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, 71 insertions, 20 deletions

diff --git a/net/atm/br2684.c b/net/atm/br2684.c
index 4819d31533e..403e71fa88f 100644
--- a/net/atm/br2684.c
+++ b/net/atm/br2684.c
@@ -68,12 +68,15 @@ struct br2684_vcc {
 	/* keep old push, pop functions for chaining */
 	void (*old_push)(struct atm_vcc *vcc, struct sk_buff *skb);
 	void (*old_pop)(struct atm_vcc *vcc, struct sk_buff *skb);
+	void (*old_release_cb)(struct atm_vcc *vcc);
+	struct module *old_owner;
 	enum br2684_encaps encaps;
 	struct list_head brvccs;
 #ifdef CONFIG_ATM_BR2684_IPFILTER
 	struct br2684_filter filter;
 #endif /* CONFIG_ATM_BR2684_IPFILTER */
 	unsigned int copies_needed, copies_failed;
+	atomic_t qspace;
 };
 
 struct br2684_dev {
@@ -181,18 +184,15 @@ static struct notifier_block atm_dev_notifier = {
 static void br2684_pop(struct atm_vcc *vcc, struct sk_buff *skb)
 {
 	struct br2684_vcc *brvcc = BR2684_VCC(vcc);
-	struct net_device *net_dev = skb->dev;
 
-	pr_debug("(vcc %p ; net_dev %p )\n", vcc, net_dev);
+	pr_debug("(vcc %p ; net_dev %p )\n", vcc, brvcc->device);
 	brvcc->old_pop(vcc, skb);
 
-	if (!net_dev)
-		return;
-
-	if (atm_may_send(vcc, 0))
-		netif_wake_queue(net_dev);
-
+	/* If the queue space just went up from zero, wake */
+	if (atomic_inc_return(&brvcc->qspace) == 1)
+		netif_wake_queue(brvcc->device);
 }
+
 /*
  * Send a packet out a particular vcc.  Not to useful right now, but paves
  * the way for multiple vcc's per itf.  Returns true if we can send,
@@ -256,16 +256,30 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct net_device *dev,
 	ATM_SKB(skb)->atm_options = atmvcc->atm_options;
 	dev->stats.tx_packets++;
 	dev->stats.tx_bytes += skb->len;
-	atmvcc->send(atmvcc, skb);
 
-	if (!atm_may_send(atmvcc, 0)) {
+	if (atomic_dec_return(&brvcc->qspace) < 1) {
+		/* No more please! */
 		netif_stop_queue(brvcc->device);
-		/*check for race with br2684_pop*/
-		if (atm_may_send(atmvcc, 0))
-			netif_start_queue(brvcc->device);
+		/* We might have raced with br2684_pop() */
+		if (unlikely(atomic_read(&brvcc->qspace) > 0))
+			netif_wake_queue(brvcc->device);
 	}
 
-	return 1;
+	/* If this fails immediately, the skb will be freed and br2684_pop()
+	   will wake the queue if appropriate. Just return an error so that
+	   the stats are updated correctly */
+	return !atmvcc->send(atmvcc, skb);
+}
+
+static void br2684_release_cb(struct atm_vcc *atmvcc)
+{
+	struct br2684_vcc *brvcc = BR2684_VCC(atmvcc);
+
+	if (atomic_read(&brvcc->qspace) > 0)
+		netif_wake_queue(brvcc->device);
+
+	if (brvcc->old_release_cb)
+		brvcc->old_release_cb(atmvcc);
 }
 
 static inline struct br2684_vcc *pick_outgoing_vcc(const struct sk_buff *skb,
@@ -279,6 +293,8 @@ static netdev_tx_t br2684_start_xmit(struct sk_buff *skb,
 {
 	struct br2684_dev *brdev = BRPRIV(dev);
 	struct br2684_vcc *brvcc;
+	struct atm_vcc *atmvcc;
+	netdev_tx_t ret = NETDEV_TX_OK;
 
 	pr_debug("skb_dst(skb)=%p\n", skb_dst(skb));
 	read_lock(&devs_lock);
@@ -289,9 +305,26 @@ static netdev_tx_t br2684_start_xmit(struct sk_buff *skb,
 		dev->stats.tx_carrier_errors++;
 		/* netif_stop_queue(dev); */
 		dev_kfree_skb(skb);
-		read_unlock(&devs_lock);
-		return NETDEV_TX_OK;
+		goto out_devs;
 	}
+	atmvcc = brvcc->atmvcc;
+
+	bh_lock_sock(sk_atm(atmvcc));
+
+	if (test_bit(ATM_VF_RELEASED, &atmvcc->flags) ||
+	    test_bit(ATM_VF_CLOSE, &atmvcc->flags) ||
+	    !test_bit(ATM_VF_READY, &atmvcc->flags)) {
+		dev->stats.tx_dropped++;
+		dev_kfree_skb(skb);
+		goto out;
+	}
+
+	if (sock_owned_by_user(sk_atm(atmvcc))) {
+		netif_stop_queue(brvcc->device);
+		ret = NETDEV_TX_BUSY;
+		goto out;
+	}
+
 	if (!br2684_xmit_vcc(skb, dev, brvcc)) {
 		/*
 		 * We should probably use netif_*_queue() here, but that
@@ -303,8 +336,11 @@ static netdev_tx_t br2684_start_xmit(struct sk_buff *skb,
 		dev->stats.tx_errors++;
 		dev->stats.tx_fifo_errors++;
 	}
+ out:
+	bh_unlock_sock(sk_atm(atmvcc));
+ out_devs:
 	read_unlock(&devs_lock);
-	return NETDEV_TX_OK;
+	return ret;
 }
 
 /*
@@ -377,9 +413,10 @@ static void br2684_close_vcc(struct br2684_vcc *brvcc)
 	list_del(&brvcc->brvccs);
 	write_unlock_irq(&devs_lock);
 	brvcc->atmvcc->user_back = NULL;	/* what about vcc->recvq ??? */
+	brvcc->atmvcc->release_cb = brvcc->old_release_cb;
 	brvcc->old_push(brvcc->atmvcc, NULL);	/* pass on the bad news */
+	module_put(brvcc->old_owner);
 	kfree(brvcc);
-	module_put(THIS_MODULE);
 }
 
 /* when AAL5 PDU comes in: */
@@ -504,6 +541,13 @@ static int br2684_regvcc(struct atm_vcc *atmvcc, void __user * arg)
 	brvcc = kzalloc(sizeof(struct br2684_vcc), GFP_KERNEL);
 	if (!brvcc)
 		return -ENOMEM;
+	/*
+	 * Allow two packets in the ATM queue. One actually being sent, and one
+	 * for the ATM 'TX done' handler to send. It shouldn't take long to get
+	 * the next one from the netdev queue, when we need it. More than that
+	 * would be bufferbloat.
+	 */
+	atomic_set(&brvcc->qspace, 2);
 	write_lock_irq(&devs_lock);
 	net_dev = br2684_find_dev(&be.ifspec);
 	if (net_dev == NULL) {
@@ -546,9 +590,13 @@ static int br2684_regvcc(struct atm_vcc *atmvcc, void __user * arg)
 	brvcc->encaps = (enum br2684_encaps)be.encaps;
 	brvcc->old_push = atmvcc->push;
 	brvcc->old_pop = atmvcc->pop;
+	brvcc->old_release_cb = atmvcc->release_cb;
+	brvcc->old_owner = atmvcc->owner;
 	barrier();
 	atmvcc->push = br2684_push;
 	atmvcc->pop = br2684_pop;
+	atmvcc->release_cb = br2684_release_cb;
+	atmvcc->owner = THIS_MODULE;
 
 	/* initialize netdev carrier state */
 	if (atmvcc->dev->signal == ATM_PHY_SIG_LOST)
@@ -687,10 +735,13 @@ static int br2684_ioctl(struct socket *sock, unsigned int cmd,
 			return -ENOIOCTLCMD;
 		if (!capable(CAP_NET_ADMIN))
 			return -EPERM;
-		if (cmd == ATM_SETBACKEND)
+		if (cmd == ATM_SETBACKEND) {
+			if (sock->state != SS_CONNECTED)
+				return -EINVAL;
 			return br2684_regvcc(atmvcc, argp);
-		else
+		} else {
 			return br2684_create(argp);
+		}
 #ifdef CONFIG_ATM_BR2684_IPFILTER
 	case BR2684_SETFILT:
 		if (atmvcc->push != br2684_push)