--- zzzz-none-000/linux-3.10.107/net/packet/af_packet.c	2017-06-27 09:49:32.000000000 +0000
+++ scorpion-7490-727/linux-3.10.107/net/packet/af_packet.c	2021-02-04 17:41:59.000000000 +0000
@@ -88,10 +88,11 @@
 #include <linux/virtio_net.h>
 #include <linux/errqueue.h>
 #include <linux/net_tstamp.h>
-
+#include <linux/percpu.h>
 #ifdef CONFIG_INET
 #include <net/inet_common.h>
 #endif
+#include <linux/bpf.h>
 
 #include "internal.h"
 
@@ -216,13 +217,21 @@
 static void packet_flush_mclist(struct sock *sk);
 
 struct packet_skb_cb {
-	unsigned int origlen;
 	union {
 		struct sockaddr_pkt pkt;
-		struct sockaddr_ll ll;
+		union {
+			/* Trick: alias skb original length with
+			 * ll.sll_family and ll.protocol in order
+			 * to save room.
+			 */
+			unsigned int origlen;
+			struct sockaddr_ll ll;
+		};
 	} sa;
 };
 
+#define vio_le() virtio_legacy_is_little_endian()
+
 #define PACKET_SKB_CB(__skb)	((struct packet_skb_cb *)((__skb)->cb))
 
 #define GET_PBDQC_FROM_RB(x)	((struct tpacket_kbdq_core *)(&(x)->prb_bdqc))
@@ -237,6 +246,42 @@
 static void __fanout_unlink(struct sock *sk, struct packet_sock *po);
 static void __fanout_link(struct sock *sk, struct packet_sock *po);
 
+static int packet_direct_xmit(struct sk_buff *skb)
+{
+	struct net_device *dev = skb->dev;
+	struct sk_buff *orig_skb = skb;
+	struct netdev_queue *txq;
+	int ret = NETDEV_TX_BUSY;
+
+	if (unlikely(!netif_running(dev) ||
+		     !netif_carrier_ok(dev)))
+		goto drop;
+
+	skb = validate_xmit_skb_list(skb, dev);
+	if (skb != orig_skb)
+		goto drop;
+
+	txq = skb_get_tx_queue(dev, skb);
+
+	local_bh_disable();
+
+	HARD_TX_LOCK(dev, txq, smp_processor_id());
+	if (!netif_xmit_frozen_or_drv_stopped(txq))
+		ret = netdev_start_xmit(skb, dev, txq, false);
+	HARD_TX_UNLOCK(dev, txq);
+
+	local_bh_enable();
+
+	if (!dev_xmit_complete(ret))
+		kfree_skb(skb);
+
+	return ret;
+drop:
+	atomic_long_inc(&dev->tx_dropped);
+	kfree_skb_list(skb);
+	return NET_XMIT_DROP;
+}
+
 static struct net_device *packet_cached_dev_get(struct packet_sock *po)
 {
 	struct net_device *dev;
@@ -261,6 +306,32 @@
 	RCU_INIT_POINTER(po->cached_dev, NULL);
 }
 
+static bool packet_use_direct_xmit(const struct packet_sock *po)
+{
+	return po->xmit == packet_direct_xmit;
+}
+
+static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
+{
+	return (u16) raw_smp_processor_id() % dev->real_num_tx_queues;
+}
+
+static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+	u16 queue_index;
+
+	if (ops->ndo_select_queue) {
+		queue_index = ops->ndo_select_queue(dev, skb, NULL,
+						    __packet_pick_tx_queue);
+		queue_index = netdev_cap_txqueue(dev, queue_index);
+	} else {
+		queue_index = __packet_pick_tx_queue(dev, skb);
+	}
+
+	skb_set_queue_mapping(skb, queue_index);
+}
+
 /* register_prot_hook must be invoked with the po->bind_lock held,
  * or from a context in which asynchronous accesses to the packet
  * socket is not possible (packet_create()).
@@ -315,7 +386,7 @@
 		__unregister_prot_hook(sk, sync);
 }
 
-static inline __pure struct page *pgv_to_page(void *addr)
+static inline struct page * __pure pgv_to_page(void *addr)
 {
 	if (is_vmalloc_addr(addr))
 		return vmalloc_to_page(addr);
@@ -372,14 +443,10 @@
 {
 	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 (shhwtstamps &&
+	    (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;
@@ -453,12 +520,11 @@
 }
 
 static void prb_shutdown_retire_blk_timer(struct packet_sock *po,
-		int tx_ring,
 		struct sk_buff_head *rb_queue)
 {
 	struct tpacket_kbdq_core *pkc;
 
-	pkc = tx_ring ? &po->tx_ring.prb_bdqc : &po->rx_ring.prb_bdqc;
+	pkc = GET_PBDQC_FROM_RB(&po->rx_ring);
 
 	spin_lock_bh(&rb_queue->lock);
 	pkc->delete_blk_timer = 1;
@@ -477,14 +543,11 @@
 	pkc->retire_blk_timer.expires = jiffies;
 }
 
-static void prb_setup_retire_blk_timer(struct packet_sock *po, int tx_ring)
+static void prb_setup_retire_blk_timer(struct packet_sock *po)
 {
 	struct tpacket_kbdq_core *pkc;
 
-	if (tx_ring)
-		BUG();
-
-	pkc = tx_ring ? &po->tx_ring.prb_bdqc : &po->rx_ring.prb_bdqc;
+	pkc = GET_PBDQC_FROM_RB(&po->rx_ring);
 	prb_init_blk_timer(po, pkc, prb_retire_rx_blk_timer_expired);
 }
 
@@ -540,9 +603,9 @@
 static void init_prb_bdqc(struct packet_sock *po,
 			struct packet_ring_buffer *rb,
 			struct pgv *pg_vec,
-			union tpacket_req_u *req_u, int tx_ring)
+			union tpacket_req_u *req_u)
 {
-	struct tpacket_kbdq_core *p1 = &rb->prb_bdqc;
+	struct tpacket_kbdq_core *p1 = GET_PBDQC_FROM_RB(rb);
 	struct tpacket_block_desc *pbd;
 
 	memset(p1, 0x0, sizeof(*p1));
@@ -567,7 +630,7 @@
 
 	p1->max_frame_len = p1->kblk_size - BLK_PLUS_PRIV(p1->blk_sizeof_priv);
 	prb_init_ft_ops(p1, req_u);
-	prb_setup_retire_blk_timer(po, tx_ring);
+	prb_setup_retire_blk_timer(po);
 	prb_open_block(p1, pbd);
 }
 
@@ -607,7 +670,7 @@
 static void prb_retire_rx_blk_timer_expired(unsigned long data)
 {
 	struct packet_sock *po = (struct packet_sock *)data;
-	struct tpacket_kbdq_core *pkc = &po->rx_ring.prb_bdqc;
+	struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(&po->rx_ring);
 	unsigned int frozen;
 	struct tpacket_block_desc *pbd;
 
@@ -637,6 +700,10 @@
 
 	if (pkc->last_kactive_blk_num == pkc->kactive_blk_num) {
 		if (!frozen) {
+			if (!BLOCK_NUM_PKTS(pbd)) {
+				/* An empty block. Just refresh the timer. */
+				goto refresh_timer;
+			}
 			prb_retire_current_block(pkc, po, TP_STATUS_BLK_TMO);
 			if (!prb_dispatch_next_block(pkc, po))
 				goto refresh_timer;
@@ -724,6 +791,7 @@
 
 	struct tpacket3_hdr *last_pkt;
 	struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1;
+	struct sock *sk = &po->sk;
 
 	if (po->stats.stats3.tp_drops)
 		status |= TP_STATUS_LOSING;
@@ -736,7 +804,11 @@
 		h1->ts_last_pkt.ts_sec = last_pkt->tp_sec;
 		h1->ts_last_pkt.ts_nsec	= last_pkt->tp_nsec;
 	} else {
-		/* Ok, we tmo'd - so get the current time */
+		/* Ok, we tmo'd - so get the current time.
+		 *
+		 * It shouldn't really happen as we don't close empty
+		 * blocks. See prb_retire_rx_blk_timer_expired().
+		 */
 		struct timespec ts;
 		getnstimeofday(&ts);
 		h1->ts_last_pkt.ts_sec = ts.tv_sec;
@@ -748,6 +820,8 @@
 	/* Flush the block */
 	prb_flush_block(pkc1, pbd1, status);
 
+	sk->sk_data_ready(sk);
+
 	pkc1->kactive_blk_num = GET_NEXT_PRB_BLK_NUM(pkc1);
 }
 
@@ -910,7 +984,7 @@
 static void prb_fill_rxhash(struct tpacket_kbdq_core *pkc,
 			struct tpacket3_hdr *ppd)
 {
-	ppd->hv1.tp_rxhash = skb_get_rxhash(pkc->skb);
+	ppd->hv1.tp_rxhash = skb_get_hash(pkc->skb);
 }
 
 static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc,
@@ -922,11 +996,13 @@
 static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc,
 			struct tpacket3_hdr *ppd)
 {
-	if (vlan_tx_tag_present(pkc->skb)) {
-		ppd->hv1.tp_vlan_tci = vlan_tx_tag_get(pkc->skb);
-		ppd->tp_status = TP_STATUS_VLAN_VALID;
+	if (skb_vlan_tag_present(pkc->skb)) {
+		ppd->hv1.tp_vlan_tci = skb_vlan_tag_get(pkc->skb);
+		ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto);
+		ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
 	} else {
 		ppd->hv1.tp_vlan_tci = 0;
+		ppd->hv1.tp_vlan_tpid = 0;
 		ppd->tp_status = TP_STATUS_AVAILABLE;
 	}
 }
@@ -934,6 +1010,7 @@
 static void prb_run_all_ft_ops(struct tpacket_kbdq_core *pkc,
 			struct tpacket3_hdr *ppd)
 {
+	ppd->hv1.tp_padding = 0;
 	prb_fill_vlan_info(pkc, ppd);
 
 	if (pkc->feature_req_word & TP_FT_REQ_FILL_RXHASH)
@@ -1112,27 +1189,122 @@
 	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)
+static void packet_inc_pending(struct packet_ring_buffer *rb)
+{
+	this_cpu_inc(*rb->pending_refcnt);
+}
+
+static void packet_dec_pending(struct packet_ring_buffer *rb)
+{
+	this_cpu_dec(*rb->pending_refcnt);
+}
+
+static unsigned int packet_read_pending(const struct packet_ring_buffer *rb)
+{
+	unsigned int refcnt = 0;
+	int cpu;
+
+	/* We don't use pending refcount in rx_ring. */
+	if (rb->pending_refcnt == NULL)
+		return 0;
+
+	for_each_possible_cpu(cpu)
+		refcnt += *per_cpu_ptr(rb->pending_refcnt, cpu);
+
+	return refcnt;
+}
+
+static int packet_alloc_pending(struct packet_sock *po)
+{
+	po->rx_ring.pending_refcnt = NULL;
+
+	po->tx_ring.pending_refcnt = alloc_percpu(unsigned int);
+	if (unlikely(po->tx_ring.pending_refcnt == NULL))
+		return -ENOBUFS;
+
+	return 0;
+}
+
+static void packet_free_pending(struct packet_sock *po)
+{
+	free_percpu(po->tx_ring.pending_refcnt);
+}
+
+#define ROOM_POW_OFF	2
+#define ROOM_NONE	0x0
+#define ROOM_LOW	0x1
+#define ROOM_NORMAL	0x2
+
+static bool __tpacket_has_room(struct packet_sock *po, int pow_off)
+{
+	int idx, len;
+
+	len = po->rx_ring.frame_max + 1;
+	idx = po->rx_ring.head;
+	if (pow_off)
+		idx += len >> pow_off;
+	if (idx >= len)
+		idx -= len;
+	return packet_lookup_frame(po, &po->rx_ring, idx, TP_STATUS_KERNEL);
+}
+
+static bool __tpacket_v3_has_room(struct packet_sock *po, int pow_off)
+{
+	int idx, len;
+
+	len = po->rx_ring.prb_bdqc.knum_blocks;
+	idx = po->rx_ring.prb_bdqc.kactive_blk_num;
+	if (pow_off)
+		idx += len >> pow_off;
+	if (idx >= len)
+		idx -= len;
+	return prb_lookup_block(po, &po->rx_ring, idx, TP_STATUS_KERNEL);
+}
+
+static int __packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb)
 {
 	struct sock *sk = &po->sk;
-	bool has_room;
+	int ret = ROOM_NONE;
 
-	if (po->prot_hook.func != tpacket_rcv)
-		return (atomic_read(&sk->sk_rmem_alloc) + skb->truesize)
-			<= sk->sk_rcvbuf;
+	if (po->prot_hook.func != tpacket_rcv) {
+		int avail = sk->sk_rcvbuf - atomic_read(&sk->sk_rmem_alloc)
+					  - (skb ? skb->truesize : 0);
+		if (avail > (sk->sk_rcvbuf >> ROOM_POW_OFF))
+			return ROOM_NORMAL;
+		else if (avail > 0)
+			return ROOM_LOW;
+		else
+			return ROOM_NONE;
+	}
 
-	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);
+	if (po->tp_version == TPACKET_V3) {
+		if (__tpacket_v3_has_room(po, ROOM_POW_OFF))
+			ret = ROOM_NORMAL;
+		else if (__tpacket_v3_has_room(po, 0))
+			ret = ROOM_LOW;
+	} else {
+		if (__tpacket_has_room(po, ROOM_POW_OFF))
+			ret = ROOM_NORMAL;
+		else if (__tpacket_has_room(po, 0))
+			ret = ROOM_LOW;
+	}
 
-	return has_room;
+	return ret;
+}
+
+static int packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb)
+{
+	int ret;
+	bool has_room;
+
+	spin_lock_bh(&po->sk.sk_receive_queue.lock);
+	ret = __packet_rcv_has_room(po, skb);
+	has_room = ret == ROOM_NORMAL;
+	if (po->pressure == has_room)
+		po->pressure = !has_room;
+	spin_unlock_bh(&po->sk.sk_receive_queue.lock);
+
+	return ret;
 }
 
 static void packet_sock_destruct(struct sock *sk)
@@ -1150,11 +1322,25 @@
 	sk_refcnt_debug_dec(sk);
 }
 
+static bool fanout_flow_is_huge(struct packet_sock *po, struct sk_buff *skb)
+{
+	u32 rxhash;
+	int i, count = 0;
+
+	rxhash = skb_get_hash(skb);
+	for (i = 0; i < ROLLOVER_HLEN; i++)
+		if (po->rollover->history[i] == rxhash)
+			count++;
+
+	po->rollover->history[prandom_u32() % ROLLOVER_HLEN] = rxhash;
+	return count > (ROLLOVER_HLEN >> 1);
+}
+
 static unsigned int fanout_demux_hash(struct packet_fanout *f,
 				      struct sk_buff *skb,
 				      unsigned int num)
 {
-	return (((u64)skb->rxhash) * num) >> 32;
+	return reciprocal_scale(__skb_get_hash_symmetric(skb), num);
 }
 
 static unsigned int fanout_demux_lb(struct packet_fanout *f,
@@ -1173,27 +1359,75 @@
 	return smp_processor_id() % num;
 }
 
+static unsigned int fanout_demux_rnd(struct packet_fanout *f,
+				     struct sk_buff *skb,
+				     unsigned int num)
+{
+	return prandom_u32_max(num);
+}
+
 static unsigned int fanout_demux_rollover(struct packet_fanout *f,
 					  struct sk_buff *skb,
-					  unsigned int idx, unsigned int skip,
+					  unsigned int idx, bool try_self,
 					  unsigned int num)
 {
-	unsigned int i, j;
+	struct packet_sock *po, *po_next, *po_skip = NULL;
+	unsigned int i, j, room = ROOM_NONE;
+
+	po = pkt_sk(f->arr[idx]);
 
-	i = j = min_t(int, f->next[idx], num - 1);
+	if (try_self) {
+		room = packet_rcv_has_room(po, skb);
+		if (room == ROOM_NORMAL ||
+		    (room == ROOM_LOW && !fanout_flow_is_huge(po, skb)))
+			return idx;
+		po_skip = po;
+	}
+
+	i = j = min_t(int, po->rollover->sock, num - 1);
 	do {
-		if (i != skip && packet_rcv_has_room(pkt_sk(f->arr[i]), skb)) {
+		po_next = pkt_sk(f->arr[i]);
+		if (po_next != po_skip && !po_next->pressure &&
+		    packet_rcv_has_room(po_next, skb) == ROOM_NORMAL) {
 			if (i != j)
-				f->next[idx] = i;
+				po->rollover->sock = i;
+			atomic_long_inc(&po->rollover->num);
+			if (room == ROOM_LOW)
+				atomic_long_inc(&po->rollover->num_huge);
 			return i;
 		}
+
 		if (++i == num)
 			i = 0;
 	} while (i != j);
 
+	atomic_long_inc(&po->rollover->num_failed);
 	return idx;
 }
 
+static unsigned int fanout_demux_qm(struct packet_fanout *f,
+				    struct sk_buff *skb,
+				    unsigned int num)
+{
+	return skb_get_queue_mapping(skb) % num;
+}
+
+static unsigned int fanout_demux_bpf(struct packet_fanout *f,
+				     struct sk_buff *skb,
+				     unsigned int num)
+{
+	struct bpf_prog *prog;
+	unsigned int ret = 0;
+
+	rcu_read_lock();
+	prog = rcu_dereference(f->bpf_prog);
+	if (prog)
+		ret = bpf_prog_run_clear_cb(prog, skb) % num;
+	rcu_read_unlock();
+
+	return ret;
+}
+
 static bool fanout_has_flag(struct packet_fanout *f, u16 flag)
 {
 	return f->flags & (flag >> 8);
@@ -1203,25 +1437,24 @@
 			     struct packet_type *pt, struct net_device *orig_dev)
 {
 	struct packet_fanout *f = pt->af_packet_priv;
-	unsigned int num = ACCESS_ONCE(f->num_members);
+	unsigned int num = READ_ONCE(f->num_members);
+	struct net *net = read_pnet(&f->net);
 	struct packet_sock *po;
 	unsigned int idx;
 
-	if (!net_eq(dev_net(dev), read_pnet(&f->net)) ||
-	    !num) {
+	if (!net_eq(dev_net(dev), net) || !num) {
 		kfree_skb(skb);
 		return 0;
 	}
 
+	if (fanout_has_flag(f, PACKET_FANOUT_FLAG_DEFRAG)) {
+		skb = ip_check_defrag(net, skb, IP_DEFRAG_AF_PACKET);
+		if (!skb)
+			return 0;
+	}
 	switch (f->type) {
 	case PACKET_FANOUT_HASH:
 	default:
-		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);
 		idx = fanout_demux_hash(f, skb, num);
 		break;
 	case PACKET_FANOUT_LB:
@@ -1230,18 +1463,25 @@
 	case PACKET_FANOUT_CPU:
 		idx = fanout_demux_cpu(f, skb, num);
 		break;
+	case PACKET_FANOUT_RND:
+		idx = fanout_demux_rnd(f, skb, num);
+		break;
+	case PACKET_FANOUT_QM:
+		idx = fanout_demux_qm(f, skb, num);
+		break;
 	case PACKET_FANOUT_ROLLOVER:
-		idx = fanout_demux_rollover(f, skb, 0, (unsigned int) -1, num);
+		idx = fanout_demux_rollover(f, skb, 0, false, num);
+		break;
+	case PACKET_FANOUT_CBPF:
+	case PACKET_FANOUT_EBPF:
+		idx = fanout_demux_bpf(f, skb, num);
 		break;
 	}
 
-	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]);
-	}
+	if (fanout_has_flag(f, PACKET_FANOUT_FLAG_ROLLOVER))
+		idx = fanout_demux_rollover(f, skb, idx, true, num);
 
+	po = pkt_sk(f->arr[idx]);
 	return po->prot_hook.func(skb, dev, &po->prot_hook, orig_dev);
 }
 
@@ -1280,16 +1520,114 @@
 	spin_unlock(&f->lock);
 }
 
-static bool match_fanout_group(struct packet_type *ptype, struct sock * sk)
+static bool match_fanout_group(struct packet_type *ptype, struct sock *sk)
 {
-	if (ptype->af_packet_priv == (void*)((struct packet_sock *)sk)->fanout)
-		return true;
+	if (sk->sk_family != PF_PACKET)
+		return false;
+
+	return ptype->af_packet_priv == pkt_sk(sk)->fanout;
+}
 
-	return false;
+static void fanout_init_data(struct packet_fanout *f)
+{
+	switch (f->type) {
+	case PACKET_FANOUT_LB:
+		atomic_set(&f->rr_cur, 0);
+		break;
+	case PACKET_FANOUT_CBPF:
+	case PACKET_FANOUT_EBPF:
+		RCU_INIT_POINTER(f->bpf_prog, NULL);
+		break;
+	}
+}
+
+static void __fanout_set_data_bpf(struct packet_fanout *f, struct bpf_prog *new)
+{
+	struct bpf_prog *old;
+
+	spin_lock(&f->lock);
+	old = rcu_dereference_protected(f->bpf_prog, lockdep_is_held(&f->lock));
+	rcu_assign_pointer(f->bpf_prog, new);
+	spin_unlock(&f->lock);
+
+	if (old) {
+		synchronize_net();
+		bpf_prog_destroy(old);
+	}
+}
+
+static int fanout_set_data_cbpf(struct packet_sock *po, char __user *data,
+				unsigned int len)
+{
+	struct bpf_prog *new;
+	struct sock_fprog fprog;
+	int ret;
+
+	if (sock_flag(&po->sk, SOCK_FILTER_LOCKED))
+		return -EPERM;
+	if (len != sizeof(fprog))
+		return -EINVAL;
+	if (copy_from_user(&fprog, data, len))
+		return -EFAULT;
+
+	ret = bpf_prog_create_from_user(&new, &fprog, NULL, false);
+	if (ret)
+		return ret;
+
+	__fanout_set_data_bpf(po->fanout, new);
+	return 0;
+}
+
+static int fanout_set_data_ebpf(struct packet_sock *po, char __user *data,
+				unsigned int len)
+{
+	struct bpf_prog *new;
+	u32 fd;
+
+	if (sock_flag(&po->sk, SOCK_FILTER_LOCKED))
+		return -EPERM;
+	if (len != sizeof(fd))
+		return -EINVAL;
+	if (copy_from_user(&fd, data, len))
+		return -EFAULT;
+
+	new = bpf_prog_get(fd);
+	if (IS_ERR(new))
+		return PTR_ERR(new);
+	if (new->type != BPF_PROG_TYPE_SOCKET_FILTER) {
+		bpf_prog_put(new);
+		return -EINVAL;
+	}
+
+	__fanout_set_data_bpf(po->fanout, new);
+	return 0;
+}
+
+static int fanout_set_data(struct packet_sock *po, char __user *data,
+			   unsigned int len)
+{
+	switch (po->fanout->type) {
+	case PACKET_FANOUT_CBPF:
+		return fanout_set_data_cbpf(po, data, len);
+	case PACKET_FANOUT_EBPF:
+		return fanout_set_data_ebpf(po, data, len);
+	default:
+		return -EINVAL;
+	};
+}
+
+static void fanout_release_data(struct packet_fanout *f)
+{
+	switch (f->type) {
+	case PACKET_FANOUT_CBPF:
+	case PACKET_FANOUT_EBPF:
+		__fanout_set_data_bpf(f, NULL);
+	};
 }
 
 static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 {
+	struct packet_rollover *rollover = NULL;
 	struct packet_sock *po = pkt_sk(sk);
 	struct packet_fanout *f, *match;
 	u8 type = type_flags & 0xff;
@@ -1303,6 +1641,10 @@
 	case PACKET_FANOUT_HASH:
 	case PACKET_FANOUT_LB:
 	case PACKET_FANOUT_CPU:
+	case PACKET_FANOUT_RND:
+	case PACKET_FANOUT_QM:
+	case PACKET_FANOUT_CBPF:
+	case PACKET_FANOUT_EBPF:
 		break;
 	default:
 		return -EINVAL;
@@ -1318,6 +1660,18 @@
 	if (po->fanout)
 		goto out;
 
+	if (type == PACKET_FANOUT_ROLLOVER ||
+	    (type_flags & PACKET_FANOUT_FLAG_ROLLOVER)) {
+		err = -ENOMEM;
+		rollover = kzalloc(sizeof(*rollover), GFP_KERNEL);
+		if (!rollover)
+			goto out;
+		atomic_long_set(&rollover->num, 0);
+		atomic_long_set(&rollover->num_huge, 0);
+		atomic_long_set(&rollover->num_failed, 0);
+		po->rollover = rollover;
+	}
+
 	match = NULL;
 	list_for_each_entry(f, &fanout_list, list) {
 		if (f->id == id &&
@@ -1338,10 +1692,10 @@
 		match->id = id;
 		match->type = type;
 		match->flags = flags;
-		atomic_set(&match->rr_cur, 0);
 		INIT_LIST_HEAD(&match->list);
 		spin_lock_init(&match->lock);
 		atomic_set(&match->sk_ref, 0);
+		fanout_init_data(match);
 		match->prot_hook.type = po->prot_hook.type;
 		match->prot_hook.dev = po->prot_hook.dev;
 		match->prot_hook.func = packet_rcv_fanout;
@@ -1363,6 +1717,10 @@
 		}
 	}
 out:
+	if (err && rollover) {
+		kfree(rollover);
+		po->rollover = NULL;
+	}
 	mutex_unlock(&fanout_mutex);
 	return err;
 }
@@ -1386,12 +1744,29 @@
 			list_del(&f->list);
 		else
 			f = NULL;
+
+		if (po->rollover)
+			kfree_rcu(po->rollover, rcu);
 	}
 	mutex_unlock(&fanout_mutex);
 
 	return f;
 }
 
+static bool packet_extra_vlan_len_allowed(const struct net_device *dev,
+					  struct sk_buff *skb)
+{
+	/* Earlier code assumed this would be a VLAN pkt, double-check
+	 * this now that we have the actual packet in hand. We can only
+	 * do this check on Ethernet devices.
+	 */
+	if (unlikely(dev->type != ARPHRD_ETHER))
+		return false;
+
+	skb_reset_mac_header(skb);
+	return likely(eth_hdr(skb)->h_proto == htons(ETH_P_8021Q));
+}
+
 static const struct proto_ops packet_ops;
 
 static const struct proto_ops packet_ops_spkt;
@@ -1401,6 +1776,7 @@
 {
 	struct sock *sk;
 	struct sockaddr_pkt *spkt;
+	struct packet_sock *po;
 
 	/*
 	 *	When we registered the protocol we saved the socket in the data
@@ -1408,6 +1784,7 @@
 	 */
 
 	sk = pt->af_packet_priv;
+	po = pkt_sk(sk);
 
 	/*
 	 *	Yank back the headers [hope the device set this
@@ -1420,7 +1797,7 @@
 	 *	so that this procedure is noop.
 	 */
 
-	if (skb->pkt_type == PACKET_LOOPBACK)
+	if (!(po->pkt_type & (1 << skb->pkt_type)))
 		goto out;
 
 	if (!net_eq(dev_net(dev), sock_net(sk)))
@@ -1468,11 +1845,11 @@
  *	protocol layers and you must therefore supply it with a complete frame
  */
 
-static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock,
-			       struct msghdr *msg, size_t len)
+static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg,
+			       size_t len)
 {
 	struct sock *sk = sock->sk;
-	struct sockaddr_pkt *saddr = (struct sockaddr_pkt *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_pkt *, saddr, msg->msg_name);
 	struct sk_buff *skb = NULL;
 	struct net_device *dev;
 	__be16 proto = 0;
@@ -1547,24 +1924,20 @@
 			if (len < hhlen)
 				skb_reset_network_header(skb);
 		}
-		err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
+		err = memcpy_from_msg(skb_put(skb, len), msg, len);
 		if (err)
 			goto out_free;
 		goto retry;
 	}
 
-	if (len > (dev->mtu + dev->hard_header_len + extra_len)) {
-		/* Earlier code assumed this would be a VLAN pkt,
-		 * double-check this now that we have the actual
-		 * packet in hand.
-		 */
-		struct ethhdr *ehdr;
-		skb_reset_mac_header(skb);
-		ehdr = eth_hdr(skb);
-		if (ehdr->h_proto != htons(ETH_P_8021Q)) {
-			err = -EMSGSIZE;
-			goto out_unlock;
-		}
+	if (!dev_validate_header(dev, skb->data, len)) {
+		err = -EINVAL;
+		goto out_unlock;
+	}
+	if (len > (dev->mtu + dev->hard_header_len + extra_len) &&
+	    !packet_extra_vlan_len_allowed(dev, skb)) {
+		err = -EMSGSIZE;
+		goto out_unlock;
 	}
 
 	skb->protocol = proto;
@@ -1590,16 +1963,16 @@
 	return err;
 }
 
-static unsigned int run_filter(const struct sk_buff *skb,
-				      const struct sock *sk,
-				      unsigned int res)
+static unsigned int run_filter(struct sk_buff *skb,
+			       const struct sock *sk,
+			       unsigned int res)
 {
 	struct sk_filter *filter;
 
 	rcu_read_lock();
 	filter = rcu_dereference(sk->sk_filter);
 	if (filter != NULL)
-		res = SK_RUN_FILTER(filter, skb);
+		res = bpf_prog_run_clear_cb(filter->prog, skb);
 	rcu_read_unlock();
 
 	return res;
@@ -1627,12 +2000,12 @@
 	int skb_len = skb->len;
 	unsigned int snaplen, res;
 
-	if (skb->pkt_type == PACKET_LOOPBACK)
-		goto drop;
-
 	sk = pt->af_packet_priv;
 	po = pkt_sk(sk);
 
+	if (!(po->pkt_type & (1 << skb->pkt_type)))
+		goto drop;
+
 	if (!net_eq(dev_net(dev), sock_net(sk)))
 		goto drop;
 
@@ -1678,13 +2051,10 @@
 		skb = nskb;
 	}
 
-	BUILD_BUG_ON(sizeof(*PACKET_SKB_CB(skb)) + MAX_ADDR_LEN - 8 >
-		     sizeof(skb->cb));
+	sock_skb_cb_check_size(sizeof(*PACKET_SKB_CB(skb)) + MAX_ADDR_LEN - 8);
 
 	sll = &PACKET_SKB_CB(skb)->sa.ll;
-	sll->sll_family = AF_PACKET;
 	sll->sll_hatype = dev->type;
-	sll->sll_protocol = skb->protocol;
 	sll->sll_pkttype = skb->pkt_type;
 	if (unlikely(po->origdev))
 		sll->sll_ifindex = orig_dev->ifindex;
@@ -1693,7 +2063,10 @@
 
 	sll->sll_halen = dev_parse_header(skb, sll->sll_addr);
 
-	PACKET_SKB_CB(skb)->origlen = skb->len;
+	/* sll->sll_family and sll->sll_protocol are set in packet_recvmsg().
+	 * Use their space for storing the original skb length.
+	 */
+	PACKET_SKB_CB(skb)->sa.origlen = skb->len;
 
 	if (pskb_trim(skb, snaplen))
 		goto drop_n_acct;
@@ -1707,10 +2080,10 @@
 
 	spin_lock(&sk->sk_receive_queue.lock);
 	po->stats.stats1.tp_packets++;
-	skb->dropcount = atomic_read(&sk->sk_drops);
+	sock_skb_set_dropcount(sk, skb);
 	__skb_queue_tail(&sk->sk_receive_queue, skb);
 	spin_unlock(&sk->sk_receive_queue.lock);
-	sk->sk_data_ready(sk, skb->len);
+	sk->sk_data_ready(sk);
 	return 0;
 
 drop_n_acct:
@@ -1745,12 +2118,19 @@
 	struct timespec ts;
 	__u32 ts_status;
 
-	if (skb->pkt_type == PACKET_LOOPBACK)
-		goto drop;
+	/* struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT.
+	 * We may add members to them until current aligned size without forcing
+	 * userspace to call getsockopt(..., PACKET_HDRLEN, ...).
+	 */
+	BUILD_BUG_ON(TPACKET_ALIGN(sizeof(*h.h2)) != 32);
+	BUILD_BUG_ON(TPACKET_ALIGN(sizeof(*h.h3)) != 48);
 
 	sk = pt->af_packet_priv;
 	po = pkt_sk(sk);
 
+	if (!(po->pkt_type & (1 << skb->pkt_type)))
+		goto drop;
+
 	if (!net_eq(dev_net(dev), sock_net(sk)))
 		goto drop;
 
@@ -1763,14 +2143,19 @@
 		}
 	}
 
-	if (skb->ip_summed == CHECKSUM_PARTIAL)
-		status |= TP_STATUS_CSUMNOTREADY;
-
 	snaplen = skb->len;
 
 	res = run_filter(skb, sk, snaplen);
 	if (!res)
 		goto drop_n_restore;
+
+	if (skb->ip_summed == CHECKSUM_PARTIAL)
+		status |= TP_STATUS_CSUMNOTREADY;
+	else if (skb->pkt_type != PACKET_OUTGOING &&
+		 (skb->ip_summed == CHECKSUM_COMPLETE ||
+		  skb_csum_unnecessary(skb)))
+		status |= TP_STATUS_CSUM_VALID;
+
 	if (snaplen > res)
 		snaplen = res;
 
@@ -1861,13 +2246,15 @@
 		h.h2->tp_net = netoff;
 		h.h2->tp_sec = ts.tv_sec;
 		h.h2->tp_nsec = ts.tv_nsec;
-		if (vlan_tx_tag_present(skb)) {
-			h.h2->tp_vlan_tci = vlan_tx_tag_get(skb);
-			status |= TP_STATUS_VLAN_VALID;
+		if (skb_vlan_tag_present(skb)) {
+			h.h2->tp_vlan_tci = skb_vlan_tag_get(skb);
+			h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto);
+			status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
 		} else {
 			h.h2->tp_vlan_tci = 0;
+			h.h2->tp_vlan_tpid = 0;
 		}
-		h.h2->tp_padding = 0;
+		memset(h.h2->tp_padding, 0, sizeof(h.h2->tp_padding));
 		hdrlen = sizeof(*h.h2);
 		break;
 	case TPACKET_V3:
@@ -1881,6 +2268,7 @@
 		h.h3->tp_net = netoff;
 		h.h3->tp_sec  = ts.tv_sec;
 		h.h3->tp_nsec = ts.tv_nsec;
+		memset(h.h3->tp_padding, 0, sizeof(h.h3->tp_padding));
 		hdrlen = sizeof(*h.h3);
 		break;
 	default:
@@ -1899,25 +2287,26 @@
 		sll->sll_ifindex = dev->ifindex;
 
 	smp_mb();
+
 #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1
-	{
+	if (po->tp_version <= TPACKET_V2) {
 		u8 *start, *end;
 
-		if (po->tp_version <= TPACKET_V2) {
-			end = (u8 *)PAGE_ALIGN((unsigned long)h.raw
-				+ macoff + snaplen);
-			for (start = h.raw; start < end; start += PAGE_SIZE)
-				flush_dcache_page(pgv_to_page(start));
-		}
-		smp_wmb();
+		end = (u8 *) PAGE_ALIGN((unsigned long) h.raw +
+					macoff + snaplen);
+
+		for (start = h.raw; start < end; start += PAGE_SIZE)
+			flush_dcache_page(pgv_to_page(start));
 	}
+	smp_wmb();
 #endif
-	if (po->tp_version <= TPACKET_V2)
+
+	if (po->tp_version <= TPACKET_V2) {
 		__packet_set_status(po, h.raw, status);
-	else
+		sk->sk_data_ready(sk);
+	} else {
 		prb_clear_blk_fill_status(&po->rx_ring);
-
-	sk->sk_data_ready(sk, 0);
+	}
 
 drop_n_restore:
 	if (skb_head != skb->data && skb_shared(skb)) {
@@ -1932,7 +2321,7 @@
 	po->stats.stats1.tp_drops++;
 	spin_unlock(&sk->sk_receive_queue.lock);
 
-	sk->sk_data_ready(sk, 0);
+	sk->sk_data_ready(sk);
 	kfree_skb(copy_skb);
 	goto drop_n_restore;
 }
@@ -1940,14 +2329,13 @@
 static void tpacket_destruct_skb(struct sk_buff *skb)
 {
 	struct packet_sock *po = pkt_sk(skb->sk);
-	void *ph;
 
 	if (likely(po->tx_ring.pg_vec)) {
+		void *ph;
 		__u32 ts;
 
 		ph = skb_shinfo(skb)->destructor_arg;
-		BUG_ON(atomic_read(&po->tx_ring.pending) == 0);
-		atomic_dec(&po->tx_ring.pending);
+		packet_dec_pending(&po->tx_ring);
 
 		ts = __packet_set_timestamp(po, ph, skb);
 		__packet_set_status(po, ph, TP_STATUS_AVAILABLE | ts);
@@ -1956,6 +2344,15 @@
 	sock_wfree(skb);
 }
 
+static void tpacket_set_protocol(const struct net_device *dev,
+				 struct sk_buff *skb)
+{
+	if (dev->type == ARPHRD_ETHER) {
+		skb_reset_mac_header(skb);
+		skb->protocol = eth_hdr(skb)->h_proto;
+	}
+}
+
 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)
@@ -1991,9 +2388,8 @@
 
 	skb_reserve(skb, hlen);
 	skb_reset_network_header(skb);
-	skb_probe_transport_header(skb, 0);
 
-	if (po->tp_tx_has_off) {
+	if (unlikely(po->tp_tx_has_off)) {
 		int off_min, off_max, off;
 		off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll);
 		off_max = po->tx_ring.frame_size - tp_len;
@@ -2030,21 +2426,19 @@
 		if (unlikely(err < 0))
 			return -EINVAL;
 	} else if (dev->hard_header_len) {
-		/* net device doesn't like empty head */
-		if (unlikely(tp_len <= dev->hard_header_len)) {
-			pr_err("packet size is too short (%d < %d)\n",
-			       tp_len, dev->hard_header_len);
-			return -EINVAL;
-		}
+		int hdrlen = min_t(int, dev->hard_header_len, tp_len);
 
 		skb_push(skb, dev->hard_header_len);
-		err = skb_store_bits(skb, 0, data,
-				dev->hard_header_len);
+		err = skb_store_bits(skb, 0, data, hdrlen);
 		if (unlikely(err))
 			return err;
+		if (!dev_validate_header(dev, skb->data, hdrlen))
+			return -EINVAL;
+		if (!skb->protocol)
+			tpacket_set_protocol(dev, skb);
 
-		data += dev->hard_header_len;
-		to_write -= dev->hard_header_len;
+		data += hdrlen;
+		to_write -= hdrlen;
 	}
 
 	offset = offset_in_page(data);
@@ -2076,6 +2470,8 @@
 		len = ((to_write > len_max) ? len_max : to_write);
 	}
 
+	skb_probe_transport_header(skb, 0);
+
 	return tp_len;
 }
 
@@ -2086,7 +2482,8 @@
 	__be16 proto;
 	int err, reserve = 0;
 	void *ph;
-	struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name);
+	bool need_wait = !(msg->msg_flags & MSG_DONTWAIT);
 	int tp_len, size_max;
 	unsigned char *addr;
 	int len_sum = 0;
@@ -2119,20 +2516,20 @@
 	if (unlikely(!(dev->flags & IFF_UP)))
 		goto out_put;
 
-	reserve = dev->hard_header_len;
-
+	if (po->sk.sk_socket->type == SOCK_RAW)
+		reserve = dev->hard_header_len;
 	size_max = po->tx_ring.frame_size
 		- (po->tp_hdrlen - sizeof(struct sockaddr_ll));
 
-	if (size_max > dev->mtu + reserve)
-		size_max = dev->mtu + reserve;
+	if (size_max > dev->mtu + reserve + VLAN_HLEN)
+		size_max = dev->mtu + reserve + VLAN_HLEN;
 
 	do {
 		ph = packet_current_frame(po, &po->tx_ring,
-				TP_STATUS_SEND_REQUEST);
-
+					  TP_STATUS_SEND_REQUEST);
 		if (unlikely(ph == NULL)) {
-			schedule();
+			if (need_wait && need_resched())
+				schedule();
 			continue;
 		}
 
@@ -2141,13 +2538,20 @@
 		tlen = dev->needed_tailroom;
 		skb = sock_alloc_send_skb(&po->sk,
 				hlen + tlen + sizeof(struct sockaddr_ll),
-				0, &err);
+				!need_wait, &err);
 
-		if (unlikely(skb == NULL))
+		if (unlikely(skb == NULL)) {
+			/* we assume the socket was initially writeable ... */
+			if (likely(len_sum > 0))
+				err = len_sum;
 			goto out_status;
-
+		}
 		tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
-				addr, hlen);
+					  addr, hlen);
+		if (likely(tp_len >= 0) &&
+		    tp_len > dev->mtu + reserve &&
+		    !packet_extra_vlan_len_allowed(dev, skb))
+			tp_len = -EMSGSIZE;
 
 		if (unlikely(tp_len < 0)) {
 			if (po->tp_loss) {
@@ -2163,12 +2567,14 @@
 			}
 		}
 
+		packet_pick_tx_queue(dev, skb);
+
 		skb->destructor = tpacket_destruct_skb;
 		__packet_set_status(po, ph, TP_STATUS_SENDING);
-		atomic_inc(&po->tx_ring.pending);
+		packet_inc_pending(&po->tx_ring);
 
 		status = TP_STATUS_SEND_REQUEST;
-		err = dev_queue_xmit(skb);
+		err = po->xmit(skb);
 		if (unlikely(err > 0)) {
 			err = net_xmit_errno(err);
 			if (err && __packet_get_status(po, ph) ==
@@ -2186,9 +2592,13 @@
 		packet_increment_head(&po->tx_ring);
 		len_sum += tp_len;
 	} while (likely((ph != NULL) ||
-			((!(msg->msg_flags & MSG_DONTWAIT)) &&
-			 (atomic_read(&po->tx_ring.pending))))
-		);
+		/* Note: packet_read_pending() might be slow if we have
+		 * to call it as it's per_cpu variable, but in fast-path
+		 * we already short-circuit the loop with the first
+		 * condition, and luckily don't have to go that path
+		 * anyway.
+		 */
+		 (need_wait && packet_read_pending(&po->tx_ring))));
 
 	err = len_sum;
 	goto out_put;
@@ -2215,7 +2625,7 @@
 		linear = len;
 
 	skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock,
-				   err);
+				   err, 0);
 	if (!skb)
 		return NULL;
 
@@ -2227,16 +2637,16 @@
 	return skb;
 }
 
-static int packet_snd(struct socket *sock,
-			  struct msghdr *msg, size_t len)
+static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 {
 	struct sock *sk = sock->sk;
-	struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name);
 	struct sk_buff *skb;
 	struct net_device *dev;
 	__be16 proto;
 	unsigned char *addr;
 	int err, reserve = 0;
+	struct sockcm_cookie sockc;
 	struct virtio_net_hdr vnet_hdr = { 0 };
 	int offset = 0;
 	int vnet_hdr_len;
@@ -2244,6 +2654,7 @@
 	unsigned short gso_type = 0;
 	int hlen, tlen, linear;
 	int extra_len = 0;
+	ssize_t n;
 
 	/*
 	 *	Get and verify the address.
@@ -2271,6 +2682,13 @@
 	if (unlikely(!(dev->flags & IFF_UP)))
 		goto out_unlock;
 
+	sockc.mark = sk->sk_mark;
+	if (msg->msg_controllen) {
+		err = sock_cmsg_send(sk, msg, &sockc);
+		if (unlikely(err))
+			goto out_unlock;
+	}
+
 	if (sock->type == SOCK_RAW)
 		reserve = dev->hard_header_len;
 	if (po->has_vnet_hdr) {
@@ -2282,19 +2700,21 @@
 
 		len -= vnet_hdr_len;
 
-		err = memcpy_fromiovec((void *)&vnet_hdr, msg->msg_iov,
-				       vnet_hdr_len);
-		if (err < 0)
+		err = -EFAULT;
+		n = copy_from_iter(&vnet_hdr, vnet_hdr_len, &msg->msg_iter);
+		if (n != vnet_hdr_len)
 			goto out_unlock;
 
 		if ((vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
-		    (vnet_hdr.csum_start + vnet_hdr.csum_offset + 2 >
-		      vnet_hdr.hdr_len))
-			vnet_hdr.hdr_len = vnet_hdr.csum_start +
-						 vnet_hdr.csum_offset + 2;
+		    (__virtio16_to_cpu(vio_le(), vnet_hdr.csum_start) +
+		     __virtio16_to_cpu(vio_le(), vnet_hdr.csum_offset) + 2 >
+		      __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len)))
+			vnet_hdr.hdr_len = __cpu_to_virtio16(vio_le(),
+				 __virtio16_to_cpu(vio_le(), vnet_hdr.csum_start) +
+				__virtio16_to_cpu(vio_le(), vnet_hdr.csum_offset) + 2);
 
 		err = -EINVAL;
-		if (vnet_hdr.hdr_len > len)
+		if (__virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len) > len)
 			goto out_unlock;
 
 		if (vnet_hdr.gso_type != VIRTIO_NET_HDR_GSO_NONE) {
@@ -2336,7 +2756,7 @@
 	err = -ENOBUFS;
 	hlen = LL_RESERVED_SPACE(dev);
 	tlen = dev->needed_tailroom;
-	linear = vnet_hdr.hdr_len;
+	linear = __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len);
 	linear = max(linear, min_t(int, len, dev->hard_header_len));
 	skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, linear,
 			       msg->msg_flags & MSG_DONTWAIT, &err);
@@ -2346,46 +2766,50 @@
 	skb_set_network_header(skb, reserve);
 
 	err = -EINVAL;
-	if (sock->type == SOCK_DGRAM &&
-	    (offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len)) < 0)
-		goto out_free;
+	if (sock->type == SOCK_DGRAM) {
+		offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len);
+		if (unlikely(offset < 0))
+			goto out_free;
+	}
 
 	/* Returns -EFAULT on error */
-	err = skb_copy_datagram_from_iovec(skb, offset, msg->msg_iov, 0, len);
+	err = skb_copy_datagram_from_iter(skb, offset, &msg->msg_iter, len);
 	if (err)
 		goto out_free;
 
+	if (sock->type == SOCK_RAW &&
+	    !dev_validate_header(dev, skb->data, len)) {
+		err = -EINVAL;
+		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,
-		 * double-check this now that we have the actual
-		 * packet in hand.
-		 */
-		struct ethhdr *ehdr;
-		skb_reset_mac_header(skb);
-		ehdr = eth_hdr(skb);
-		if (ehdr->h_proto != htons(ETH_P_8021Q)) {
-			err = -EMSGSIZE;
-			goto out_free;
-		}
+	if (!gso_type && (len > dev->mtu + reserve + extra_len) &&
+	    !packet_extra_vlan_len_allowed(dev, skb)) {
+		err = -EMSGSIZE;
+		goto out_free;
 	}
 
 	skb->protocol = proto;
 	skb->dev = dev;
 	skb->priority = sk->sk_priority;
-	skb->mark = sk->sk_mark;
+	skb->mark = sockc.mark;
+
+	packet_pick_tx_queue(dev, skb);
 
 	if (po->has_vnet_hdr) {
 		if (vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
-			if (!skb_partial_csum_set(skb, vnet_hdr.csum_start,
-						  vnet_hdr.csum_offset)) {
+			u16 s = __virtio16_to_cpu(vio_le(), vnet_hdr.csum_start);
+			u16 o = __virtio16_to_cpu(vio_le(), vnet_hdr.csum_offset);
+			if (!skb_partial_csum_set(skb, s, o)) {
 				err = -EINVAL;
 				goto out_free;
 			}
 		}
 
-		skb_shinfo(skb)->gso_size = vnet_hdr.gso_size;
+		skb_shinfo(skb)->gso_size =
+			__virtio16_to_cpu(vio_le(), vnet_hdr.gso_size);
 		skb_shinfo(skb)->gso_type = gso_type;
 
 		/* Header must be checked, and gso_segs computed. */
@@ -2400,11 +2824,7 @@
 	if (unlikely(extra_len == 4))
 		skb->no_fcs = 1;
 
-	/*
-	 *	Now send it
-	 */
-
-	err = dev_queue_xmit(skb);
+	err = po->xmit(skb);
 	if (err > 0 && (err = net_xmit_errno(err)) != 0)
 		goto out_unlock;
 
@@ -2421,11 +2841,11 @@
 	return err;
 }
 
-static int packet_sendmsg(struct kiocb *iocb, struct socket *sock,
-		struct msghdr *msg, size_t len)
+static int packet_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 {
 	struct sock *sk = sock->sk;
 	struct packet_sock *po = pkt_sk(sk);
+
 	if (po->tx_ring.pg_vec)
 		return tpacket_snd(po, msg);
 	else
@@ -2486,6 +2906,7 @@
 	synchronize_net();
 
 	if (f) {
+		fanout_release_data(f);
 		kfree(f);
 	}
 	/*
@@ -2497,6 +2918,7 @@
 	/* Purge queues */
 
 	skb_queue_purge(&sk->sk_receive_queue);
+	packet_free_pending(po);
 	sk_refcnt_debug_release(sk);
 
 	sock_put(sk);
@@ -2507,36 +2929,78 @@
  *	Attach a packet hook.
  */
 
-static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 protocol)
+static int packet_do_bind(struct sock *sk, const char *name, int ifindex,
+			  __be16 proto)
 {
 	struct packet_sock *po = pkt_sk(sk);
+	struct net_device *dev_curr;
+	__be16 proto_curr;
+	bool need_rehook;
+	struct net_device *dev = NULL;
+	int ret = 0;
+	bool unlisted = false;
 
-	if (po->fanout) {
-		if (dev)
-			dev_put(dev);
-
+	if (po->fanout)
 		return -EINVAL;
-	}
 
 	lock_sock(sk);
-
 	spin_lock(&po->bind_lock);
-	unregister_prot_hook(sk, true);
+	rcu_read_lock();
 
-	po->num = protocol;
-	po->prot_hook.type = protocol;
-	if (po->prot_hook.dev)
-		dev_put(po->prot_hook.dev);
+	if (name) {
+		dev = dev_get_by_name_rcu(sock_net(sk), name);
+		if (!dev) {
+			ret = -ENODEV;
+			goto out_unlock;
+		}
+	} else if (ifindex) {
+		dev = dev_get_by_index_rcu(sock_net(sk), ifindex);
+		if (!dev) {
+			ret = -ENODEV;
+			goto out_unlock;
+		}
+	}
+
+	if (dev)
+		dev_hold(dev);
+
+	proto_curr = po->prot_hook.type;
+	dev_curr = po->prot_hook.dev;
 
-	po->prot_hook.dev = dev;
-	po->ifindex = dev ? dev->ifindex : 0;
+	need_rehook = proto_curr != proto || dev_curr != dev;
 
-	packet_cached_dev_assign(po, dev);
+	if (need_rehook) {
+		if (po->running) {
+			rcu_read_unlock();
+			__unregister_prot_hook(sk, true);
+			rcu_read_lock();
+			dev_curr = po->prot_hook.dev;
+			if (dev)
+				unlisted = !dev_get_by_index_rcu(sock_net(sk),
+								 dev->ifindex);
+		}
+
+		po->num = proto;
+		po->prot_hook.type = proto;
+
+		if (unlikely(unlisted)) {
+			dev_put(dev);
+			po->prot_hook.dev = NULL;
+			po->ifindex = -1;
+			packet_cached_dev_reset(po);
+		} else {
+			po->prot_hook.dev = dev;
+			po->ifindex = dev ? dev->ifindex : 0;
+			packet_cached_dev_assign(po, dev);
+		}
+	}
+	if (dev_curr)
+		dev_put(dev_curr);
 
-	if (protocol == 0)
+	if (proto == 0 || !need_rehook)
 		goto out_unlock;
 
-	if (!dev || (dev->flags & IFF_UP)) {
+	if (!unlisted && (!dev || (dev->flags & IFF_UP))) {
 		register_prot_hook(sk);
 	} else {
 		sk->sk_err = ENETDOWN;
@@ -2545,9 +3009,10 @@
 	}
 
 out_unlock:
+	rcu_read_unlock();
 	spin_unlock(&po->bind_lock);
 	release_sock(sk);
-	return 0;
+	return ret;
 }
 
 /*
@@ -2559,8 +3024,6 @@
 {
 	struct sock *sk = sock->sk;
 	char name[sizeof(uaddr->sa_data) + 1];
-	struct net_device *dev;
-	int err = -ENODEV;
 
 	/*
 	 *	Check legality
@@ -2574,19 +3037,13 @@
 	memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data));
 	name[sizeof(uaddr->sa_data)] = 0;
 
-	dev = dev_get_by_name(sock_net(sk), name);
-	if (dev)
-		err = packet_do_bind(sk, dev, pkt_sk(sk)->num);
-	return err;
+	return packet_do_bind(sk, name, 0, pkt_sk(sk)->num);
 }
 
 static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 {
 	struct sockaddr_ll *sll = (struct sockaddr_ll *)uaddr;
 	struct sock *sk = sock->sk;
-	struct net_device *dev = NULL;
-	int err;
-
 
 	/*
 	 *	Check legality
@@ -2597,16 +3054,8 @@
 	if (sll->sll_family != AF_PACKET)
 		return -EINVAL;
 
-	if (sll->sll_ifindex) {
-		err = -ENODEV;
-		dev = dev_get_by_index(sock_net(sk), sll->sll_ifindex);
-		if (dev == NULL)
-			goto out;
-	}
-	err = packet_do_bind(sk, dev, sll->sll_protocol ? : pkt_sk(sk)->num);
-
-out:
-	return err;
+	return packet_do_bind(sk, NULL, sll->sll_ifindex,
+			      sll->sll_protocol ? : pkt_sk(sk)->num);
 }
 
 static struct proto packet_proto = {
@@ -2636,7 +3085,7 @@
 	sock->state = SS_UNCONNECTED;
 
 	err = -ENOBUFS;
-	sk = sk_alloc(net, PF_PACKET, GFP_KERNEL, &packet_proto);
+	sk = sk_alloc(net, PF_PACKET, GFP_KERNEL, &packet_proto, kern);
 	if (sk == NULL)
 		goto out;
 
@@ -2649,6 +3098,11 @@
 	po = pkt_sk(sk);
 	sk->sk_family = PF_PACKET;
 	po->num = proto;
+	po->xmit = dev_queue_xmit;
+
+	err = packet_alloc_pending(po);
+	if (err)
+		goto out2;
 
 	packet_cached_dev_reset(po);
 
@@ -2661,7 +3115,9 @@
 
 	spin_lock_init(&po->bind_lock);
 	mutex_init(&po->pg_vec_lock);
+	po->rollover = NULL;
 	po->prot_hook.func = packet_rcv;
+	po->pkt_type = PACKET_MASK_ANY & ~(1 << PACKET_LOOPBACK);
 
 	if (sock->type == SOCK_PACKET)
 		po->prot_hook.func = packet_rcv_spkt;
@@ -2682,51 +3138,8 @@
 	preempt_enable();
 
 	return 0;
-out:
-	return err;
-}
-
-static int packet_recv_error(struct sock *sk, struct msghdr *msg, int len)
-{
-	struct sock_exterr_skb *serr;
-	struct sk_buff *skb, *skb2;
-	int copied, err;
-
-	err = -EAGAIN;
-	skb = skb_dequeue(&sk->sk_error_queue);
-	if (skb == NULL)
-		goto out;
-
-	copied = skb->len;
-	if (copied > len) {
-		msg->msg_flags |= MSG_TRUNC;
-		copied = len;
-	}
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
-	if (err)
-		goto out_free_skb;
-
-	sock_recv_timestamp(msg, sk, skb);
-
-	serr = SKB_EXT_ERR(skb);
-	put_cmsg(msg, SOL_PACKET, PACKET_TX_TIMESTAMP,
-		 sizeof(serr->ee), &serr->ee);
-
-	msg->msg_flags |= MSG_ERRQUEUE;
-	err = copied;
-
-	/* Reset and regenerate socket error */
-	spin_lock_bh(&sk->sk_error_queue.lock);
-	sk->sk_err = 0;
-	if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) {
-		sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno;
-		spin_unlock_bh(&sk->sk_error_queue.lock);
-		sk->sk_error_report(sk);
-	} else
-		spin_unlock_bh(&sk->sk_error_queue.lock);
-
-out_free_skb:
-	kfree_skb(skb);
+out2:
+	sk_free(sk);
 out:
 	return err;
 }
@@ -2736,13 +3149,14 @@
  *	If necessary we block.
  */
 
-static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
-			  struct msghdr *msg, size_t len, int flags)
+static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+			  int flags)
 {
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb;
 	int copied, err;
 	int vnet_hdr_len = 0;
+	unsigned int origlen = 0;
 
 	err = -EINVAL;
 	if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT|MSG_ERRQUEUE))
@@ -2755,7 +3169,8 @@
 #endif
 
 	if (flags & MSG_ERRQUEUE) {
-		err = packet_recv_error(sk, msg, len);
+		err = sock_recv_errqueue(sk, msg, len,
+					 SOL_PACKET, PACKET_TX_TIMESTAMP);
 		goto out;
 	}
 
@@ -2779,6 +3194,9 @@
 	if (skb == NULL)
 		goto out;
 
+	if (pkt_sk(sk)->pressure)
+		packet_rcv_has_room(pkt_sk(sk), NULL);
+
 	if (pkt_sk(sk)->has_vnet_hdr) {
 		struct virtio_net_hdr vnet_hdr = { 0 };
 
@@ -2793,8 +3211,10 @@
 			struct skb_shared_info *sinfo = skb_shinfo(skb);
 
 			/* This is a hint as to how much should be linear. */
-			vnet_hdr.hdr_len = skb_headlen(skb);
-			vnet_hdr.gso_size = sinfo->gso_size;
+			vnet_hdr.hdr_len =
+				__cpu_to_virtio16(vio_le(), skb_headlen(skb));
+			vnet_hdr.gso_size =
+				__cpu_to_virtio16(vio_le(), sinfo->gso_size);
 			if (sinfo->gso_type & SKB_GSO_TCPV4)
 				vnet_hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
 			else if (sinfo->gso_type & SKB_GSO_TCPV6)
@@ -2812,14 +3232,15 @@
 
 		if (skb->ip_summed == CHECKSUM_PARTIAL) {
 			vnet_hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
-			vnet_hdr.csum_start = skb_checksum_start_offset(skb);
-			vnet_hdr.csum_offset = skb->csum_offset;
+			vnet_hdr.csum_start = __cpu_to_virtio16(vio_le(),
+					  skb_checksum_start_offset(skb));
+			vnet_hdr.csum_offset = __cpu_to_virtio16(vio_le(),
+							 skb->csum_offset);
 		} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
 			vnet_hdr.flags = VIRTIO_NET_HDR_F_DATA_VALID;
 		} /* else everything is zero */
 
-		err = memcpy_toiovec(msg->msg_iov, (void *)&vnet_hdr,
-				     vnet_hdr_len);
+		err = memcpy_to_msg(msg, (void *)&vnet_hdr, vnet_hdr_len);
 		if (err < 0)
 			goto out_free;
 	}
@@ -2834,10 +3255,19 @@
 		msg->msg_flags |= MSG_TRUNC;
 	}
 
-	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err)
 		goto out_free;
 
+	if (sock->type != SOCK_PACKET) {
+		struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll;
+
+		/* Original length was stored in sockaddr_ll fields */
+		origlen = PACKET_SKB_CB(skb)->sa.origlen;
+		sll->sll_family = AF_PACKET;
+		sll->sll_protocol = skb->protocol;
+	}
+
 	sock_recv_ts_and_drops(msg, sk, skb);
 
 	if (msg->msg_name) {
@@ -2845,9 +3275,11 @@
 		 * in, we fill it in now.
 		 */
 		if (sock->type == SOCK_PACKET) {
+			__sockaddr_check_size(sizeof(struct sockaddr_pkt));
 			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);
 		}
@@ -2861,17 +3293,23 @@
 		aux.tp_status = TP_STATUS_USER;
 		if (skb->ip_summed == CHECKSUM_PARTIAL)
 			aux.tp_status |= TP_STATUS_CSUMNOTREADY;
-		aux.tp_len = PACKET_SKB_CB(skb)->origlen;
+		else if (skb->pkt_type != PACKET_OUTGOING &&
+			 (skb->ip_summed == CHECKSUM_COMPLETE ||
+			  skb_csum_unnecessary(skb)))
+			aux.tp_status |= TP_STATUS_CSUM_VALID;
+
+		aux.tp_len = origlen;
 		aux.tp_snaplen = skb->len;
 		aux.tp_mac = 0;
 		aux.tp_net = skb_network_offset(skb);
-		if (vlan_tx_tag_present(skb)) {
-			aux.tp_vlan_tci = vlan_tx_tag_get(skb);
-			aux.tp_status |= TP_STATUS_VLAN_VALID;
+		if (skb_vlan_tag_present(skb)) {
+			aux.tp_vlan_tci = skb_vlan_tag_get(skb);
+			aux.tp_vlan_tpid = ntohs(skb->vlan_proto);
+			aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
 		} else {
 			aux.tp_vlan_tci = 0;
+			aux.tp_vlan_tpid = 0;
 		}
-		aux.tp_padding = 0;
 		put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux);
 	}
 
@@ -2953,10 +3391,8 @@
 		break;
 	case PACKET_MR_PROMISC:
 		return dev_set_promiscuity(dev, what);
-		break;
 	case PACKET_MR_ALLMULTI:
 		return dev_set_allmulti(dev, what);
-		break;
 	case PACKET_MR_UNICAST:
 		if (i->alen != dev->addr_len)
 			return -EINVAL;
@@ -2971,11 +3407,18 @@
 	return 0;
 }
 
-static void packet_dev_mclist(struct net_device *dev, struct packet_mclist *i, int what)
+static void packet_dev_mclist_delete(struct net_device *dev,
+				     struct packet_mclist **mlp)
 {
-	for ( ; i; i = i->next) {
-		if (i->ifindex == dev->ifindex)
-			packet_dev_mc(dev, i, what);
+	struct packet_mclist *ml;
+
+	while ((ml = *mlp) != NULL) {
+		if (ml->ifindex == dev->ifindex) {
+			packet_dev_mc(dev, ml, -1);
+			*mlp = ml->next;
+			kfree(ml);
+		} else
+			mlp = &ml->next;
 	}
 }
 
@@ -3053,12 +3496,11 @@
 					packet_dev_mc(dev, ml, -1);
 				kfree(ml);
 			}
-			rtnl_unlock();
-			return 0;
+			break;
 		}
 	}
 	rtnl_unlock();
-	return -EADDRNOTAVAIL;
+	return 0;
 }
 
 static void packet_flush_mclist(struct sock *sk)
@@ -3187,8 +3629,6 @@
 			return -EBUSY;
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
-		if (val > INT_MAX)
-			return -EINVAL;
 		po->tp_reserve = val;
 		return 0;
 	}
@@ -3268,6 +3708,13 @@
 
 		return fanout_add(sk, val & 0xffff, val >> 16);
 	}
+	case PACKET_FANOUT_DATA:
+	{
+		if (!po->fanout)
+			return -EINVAL;
+
+		return fanout_set_data(po, optval, optlen);
+	}
 	case PACKET_TX_HAS_OFF:
 	{
 		unsigned int val;
@@ -3281,6 +3728,28 @@
 		po->tp_tx_has_off = !!val;
 		return 0;
 	}
+	case PACKET_QDISC_BYPASS:
+	{
+		int val;
+
+		if (optlen != sizeof(val))
+			return -EINVAL;
+		if (copy_from_user(&val, optval, sizeof(val)))
+			return -EFAULT;
+
+		po->xmit = val ? packet_direct_xmit : dev_queue_xmit;
+		return 0;
+	}
+        case PACKET_RECV_TYPE:
+        {
+                unsigned int val;
+                if (optlen != sizeof(val))
+                        return -EINVAL;
+                if (copy_from_user(&val, optval, sizeof(val)))
+                        return -EFAULT;
+                po->pkt_type = val & ~BIT(PACKET_LOOPBACK);
+                return 0;
+        }
 	default:
 		return -ENOPROTOOPT;
 	}
@@ -3295,6 +3764,7 @@
 	struct packet_sock *po = pkt_sk(sk);
 	void *data = &val;
 	union tpacket_stats_u st;
+	struct tpacket_rollover_stats rstats;
 
 	if (level != SOL_PACKET)
 		return -ENOPROTOOPT;
@@ -3332,6 +3802,13 @@
 	case PACKET_VNET_HDR:
 		val = po->has_vnet_hdr;
 		break;
+	case PACKET_RECV_TYPE:
+		if (len > sizeof(unsigned int))
+			len = sizeof(unsigned int);
+		val = po->pkt_type;
+
+		data = &val;
+		break;
 	case PACKET_VERSION:
 		val = po->tp_version;
 		break;
@@ -3370,9 +3847,21 @@
 			((u32)po->fanout->flags << 24)) :
 		       0);
 		break;
+	case PACKET_ROLLOVER_STATS:
+		if (!po->rollover)
+			return -EINVAL;
+		rstats.tp_all = atomic_long_read(&po->rollover->num);
+		rstats.tp_huge = atomic_long_read(&po->rollover->num_huge);
+		rstats.tp_failed = atomic_long_read(&po->rollover->num_failed);
+		data = &rstats;
+		lv = sizeof(rstats);
+		break;
 	case PACKET_TX_HAS_OFF:
 		val = po->tp_tx_has_off;
 		break;
+	case PACKET_QDISC_BYPASS:
+		val = packet_use_direct_xmit(po);
+		break;
 	default:
 		return -ENOPROTOOPT;
 	}
@@ -3387,10 +3876,11 @@
 }
 
 
-static int packet_notifier(struct notifier_block *this, unsigned long msg, void *data)
+static int packet_notifier(struct notifier_block *this,
+			   unsigned long msg, void *ptr)
 {
 	struct sock *sk;
-	struct net_device *dev = data;
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct net *net = dev_net(dev);
 
 	rcu_read_lock();
@@ -3400,7 +3890,7 @@
 		switch (msg) {
 		case NETDEV_UNREGISTER:
 			if (po->mclist)
-				packet_dev_mclist(dev, po->mclist, -1);
+				packet_dev_mclist_delete(dev, &po->mclist);
 			/* fallthrough */
 
 		case NETDEV_DOWN:
@@ -3503,6 +3993,8 @@
 			TP_STATUS_KERNEL))
 			mask |= POLLIN | POLLRDNORM;
 	}
+	if (po->pressure && __packet_rcv_has_room(po, NULL) == ROOM_NORMAL)
+		po->pressure = 0;
 	spin_unlock_bh(&sk->sk_receive_queue.lock);
 	spin_lock_bh(&sk->sk_write_queue.lock);
 	if (po->tx_ring.pg_vec) {
@@ -3563,34 +4055,26 @@
 
 static char *alloc_one_pg_vec_page(unsigned long order)
 {
-	char *buffer = NULL;
+	char *buffer;
 	gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP |
 			  __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY;
 
 	buffer = (char *) __get_free_pages(gfp_flags, order);
-
 	if (buffer)
 		return buffer;
 
-	/*
-	 * __get_free_pages failed, fall back to vmalloc
-	 */
+	/* __get_free_pages failed, fall back to vmalloc */
 	buffer = vzalloc((1 << order) * PAGE_SIZE);
-
 	if (buffer)
 		return buffer;
 
-	/*
-	 * vmalloc failed, lets dig into swap here
-	 */
+	/* vmalloc failed, lets dig into swap here */
 	gfp_flags &= ~__GFP_NORETRY;
-	buffer = (char *)__get_free_pages(gfp_flags, order);
+	buffer = (char *) __get_free_pages(gfp_flags, order);
 	if (buffer)
 		return buffer;
 
-	/*
-	 * complete and utter failure
-	 */
+	/* complete and utter failure */
 	return NULL;
 }
 
@@ -3646,7 +4130,7 @@
 	if (!closing) {
 		if (atomic_read(&po->mapped))
 			goto out;
-		if (atomic_read(&rb->pending))
+		if (packet_read_pending(rb))
 			goto out;
 	}
 
@@ -3671,11 +4155,11 @@
 		err = -EINVAL;
 		if (unlikely((int)req->tp_block_size <= 0))
 			goto out;
-		if (unlikely(req->tp_block_size & (PAGE_SIZE - 1)))
+		if (unlikely(!PAGE_ALIGNED(req->tp_block_size)))
 			goto out;
 		if (po->tp_version >= TPACKET_V3 &&
-		    req->tp_block_size <=
-			  BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv))
+		    (int)(req->tp_block_size -
+			  BLK_PLUS_PRIV(req_u->req3.tp_sizeof_priv)) <= 0)
 			goto out;
 		if (unlikely(req->tp_frame_size < po->tp_hdrlen +
 					po->tp_reserve))
@@ -3683,10 +4167,8 @@
 		if (unlikely(req->tp_frame_size & (TPACKET_ALIGNMENT - 1)))
 			goto out;
 
-		rb->frames_per_block = req->tp_block_size/req->tp_frame_size;
-		if (unlikely(rb->frames_per_block <= 0))
-			goto out;
-		if (unlikely(req->tp_block_size > UINT_MAX / req->tp_block_nr))
+		rb->frames_per_block = req->tp_block_size / req->tp_frame_size;
+		if (unlikely(rb->frames_per_block == 0))
 			goto out;
 		if (unlikely((rb->frames_per_block * req->tp_block_nr) !=
 					req->tp_frame_nr))
@@ -3703,7 +4185,7 @@
 		 * it above but just being paranoid
 		 */
 			if (!tx_ring)
-				init_prb_bdqc(po, rb, pg_vec, req_u, tx_ring);
+				init_prb_bdqc(po, rb, pg_vec, req_u);
 			break;
 		default:
 			break;
@@ -3762,7 +4244,7 @@
 	if (closing && (po->tp_version > TPACKET_V2)) {
 		/* Because we don't support block-based V3 on tx-ring */
 		if (!tx_ring)
-			prb_shutdown_retire_blk_timer(po, tx_ring, rb_queue);
+			prb_shutdown_retire_blk_timer(po, rb_queue);
 	}
 
 	if (pg_vec)