These changes are the raw update to linux-4.4.6-rt14. Kernel sources

are taken from kernel.org, and rt patch from the rt wiki download page.

During the rebasing, the following patch collided:

Force tick interrupt and get rid of softirq magic(I70131fb85).

Collisions have been removed because its logic was found on the
source already.

Change-Id: I7f57a4081d9deaa0d9ccfc41a6c8daccdee3b769
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>

2 files changed, 431 insertions, 149 deletions

diff --git a/kernel/net/packet/af_packet.c b/kernel/net/packet/af_packet.c
index f9f259247..2c23bae0e 100644
--- a/kernel/net/packet/af_packet.c
+++ b/kernel/net/packet/af_packet.c
@@ -93,6 +93,7 @@
 #ifdef CONFIG_INET
 #include <net/inet_common.h>
 #endif
+#include <linux/bpf.h>
 
 #include "internal.h"
 
@@ -230,6 +231,8 @@ struct packet_skb_cb {
 	} 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))
@@ -519,13 +522,11 @@ static void prb_del_retire_blk_timer(struct tpacket_kbdq_core *pkc)
 }
 
 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 ? GET_PBDQC_FROM_RB(&po->tx_ring) :
-			GET_PBDQC_FROM_RB(&po->rx_ring);
+	pkc = GET_PBDQC_FROM_RB(&po->rx_ring);
 
 	spin_lock_bh(&rb_queue->lock);
 	pkc->delete_blk_timer = 1;
@@ -544,15 +545,11 @@ static void prb_init_blk_timer(struct packet_sock *po,
 	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 ? GET_PBDQC_FROM_RB(&po->tx_ring) :
-			GET_PBDQC_FROM_RB(&po->rx_ring);
+	pkc = GET_PBDQC_FROM_RB(&po->rx_ring);
 	prb_init_blk_timer(po, pkc, prb_retire_rx_blk_timer_expired);
 }
 
@@ -608,7 +605,7 @@ static void prb_init_ft_ops(struct tpacket_kbdq_core *p1,
 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 = GET_PBDQC_FROM_RB(rb);
 	struct tpacket_block_desc *pbd;
@@ -635,7 +632,7 @@ static void init_prb_bdqc(struct packet_sock *po,
 
 	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);
 }
 
@@ -1235,27 +1232,81 @@ static void packet_free_pending(struct packet_sock *po)
 	free_percpu(po->tx_ring.pending_refcnt);
 }
 
-static bool packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb)
+#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) {
+		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;
+	}
 
-	if (po->prot_hook.func != tpacket_rcv)
-		return (atomic_read(&sk->sk_rmem_alloc) + skb->truesize)
-			<= sk->sk_rcvbuf;
+	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;
+	}
 
-	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 ret;
+}
 
-	return has_room;
+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)
@@ -1273,6 +1324,20 @@ static void packet_sock_destruct(struct sock *sk)
 	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)
@@ -1305,22 +1370,40 @@ static unsigned int fanout_demux_rnd(struct packet_fanout *f,
 
 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;
 
-	i = j = min_t(int, f->next[idx], num - 1);
+	po = pkt_sk(f->arr[idx]);
+
+	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;
 }
 
@@ -1331,6 +1414,22 @@ static unsigned int fanout_demux_qm(struct packet_fanout *f,
 	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);
@@ -1341,17 +1440,17 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 {
 	struct packet_fanout *f = pt->af_packet_priv;
 	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(skb, IP_DEFRAG_AF_PACKET);
+		skb = ip_check_defrag(net, skb, IP_DEFRAG_AF_PACKET);
 		if (!skb)
 			return 0;
 	}
@@ -1373,17 +1472,18 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 		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);
 }
 
@@ -1420,10 +1520,107 @@ static void __fanout_unlink(struct sock *sk, struct packet_sock *po)
 
 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 false;
+	return ptype->af_packet_priv == pkt_sk(sk)->fanout;
+}
+
+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)
@@ -1443,6 +1640,8 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 	case PACKET_FANOUT_CPU:
 	case PACKET_FANOUT_RND:
 	case PACKET_FANOUT_QM:
+	case PACKET_FANOUT_CBPF:
+	case PACKET_FANOUT_EBPF:
 		break;
 	default:
 		return -EINVAL;
@@ -1454,6 +1653,16 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 	if (po->fanout)
 		return -EALREADY;
 
+	if (type == PACKET_FANOUT_ROLLOVER ||
+	    (type_flags & PACKET_FANOUT_FLAG_ROLLOVER)) {
+		po->rollover = kzalloc(sizeof(*po->rollover), GFP_KERNEL);
+		if (!po->rollover)
+			return -ENOMEM;
+		atomic_long_set(&po->rollover->num, 0);
+		atomic_long_set(&po->rollover->num_huge, 0);
+		atomic_long_set(&po->rollover->num_failed, 0);
+	}
+
 	mutex_lock(&fanout_mutex);
 	match = NULL;
 	list_for_each_entry(f, &fanout_list, list) {
@@ -1475,10 +1684,10 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		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;
@@ -1502,6 +1711,10 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 	}
 out:
 	mutex_unlock(&fanout_mutex);
+	if (err) {
+		kfree(po->rollover);
+		po->rollover = NULL;
+	}
 	return err;
 }
 
@@ -1520,9 +1733,27 @@ static void fanout_release(struct sock *sk)
 	if (atomic_dec_and_test(&f->sk_ref)) {
 		list_del(&f->list);
 		dev_remove_pack(&f->prot_hook);
+		fanout_release_data(f);
 		kfree(f);
 	}
 	mutex_unlock(&fanout_mutex);
+
+	if (po->rollover)
+		kfree_rcu(po->rollover, rcu);
+}
+
+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;
@@ -1686,18 +1917,10 @@ retry:
 		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 (len > (dev->mtu + dev->hard_header_len + extra_len) &&
+	    !packet_extra_vlan_len_allowed(dev, skb)) {
+		err = -EMSGSIZE;
+		goto out_unlock;
 	}
 
 	skb->protocol = proto;
@@ -1723,16 +1946,16 @@ out_free:
 	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;
@@ -2107,8 +2330,8 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
 static bool ll_header_truncated(const struct net_device *dev, int len)
 {
 	/* net device doesn't like empty head */
-	if (unlikely(len <= dev->hard_header_len)) {
-		net_warn_ratelimited("%s: packet size is too short (%d <= %d)\n",
+	if (unlikely(len < dev->hard_header_len)) {
+		net_warn_ratelimited("%s: packet size is too short (%d < %d)\n",
 				     current->comm, len, dev->hard_header_len);
 		return true;
 	}
@@ -2116,6 +2339,15 @@ static bool ll_header_truncated(const struct net_device *dev, int len)
 	return false;
 }
 
+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)
@@ -2152,8 +2384,6 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 	skb_reserve(skb, hlen);
 	skb_reset_network_header(skb);
 
-	if (!packet_use_direct_xmit(po))
-		skb_probe_transport_header(skb, 0);
 	if (unlikely(po->tp_tx_has_off)) {
 		int off_min, off_max, off;
 		off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll);
@@ -2199,6 +2429,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 				dev->hard_header_len);
 		if (unlikely(err))
 			return err;
+		if (!skb->protocol)
+			tpacket_set_protocol(dev, skb);
 
 		data += dev->hard_header_len;
 		to_write -= dev->hard_header_len;
@@ -2233,6 +2465,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		len = ((to_write > len_max) ? len_max : to_write);
 	}
 
+	skb_probe_transport_header(skb, 0);
+
 	return tp_len;
 }
 
@@ -2277,12 +2511,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	if (unlikely(!(dev->flags & IFF_UP)))
 		goto out_put;
 
-	reserve = dev->hard_header_len + VLAN_HLEN;
+	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,
@@ -2309,18 +2544,10 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
 					  addr, hlen);
 		if (likely(tp_len >= 0) &&
-		    tp_len > dev->mtu + dev->hard_header_len) {
-			struct ethhdr *ehdr;
-			/* Earlier code assumed this would be a VLAN pkt,
-			 * double-check this now that we have the actual
-			 * packet in hand.
-			 */
+		    tp_len > dev->mtu + reserve &&
+		    !packet_extra_vlan_len_allowed(dev, skb))
+			tp_len = -EMSGSIZE;
 
-			skb_reset_mac_header(skb);
-			ehdr = eth_hdr(skb);
-			if (ehdr->h_proto != htons(ETH_P_8021Q))
-				tp_len = -EMSGSIZE;
-		}
 		if (unlikely(tp_len < 0)) {
 			if (po->tp_loss) {
 				__packet_set_status(po, ph,
@@ -2414,6 +2641,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	__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;
@@ -2449,6 +2677,13 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	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) {
@@ -2466,15 +2701,15 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 			goto out_unlock;
 
 		if ((vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
-		    (__virtio16_to_cpu(false, vnet_hdr.csum_start) +
-		     __virtio16_to_cpu(false, vnet_hdr.csum_offset) + 2 >
-		      __virtio16_to_cpu(false, vnet_hdr.hdr_len)))
-			vnet_hdr.hdr_len = __cpu_to_virtio16(false,
-				 __virtio16_to_cpu(false, vnet_hdr.csum_start) +
-				__virtio16_to_cpu(false, 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 (__virtio16_to_cpu(false, 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) {
@@ -2517,7 +2752,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	hlen = LL_RESERVED_SPACE(dev);
 	tlen = dev->needed_tailroom;
 	skb = packet_alloc_skb(sk, hlen + tlen, hlen, len,
-			       __virtio16_to_cpu(false, vnet_hdr.hdr_len),
+			       __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len),
 			       msg->msg_flags & MSG_DONTWAIT, &err);
 	if (skb == NULL)
 		goto out_unlock;
@@ -2541,31 +2776,23 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 
 	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) {
-			u16 s = __virtio16_to_cpu(false, vnet_hdr.csum_start);
-			u16 o = __virtio16_to_cpu(false, 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;
@@ -2573,7 +2800,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		}
 
 		skb_shinfo(skb)->gso_size =
-			__virtio16_to_cpu(false, vnet_hdr.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. */
@@ -2583,8 +2810,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		len += vnet_hdr_len;
 	}
 
-	if (!packet_use_direct_xmit(po))
-		skb_probe_transport_header(skb, reserve);
+	skb_probe_transport_header(skb, reserve);
+
 	if (unlikely(extra_len == 4))
 		skb->no_fcs = 1;
 
@@ -2687,22 +2914,40 @@ static int packet_release(struct socket *sock)
  *	Attach a packet hook.
  */
 
-static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
+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);
+	rcu_read_lock();
+
+	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;
@@ -2710,14 +2955,29 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 	need_rehook = proto_curr != proto || dev_curr != dev;
 
 	if (need_rehook) {
-		unregister_prot_hook(sk, true);
+		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;
-		po->prot_hook.dev = dev;
 
-		po->ifindex = dev ? dev->ifindex : 0;
-		packet_cached_dev_assign(po, dev);
+		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);
@@ -2725,7 +2985,7 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 	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;
@@ -2734,9 +2994,10 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 	}
 
 out_unlock:
+	rcu_read_unlock();
 	spin_unlock(&po->bind_lock);
 	release_sock(sk);
-	return 0;
+	return ret;
 }
 
 /*
@@ -2748,8 +3009,6 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
 {
 	struct sock *sk = sock->sk;
 	char name[15];
-	struct net_device *dev;
-	int err = -ENODEV;
 
 	/*
 	 *	Check legality
@@ -2759,19 +3018,13 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
 		return -EINVAL;
 	strlcpy(name, uaddr->sa_data, sizeof(name));
 
-	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
@@ -2782,16 +3035,8 @@ static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len
 	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 = {
@@ -2821,7 +3066,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
 	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;
 
@@ -2851,6 +3096,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
 
 	spin_lock_init(&po->bind_lock);
 	mutex_init(&po->pg_vec_lock);
+	po->rollover = NULL;
 	po->prot_hook.func = packet_rcv;
 
 	if (sock->type == SOCK_PACKET)
@@ -2928,6 +3174,9 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	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 };
 
@@ -2943,9 +3192,9 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 
 			/* This is a hint as to how much should be linear. */
 			vnet_hdr.hdr_len =
-				__cpu_to_virtio16(false, skb_headlen(skb));
+				__cpu_to_virtio16(vio_le(), skb_headlen(skb));
 			vnet_hdr.gso_size =
-				__cpu_to_virtio16(false, sinfo->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)
@@ -2963,9 +3212,9 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 
 		if (skb->ip_summed == CHECKSUM_PARTIAL) {
 			vnet_hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
-			vnet_hdr.csum_start = __cpu_to_virtio16(false,
+			vnet_hdr.csum_start = __cpu_to_virtio16(vio_le(),
 					  skb_checksum_start_offset(skb));
-			vnet_hdr.csum_offset = __cpu_to_virtio16(false,
+			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;
@@ -3432,6 +3681,13 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		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;
@@ -3471,6 +3727,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 	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;
@@ -3546,6 +3803,15 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 			((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;
@@ -3683,6 +3949,8 @@ static unsigned int packet_poll(struct file *file, struct socket *sock,
 			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) {
@@ -3842,7 +4110,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		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 &&
 		    (int)(req->tp_block_size -
@@ -3854,8 +4122,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		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))
+		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))
@@ -3872,7 +4140,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		 * 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;
@@ -3932,7 +4200,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	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);
 	}
 	release_sock(sk);
 
diff --git a/kernel/net/packet/internal.h b/kernel/net/packet/internal.h
index fe6e20cae..9ee46314b 100644
--- a/kernel/net/packet/internal.h
+++ b/kernel/net/packet/internal.h
@@ -79,15 +79,27 @@ struct packet_fanout {
 	u16			id;
 	u8			type;
 	u8			flags;
-	atomic_t		rr_cur;
+	union {
+		atomic_t		rr_cur;
+		struct bpf_prog __rcu	*bpf_prog;
+	};
 	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;
 };
 
+struct packet_rollover {
+	int			sock;
+	struct rcu_head		rcu;
+	atomic_long_t		num;
+	atomic_long_t		num_huge;
+	atomic_long_t		num_failed;
+#define ROLLOVER_HLEN	(L1_CACHE_BYTES / sizeof(u32))
+	u32			history[ROLLOVER_HLEN] ____cacheline_aligned;
+} ____cacheline_aligned_in_smp;
+
 struct packet_sock {
 	/* struct sock has to be the first member of packet_sock */
 	struct sock		sk;
@@ -102,8 +114,10 @@ struct packet_sock {
 				auxdata:1,
 				origdev:1,
 				has_vnet_hdr:1;
+	int			pressure;
 	int			ifindex;	/* bound device		*/
 	__be16			num;
+	struct packet_rollover	*rollover;
 	struct packet_mclist	*mclist;
 	atomic_t		mapped;
 	enum tpacket_versions	tp_version;