net: Add max rate tx queue attribute

This adds a tx_maxrate attribute to the tx queue sysfs entry allowing
for max-rate limiting. Along with DCB-ETS and BQL this provides another
knob to tune queue performance. The limit units are Mbps.

By default it is disabled. To disable the rate limitation after it
has been set for a queue, it should be set to zero.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 80 insertions, 12 deletions

diff --git a/Documentation/ABI/testing/sysfs-class-net-queues b/Documentation/ABI/testing/sysfs-class-net-queues
index 5e9aeb91d355..0c0df91b1516 100644
--- a/Documentation/ABI/testing/sysfs-class-net-queues
+++ b/Documentation/ABI/testing/sysfs-class-net-queues
@@ -24,6 +24,14 @@ Description:
 		Indicates the number of transmit timeout events seen by this
 		network interface transmit queue.
 
+What:		/sys/class/<iface>/queues/tx-<queue>/tx_maxrate
+Date:		March 2015
+KernelVersion:	4.1
+Contact:	netdev@vger.kernel.org
+Description:
+		A Mbps max-rate set for the queue, a value of zero means disabled,
+		default is disabled.
+
 What:		/sys/class/<iface>/queues/tx-<queue>/xps_cpus
 Date:		November 2010
 KernelVersion:	2.6.38
diff --git a/Documentation/networking/scaling.txt b/Documentation/networking/scaling.txt
index 99ca40e8e810..cbfac0949635 100644
--- a/Documentation/networking/scaling.txt
+++ b/Documentation/networking/scaling.txt
@@ -421,6 +421,15 @@ best CPUs to share a given queue are probably those that share the cache
 with the CPU that processes transmit completions for that queue
 (transmit interrupts).
 
+Per TX Queue rate limitation:
+=============================
+
+These are rate-limitation mechanisms implemented by HW, where currently
+a max-rate attribute is supported, by setting a Mbps value to
+
+/sys/class/net/<dev>/queues/tx-<n>/tx_maxrate
+
+A value of zero means disabled, and this is the default.
 
 Further Information
 ===================
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index dd1d069758be..76c5de4978a8 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -587,6 +587,7 @@ struct netdev_queue {
 #ifdef CONFIG_BQL
 	struct dql		dql;
 #endif
+	unsigned long		tx_maxrate;
 } ____cacheline_aligned_in_smp;
 
 static inline int netdev_queue_numa_node_read(const struct netdev_queue *q)
@@ -1022,6 +1023,10 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
  *	be otherwise expressed by feature flags. The check is called with
  *	the set of features that the stack has calculated and it returns
  *	those the driver believes to be appropriate.
+ * int (*ndo_set_tx_maxrate)(struct net_device *dev,
+ *			     int queue_index, u32 maxrate);
+ *	Called when a user wants to set a max-rate limitation of specific
+ *	TX queue.
  */
 struct net_device_ops {
 	int			(*ndo_init)(struct net_device *dev);
@@ -1178,6 +1183,9 @@ struct net_device_ops {
 	netdev_features_t	(*ndo_features_check) (struct sk_buff *skb,
 						       struct net_device *dev,
 						       netdev_features_t features);
+	int			(*ndo_set_tx_maxrate)(struct net_device *dev,
+						      int queue_index,
+						      u32 maxrate);
 };
 
 /**
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index cf30620a88e1..7e58bd7ec232 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -951,6 +951,60 @@ static ssize_t show_trans_timeout(struct netdev_queue *queue,
 	return sprintf(buf, "%lu", trans_timeout);
 }
 
+#ifdef CONFIG_XPS
+static inline unsigned int get_netdev_queue_index(struct netdev_queue *queue)
+{
+	struct net_device *dev = queue->dev;
+	int i;
+
+	for (i = 0; i < dev->num_tx_queues; i++)
+		if (queue == &dev->_tx[i])
+			break;
+
+	BUG_ON(i >= dev->num_tx_queues);
+
+	return i;
+}
+
+static ssize_t show_tx_maxrate(struct netdev_queue *queue,
+			       struct netdev_queue_attribute *attribute,
+			       char *buf)
+{
+	return sprintf(buf, "%lu\n", queue->tx_maxrate);
+}
+
+static ssize_t set_tx_maxrate(struct netdev_queue *queue,
+			      struct netdev_queue_attribute *attribute,
+			      const char *buf, size_t len)
+{
+	struct net_device *dev = queue->dev;
+	int err, index = get_netdev_queue_index(queue);
+	u32 rate = 0;
+
+	err = kstrtou32(buf, 10, &rate);
+	if (err < 0)
+		return err;
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	err = -EOPNOTSUPP;
+	if (dev->netdev_ops->ndo_set_tx_maxrate)
+		err = dev->netdev_ops->ndo_set_tx_maxrate(dev, index, rate);
+
+	rtnl_unlock();
+	if (!err) {
+		queue->tx_maxrate = rate;
+		return len;
+	}
+	return err;
+}
+
+static struct netdev_queue_attribute queue_tx_maxrate =
+	__ATTR(tx_maxrate, S_IRUGO | S_IWUSR,
+	       show_tx_maxrate, set_tx_maxrate);
+#endif
+
 static struct netdev_queue_attribute queue_trans_timeout =
 	__ATTR(tx_timeout, S_IRUGO, show_trans_timeout, NULL);
 
@@ -1065,18 +1119,6 @@ static struct attribute_group dql_group = {
 #endif /* CONFIG_BQL */
 
 #ifdef CONFIG_XPS
-static unsigned int get_netdev_queue_index(struct netdev_queue *queue)
-{
-	struct net_device *dev = queue->dev;
-	unsigned int i;
-
-	i = queue - dev->_tx;
-	BUG_ON(i >= dev->num_tx_queues);
-
-	return i;
-}
-
-
 static ssize_t show_xps_map(struct netdev_queue *queue,
 			    struct netdev_queue_attribute *attribute, char *buf)
 {
@@ -1153,6 +1195,7 @@ static struct attribute *netdev_queue_default_attrs[] = {
 	&queue_trans_timeout.attr,
 #ifdef CONFIG_XPS
 	&xps_cpus_attribute.attr,
+	&queue_tx_maxrate.attr,
 #endif
 	NULL
 };