Merge branch 'net-sched-allow-user-to-select-txqueue'

Tonghao Zhang says:

====================
net: sched: allow user to select txqueue

From: Tonghao Zhang <xiangxia.m.yue@gmail.com>

Patch 1 allow user to select txqueue in clsact hook.
Patch 2 support skbhash to select txqueue.
====================

Link: https://lore.kernel.org/r/20220415164046.26636-1-xiangxia.m.yue@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

include/linux/netdevice.h

@@ -3061,6 +3061,9 @@ struct softnet_data {
 	struct {
 		u16 recursion;
 		u8  more;
+#ifdef CONFIG_NET_EGRESS
+		u8  skip_txqueue;
+#endif
 	} xmit;
 #ifdef CONFIG_RPS
 	/* input_queue_head should be written by cpu owning this struct,

include/linux/rtnetlink.h

@@ -100,6 +100,7 @@ void net_dec_ingress_queue(void);
 #ifdef CONFIG_NET_EGRESS
 void net_inc_egress_queue(void);
 void net_dec_egress_queue(void);
+void netdev_xmit_skip_txqueue(bool skip);
 #endif
 
 void rtnetlink_init(void);

include/net/tc_act/tc_skbedit.h

@@ -17,6 +17,7 @@ struct tcf_skbedit_params {
 	u32 mark;
 	u32 mask;
 	u16 queue_mapping;
+	u16 mapping_mod;
 	u16 ptype;
 	struct rcu_head rcu;
 };

include/uapi/linux/tc_act/tc_skbedit.h

@@ -29,6 +29,7 @@
 #define SKBEDIT_F_PTYPE			0x8
 #define SKBEDIT_F_MASK			0x10
 #define SKBEDIT_F_INHERITDSFIELD	0x20
+#define SKBEDIT_F_TXQ_SKBHASH		0x40
 
 struct tc_skbedit {
 	tc_gen;
@@ -45,6 +46,7 @@ enum {
 	TCA_SKBEDIT_PTYPE,
 	TCA_SKBEDIT_MASK,
 	TCA_SKBEDIT_FLAGS,
+	TCA_SKBEDIT_QUEUE_MAPPING_MAX,
 	__TCA_SKBEDIT_MAX
 };
 #define TCA_SKBEDIT_MAX (__TCA_SKBEDIT_MAX - 1)

net/core/dev.c

@@ -3925,6 +3925,25 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
 
 	return skb;
 }
+
+static struct netdev_queue *
+netdev_tx_queue_mapping(struct net_device *dev, struct sk_buff *skb)
+{
+	int qm = skb_get_queue_mapping(skb);
+
+	return netdev_get_tx_queue(dev, netdev_cap_txqueue(dev, qm));
+}
+
+static bool netdev_xmit_txqueue_skipped(void)
+{
+	return __this_cpu_read(softnet_data.xmit.skip_txqueue);
+}
+
+void netdev_xmit_skip_txqueue(bool skip)
+{
+	__this_cpu_write(softnet_data.xmit.skip_txqueue, skip);
+}
+EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue);
 #endif /* CONFIG_NET_EGRESS */
 
 #ifdef CONFIG_XPS
@@ -4095,7 +4114,7 @@ struct netdev_queue *netdev_core_pick_tx(struct net_device *dev,
 static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 {
 	struct net_device *dev = skb->dev;
-	struct netdev_queue *txq;
+	struct netdev_queue *txq = NULL;
 	struct Qdisc *q;
 	int rc = -ENOMEM;
 	bool again = false;
@@ -4123,11 +4142,17 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 			if (!skb)
 				goto out;
 		}
+
+		netdev_xmit_skip_txqueue(false);
+
 		nf_skip_egress(skb, true);
 		skb = sch_handle_egress(skb, &rc, dev);
 		if (!skb)
 			goto out;
 		nf_skip_egress(skb, false);
+
+		if (netdev_xmit_txqueue_skipped())
+			txq = netdev_tx_queue_mapping(dev, skb);
 	}
 #endif
 	/* If device/qdisc don't need skb->dst, release it right now while
@@ -4138,7 +4163,9 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 	else
 		skb_dst_force(skb);
 
+	if (!txq)
 		txq = netdev_core_pick_tx(dev, skb, sb_dev);
+
 	q = rcu_dereference_bh(txq->qdisc);
 
 	trace_net_dev_queue(skb);

net/sched/act_skbedit.c

@@ -23,6 +23,20 @@
 static unsigned int skbedit_net_id;
 static struct tc_action_ops act_skbedit_ops;
 
+static u16 tcf_skbedit_hash(struct tcf_skbedit_params *params,
+			    struct sk_buff *skb)
+{
+	u16 queue_mapping = params->queue_mapping;
+
+	if (params->flags & SKBEDIT_F_TXQ_SKBHASH) {
+		u32 hash = skb_get_hash(skb);
+
+		queue_mapping += hash % params->mapping_mod;
+	}
+
+	return netdev_cap_txqueue(skb->dev, queue_mapping);
+}
+
 static int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a,
 			   struct tcf_result *res)
 {
@@ -58,8 +72,12 @@ static int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a,
 		}
 	}
 	if (params->flags & SKBEDIT_F_QUEUE_MAPPING &&
-	    skb->dev->real_num_tx_queues > params->queue_mapping)
+	    skb->dev->real_num_tx_queues > params->queue_mapping) {
-		skb_set_queue_mapping(skb, params->queue_mapping);
+#ifdef CONFIG_NET_EGRESS
+		netdev_xmit_skip_txqueue(true);
+#endif
+		skb_set_queue_mapping(skb, tcf_skbedit_hash(params, skb));
+	}
 	if (params->flags & SKBEDIT_F_MARK) {
 		skb->mark &= ~params->mask;
 		skb->mark |= params->mark & params->mask;
@@ -92,6 +110,7 @@ static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = {
 	[TCA_SKBEDIT_PTYPE]		= { .len = sizeof(u16) },
 	[TCA_SKBEDIT_MASK]		= { .len = sizeof(u32) },
 	[TCA_SKBEDIT_FLAGS]		= { .len = sizeof(u64) },
+	[TCA_SKBEDIT_QUEUE_MAPPING_MAX]	= { .len = sizeof(u16) },
 };
 
 static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
@@ -108,6 +127,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 	struct tcf_skbedit *d;
 	u32 flags = 0, *priority = NULL, *mark = NULL, *mask = NULL;
 	u16 *queue_mapping = NULL, *ptype = NULL;
+	u16 mapping_mod = 1;
 	bool exists = false;
 	int ret = 0, err;
 	u32 index;
@@ -153,6 +173,25 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 	if (tb[TCA_SKBEDIT_FLAGS] != NULL) {
 		u64 *pure_flags = nla_data(tb[TCA_SKBEDIT_FLAGS]);
 
+		if (*pure_flags & SKBEDIT_F_TXQ_SKBHASH) {
+			u16 *queue_mapping_max;
+
+			if (!tb[TCA_SKBEDIT_QUEUE_MAPPING] ||
+			    !tb[TCA_SKBEDIT_QUEUE_MAPPING_MAX]) {
+				NL_SET_ERR_MSG_MOD(extack, "Missing required range of queue_mapping.");
+				return -EINVAL;
+			}
+
+			queue_mapping_max =
+				nla_data(tb[TCA_SKBEDIT_QUEUE_MAPPING_MAX]);
+			if (*queue_mapping_max < *queue_mapping) {
+				NL_SET_ERR_MSG_MOD(extack, "The range of queue_mapping is invalid, max < min.");
+				return -EINVAL;
+			}
+
+			mapping_mod = *queue_mapping_max - *queue_mapping + 1;
+			flags |= SKBEDIT_F_TXQ_SKBHASH;
+		}
 		if (*pure_flags & SKBEDIT_F_INHERITDSFIELD)
 			flags |= SKBEDIT_F_INHERITDSFIELD;
 	}
@@ -204,8 +243,10 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 	params_new->flags = flags;
 	if (flags & SKBEDIT_F_PRIORITY)
 		params_new->priority = *priority;
-	if (flags & SKBEDIT_F_QUEUE_MAPPING)
+	if (flags & SKBEDIT_F_QUEUE_MAPPING) {
 		params_new->queue_mapping = *queue_mapping;
+		params_new->mapping_mod = mapping_mod;
+	}
 	if (flags & SKBEDIT_F_MARK)
 		params_new->mark = *mark;
 	if (flags & SKBEDIT_F_PTYPE)
@@ -272,6 +313,13 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a,
 		goto nla_put_failure;
 	if (params->flags & SKBEDIT_F_INHERITDSFIELD)
 		pure_flags |= SKBEDIT_F_INHERITDSFIELD;
+	if (params->flags & SKBEDIT_F_TXQ_SKBHASH) {
+		if (nla_put_u16(skb, TCA_SKBEDIT_QUEUE_MAPPING_MAX,
+				params->queue_mapping + params->mapping_mod - 1))
+			goto nla_put_failure;
+
+		pure_flags |= SKBEDIT_F_TXQ_SKBHASH;
+	}
 	if (pure_flags != 0 &&
 	    nla_put(skb, TCA_SKBEDIT_FLAGS, sizeof(pure_flags), &pure_flags))
 		goto nla_put_failure;
@@ -321,6 +369,7 @@ static size_t tcf_skbedit_get_fill_size(const struct tc_action *act)
 	return nla_total_size(sizeof(struct tc_skbedit))
 		+ nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_PRIORITY */
 		+ nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_QUEUE_MAPPING */
+		+ nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_QUEUE_MAPPING_MAX */
 		+ nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_MARK */
 		+ nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_PTYPE */
 		+ nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_MASK */