[PATCH V3 net-next 2/5] xen-netback: Add support for multiple queues

["Andrew J. Bennieston" <andrew.bennieston@citrix.com>]

From: "Andrew J. Bennieston" <andrew.bennieston@citrix.com>

Builds on the refactoring of the previous patch to implement multiple
queues between xen-netfront and xen-netback.

Writes the maximum supported number of queues into XenStore, and reads
the values written by the frontend to determine how many queues to use.

Ring references and event channels are read from XenStore on a per-queue
basis and rings are connected accordingly.

Signed-off-by: Andrew J. Bennieston <andrew.bennieston@citrix.com>
---
 drivers/net/xen-netback/common.h    |    2 +
 drivers/net/xen-netback/interface.c |    7 +++-
 drivers/net/xen-netback/netback.c   |    6 +++
 drivers/net/xen-netback/xenbus.c    |   76 ++++++++++++++++++++++++++++++-----
 4 files changed, 80 insertions(+), 11 deletions(-)

diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 2550867..8180929 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -261,4 +261,6 @@ void xenvif_carrier_on(struct xenvif *vif);
 
 extern bool separate_tx_rx_irq;
 
+extern unsigned int xenvif_max_queues;
+
 #endif /* __XEN_NETBACK__COMMON_H__ */
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index daf93f6..bc7a82d 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -373,7 +373,12 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
 	char name[IFNAMSIZ] = {};
 
 	snprintf(name, IFNAMSIZ - 1, "vif%u.%u", domid, handle);
-	dev = alloc_netdev_mq(sizeof(struct xenvif), name, ether_setup, 1);
+	/* Allocate a netdev with the max. supported number of queues.
+	 * When the guest selects the desired number, it will be updated
+	 * via netif_set_real_num_tx_queues().
+	 */
+	dev = alloc_netdev_mq(sizeof(struct xenvif), name, ether_setup,
+			      xenvif_max_queues);
 	if (dev == NULL) {
 		pr_warn("Could not allocate netdev for %s\n", name);
 		return ERR_PTR(-ENOMEM);
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 46b2f5b..aeb5ffa 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -54,6 +54,9 @@
 bool separate_tx_rx_irq = 1;
 module_param(separate_tx_rx_irq, bool, 0644);
 
+unsigned int xenvif_max_queues;
+module_param(xenvif_max_queues, uint, 0644);
+
 /*
  * This is the maximum slots a skb can have. If a guest sends a skb
  * which exceeds this limit it is considered malicious.
@@ -1585,6 +1588,9 @@ static int __init netback_init(void)
 	if (!xen_domain())
 		return -ENODEV;
 
+	/* Allow as many queues as there are CPUs, by default */
+	xenvif_max_queues = num_online_cpus();
+
 	if (fatal_skb_slots < XEN_NETBK_LEGACY_SLOTS_MAX) {
 		pr_info("fatal_skb_slots too small (%d), bump it to XEN_NETBK_LEGACY_SLOTS_MAX (%d)\n",
 			fatal_skb_slots, XEN_NETBK_LEGACY_SLOTS_MAX);
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index f23ea0a..d11f51e 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -20,6 +20,7 @@
 
 #include "common.h"
 #include <linux/vmalloc.h>
+#include <linux/rtnetlink.h>
 
 struct backend_info {
 	struct xenbus_device *dev;
@@ -159,6 +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;
@@ -490,6 +497,23 @@ static void connect(struct backend_info *be)
 	unsigned long credit_bytes, credit_usec;
 	unsigned int queue_index;
 	struct xenvif_queue *queue;
+	unsigned int requested_num_queues;
+
+	/* 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) {
@@ -500,9 +524,13 @@ static void connect(struct backend_info *be)
 	xen_net_read_rate(dev, &credit_bytes, &credit_usec);
 	read_xenbus_vif_flags(be);
 
-	be->vif->num_queues = 1;
+	/* Use the number of queues requested by the frontend */
+	be->vif->num_queues = requested_num_queues;
 	be->vif->queues = vzalloc(be->vif->num_queues *
 			sizeof(struct xenvif_queue));
+	rtnl_lock();
+	netif_set_real_num_tx_queues(be->vif->dev, be->vif->num_queues);
+	rtnl_unlock();
 
 	for (queue_index = 0; queue_index < be->vif->num_queues; ++queue_index) {
 		queue = &be->vif->queues[queue_index];
@@ -547,29 +575,52 @@ static int connect_rings(struct backend_info *be, struct xenvif_queue *queue)
 	unsigned long tx_ring_ref, rx_ring_ref;
 	unsigned int tx_evtchn, rx_evtchn;
 	int err;
+	char *xspath = NULL;
+	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 (queue->vif->num_queues == 1) {
+		xspath = (char *)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;
 	}
@@ -582,10 +633,15 @@ static int connect_rings(struct backend_info *be, struct xenvif_queue *queue)
 				 "mapping shared-frames %lu/%lu port tx %u rx %u",
 				 tx_ring_ref, rx_ring_ref,
 				 tx_evtchn, rx_evtchn);
-		return err;
+		goto err;
 	}
 
-	return 0;
+	err = 0;
+err: /* Regular return falls through with err == 0 */
+	if (xspath != dev->otherend)
+		kfree(xspath);
+
+	return err;
 }
 
 static int read_xenbus_vif_flags(struct backend_info *be)
-- 
1.7.10.4