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

Pull networking changes from David Miller:

1) Allow to dump, monitor, and change the bridge multicast database
   using netlink.  From Cong Wang.

2) RFC 5961 TCP blind data injection attack mitigation, from Eric
   Dumazet.

3) Networking user namespace support from Eric W. Biederman.

4) tuntap/virtio-net multiqueue support by Jason Wang.

5) Support for checksum offload of encapsulated packets (basically,
   tunneled traffic can still be checksummed by HW).  From Joseph
   Gasparakis.

6) Allow BPF filter access to VLAN tags, from Eric Dumazet and
   Daniel Borkmann.

7) Bridge port parameters over netlink and BPDU blocking support
   from Stephen Hemminger.

8) Improve data access patterns during inet socket demux by rearranging
   socket layout, from Eric Dumazet.

9) TIPC protocol updates and cleanups from Ying Xue, Paul Gortmaker, and
   Jon Maloy.

10) Update TCP socket hash sizing to be more in line with current day
    realities.  The existing heurstics were choosen a decade ago.
    From Eric Dumazet.

11) Fix races, queue bloat, and excessive wakeups in ATM and
    associated drivers, from Krzysztof Mazur and David Woodhouse.

12) Support DOVE (Distributed Overlay Virtual Ethernet) extensions
    in VXLAN driver, from David Stevens.

13) Add "oops_only" mode to netconsole, from Amerigo Wang.

14) Support set and query of VEB/VEPA bridge mode via PF_BRIDGE, also
    allow DCB netlink to work on namespaces other than the initial
    namespace.  From John Fastabend.

15) Support PTP in the Tigon3 driver, from Matt Carlson.

16) tun/vhost zero copy fixes and improvements, plus turn it on
    by default, from Michael S. Tsirkin.

17) Support per-association statistics in SCTP, from Michele
    Baldessari.

And many, many, driver updates, cleanups, and improvements.  Too
numerous to mention individually.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1722 commits)
  net/mlx4_en: Add support for destination MAC in steering rules
  net/mlx4_en: Use generic etherdevice.h functions.
  net: ethtool: Add destination MAC address to flow steering API
  bridge: add support of adding and deleting mdb entries
  bridge: notify mdb changes via netlink
  ndisc: Unexport ndisc_{build,send}_skb().
  uapi: add missing netconf.h to export list
  pkt_sched: avoid requeues if possible
  solos-pci: fix double-free of TX skb in DMA mode
  bnx2: Fix accidental reversions.
  bna: Driver Version Updated to 3.1.2.1
  bna: Firmware update
  bna: Add RX State
  bna: Rx Page Based Allocation
  bna: TX Intr Coalescing Fix
  bna: Tx and Rx Optimizations
  bna: Code Cleanup and Enhancements
  ath9k: check pdata variable before dereferencing it
  ath5k: RX timestamp is reported at end of frame
  ath9k_htc: RX timestamp is reported at end of frame
  ...

1 files changed, 46 insertions, 4 deletions

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 94060edbbd7..e639645e8fe 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1881,7 +1881,35 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 	skb_reserve(skb, hlen);
 	skb_reset_network_header(skb);
 
-	data = ph.raw + po->tp_hdrlen - sizeof(struct sockaddr_ll);
+	if (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;
+		if (sock->type == SOCK_DGRAM) {
+			switch (po->tp_version) {
+			case TPACKET_V2:
+				off = ph.h2->tp_net;
+				break;
+			default:
+				off = ph.h1->tp_net;
+				break;
+			}
+		} else {
+			switch (po->tp_version) {
+			case TPACKET_V2:
+				off = ph.h2->tp_mac;
+				break;
+			default:
+				off = ph.h1->tp_mac;
+				break;
+			}
+		}
+		if (unlikely((off < off_min) || (off_max < off)))
+			return -EINVAL;
+		data = ph.raw + off;
+	} else {
+		data = ph.raw + po->tp_hdrlen - sizeof(struct sockaddr_ll);
+	}
 	to_write = tp_len;
 
 	if (sock->type == SOCK_DGRAM) {
@@ -1907,7 +1935,6 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		to_write -= dev->hard_header_len;
 	}
 
-	err = -EFAULT;
 	offset = offset_in_page(data);
 	len_max = PAGE_SIZE - offset;
 	len = ((to_write > len_max) ? len_max : to_write);
@@ -1957,7 +1984,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 
 	mutex_lock(&po->pg_vec_lock);
 
-	err = -EBUSY;
 	if (saddr == NULL) {
 		dev = po->prot_hook.dev;
 		proto	= po->num;
@@ -2478,7 +2504,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
 	__be16 proto = (__force __be16)protocol; /* weird, but documented */
 	int err;
 
-	if (!capable(CAP_NET_RAW))
+	if (!ns_capable(net->user_ns, CAP_NET_RAW))
 		return -EPERM;
 	if (sock->type != SOCK_DGRAM && sock->type != SOCK_RAW &&
 	    sock->type != SOCK_PACKET)
@@ -3111,6 +3137,19 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 
 		return fanout_add(sk, val & 0xffff, val >> 16);
 	}
+	case PACKET_TX_HAS_OFF:
+	{
+		unsigned int val;
+
+		if (optlen != sizeof(val))
+			return -EINVAL;
+		if (po->rx_ring.pg_vec || po->tx_ring.pg_vec)
+			return -EBUSY;
+		if (copy_from_user(&val, optval, sizeof(val)))
+			return -EFAULT;
+		po->tp_tx_has_off = !!val;
+		return 0;
+	}
 	default:
 		return -ENOPROTOOPT;
 	}
@@ -3202,6 +3241,9 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 			((u32)po->fanout->type << 16)) :
 		       0);
 		break;
+	case PACKET_TX_HAS_OFF:
+		val = po->tp_tx_has_off;
+		break;
 	default:
 		return -ENOPROTOOPT;
 	}