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>

diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index bf79f3a890af263dcb52056a56bbdf751e28064f..05f18e81f3e87df005d222f253aa243c48dc0393 100644 (file)
--- a/include/net/pkt_sched.h
+++ b/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

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 22179b2fda72a0a1c2fddc07eeda40716a443a46..c70e6d2b2fdd656d25a7844bd4b030ca25544e91 100644 (file)
--- a/include/net/sch_generic.h
+++ b/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);

diff --git a/net/core/dev.c b/net/core/dev.c
index 2a352e668d103948121970350d344f18b98f4aba..c4708e2487fb67e09df99ff0cb2f17cb51795b5d 100644 (file)
--- a/net/core/dev.c
+++ b/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;
-       qdisc_skb_cb(skb)->post_ct = false;
+       tc_skb_cb(skb)->mru = 0;
+       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;
-       qdisc_skb_cb(skb)->post_ct = false;
+       tc_skb_cb(skb)->mru = 0;
+       tc_skb_cb(skb)->post_ct = false;
        skb->tc_at_ingress = 1;
        mini_qdisc_bstats_cpu_update(miniq, skb);
 

diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 90866ae45573a7ec3ff783c070555e56df126c3c..98e248b9c0b17e76bc764997ddc2bcd134b18c7a 100644 (file)
--- a/net/sched/act_ct.c
+++ b/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;

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index e54f0a42270c1ba9f47bdb3968c11b5c777c8bb1..ff8a9383bf1c4a05f9ecef50f352c8b0379edee7 100644 (file)
--- a/net/sched/cls_api.c
+++ b/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->post_ct = qdisc_skb_cb(skb)->post_ct;
+               ext->mru = cb->mru;
+               ext->post_ct = cb->post_ct;
        }
 
        return ret;

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index aab13ba1176729cca0e4f010c82a9b467353ce44..9782b93db1b342eee138fac62f05c1b850d890ad 100644 (file)
--- a/net/sched/cls_flower.c
+++ b/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;

diff --git a/net/sched/sch_frag.c b/net/sched/sch_frag.c
index 8c06381391d6feecaa792f6046c65b8951473f42..5ded4c8672a64dc806b7fb755e809b2383eaab10 100644 (file)
--- a/net/sched/sch_frag.c
+++ b/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)