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

Pull networking updates from David Miller:

 1) Seccomp BPF filters can now be JIT'd, from Alexei Starovoitov.

 2) Multiqueue support in xen-netback and xen-netfront, from Andrew J
    Benniston.

 3) Allow tweaking of aggregation settings in cdc_ncm driver, from Bjørn
    Mork.

 4) BPF now has a "random" opcode, from Chema Gonzalez.

 5) Add more BPF documentation and improve test framework, from Daniel
    Borkmann.

 6) Support TCP fastopen over ipv6, from Daniel Lee.

 7) Add software TSO helper functions and use them to support software
    TSO in mvneta and mv643xx_eth drivers.  From Ezequiel Garcia.

 8) Support software TSO in fec driver too, from Nimrod Andy.

 9) Add Broadcom SYSTEMPORT driver, from Florian Fainelli.

10) Handle broadcasts more gracefully over macvlan when there are large
    numbers of interfaces configured, from Herbert Xu.

11) Allow more control over fwmark used for non-socket based responses,
    from Lorenzo Colitti.

12) Do TCP congestion window limiting based upon measurements, from Neal
    Cardwell.

13) Support busy polling in SCTP, from Neal Horman.

14) Allow RSS key to be configured via ethtool, from Venkata Duvvuru.

15) Bridge promisc mode handling improvements from Vlad Yasevich.

16) Don't use inetpeer entries to implement ID generation any more, it
    performs poorly, from Eric Dumazet.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1522 commits)
  rtnetlink: fix userspace API breakage for iproute2 < v3.9.0
  tcp: fixing TLP's FIN recovery
  net: fec: Add software TSO support
  net: fec: Add Scatter/gather support
  net: fec: Increase buffer descriptor entry number
  net: fec: Factorize feature setting
  net: fec: Enable IP header hardware checksum
  net: fec: Factorize the .xmit transmit function
  bridge: fix compile error when compiling without IPv6 support
  bridge: fix smatch warning / potential null pointer dereference
  via-rhine: fix full-duplex with autoneg disable
  bnx2x: Enlarge the dorq threshold for VFs
  bnx2x: Check for UNDI in uncommon branch
  bnx2x: Fix 1G-baseT link
  bnx2x: Fix link for KR with swapped polarity lane
  sctp: Fix sk_ack_backlog wrap-around problem
  net/core: Add VF link state control policy
  net/fsl: xgmac_mdio is dependent on OF_MDIO
  net/fsl: Make xgmac_mdio read error message useful
  net_sched: drr: warn when qdisc is not work conserving
  ...

1 files changed, 153 insertions, 29 deletions

diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 7a206cffb062..96c63dc2509e 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -19,6 +19,8 @@
 */
 
 #include "common.h"
+#include <linux/vmalloc.h>
+#include <linux/rtnetlink.h>
 
 struct backend_info {
 	struct xenbus_device *dev;
@@ -34,8 +36,9 @@ struct backend_info {
 	u8 have_hotplug_status_watch:1;
 };
 
-static int connect_rings(struct backend_info *);
-static void connect(struct backend_info *);
+static int connect_rings(struct backend_info *be, struct xenvif_queue *queue);
+static void connect(struct backend_info *be);
+static int read_xenbus_vif_flags(struct backend_info *be);
 static void backend_create_xenvif(struct backend_info *be);
 static void unregister_hotplug_status_watch(struct backend_info *be);
 static void set_backend_state(struct backend_info *be,
@@ -157,6 +160,12 @@ static int netback_probe(struct xenbus_device *dev,
 	if (err)
 		pr_debug("Error writing feature-split-event-channels\n");
 
+	/* Multi-queue support: This is an optional feature. */
+	err = xenbus_printf(XBT_NIL, dev->nodename,
+			    "multi-queue-max-queues", "%u", xenvif_max_queues);
+	if (err)
+		pr_debug("Error writing multi-queue-max-queues\n");
+
 	err = xenbus_switch_state(dev, XenbusStateInitWait);
 	if (err)
 		goto fail;
@@ -485,10 +494,26 @@ static void connect(struct backend_info *be)
 {
 	int err;
 	struct xenbus_device *dev = be->dev;
+	unsigned long credit_bytes, credit_usec;
+	unsigned int queue_index;
+	unsigned int requested_num_queues;
+	struct xenvif_queue *queue;
 
-	err = connect_rings(be);
-	if (err)
+	/* Check whether the frontend requested multiple queues
+	 * and read the number requested.
+	 */
+	err = xenbus_scanf(XBT_NIL, dev->otherend,
+			   "multi-queue-num-queues",
+			   "%u", &requested_num_queues);
+	if (err < 0) {
+		requested_num_queues = 1; /* Fall back to single queue */
+	} else if (requested_num_queues > xenvif_max_queues) {
+		/* buggy or malicious guest */
+		xenbus_dev_fatal(dev, err,
+				 "guest requested %u queues, exceeding the maximum of %u.",
+				 requested_num_queues, xenvif_max_queues);
 		return;
+	}
 
 	err = xen_net_read_mac(dev, be->vif->fe_dev_addr);
 	if (err) {
@@ -496,9 +521,54 @@ static void connect(struct backend_info *be)
 		return;
 	}
 
-	xen_net_read_rate(dev, &be->vif->credit_bytes,
-			  &be->vif->credit_usec);
-	be->vif->remaining_credit = be->vif->credit_bytes;
+	xen_net_read_rate(dev, &credit_bytes, &credit_usec);
+	read_xenbus_vif_flags(be);
+
+	/* Use the number of queues requested by the frontend */
+	be->vif->queues = vzalloc(requested_num_queues *
+				  sizeof(struct xenvif_queue));
+	rtnl_lock();
+	netif_set_real_num_tx_queues(be->vif->dev, requested_num_queues);
+	rtnl_unlock();
+
+	for (queue_index = 0; queue_index < requested_num_queues; ++queue_index) {
+		queue = &be->vif->queues[queue_index];
+		queue->vif = be->vif;
+		queue->id = queue_index;
+		snprintf(queue->name, sizeof(queue->name), "%s-q%u",
+				be->vif->dev->name, queue->id);
+
+		err = xenvif_init_queue(queue);
+		if (err) {
+			/* xenvif_init_queue() cleans up after itself on
+			 * failure, but we need to clean up any previously
+			 * initialised queues. Set num_queues to i so that
+			 * earlier queues can be destroyed using the regular
+			 * disconnect logic.
+			 */
+			rtnl_lock();
+			netif_set_real_num_tx_queues(be->vif->dev, queue_index);
+			rtnl_unlock();
+			goto err;
+		}
+
+		queue->remaining_credit = credit_bytes;
+
+		err = connect_rings(be, queue);
+		if (err) {
+			/* connect_rings() cleans up after itself on failure,
+			 * but we need to clean up after xenvif_init_queue() here,
+			 * and also clean up any previously initialised queues.
+			 */
+			xenvif_deinit_queue(queue);
+			rtnl_lock();
+			netif_set_real_num_tx_queues(be->vif->dev, queue_index);
+			rtnl_unlock();
+			goto err;
+		}
+	}
+
+	xenvif_carrier_on(be->vif);
 
 	unregister_hotplug_status_watch(be);
 	err = xenbus_watch_pathfmt(dev, &be->hotplug_status_watch,
@@ -507,45 +577,109 @@ static void connect(struct backend_info *be)
 	if (!err)
 		be->have_hotplug_status_watch = 1;
 
-	netif_wake_queue(be->vif->dev);
+	netif_tx_wake_all_queues(be->vif->dev);
+
+	return;
+
+err:
+	if (be->vif->dev->real_num_tx_queues > 0)
+		xenvif_disconnect(be->vif); /* Clean up existing queues */
+	vfree(be->vif->queues);
+	be->vif->queues = NULL;
+	rtnl_lock();
+	netif_set_real_num_tx_queues(be->vif->dev, 0);
+	rtnl_unlock();
+	return;
 }
 
 
-static int connect_rings(struct backend_info *be)
+static int connect_rings(struct backend_info *be, struct xenvif_queue *queue)
 {
-	struct xenvif *vif = be->vif;
 	struct xenbus_device *dev = be->dev;
+	unsigned int num_queues = queue->vif->dev->real_num_tx_queues;
 	unsigned long tx_ring_ref, rx_ring_ref;
-	unsigned int tx_evtchn, rx_evtchn, rx_copy;
+	unsigned int tx_evtchn, rx_evtchn;
 	int err;
-	int val;
+	char *xspath;
+	size_t xspathsize;
+	const size_t xenstore_path_ext_size = 11; /* sufficient for "/queue-NNN" */
+
+	/* If the frontend requested 1 queue, or we have fallen back
+	 * to single queue due to lack of frontend support for multi-
+	 * queue, expect the remaining XenStore keys in the toplevel
+	 * directory. Otherwise, expect them in a subdirectory called
+	 * queue-N.
+	 */
+	if (num_queues == 1) {
+		xspath = kzalloc(strlen(dev->otherend) + 1, GFP_KERNEL);
+		if (!xspath) {
+			xenbus_dev_fatal(dev, -ENOMEM,
+					 "reading ring references");
+			return -ENOMEM;
+		}
+		strcpy(xspath, dev->otherend);
+	} else {
+		xspathsize = strlen(dev->otherend) + xenstore_path_ext_size;
+		xspath = kzalloc(xspathsize, GFP_KERNEL);
+		if (!xspath) {
+			xenbus_dev_fatal(dev, -ENOMEM,
+					 "reading ring references");
+			return -ENOMEM;
+		}
+		snprintf(xspath, xspathsize, "%s/queue-%u", dev->otherend,
+			 queue->id);
+	}
 
-	err = xenbus_gather(XBT_NIL, dev->otherend,
+	err = xenbus_gather(XBT_NIL, xspath,
 			    "tx-ring-ref", "%lu", &tx_ring_ref,
 			    "rx-ring-ref", "%lu", &rx_ring_ref, NULL);
 	if (err) {
 		xenbus_dev_fatal(dev, err,
 				 "reading %s/ring-ref",
-				 dev->otherend);
-		return err;
+				 xspath);
+		goto err;
 	}
 
 	/* Try split event channels first, then single event channel. */
-	err = xenbus_gather(XBT_NIL, dev->otherend,
+	err = xenbus_gather(XBT_NIL, xspath,
 			    "event-channel-tx", "%u", &tx_evtchn,
 			    "event-channel-rx", "%u", &rx_evtchn, NULL);
 	if (err < 0) {
-		err = xenbus_scanf(XBT_NIL, dev->otherend,
+		err = xenbus_scanf(XBT_NIL, xspath,
 				   "event-channel", "%u", &tx_evtchn);
 		if (err < 0) {
 			xenbus_dev_fatal(dev, err,
 					 "reading %s/event-channel(-tx/rx)",
-					 dev->otherend);
-			return err;
+					 xspath);
+			goto err;
 		}
 		rx_evtchn = tx_evtchn;
 	}
 
+	/* Map the shared frame, irq etc. */
+	err = xenvif_connect(queue, tx_ring_ref, rx_ring_ref,
+			     tx_evtchn, rx_evtchn);
+	if (err) {
+		xenbus_dev_fatal(dev, err,
+				 "mapping shared-frames %lu/%lu port tx %u rx %u",
+				 tx_ring_ref, rx_ring_ref,
+				 tx_evtchn, rx_evtchn);
+		goto err;
+	}
+
+	err = 0;
+err: /* Regular return falls through with err == 0 */
+	kfree(xspath);
+	return err;
+}
+
+static int read_xenbus_vif_flags(struct backend_info *be)
+{
+	struct xenvif *vif = be->vif;
+	struct xenbus_device *dev = be->dev;
+	unsigned int rx_copy;
+	int err, val;
+
 	err = xenbus_scanf(XBT_NIL, dev->otherend, "request-rx-copy", "%u",
 			   &rx_copy);
 	if (err == -ENOENT) {
@@ -621,16 +755,6 @@ static int connect_rings(struct backend_info *be)
 		val = 0;
 	vif->ipv6_csum = !!val;
 
-	/* Map the shared frame, irq etc. */
-	err = xenvif_connect(vif, tx_ring_ref, rx_ring_ref,
-			     tx_evtchn, rx_evtchn);
-	if (err) {
-		xenbus_dev_fatal(dev, err,
-				 "mapping shared-frames %lu/%lu port tx %u rx %u",
-				 tx_ring_ref, rx_ring_ref,
-				 tx_evtchn, rx_evtchn);
-		return err;
-	}
 	return 0;
 }