idx = fanout_demux_rollover(f, skb, idx, idx, num);
+		po = pkt_sk(f->arr[idx]);
+	}
 
 	return po->prot_hook.func(skb, dev, &po->prot_hook, orig_dev);
 }
@@ -1175,10 +1281,13 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 	struct packet_sock *po = pkt_sk(sk);
 	struct packet_fanout *f, *match;
 	u8 type = type_flags & 0xff;
-	u8 defrag = (type_flags & PACKET_FANOUT_FLAG_DEFRAG) ? 1 : 0;
+	u8 flags = type_flags >> 8;
 	int err;
 
 	switch (type) {
+	case PACKET_FANOUT_ROLLOVER:
+		if (type_flags & PACKET_FANOUT_FLAG_ROLLOVER)
+			return -EINVAL;
 	case PACKET_FANOUT_HASH:
 	case PACKET_FANOUT_LB:
 	case PACKET_FANOUT_CPU:
@@ -1203,7 +1312,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		}
 	}
 	err = -EINVAL;
-	if (match && match->defrag != defrag)
+	if (match && match->flags != flags)
 		goto out;
 	if (!match) {
 		err = -ENOMEM;
@@ -1213,7 +1322,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		write_pnet(&match->net, sock_net(sk));
 		match->id = id;
 		match->type = type;
-		match->defrag = defrag;
+		match->flags = flags;
 		atomic_set(&match->rr_cur, 0);
 		INIT_LIST_HEAD(&match->list);
 		spin_lock_init(&match->lock);
@@ -1443,13 +1552,14 @@ retry:
 	skb->dev = dev;
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
-	err = sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags);
-	if (err < 0)
-		goto out_unlock;
+
+	sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags);
 
 	if (unlikely(extra_len == 4))
 		skb->no_fcs = 1;
 
+	skb_probe_transport_header(skb, 0);
+
 	dev_queue_xmit(skb);
 	rcu_read_unlock();
 	return len;
@@ -1577,7 +1687,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
 	nf_reset(skb);
 
 	spin_lock(&sk->sk_receive_queue.lock);
-	po->stats.tp_packets++;
+	po->stats.stats1.tp_packets++;
 	skb->dropcount = atomic_read(&sk->sk_drops);
 	__skb_queue_tail(&sk->sk_receive_queue, skb);
 	spin_unlock(&sk->sk_receive_queue.lock);
@@ -1586,7 +1696,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
 
 drop_n_acct:
 	spin_lock(&sk->sk_receive_queue.lock);
-	po->stats.tp_drops++;
+	po->stats.stats1.tp_drops++;
 	atomic_inc(&sk->sk_drops);
 	spin_unlock(&sk->sk_receive_queue.lock);
 
@@ -1606,21 +1716,15 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	struct sock *sk;
 	struct packet_sock *po;
 	struct sockaddr_ll *sll;
-	union {
-		struct tpacket_hdr *h1;
-		struct tpacket2_hdr *h2;
-		struct tpacket3_hdr *h3;
-		void *raw;
-	} h;
+	union tpacket_uhdr h;
 	u8 *skb_head = skb->data;
 	int skb_len = skb->len;
 	unsigned int snaplen, res;
 	unsigned long status = TP_STATUS_USER;
 	unsigned short macoff, netoff, hdrlen;
 	struct sk_buff *copy_skb = NULL;
-	struct timeval tv;
 	struct timespec ts;
-	struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb);
+	__u32 ts_status;
 
 	if (skb->pkt_type == PACKET_LOOPBACK)
 		goto drop;
@@ -1692,10 +1796,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	 * Anyways, moving it for V1/V2 only as V3 doesn't need this
 	 * at packet level.
 	 */
-		if (po->stats.tp_drops)
+		if (po->stats.stats1.tp_drops)
 			status |= TP_STATUS_LOSING;
 	}
-	po->stats.tp_packets++;
+	po->stats.stats1.tp_packets++;
 	if (copy_skb) {
 		status |= TP_STATUS_COPY;
 		__skb_queue_tail(&sk->sk_receive_queue, copy_skb);
@@ -1704,24 +1808,19 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 
 	skb_copy_bits(skb, 0, h.raw + macoff, snaplen);
 
+	if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp)))
+		getnstimeofday(&ts);
+
+	status |= ts_status;
+
 	switch (po->tp_version) {
 	case TPACKET_V1:
 		h.h1->tp_len = skb->len;
 		h.h1->tp_snaplen = snaplen;
 		h.h1->tp_mac = macoff;
 		h.h1->tp_net = netoff;
-		if ((po->tp_tstamp & SOF_TIMESTAMPING_SYS_HARDWARE)
-				&& shhwtstamps->syststamp.tv64)
-			tv = ktime_to_timeval(shhwtstamps->syststamp);
-		else if ((po->tp_tstamp & SOF_TIMESTAMPING_RAW_HARDWARE)
-				&& shhwtstamps->hwtstamp.tv64)
-			tv = ktime_to_timeval(shhwtstamps->hwtstamp);
-		else if (skb->tstamp.tv64)
-			tv = ktime_to_timeval(skb->tstamp);
-		else
-			do_gettimeofday(&tv);
-		h.h1->tp_sec = tv.tv_sec;
-		h.h1->tp_usec = tv.tv_usec;
+		h.h1->tp_sec = ts.tv_sec;
+		h.h1->tp_usec = ts.tv_nsec / NSEC_PER_USEC;
 		hdrlen = sizeof(*h.h1);
 		break;
 	case TPACKET_V2:
@@ -1729,16 +1828,6 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		h.h2->tp_snaplen = snaplen;
 		h.h2->tp_mac = macoff;
 		h.h2->tp_net = netoff;
-		if ((po->tp_tstamp & SOF_TIMESTAMPING_SYS_HARDWARE)
-				&& shhwtstamps->syststamp.tv64)
-			ts = ktime_to_timespec(shhwtstamps->syststamp);
-		else if ((po->tp_tstamp & SOF_TIMESTAMPING_RAW_HARDWARE)
-				&& shhwtstamps->hwtstamp.tv64)
-			ts = ktime_to_timespec(shhwtstamps->hwtstamp);
-		else if (skb->tstamp.tv64)
-			ts = ktime_to_timespec(skb->tstamp);
-		else
-			getnstimeofday(&ts);
 		h.h2->tp_sec = ts.tv_sec;
 		h.h2->tp_nsec = ts.tv_nsec;
 		if (vlan_tx_tag_present(skb)) {
@@ -1759,16 +1848,6 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		h.h3->tp_snaplen = snaplen;
 		h.h3->tp_mac = macoff;
 		h.h3->tp_net = netoff;
-		if ((po->tp_tstamp & SOF_TIMESTAMPING_SYS_HARDWARE)
-				&& shhwtstamps->syststamp.tv64)
-			ts = ktime_to_timespec(shhwtstamps->syststamp);
-		else if ((po->tp_tstamp & SOF_TIMESTAMPING_RAW_HARDWARE)
-				&& shhwtstamps->hwtstamp.tv64)
-			ts = ktime_to_timespec(shhwtstamps->hwtstamp);
-		else if (skb->tstamp.tv64)
-			ts = ktime_to_timespec(skb->tstamp);
-		else
-			getnstimeofday(&ts);
 		h.h3->tp_sec  = ts.tv_sec;
 		h.h3->tp_nsec = ts.tv_nsec;
 		hdrlen = sizeof(*h.h3);
@@ -1819,7 +1898,7 @@ drop:
 	return 0;
 
 ring_is_full:
-	po->stats.tp_drops++;
+	po->stats.stats1.tp_drops++;
 	spin_unlock(&sk->sk_receive_queue.lock);
 
 	sk->sk_data_ready(sk, 0);
@@ -1833,10 +1912,14 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
 	void *ph;
 
 	if (likely(po->tx_ring.pg_vec)) {
+		__u32 ts;
+
 		ph = skb_shinfo(skb)->destructor_arg;
 		BUG_ON(atomic_read(&po->tx_ring.pending) == 0);
 		atomic_dec(&po->tx_ring.pending);
-		__packet_set_status(po, ph, TP_STATUS_AVAILABLE);
+
+		ts = __packet_set_timestamp(po, ph, skb);
+		__packet_set_status(po, ph, TP_STATUS_AVAILABLE | ts);
 	}
 
 	sock_wfree(skb);
@@ -1846,11 +1929,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		void *frame, struct net_device *dev, int size_max,
 		__be16 proto, unsigned char *addr, int hlen)
 {
-	union {
-		struct tpacket_hdr *h1;
-		struct tpacket2_hdr *h2;
-		void *raw;
-	} ph;
+	union tpacket_uhdr ph;
 	int to_write, offset, len, tp_len, nr_frags, len_max;
 	struct socket *sock = po->sk.sk_socket;
 	struct page *page;
@@ -1863,6 +1942,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 	skb->dev = dev;
 	skb->priority = po->sk.sk_priority;
 	skb->mark = po->sk.sk_mark;
+	sock_tx_timestamp(&po->sk, &skb_shinfo(skb)->tx_flags);
 	skb_shinfo(skb)->destructor_arg = ph.raw;
 
 	switch (po->tp_version) {
@@ -1880,6 +1960,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 
 	skb_reserve(skb, hlen);
 	skb_reset_network_header(skb);
+	skb_probe_transport_header(skb, 0);
 
 	if (po->tp_tx_has_off) {
 		int off_min, off_max, off;
@@ -2247,9 +2328,8 @@ static int packet_snd(struct socket *sock,
 	err = skb_copy_datagram_from_iovec(skb, offset, msg->msg_iov, 0, len);
 	if (err)
 		goto out_free;
-	err = sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags);
-	if (err < 0)
-		goto out_free;
+
+	sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags);
 
 	if (!gso_type && (len > dev->mtu + reserve + extra_len)) {
 		/* Earlier code assumed this would be a VLAN pkt,
@@ -2289,6 +2369,8 @@ static int packet_snd(struct socket *sock,
 		len += vnet_hdr_len;
 	}
 
+	skb_probe_transport_header(skb, reserve);
+
 	if (unlikely(extra_len == 4))
 		skb->no_fcs = 1;
 
@@ -3165,8 +3247,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 	struct sock *sk = sock->sk;
 	struct packet_sock *po = pkt_sk(sk);
 	void *data = &val;
-	struct tpacket_stats st;
-	union tpacket_stats_u st_u;
+	union tpacket_stats_u st;
 
 	if (level != SOL_PACKET)
 		return -ENOPROTOOPT;
@@ -3180,22 +3261,18 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 	switch (optname) {
 	case PACKET_STATISTICS:
 		spin_lock_bh(&sk->sk_receive_queue.lock);
+		memcpy(&st, &po->stats, sizeof(st));
+		memset(&po->stats, 0, sizeof(po->stats));
+		spin_unlock_bh(&sk->sk_receive_queue.lock);
+
 		if (po->tp_version == TPACKET_V3) {
 			lv = sizeof(struct tpacket_stats_v3);
-			memcpy(&st_u.stats3, &po->stats,
-			       sizeof(struct tpacket_stats));
-			st_u.stats3.tp_freeze_q_cnt =
-					po->stats_u.stats3.tp_freeze_q_cnt;
-			st_u.stats3.tp_packets += po->stats.tp_drops;
-			data = &st_u.stats3;
+			data = &st.stats3;
 		} else {
 			lv = sizeof(struct tpacket_stats);
-			st = po->stats;
-			st.tp_packets += st.tp_drops;
-			data = &st;
+			data = &st.stats1;
 		}
-		memset(&po->stats, 0, sizeof(st));
-		spin_unlock_bh(&sk->sk_receive_queue.lock);
+
 		break;
 	case PACKET_AUXDATA:
 		val = po->auxdata;
@@ -3240,7 +3317,8 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 	case PACKET_FANOUT:
 		val = (po->fanout ?
 		       ((u32)po->fanout->id |
-			((u32)po->fanout->type << 16)) :
+			((u32)po->fanout->type << 16) |
+			((u32)po->fanout->flags << 24)) :
 		       0);
 		break;
 	case PACKET_TX_HAS_OFF:
diff --git a/net/packet/diag.c b/net/packet/diag.c
index d3fcd1ebef7..a9584a2f6d6 100644
--- a/net/packet/diag.c
+++ b/net/packet/diag.c
@@ -125,8 +125,10 @@ static int pdiag_put_fanout(struct packet_sock *po, struct sk_buff *nlskb)
 	return ret;
 }
 
-static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct packet_diag_req *req,
-		u32 portid, u32 seq, u32 flags, int sk_ino)
+static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
+			struct packet_diag_req *req,
+			struct user_namespace *user_ns,
+			u32 portid, u32 seq, u32 flags, int sk_ino)
 {
 	struct nlmsghdr *nlh;
 	struct packet_diag_msg *rp;
@@ -147,6 +149,11 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct packet_diag
 			pdiag_put_info(po, skb))
 		goto out_nlmsg_trim;
 
+	if ((req->pdiag_show & PACKET_SHOW_INFO) &&
+	    nla_put_u32(skb, PACKET_DIAG_UID,
+			from_kuid_munged(user_ns, sock_i_uid(sk))))
+		goto out_nlmsg_trim;
+
 	if ((req->pdiag_show & PACKET_SHOW_MCLIST) &&
 			pdiag_put_mclist(po, skb))
 		goto out_nlmsg_trim;
@@ -159,6 +166,14 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct packet_diag
 			pdiag_put_fanout(po, skb))
 		goto out_nlmsg_trim;
 
+	if ((req->pdiag_show & PACKET_SHOW_MEMINFO) &&
+	    sock_diag_put_meminfo(sk, skb, PACKET_DIAG_MEMINFO))
+		goto out_nlmsg_trim;
+
+	if ((req->pdiag_show & PACKET_SHOW_FILTER) &&
+	    sock_diag_put_filterinfo(user_ns, sk, skb, PACKET_DIAG_FILTER))
+		goto out_nlmsg_trim;
+
 	return nlmsg_end(skb, nlh);
 
 out_nlmsg_trim:
@@ -183,9 +198,11 @@ static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 		if (num < s_num)
 			goto next;
 
-		if (sk_diag_fill(sk, skb, req, NETLINK_CB(cb->skb).portid,
-					cb->nlh->nlmsg_seq, NLM_F_MULTI,
-					sock_i_ino(sk)) < 0)
+		if (sk_diag_fill(sk, skb, req,
+				 sk_user_ns(NETLINK_CB(cb->skb).sk),
+				 NETLINK_CB(cb->skb).portid,
+				 cb->nlh->nlmsg_seq, NLM_F_MULTI,
+				 sock_i_ino(sk)) < 0)
 			goto done;
 next:
 		num++;
diff --git a/net/packet/internal.h b/net/packet/internal.h
index e84cab8cb7a..c4e4b456120 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -54,6 +54,7 @@ struct pgv {
 
 struct packet_ring_buffer {
 	struct pgv		*pg_vec;
+
 	unsigned int		head;
 	unsigned int		frames_per_block;
 	unsigned int		frame_size;
@@ -63,8 +64,9 @@ struct packet_ring_buffer {
 	unsigned int		pg_vec_pages;
 	unsigned int		pg_vec_len;
 
-	struct tpacket_kbdq_core	prb_bdqc;
 	atomic_t		pending;
+
+	struct tpacket_kbdq_core	prb_bdqc;
 };
 
 extern struct mutex fanout_mutex;
@@ -77,10 +79,11 @@ struct packet_fanout {
 	unsigned int		num_members;
 	u16			id;
 	u8			type;
-	u8			defrag;
+	u8			flags;
 	atomic_t		rr_cur;
 	struct list_head	list;
 	struct sock		*arr[PACKET_FANOUT_MAX];
+	int			next[PACKET_FANOUT_MAX];
 	spinlock_t		lock;
 	atomic_t		sk_ref;
 	struct packet_type	prot_hook ____cacheline_aligned_in_smp;
@@ -90,8 +93,7 @@ struct packet_sock {
 	/* struct sock has to be the first member of packet_sock */
 	struct sock		sk;
 	struct packet_fanout	*fanout;
-	struct tpacket_stats	stats;
-	union  tpacket_stats_u	stats_u;
+	union  tpacket_stats_u	stats;
 	struct packet_ring_buffer	rx_ring;
 	struct packet_ring_buffer	tx_ring;
 	int			copy_thresh;