net/sched: Extend qdisc control block with tc control block

BPF layer extends the qdisc control block via struct bpf_skb_data_end
and because of that there is no more room to add variables to the
qdisc layer control block without going over the skb->cb size.

Extend the qdisc control block with a tc control block,
and move all tc related variables to there as a pre-step for
extending the tc control block with additional members.

Signed-off-by: Paul Blakey <paulb@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/net/pkt_sched.h

@@ -193,4 +193,19 @@ static inline void skb_txtime_consumed(struct sk_buff *skb)
 	skb->tstamp = ktime_set(0, 0);
 }
 
+struct tc_skb_cb {
+	struct qdisc_skb_cb qdisc_cb;
+
+	u16 mru;
+	bool post_ct;
+};
+
+static inline struct tc_skb_cb *tc_skb_cb(const struct sk_buff *skb)
+{
+	struct tc_skb_cb *cb = (struct tc_skb_cb *)skb->cb;
+
+	BUILD_BUG_ON(sizeof(*cb) > sizeof_field(struct sk_buff, cb));
+	return cb;
+}
+
 #endif

include/net/sch_generic.h

@@ -447,8 +447,6 @@ struct qdisc_skb_cb {
 	};
 #define QDISC_CB_PRIV_LEN 20
 	unsigned char		data[QDISC_CB_PRIV_LEN];
-	u16			mru;
-	bool			post_ct;
 };
 
 typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv);

net/core/dev.c

@@ -3941,8 +3941,8 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
 		return skb;
 
 	/* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */
-	qdisc_skb_cb(skb)->mru = 0;
+	tc_skb_cb(skb)->mru = 0;
-	qdisc_skb_cb(skb)->post_ct = false;
+	tc_skb_cb(skb)->post_ct = false;
 	mini_qdisc_bstats_cpu_update(miniq, skb);
 
 	switch (tcf_classify(skb, miniq->block, miniq->filter_list, &cl_res, false)) {
@@ -5103,8 +5103,8 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 	}
 
 	qdisc_skb_cb(skb)->pkt_len = skb->len;
-	qdisc_skb_cb(skb)->mru = 0;
+	tc_skb_cb(skb)->mru = 0;
-	qdisc_skb_cb(skb)->post_ct = false;
+	tc_skb_cb(skb)->post_ct = false;
 	skb->tc_at_ingress = 1;
 	mini_qdisc_bstats_cpu_update(miniq, skb);
 

net/sched/act_ct.c

@@ -690,10 +690,10 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 				   u8 family, u16 zone, bool *defrag)
 {
 	enum ip_conntrack_info ctinfo;
-	struct qdisc_skb_cb cb;
 	struct nf_conn *ct;
 	int err = 0;
 	bool frag;
+	u16 mru;
 
 	/* Previously seen (loopback)? Ignore. */
 	ct = nf_ct_get(skb, &ctinfo);
@@ -708,7 +708,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 		return err;
 
 	skb_get(skb);
-	cb = *qdisc_skb_cb(skb);
+	mru = tc_skb_cb(skb)->mru;
 
 	if (family == NFPROTO_IPV4) {
 		enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone;
@@ -722,7 +722,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 
 		if (!err) {
 			*defrag = true;
-			cb.mru = IPCB(skb)->frag_max_size;
+			mru = IPCB(skb)->frag_max_size;
 		}
 	} else { /* NFPROTO_IPV6 */
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
@@ -735,7 +735,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 
 		if (!err) {
 			*defrag = true;
-			cb.mru = IP6CB(skb)->frag_max_size;
+			mru = IP6CB(skb)->frag_max_size;
 		}
 #else
 		err = -EOPNOTSUPP;
@@ -744,7 +744,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 	}
 
 	if (err != -EINPROGRESS)
-		*qdisc_skb_cb(skb) = cb;
+		tc_skb_cb(skb)->mru = mru;
 	skb_clear_hash(skb);
 	skb->ignore_df = 1;
 	return err;
@@ -963,7 +963,7 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
 	tcf_action_update_bstats(&c->common, skb);
 
 	if (clear) {
-		qdisc_skb_cb(skb)->post_ct = false;
+		tc_skb_cb(skb)->post_ct = false;
 		ct = nf_ct_get(skb, &ctinfo);
 		if (ct) {
 			nf_conntrack_put(&ct->ct_general);
@@ -1048,7 +1048,7 @@ do_nat:
 out_push:
 	skb_push_rcsum(skb, nh_ofs);
 
-	qdisc_skb_cb(skb)->post_ct = true;
+	tc_skb_cb(skb)->post_ct = true;
 out_clear:
 	if (defrag)
 		qdisc_skb_cb(skb)->pkt_len = skb->len;

net/sched/cls_api.c

@@ -1617,12 +1617,14 @@ int tcf_classify(struct sk_buff *skb,
 
 	/* If we missed on some chain */
 	if (ret == TC_ACT_UNSPEC && last_executed_chain) {
+		struct tc_skb_cb *cb = tc_skb_cb(skb);
+
 		ext = tc_skb_ext_alloc(skb);
 		if (WARN_ON_ONCE(!ext))
 			return TC_ACT_SHOT;
 		ext->chain = last_executed_chain;
-		ext->mru = qdisc_skb_cb(skb)->mru;
+		ext->mru = cb->mru;
-		ext->post_ct = qdisc_skb_cb(skb)->post_ct;
+		ext->post_ct = cb->post_ct;
 	}
 
 	return ret;

net/sched/cls_flower.c

@@ -19,6 +19,7 @@
 
 #include <net/sch_generic.h>
 #include <net/pkt_cls.h>
+#include <net/pkt_sched.h>
 #include <net/ip.h>
 #include <net/flow_dissector.h>
 #include <net/geneve.h>
@@ -309,7 +310,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 		       struct tcf_result *res)
 {
 	struct cls_fl_head *head = rcu_dereference_bh(tp->root);
-	bool post_ct = qdisc_skb_cb(skb)->post_ct;
+	bool post_ct = tc_skb_cb(skb)->post_ct;
 	struct fl_flow_key skb_key;
 	struct fl_flow_mask *mask;
 	struct cls_fl_filter *f;

net/sched/sch_frag.c

@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 #include <net/netlink.h>
 #include <net/sch_generic.h>
+#include <net/pkt_sched.h>
 #include <net/dst.h>
 #include <net/ip.h>
 #include <net/ip6_fib.h>
@@ -137,7 +138,7 @@ err:
 
 int sch_frag_xmit_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb))
 {
-	u16 mru = qdisc_skb_cb(skb)->mru;
+	u16 mru = tc_skb_cb(skb)->mru;
 	int err;
 
 	if (mru && skb->len > mru + skb->dev->hard_header_len)