Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Add TX fast path in mac80211, from Johannes Berg.

 2) Add TSO/GRO support to ibmveth, from Thomas Falcon

 3) Move away from cached routes in ipv6, just like ipv4, from Martin
    KaFai Lau.

 4) Lots of new rhashtable tests, from Thomas Graf.

 5) Run ingress qdisc lockless, from Alexei Starovoitov.

 6) Allow servers to fetch TCP packet headers for SYN packets of new
    connections, for fingerprinting.  From Eric Dumazet.

 7) Add mode parameter to pktgen, for testing receive.  From Alexei
    Starovoitov.

 8) Cache access optimizations via simplifications of build_skb(), from
    Alexander Duyck.

 9) Move page frag allocator under mm/, also from Alexander.

10) Add xmit_more support to hv_netvsc, from KY Srinivasan.

11) Add a counter guard in case we try to perform endless reclassify
    loops in the packet scheduler.

12) Extern flow dissector to be programmable and use it in new "Flower"
    classifier.  From Jiri Pirko.

13) AF_PACKET fanout rollover fixes, performance improvements, and new
    statistics.  From Willem de Bruijn.

14) Add netdev driver for GENEVE tunnels, from John W Linville.

15) Add ingress netfilter hooks and filtering, from Pablo Neira Ayuso.

16) Fix handling of epoll edge triggers in TCP, from Eric Dumazet.

17) Add an ECN retry fallback for the initial TCP handshake, from Daniel
    Borkmann.

18) Add tail call support to BPF, from Alexei Starovoitov.

19) Add several pktgen helper scripts, from Jesper Dangaard Brouer.

20) Add zerocopy support to AF_UNIX, from Hannes Frederic Sowa.

21) Favor even port numbers for allocation to connect() requests, and
    odd port numbers for bind(0), in an effort to help avoid
    ip_local_port_range exhaustion.  From Eric Dumazet.

22) Add Cavium ThunderX driver, from Sunil Goutham.

23) Allow bpf programs to access skb_iif and dev->ifindex SKB metadata,
    from Alexei Starovoitov.

24) Add support for T6 chips in cxgb4vf driver, from Hariprasad Shenai.

25) Double TCP Small Queues default to 256K to accomodate situations
    like the XEN driver and wireless aggregation.  From Wei Liu.

26) Add more entropy inputs to flow dissector, from Tom Herbert.

27) Add CDG congestion control algorithm to TCP, from Kenneth Klette
    Jonassen.

28) Convert ipset over to RCU locking, from Jozsef Kadlecsik.

29) Track and act upon link status of ipv4 route nexthops, from Andy
    Gospodarek.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1670 commits)
  bridge: vlan: flush the dynamically learned entries on port vlan delete
  bridge: multicast: add a comment to br_port_state_selection about blocking state
  net: inet_diag: export IPV6_V6ONLY sockopt
  stmmac: troubleshoot unexpected bits in des0 & des1
  net: ipv4 sysctl option to ignore routes when nexthop link is down
  net: track link-status of ipv4 nexthops
  net: switchdev: ignore unsupported bridge flags
  net: Cavium: Fix MAC address setting in shutdown state
  drivers: net: xgene: fix for ACPI support without ACPI
  ip: report the original address of ICMP messages
  net/mlx5e: Prefetch skb data on RX
  net/mlx5e: Pop cq outside mlx5e_get_cqe
  net/mlx5e: Remove mlx5e_cq.sqrq back-pointer
  net/mlx5e: Remove extra spaces
  net/mlx5e: Avoid TX CQE generation if more xmit packets expected
  net/mlx5e: Avoid redundant dev_kfree_skb() upon NOP completion
  net/mlx5e: Remove re-assignment of wq type in mlx5e_enable_rq()
  net/mlx5e: Use skb_shinfo(skb)->gso_segs rather than counting them
  net/mlx5e: Static mapping of netdev priv resources to/from netdev TX queues
  net/mlx4_en: Use HW counters for rx/tx bytes/packets in PF device
  ...

1 files changed, 148 insertions, 50 deletions

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index b5989c6ee551..c9e8741226c6 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -543,15 +543,11 @@ 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);
 }
 
@@ -607,7 +603,7 @@ 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;
@@ -634,7 +630,7 @@ 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);
 }
 
@@ -1234,27 +1230,81 @@ 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)
@@ -1272,14 +1322,18 @@ static void packet_sock_destruct(struct sock *sk)
 	sk_refcnt_debug_dec(sk);
 }
 
-static int fanout_rr_next(struct packet_fanout *f, unsigned int num)
+static bool fanout_flow_is_huge(struct packet_sock *po, struct sk_buff *skb)
 {
-	int x = atomic_read(&f->rr_cur) + 1;
+	u32 rxhash;
+	int i, count = 0;
 
-	if (x >= num)
-		x = 0;
+	rxhash = skb_get_hash(skb);
+	for (i = 0; i < ROLLOVER_HLEN; i++)
+		if (po->rollover->history[i] == rxhash)
+			count++;
 
-	return x;
+	po->rollover->history[prandom_u32() % ROLLOVER_HLEN] = rxhash;
+	return count > (ROLLOVER_HLEN >> 1);
 }
 
 static unsigned int fanout_demux_hash(struct packet_fanout *f,
@@ -1293,13 +1347,9 @@ static unsigned int fanout_demux_lb(struct packet_fanout *f,
 				    struct sk_buff *skb,
 				    unsigned int num)
 {
-	int cur, old;
+	unsigned int val = atomic_inc_return(&f->rr_cur);
 
-	cur = atomic_read(&f->rr_cur);
-	while ((old = atomic_cmpxchg(&f->rr_cur, cur,
-				     fanout_rr_next(f, num))) != cur)
-		cur = old;
-	return cur;
+	return val % num;
 }
 
 static unsigned int fanout_demux_cpu(struct packet_fanout *f,
@@ -1318,22 +1368,40 @@ 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;
 }
 
@@ -1353,7 +1421,7 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 			     struct packet_type *pt, struct net_device *orig_dev)
 {
 	struct packet_fanout *f = pt->af_packet_priv;
-	unsigned int num = f->num_members;
+	unsigned int num = READ_ONCE(f->num_members);
 	struct packet_sock *po;
 	unsigned int idx;
 
@@ -1386,17 +1454,14 @@ 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;
 	}
 
-	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);
 }
 
@@ -1467,6 +1532,16 @@ 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) {
@@ -1515,6 +1590,10 @@ 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;
 }
 
@@ -1536,6 +1615,9 @@ static void fanout_release(struct sock *sk)
 		kfree(f);
 	}
 	mutex_unlock(&fanout_mutex);
+
+	if (po->rollover)
+		kfree_rcu(po->rollover, rcu);
 }
 
 static const struct proto_ops packet_ops;
@@ -2835,7 +2917,7 @@ 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;
 
@@ -2865,6 +2947,7 @@ 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)
@@ -2942,6 +3025,9 @@ 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 };
 
@@ -3485,6 +3571,7 @@ 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;
@@ -3560,6 +3647,15 @@ 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;
@@ -3697,6 +3793,8 @@ 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) {
@@ -3886,7 +3984,7 @@ 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;