Merge branch 'virtio_rx_merging'

Michael Dalton says:

====================
virtio-net: mergeable rx buffer size auto-tuning

The virtio-net device currently uses aligned MTU-sized mergeable receive
packet buffers. Network throughput for workloads with large average
packet size can be improved by posting larger receive packet buffers.
However, due to SKB truesize effects, posting large (e.g, PAGE_SIZE)
buffers reduces the throughput of workloads that do not benefit from GRO
and have no large inbound packets.

This patchset introduces virtio-net mergeable buffer size auto-tuning,
with buffer sizes ranging from aligned MTU-size to PAGE_SIZE. Packet
buffer size is chosen based on a per-receive queue EWMA of incoming
packet size.

To unify mergeable receive buffer memory allocation and improve
SKB frag coalescing, all mergeable buffer memory allocation is
migrated to per-receive queue page frag allocators.

The per-receive queue mergeable packet buffer size is exported via
sysfs, and the network device sysfs layer has been extended to add
support for device-specific per-receive queue sysfs attribute groups.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/netdevice.h

@@ -668,15 +668,28 @@ extern struct rps_sock_flow_table __rcu *rps_sock_flow_table;
 bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id,
 			 u16 filter_id);
 #endif
+#endif /* CONFIG_RPS */
 
 /* This structure contains an instance of an RX queue. */
 struct netdev_rx_queue {
+#ifdef CONFIG_RPS
 	struct rps_map __rcu		*rps_map;
 	struct rps_dev_flow_table __rcu	*rps_flow_table;
+#endif
 	struct kobject			kobj;
 	struct net_device		*dev;
 } ____cacheline_aligned_in_smp;
-#endif /* CONFIG_RPS */
+
+/*
+ * RX queue sysfs structures and functions.
+ */
+struct rx_queue_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct netdev_rx_queue *queue,
+	    struct rx_queue_attribute *attr, char *buf);
+	ssize_t (*store)(struct netdev_rx_queue *queue,
+	    struct rx_queue_attribute *attr, const char *buf, size_t len);
+};
 
 #ifdef CONFIG_XPS
 /*
@@ -1313,7 +1326,7 @@ struct net_device {
 						   unicast) */
 
 
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 	struct netdev_rx_queue	*_rx;
 
 	/* Number of RX queues allocated at register_netdev() time */
@@ -1424,6 +1437,8 @@ struct net_device {
 	struct device		dev;
 	/* space for optional device, statistics, and wireless sysfs groups */
 	const struct attribute_group *sysfs_groups[4];
+	/* space for optional per-rx queue attributes */
+	const struct attribute_group *sysfs_rx_queue_group;
 
 	/* rtnetlink link ops */
 	const struct rtnl_link_ops *rtnl_link_ops;
@@ -2375,7 +2390,7 @@ static inline bool netif_is_multiqueue(const struct net_device *dev)
 
 int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq);
 
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq);
 #else
 static inline int netif_set_real_num_rx_queues(struct net_device *dev,
@@ -2394,7 +2409,7 @@ static inline int netif_copy_real_num_queues(struct net_device *to_dev,
 					   from_dev->real_num_tx_queues);
 	if (err)
 		return err;
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 	return netif_set_real_num_rx_queues(to_dev,
 					    from_dev->real_num_rx_queues);
 #else
@@ -2402,6 +2417,18 @@ static inline int netif_copy_real_num_queues(struct net_device *to_dev,
 #endif
 }
 
+#ifdef CONFIG_SYSFS
+static inline unsigned int get_netdev_rx_queue_index(
+		struct netdev_rx_queue *queue)
+{
+	struct net_device *dev = queue->dev;
+	int index = queue - dev->_rx;
+
+	BUG_ON(index >= dev->num_rx_queues);
+	return index;
+}
+#endif
+
 #define DEFAULT_MAX_NUM_RSS_QUEUES	(8)
 int netif_get_num_default_rss_queues(void);
 

lib/average.c

@@ -53,8 +53,10 @@ EXPORT_SYMBOL(ewma_init);
  */
 struct ewma *ewma_add(struct ewma *avg, unsigned long val)
 {
-	avg->internal = avg->internal  ?
-		(((avg->internal << avg->weight) - avg->internal) +
+	unsigned long internal = ACCESS_ONCE(avg->internal);
+
+	ACCESS_ONCE(avg->internal) = internal ?
+		(((internal << avg->weight) - internal) +
 			(val << avg->factor)) >> avg->weight :
 		(val << avg->factor);
 	return avg;

net/core/dev.c

@@ -2083,7 +2083,7 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq)
 }
 EXPORT_SYMBOL(netif_set_real_num_tx_queues);
 
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 /**
  *	netif_set_real_num_rx_queues - set actual number of RX queues used
  *	@dev: Network device
@@ -5764,7 +5764,7 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev,
 }
 EXPORT_SYMBOL(netif_stacked_transfer_operstate);
 
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 static int netif_alloc_rx_queues(struct net_device *dev)
 {
 	unsigned int i, count = dev->num_rx_queues;
@@ -6309,7 +6309,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 		return NULL;
 	}
 
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 	if (rxqs < 1) {
 		pr_err("alloc_netdev: Unable to allocate device with zero RX queues\n");
 		return NULL;
@@ -6365,7 +6365,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	if (netif_alloc_netdev_queues(dev))
 		goto free_all;
 
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 	dev->num_rx_queues = rxqs;
 	dev->real_num_rx_queues = rxqs;
 	if (netif_alloc_rx_queues(dev))
@@ -6385,7 +6385,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 free_pcpu:
 	free_percpu(dev->pcpu_refcnt);
 	netif_free_tx_queues(dev);
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 	kfree(dev->_rx);
 #endif
 
@@ -6410,7 +6410,7 @@ void free_netdev(struct net_device *dev)
 	release_net(dev_net(dev));
 
 	netif_free_tx_queues(dev);
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 	kfree(dev->_rx);
 #endif
 

net/core/net-sysfs.c

@@ -498,17 +498,7 @@ static struct attribute_group wireless_group = {
 #define net_class_groups	NULL
 #endif /* CONFIG_SYSFS */
 
-#ifdef CONFIG_RPS
-/*
- * RX queue sysfs structures and functions.
- */
-struct rx_queue_attribute {
-	struct attribute attr;
-	ssize_t (*show)(struct netdev_rx_queue *queue,
-	    struct rx_queue_attribute *attr, char *buf);
-	ssize_t (*store)(struct netdev_rx_queue *queue,
-	    struct rx_queue_attribute *attr, const char *buf, size_t len);
-};
+#ifdef CONFIG_SYSFS
 #define to_rx_queue_attr(_attr) container_of(_attr,		\
     struct rx_queue_attribute, attr)
 
@@ -543,6 +533,7 @@ static const struct sysfs_ops rx_queue_sysfs_ops = {
 	.store = rx_queue_attr_store,
 };
 
+#ifdef CONFIG_RPS
 static ssize_t show_rps_map(struct netdev_rx_queue *queue,
 			    struct rx_queue_attribute *attribute, char *buf)
 {
@@ -718,16 +709,20 @@ static struct rx_queue_attribute rps_cpus_attribute =
 static struct rx_queue_attribute rps_dev_flow_table_cnt_attribute =
 	__ATTR(rps_flow_cnt, S_IRUGO | S_IWUSR,
 	    show_rps_dev_flow_table_cnt, store_rps_dev_flow_table_cnt);
+#endif /* CONFIG_RPS */
 
 static struct attribute *rx_queue_default_attrs[] = {
+#ifdef CONFIG_RPS
 	&rps_cpus_attribute.attr,
 	&rps_dev_flow_table_cnt_attribute.attr,
+#endif
 	NULL
 };
 
 static void rx_queue_release(struct kobject *kobj)
 {
 	struct netdev_rx_queue *queue = to_rx_queue(kobj);
+#ifdef CONFIG_RPS
 	struct rps_map *map;
 	struct rps_dev_flow_table *flow_table;
 
@@ -743,6 +738,7 @@ static void rx_queue_release(struct kobject *kobj)
 		RCU_INIT_POINTER(queue->rps_flow_table, NULL);
 		call_rcu(&flow_table->rcu, rps_dev_flow_table_release);
 	}
+#endif
 
 	memset(kobj, 0, sizeof(*kobj));
 	dev_put(queue->dev);
@@ -763,25 +759,36 @@ static int rx_queue_add_kobject(struct net_device *net, int index)
 	kobj->kset = net->queues_kset;
 	error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL,
 	    "rx-%u", index);
-	if (error) {
-		kobject_put(kobj);
-		return error;
+	if (error)
+		goto exit;
+
+	if (net->sysfs_rx_queue_group) {
+		error = sysfs_create_group(kobj, net->sysfs_rx_queue_group);
+		if (error)
+			goto exit;
 	}
 
 	kobject_uevent(kobj, KOBJ_ADD);
 	dev_hold(queue->dev);
 
+	return error;
+exit:
+	kobject_put(kobj);
 	return error;
 }
-#endif /* CONFIG_RPS */
+#endif /* CONFIG_SYFS */
 
 int
 net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num)
 {
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 	int i;
 	int error = 0;
 
+#ifndef CONFIG_RPS
+	if (!net->sysfs_rx_queue_group)
+		return 0;
+#endif
 	for (i = old_num; i < new_num; i++) {
 		error = rx_queue_add_kobject(net, i);
 		if (error) {
@@ -790,8 +797,12 @@ net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num)
 		}
 	}
 
-	while (--i >= new_num)
+	while (--i >= new_num) {
+		if (net->sysfs_rx_queue_group)
+			sysfs_remove_group(&net->_rx[i].kobj,
+					   net->sysfs_rx_queue_group);
 		kobject_put(&net->_rx[i].kobj);
+	}
 
 	return error;
 #else
@@ -1155,9 +1166,6 @@ static int register_queue_kobjects(struct net_device *net)
 	    NULL, &net->dev.kobj);
 	if (!net->queues_kset)
 		return -ENOMEM;
-#endif
-
-#ifdef CONFIG_RPS
 	real_rx = net->real_num_rx_queues;
 #endif
 	real_tx = net->real_num_tx_queues;
@@ -1184,7 +1192,7 @@ static void remove_queue_kobjects(struct net_device *net)
 {
 	int real_rx = 0, real_tx = 0;
 
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
 	real_rx = net->real_num_rx_queues;
 #endif
 	real_tx = net->real_num_tx_queues;

net/core/sock.c

@@ -1836,9 +1836,7 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio)
 		put_page(pfrag->page);
 	}
 
-	/* We restrict high order allocations to users that can afford to wait */
-	order = (prio & __GFP_WAIT) ? SKB_FRAG_PAGE_ORDER : 0;
-
+	order = SKB_FRAG_PAGE_ORDER;
 	do {
 		gfp_t gfp = prio;