Merge branch 'net_sched-reflect-tx_queue_len-change-for-pfifo_fast'

Cong Wang says:

====================
net_sched: reflect tx_queue_len change for pfifo_fast

This pathcset restores the pfifo_fast qdisc behavior of dropping
packets based on latest dev->tx_queue_len. Patch 1 introduces
a helper, patch 2 introduces a new Qdisc ops which is called when
we modify tx_queue_len, patch 3 implements this ops for pfifo_fast.

Please see each patch for details.

---
v3: use skb_array_resize_multiple()
v2: handle error case for ->change_tx_queue_len()
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

include/linux/netdevice.h

@@ -3331,6 +3331,7 @@ int dev_get_alias(const struct net_device *, char *, size_t);
 int dev_change_net_namespace(struct net_device *, struct net *, const char *);
 int __dev_set_mtu(struct net_device *, int);
 int dev_set_mtu(struct net_device *, int);
+int dev_change_tx_queue_len(struct net_device *, unsigned long);
 void dev_set_group(struct net_device *, int);
 int dev_set_mac_address(struct net_device *, struct sockaddr *);
 int dev_change_carrier(struct net_device *, bool new_carrier);

include/net/sch_generic.h

@@ -200,6 +200,7 @@ struct Qdisc_ops {
 					  struct nlattr *arg,
 					  struct netlink_ext_ack *extack);
 	void			(*attach)(struct Qdisc *sch);
+	int			(*change_tx_queue_len)(struct Qdisc *, unsigned int);
 
 	int			(*dump)(struct Qdisc *, struct sk_buff *);
 	int			(*dump_stats)(struct Qdisc *, struct gnet_dump *);
@@ -489,6 +490,7 @@ void qdisc_class_hash_remove(struct Qdisc_class_hash *,
 void qdisc_class_hash_grow(struct Qdisc *, struct Qdisc_class_hash *);
 void qdisc_class_hash_destroy(struct Qdisc_class_hash *);
 
+int dev_qdisc_change_tx_queue_len(struct net_device *dev);
 void dev_init_scheduler(struct net_device *dev);
 void dev_shutdown(struct net_device *dev);
 void dev_activate(struct net_device *dev);

net/core/dev.c

@@ -7047,6 +7047,35 @@ int dev_set_mtu(struct net_device *dev, int new_mtu)
 }
 EXPORT_SYMBOL(dev_set_mtu);
 
+/**
+ *	dev_change_tx_queue_len - Change TX queue length of a netdevice
+ *	@dev: device
+ *	@new_len: new tx queue length
+ */
+int dev_change_tx_queue_len(struct net_device *dev, unsigned long new_len)
+{
+	unsigned int orig_len = dev->tx_queue_len;
+	int res;
+
+	if (new_len != (unsigned int)new_len)
+		return -ERANGE;
+
+	if (new_len != orig_len) {
+		dev->tx_queue_len = new_len;
+		res = call_netdevice_notifiers(NETDEV_CHANGE_TX_QUEUE_LEN, dev);
+		res = notifier_to_errno(res);
+		if (res) {
+			netdev_err(dev,
+				   "refused to change device tx_queue_len\n");
+			dev->tx_queue_len = orig_len;
+			return res;
+		}
+		return dev_qdisc_change_tx_queue_len(dev);
+	}
+
+	return 0;
+}
+
 /**
  *	dev_set_group - Change group this device belongs to
  *	@dev: device

net/core/net-sysfs.c

@@ -346,37 +346,14 @@ static ssize_t flags_store(struct device *dev, struct device_attribute *attr,
 }
 NETDEVICE_SHOW_RW(flags, fmt_hex);
 
-static int change_tx_queue_len(struct net_device *dev, unsigned long new_len)
-{
-	unsigned int orig_len = dev->tx_queue_len;
-	int res;
-
-	if (new_len != (unsigned int)new_len)
-		return -ERANGE;
-
-	if (new_len != orig_len) {
-		dev->tx_queue_len = new_len;
-		res = call_netdevice_notifiers(NETDEV_CHANGE_TX_QUEUE_LEN, dev);
-		res = notifier_to_errno(res);
-		if (res) {
-			netdev_err(dev,
-				   "refused to change device tx_queue_len\n");
-			dev->tx_queue_len = orig_len;
-			return -EFAULT;
-		}
-	}
-
-	return 0;
-}
-
 static ssize_t tx_queue_len_store(struct device *dev,
 				  struct device_attribute *attr,
 				  const char *buf, size_t len)
 {
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
 
-	return netdev_store(dev, attr, buf, len, change_tx_queue_len);
+	return netdev_store(dev, attr, buf, len, dev_change_tx_queue_len);
 }
 NETDEVICE_SHOW_RW(tx_queue_len, fmt_dec);
 

net/core/rtnetlink.c

@@ -2337,19 +2337,11 @@ static int do_setlink(const struct sk_buff *skb,
 
 	if (tb[IFLA_TXQLEN]) {
 		unsigned int value = nla_get_u32(tb[IFLA_TXQLEN]);
-		unsigned int orig_len = dev->tx_queue_len;
-
-		if (dev->tx_queue_len ^ value) {
-			dev->tx_queue_len = value;
-			err = call_netdevice_notifiers(
-			      NETDEV_CHANGE_TX_QUEUE_LEN, dev);
-			err = notifier_to_errno(err);
-			if (err) {
-				dev->tx_queue_len = orig_len;
-				goto errout;
-			}
-			status |= DO_SETLINK_MODIFIED;
-		}
+
+		err = dev_change_tx_queue_len(dev, value);
+		if (err)
+			goto errout;
+		status |= DO_SETLINK_MODIFIED;
 	}
 
 	if (tb[IFLA_GSO_MAX_SIZE]) {

net/sched/sch_generic.c

@@ -763,6 +763,23 @@ static void pfifo_fast_destroy(struct Qdisc *sch)
 	}
 }
 
+static int pfifo_fast_change_tx_queue_len(struct Qdisc *sch,
+					  unsigned int new_len)
+{
+	struct pfifo_fast_priv *priv = qdisc_priv(sch);
+	struct skb_array *bands[PFIFO_FAST_BANDS];
+	int prio;
+
+	for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) {
+		struct skb_array *q = band2list(priv, prio);
+
+		bands[prio] = q;
+	}
+
+	return skb_array_resize_multiple(bands, PFIFO_FAST_BANDS, new_len,
+					 GFP_KERNEL);
+}
+
 struct Qdisc_ops pfifo_fast_ops __read_mostly = {
 	.id		=	"pfifo_fast",
 	.priv_size	=	sizeof(struct pfifo_fast_priv),
@@ -773,6 +790,7 @@ struct Qdisc_ops pfifo_fast_ops __read_mostly = {
 	.destroy	=	pfifo_fast_destroy,
 	.reset		=	pfifo_fast_reset,
 	.dump		=	pfifo_fast_dump,
+	.change_tx_queue_len =  pfifo_fast_change_tx_queue_len,
 	.owner		=	THIS_MODULE,
 	.static_flags	=	TCQ_F_NOLOCK | TCQ_F_CPUSTATS,
 };
@@ -1178,6 +1196,39 @@ void dev_deactivate(struct net_device *dev)
 }
 EXPORT_SYMBOL(dev_deactivate);
 
+static int qdisc_change_tx_queue_len(struct net_device *dev,
+				     struct netdev_queue *dev_queue)
+{
+	struct Qdisc *qdisc = dev_queue->qdisc_sleeping;
+	const struct Qdisc_ops *ops = qdisc->ops;
+
+	if (ops->change_tx_queue_len)
+		return ops->change_tx_queue_len(qdisc, dev->tx_queue_len);
+	return 0;
+}
+
+int dev_qdisc_change_tx_queue_len(struct net_device *dev)
+{
+	bool up = dev->flags & IFF_UP;
+	unsigned int i;
+	int ret = 0;
+
+	if (up)
+		dev_deactivate(dev);
+
+	for (i = 0; i < dev->num_tx_queues; i++) {
+		ret = qdisc_change_tx_queue_len(dev, &dev->_tx[i]);
+
+		/* TODO: revert changes on a partial failure */
+		if (ret)
+			break;
+	}
+
+	if (up)
+		dev_activate(dev);
+	return ret;
+}
+
 static void dev_init_scheduler_queue(struct net_device *dev,
 				     struct netdev_queue *dev_queue,
 				     void *_qdisc)