summaryrefslogtreecommitdiff
path: root/net/sched
diff options
context:
space:
mode:
Diffstat (limited to 'net/sched')
-rw-r--r--net/sched/act_api.c17
-rw-r--r--net/sched/act_bpf.c2
-rw-r--r--net/sched/act_ct.c146
-rw-r--r--net/sched/act_police.c62
-rw-r--r--net/sched/act_vlan.c13
-rw-r--r--net/sched/cls_api.c49
-rw-r--r--net/sched/cls_bpf.c2
-rw-r--r--net/sched/cls_flower.c116
-rw-r--r--net/sched/sch_api.c22
-rw-r--r--net/sched/sch_generic.c29
10 files changed, 369 insertions, 89 deletions
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 32563cef85bf..4f51094da9da 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -274,7 +274,7 @@ static int tcf_action_offload_add_ex(struct tc_action *action,
err = tc_setup_action(&fl_action->action, actions);
if (err) {
NL_SET_ERR_MSG_MOD(extack,
- "Failed to setup tc actions for offload\n");
+ "Failed to setup tc actions for offload");
goto fl_err;
}
@@ -1037,6 +1037,7 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
restart_act_graph:
for (i = 0; i < nr_actions; i++) {
const struct tc_action *a = actions[i];
+ int repeat_ttl;
if (jmp_prgcnt > 0) {
jmp_prgcnt -= 1;
@@ -1045,11 +1046,17 @@ restart_act_graph:
if (tc_act_skip_sw(a->tcfa_flags))
continue;
+
+ repeat_ttl = 32;
repeat:
ret = a->ops->act(skb, a, res);
- if (ret == TC_ACT_REPEAT)
- goto repeat; /* we need a ttl - JHS */
-
+ if (unlikely(ret == TC_ACT_REPEAT)) {
+ if (--repeat_ttl != 0)
+ goto repeat;
+ /* suspicious opcode, stop pipeline */
+ net_warn_ratelimited("TC_ACT_REPEAT abuse ?\n");
+ return TC_ACT_OK;
+ }
if (TC_ACT_EXT_CMP(ret, TC_ACT_JUMP)) {
jmp_prgcnt = ret & TCA_ACT_MAX_PRIO_MASK;
if (!jmp_prgcnt || (jmp_prgcnt > nr_actions)) {
@@ -1439,6 +1446,8 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
continue;
if (skip_sw != tc_act_skip_sw(act->tcfa_flags) ||
skip_hw != tc_act_skip_hw(act->tcfa_flags)) {
+ NL_SET_ERR_MSG(extack,
+ "Mismatch between action and filter offload flags");
err = -EINVAL;
goto err;
}
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index a77d8908e737..fea2d78b9ddc 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -53,6 +53,8 @@ static int tcf_bpf_act(struct sk_buff *skb, const struct tc_action *act,
bpf_compute_data_pointers(skb);
filter_res = bpf_prog_run(filter, skb);
}
+ if (unlikely(!skb->tstamp && skb->mono_delivery_time))
+ skb->mono_delivery_time = 0;
if (skb_sk_is_prefetched(skb) && filter_res != TC_ACT_OK)
skb_orphan(skb);
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index f99247fc6468..6a34f7b80a6d 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -57,12 +57,6 @@ static const struct rhashtable_params zones_params = {
.automatic_shrinking = true,
};
-static struct nf_ct_ext_type act_ct_extend __read_mostly = {
- .len = sizeof(struct nf_conn_act_ct_ext),
- .align = __alignof__(struct nf_conn_act_ct_ext),
- .id = NF_CT_EXT_ACT_CT,
-};
-
static struct flow_action_entry *
tcf_ct_flow_table_flow_action_get_next(struct flow_action *flow_action)
{
@@ -361,6 +355,13 @@ static void tcf_ct_flow_table_put(struct tcf_ct_params *params)
}
}
+static void tcf_ct_flow_tc_ifidx(struct flow_offload *entry,
+ struct nf_conn_act_ct_ext *act_ct_ext, u8 dir)
+{
+ entry->tuplehash[dir].tuple.xmit_type = FLOW_OFFLOAD_XMIT_TC;
+ entry->tuplehash[dir].tuple.tc.iifidx = act_ct_ext->ifindex[dir];
+}
+
static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft,
struct nf_conn *ct,
bool tcp)
@@ -385,10 +386,8 @@ static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft,
act_ct_ext = nf_conn_act_ct_ext_find(ct);
if (act_ct_ext) {
- entry->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.iifidx =
- act_ct_ext->ifindex[IP_CT_DIR_ORIGINAL];
- entry->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.iifidx =
- act_ct_ext->ifindex[IP_CT_DIR_REPLY];
+ tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_ORIGINAL);
+ tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_REPLY);
}
err = flow_offload_add(&ct_ft->nf_ft, entry);
@@ -421,6 +420,19 @@ static void tcf_ct_flow_table_process_conn(struct tcf_ct_flow_table *ct_ft,
break;
case IPPROTO_UDP:
break;
+#ifdef CONFIG_NF_CT_PROTO_GRE
+ case IPPROTO_GRE: {
+ struct nf_conntrack_tuple *tuple;
+
+ if (ct->status & IPS_NAT_MASK)
+ return;
+ tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
+ /* No support for GRE v1 */
+ if (tuple->src.u.gre.key || tuple->dst.u.gre.key)
+ return;
+ break;
+ }
+#endif
default:
return;
}
@@ -440,6 +452,8 @@ tcf_ct_flow_table_fill_tuple_ipv4(struct sk_buff *skb,
struct flow_ports *ports;
unsigned int thoff;
struct iphdr *iph;
+ size_t hdrsize;
+ u8 ipproto;
if (!pskb_network_may_pull(skb, sizeof(*iph)))
return false;
@@ -451,29 +465,54 @@ tcf_ct_flow_table_fill_tuple_ipv4(struct sk_buff *skb,
unlikely(thoff != sizeof(struct iphdr)))
return false;
- if (iph->protocol != IPPROTO_TCP &&
- iph->protocol != IPPROTO_UDP)
+ ipproto = iph->protocol;
+ switch (ipproto) {
+ case IPPROTO_TCP:
+ hdrsize = sizeof(struct tcphdr);
+ break;
+ case IPPROTO_UDP:
+ hdrsize = sizeof(*ports);
+ break;
+#ifdef CONFIG_NF_CT_PROTO_GRE
+ case IPPROTO_GRE:
+ hdrsize = sizeof(struct gre_base_hdr);
+ break;
+#endif
+ default:
return false;
+ }
if (iph->ttl <= 1)
return false;
- if (!pskb_network_may_pull(skb, iph->protocol == IPPROTO_TCP ?
- thoff + sizeof(struct tcphdr) :
- thoff + sizeof(*ports)))
+ if (!pskb_network_may_pull(skb, thoff + hdrsize))
return false;
- iph = ip_hdr(skb);
- if (iph->protocol == IPPROTO_TCP)
+ switch (ipproto) {
+ case IPPROTO_TCP:
*tcph = (void *)(skb_network_header(skb) + thoff);
+ fallthrough;
+ case IPPROTO_UDP:
+ ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
+ tuple->src_port = ports->source;
+ tuple->dst_port = ports->dest;
+ break;
+ case IPPROTO_GRE: {
+ struct gre_base_hdr *greh;
+
+ greh = (struct gre_base_hdr *)(skb_network_header(skb) + thoff);
+ if ((greh->flags & GRE_VERSION) != GRE_VERSION_0)
+ return false;
+ break;
+ }
+ }
+
+ iph = ip_hdr(skb);
- ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
tuple->src_v4.s_addr = iph->saddr;
tuple->dst_v4.s_addr = iph->daddr;
- tuple->src_port = ports->source;
- tuple->dst_port = ports->dest;
tuple->l3proto = AF_INET;
- tuple->l4proto = iph->protocol;
+ tuple->l4proto = ipproto;
return true;
}
@@ -486,36 +525,63 @@ tcf_ct_flow_table_fill_tuple_ipv6(struct sk_buff *skb,
struct flow_ports *ports;
struct ipv6hdr *ip6h;
unsigned int thoff;
+ size_t hdrsize;
+ u8 nexthdr;
if (!pskb_network_may_pull(skb, sizeof(*ip6h)))
return false;
ip6h = ipv6_hdr(skb);
+ thoff = sizeof(*ip6h);
- if (ip6h->nexthdr != IPPROTO_TCP &&
- ip6h->nexthdr != IPPROTO_UDP)
- return false;
+ nexthdr = ip6h->nexthdr;
+ switch (nexthdr) {
+ case IPPROTO_TCP:
+ hdrsize = sizeof(struct tcphdr);
+ break;
+ case IPPROTO_UDP:
+ hdrsize = sizeof(*ports);
+ break;
+#ifdef CONFIG_NF_CT_PROTO_GRE
+ case IPPROTO_GRE:
+ hdrsize = sizeof(struct gre_base_hdr);
+ break;
+#endif
+ default:
+ return -1;
+ }
if (ip6h->hop_limit <= 1)
return false;
- thoff = sizeof(*ip6h);
- if (!pskb_network_may_pull(skb, ip6h->nexthdr == IPPROTO_TCP ?
- thoff + sizeof(struct tcphdr) :
- thoff + sizeof(*ports)))
+ if (!pskb_network_may_pull(skb, thoff + hdrsize))
return false;
- ip6h = ipv6_hdr(skb);
- if (ip6h->nexthdr == IPPROTO_TCP)
+ switch (nexthdr) {
+ case IPPROTO_TCP:
*tcph = (void *)(skb_network_header(skb) + thoff);
+ fallthrough;
+ case IPPROTO_UDP:
+ ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
+ tuple->src_port = ports->source;
+ tuple->dst_port = ports->dest;
+ break;
+ case IPPROTO_GRE: {
+ struct gre_base_hdr *greh;
+
+ greh = (struct gre_base_hdr *)(skb_network_header(skb) + thoff);
+ if ((greh->flags & GRE_VERSION) != GRE_VERSION_0)
+ return false;
+ break;
+ }
+ }
+
+ ip6h = ipv6_hdr(skb);
- ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
tuple->src_v6 = ip6h->saddr;
tuple->dst_v6 = ip6h->daddr;
- tuple->src_port = ports->source;
- tuple->dst_port = ports->dest;
tuple->l3proto = AF_INET6;
- tuple->l4proto = ip6h->nexthdr;
+ tuple->l4proto = nexthdr;
return true;
}
@@ -533,11 +599,6 @@ static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p,
struct nf_conn *ct;
u8 dir;
- /* Previously seen or loopback */
- ct = nf_ct_get(skb, &ctinfo);
- if ((ct && !nf_ct_is_template(ct)) || ctinfo == IP_CT_UNTRACKED)
- return false;
-
switch (family) {
case NFPROTO_IPV4:
if (!tcf_ct_flow_table_fill_tuple_ipv4(skb, &tuple, &tcph))
@@ -1608,16 +1669,10 @@ static int __init ct_init_module(void)
if (err)
goto err_register;
- err = nf_ct_extend_register(&act_ct_extend);
- if (err)
- goto err_register_extend;
-
static_branch_inc(&tcf_frag_xmit_count);
return 0;
-err_register_extend:
- tcf_unregister_action(&act_ct_ops, &ct_net_ops);
err_register:
tcf_ct_flow_tables_uninit();
err_tbl_init:
@@ -1628,7 +1683,6 @@ err_tbl_init:
static void __exit ct_cleanup_module(void)
{
static_branch_dec(&tcf_frag_xmit_count);
- nf_ct_extend_unregister(&act_ct_extend);
tcf_unregister_action(&act_ct_ops, &ct_net_ops);
tcf_ct_flow_tables_uninit();
destroy_workqueue(act_ct_wq);
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 0923aa2b8f8a..f4d917705263 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -239,6 +239,20 @@ release_idr:
return err;
}
+static bool tcf_police_mtu_check(struct sk_buff *skb, u32 limit)
+{
+ u32 len;
+
+ if (skb_is_gso(skb))
+ return skb_gso_validate_mac_len(skb, limit);
+
+ len = qdisc_pkt_len(skb);
+ if (skb_at_tc_ingress(skb))
+ len += skb->mac_len;
+
+ return len <= limit;
+}
+
static int tcf_police_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
@@ -261,7 +275,7 @@ static int tcf_police_act(struct sk_buff *skb, const struct tc_action *a,
goto inc_overlimits;
}
- if (qdisc_pkt_len(skb) <= p->tcfp_mtu) {
+ if (tcf_police_mtu_check(skb, p->tcfp_mtu)) {
if (!p->rate_present && !p->pps_present) {
ret = p->tcfp_result;
goto end;
@@ -405,20 +419,66 @@ static int tcf_police_search(struct net *net, struct tc_action **a, u32 index)
return tcf_idr_search(tn, a, index);
}
+static int tcf_police_act_to_flow_act(int tc_act, u32 *extval)
+{
+ int act_id = -EOPNOTSUPP;
+
+ if (!TC_ACT_EXT_OPCODE(tc_act)) {
+ if (tc_act == TC_ACT_OK)
+ act_id = FLOW_ACTION_ACCEPT;
+ else if (tc_act == TC_ACT_SHOT)
+ act_id = FLOW_ACTION_DROP;
+ else if (tc_act == TC_ACT_PIPE)
+ act_id = FLOW_ACTION_PIPE;
+ } else if (TC_ACT_EXT_CMP(tc_act, TC_ACT_GOTO_CHAIN)) {
+ act_id = FLOW_ACTION_GOTO;
+ *extval = tc_act & TC_ACT_EXT_VAL_MASK;
+ } else if (TC_ACT_EXT_CMP(tc_act, TC_ACT_JUMP)) {
+ act_id = FLOW_ACTION_JUMP;
+ *extval = tc_act & TC_ACT_EXT_VAL_MASK;
+ }
+
+ return act_id;
+}
+
static int tcf_police_offload_act_setup(struct tc_action *act, void *entry_data,
u32 *index_inc, bool bind)
{
if (bind) {
struct flow_action_entry *entry = entry_data;
+ struct tcf_police *police = to_police(act);
+ struct tcf_police_params *p;
+ int act_id;
+
+ p = rcu_dereference_protected(police->params,
+ lockdep_is_held(&police->tcf_lock));
entry->id = FLOW_ACTION_POLICE;
entry->police.burst = tcf_police_burst(act);
entry->police.rate_bytes_ps =
tcf_police_rate_bytes_ps(act);
+ entry->police.peakrate_bytes_ps = tcf_police_peakrate_bytes_ps(act);
+ entry->police.avrate = tcf_police_tcfp_ewma_rate(act);
+ entry->police.overhead = tcf_police_rate_overhead(act);
entry->police.burst_pkt = tcf_police_burst_pkt(act);
entry->police.rate_pkt_ps =
tcf_police_rate_pkt_ps(act);
entry->police.mtu = tcf_police_tcfp_mtu(act);
+
+ act_id = tcf_police_act_to_flow_act(police->tcf_action,
+ &entry->police.exceed.extval);
+ if (act_id < 0)
+ return act_id;
+
+ entry->police.exceed.act_id = act_id;
+
+ act_id = tcf_police_act_to_flow_act(p->tcfp_result,
+ &entry->police.notexceed.extval);
+ if (act_id < 0)
+ return act_id;
+
+ entry->police.notexceed.act_id = act_id;
+
*index_inc = 1;
} else {
struct flow_offload_action *fl_action = entry_data;
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 756e2dcde1cd..883454c4f921 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -390,6 +390,13 @@ static int tcf_vlan_offload_act_setup(struct tc_action *act, void *entry_data,
entry->vlan.proto = tcf_vlan_push_proto(act);
entry->vlan.prio = tcf_vlan_push_prio(act);
break;
+ case TCA_VLAN_ACT_POP_ETH:
+ entry->id = FLOW_ACTION_VLAN_POP_ETH;
+ break;
+ case TCA_VLAN_ACT_PUSH_ETH:
+ entry->id = FLOW_ACTION_VLAN_PUSH_ETH;
+ tcf_vlan_push_eth(entry->vlan_push_eth.src, entry->vlan_push_eth.dst, act);
+ break;
default:
return -EOPNOTSUPP;
}
@@ -407,6 +414,12 @@ static int tcf_vlan_offload_act_setup(struct tc_action *act, void *entry_data,
case TCA_VLAN_ACT_MODIFY:
fl_action->id = FLOW_ACTION_VLAN_MANGLE;
break;
+ case TCA_VLAN_ACT_POP_ETH:
+ fl_action->id = FLOW_ACTION_VLAN_POP_ETH;
+ break;
+ case TCA_VLAN_ACT_PUSH_ETH:
+ fl_action->id = FLOW_ACTION_VLAN_PUSH_ETH;
+ break;
default:
return -EOPNOTSUPP;
}
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 5f0f346b576f..2957f8f5cea7 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -49,6 +49,23 @@ static LIST_HEAD(tcf_proto_base);
/* Protects list of registered TC modules. It is pure SMP lock. */
static DEFINE_RWLOCK(cls_mod_lock);
+#ifdef CONFIG_NET_CLS_ACT
+DEFINE_STATIC_KEY_FALSE(tc_skb_ext_tc);
+EXPORT_SYMBOL(tc_skb_ext_tc);
+
+void tc_skb_ext_tc_enable(void)
+{
+ static_branch_inc(&tc_skb_ext_tc);
+}
+EXPORT_SYMBOL(tc_skb_ext_tc_enable);
+
+void tc_skb_ext_tc_disable(void)
+{
+ static_branch_dec(&tc_skb_ext_tc);
+}
+EXPORT_SYMBOL(tc_skb_ext_tc_disable);
+#endif
+
static u32 destroy_obj_hashfn(const struct tcf_proto *tp)
{
return jhash_3words(tp->chain->index, tp->prio,
@@ -1044,7 +1061,7 @@ static int __tcf_qdisc_find(struct net *net, struct Qdisc **q,
/* Find qdisc */
if (!*parent) {
- *q = dev->qdisc;
+ *q = rcu_dereference(dev->qdisc);
*parent = (*q)->handle;
} else {
*q = qdisc_lookup_rcu(dev, TC_H_MAJ(*parent));
@@ -1615,19 +1632,21 @@ int tcf_classify(struct sk_buff *skb,
ret = __tcf_classify(skb, tp, orig_tp, res, compat_mode,
&last_executed_chain);
- /* If we missed on some chain */
- if (ret == TC_ACT_UNSPEC && last_executed_chain) {
- struct tc_skb_cb *cb = tc_skb_cb(skb);
+ if (tc_skb_ext_tc_enabled()) {
+ /* 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 = cb->mru;
- ext->post_ct = cb->post_ct;
- ext->post_ct_snat = cb->post_ct_snat;
- ext->post_ct_dnat = cb->post_ct_dnat;
- ext->zone = cb->zone;
+ ext = tc_skb_ext_alloc(skb);
+ if (WARN_ON_ONCE(!ext))
+ return TC_ACT_SHOT;
+ ext->chain = last_executed_chain;
+ ext->mru = cb->mru;
+ ext->post_ct = cb->post_ct;
+ ext->post_ct_snat = cb->post_ct_snat;
+ ext->post_ct_dnat = cb->post_ct_dnat;
+ ext->zone = cb->zone;
+ }
}
return ret;
@@ -2587,7 +2606,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
parent = tcm->tcm_parent;
if (!parent)
- q = dev->qdisc;
+ q = rtnl_dereference(dev->qdisc);
else
q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
if (!q)
@@ -2962,7 +2981,7 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
return skb->len;
if (!tcm->tcm_parent)
- q = dev->qdisc;
+ q = rtnl_dereference(dev->qdisc);
else
q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index df19a847829e..c85b85a192bf 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -102,6 +102,8 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
bpf_compute_data_pointers(skb);
filter_res = bpf_prog_run(prog->filter, skb);
}
+ if (unlikely(!skb->tstamp && skb->mono_delivery_time))
+ skb->mono_delivery_time = 0;
if (prog->exts_integrated) {
res->class = 0;
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 1a9b1f140f9e..c80fc49c0da1 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -25,6 +25,7 @@
#include <net/geneve.h>
#include <net/vxlan.h>
#include <net/erspan.h>
+#include <net/gtp.h>
#include <net/dst.h>
#include <net/dst_metadata.h>
@@ -723,6 +724,7 @@ enc_opts_policy[TCA_FLOWER_KEY_ENC_OPTS_MAX + 1] = {
[TCA_FLOWER_KEY_ENC_OPTS_GENEVE] = { .type = NLA_NESTED },
[TCA_FLOWER_KEY_ENC_OPTS_VXLAN] = { .type = NLA_NESTED },
[TCA_FLOWER_KEY_ENC_OPTS_ERSPAN] = { .type = NLA_NESTED },
+ [TCA_FLOWER_KEY_ENC_OPTS_GTP] = { .type = NLA_NESTED },
};
static const struct nla_policy
@@ -747,6 +749,12 @@ erspan_opt_policy[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX + 1] = {
};
static const struct nla_policy
+gtp_opt_policy[TCA_FLOWER_KEY_ENC_OPT_GTP_MAX + 1] = {
+ [TCA_FLOWER_KEY_ENC_OPT_GTP_PDU_TYPE] = { .type = NLA_U8 },
+ [TCA_FLOWER_KEY_ENC_OPT_GTP_QFI] = { .type = NLA_U8 },
+};
+
+static const struct nla_policy
mpls_stack_entry_policy[TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX + 1] = {
[TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH] = { .type = NLA_U8 },
[TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL] = { .type = NLA_U8 },
@@ -1262,6 +1270,49 @@ static int fl_set_erspan_opt(const struct nlattr *nla, struct fl_flow_key *key,
return sizeof(*md);
}
+static int fl_set_gtp_opt(const struct nlattr *nla, struct fl_flow_key *key,
+ int depth, int option_len,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[TCA_FLOWER_KEY_ENC_OPT_GTP_MAX + 1];
+ struct gtp_pdu_session_info *sinfo;
+ u8 len = key->enc_opts.len;
+ int err;
+
+ sinfo = (struct gtp_pdu_session_info *)&key->enc_opts.data[len];
+ memset(sinfo, 0xff, option_len);
+
+ if (!depth)
+ return sizeof(*sinfo);
+
+ if (nla_type(nla) != TCA_FLOWER_KEY_ENC_OPTS_GTP) {
+ NL_SET_ERR_MSG_MOD(extack, "Non-gtp option type for mask");
+ return -EINVAL;
+ }
+
+ err = nla_parse_nested(tb, TCA_FLOWER_KEY_ENC_OPT_GTP_MAX, nla,
+ gtp_opt_policy, extack);
+ if (err < 0)
+ return err;
+
+ if (!option_len &&
+ (!tb[TCA_FLOWER_KEY_ENC_OPT_GTP_PDU_TYPE] ||
+ !tb[TCA_FLOWER_KEY_ENC_OPT_GTP_QFI])) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Missing tunnel key gtp option pdu type or qfi");
+ return -EINVAL;
+ }
+
+ if (tb[TCA_FLOWER_KEY_ENC_OPT_GTP_PDU_TYPE])
+ sinfo->pdu_type =
+ nla_get_u8(tb[TCA_FLOWER_KEY_ENC_OPT_GTP_PDU_TYPE]);
+
+ if (tb[TCA_FLOWER_KEY_ENC_OPT_GTP_QFI])
+ sinfo->qfi = nla_get_u8(tb[TCA_FLOWER_KEY_ENC_OPT_GTP_QFI]);
+
+ return sizeof(*sinfo);
+}
+
static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key,
struct fl_flow_key *mask,
struct netlink_ext_ack *extack)
@@ -1386,6 +1437,38 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key,
return -EINVAL;
}
break;
+ case TCA_FLOWER_KEY_ENC_OPTS_GTP:
+ if (key->enc_opts.dst_opt_type) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Duplicate type for gtp options");
+ return -EINVAL;
+ }
+ option_len = 0;
+ key->enc_opts.dst_opt_type = TUNNEL_GTP_OPT;
+ option_len = fl_set_gtp_opt(nla_opt_key, key,
+ key_depth, option_len,
+ extack);
+ if (option_len < 0)
+ return option_len;
+
+ key->enc_opts.len += option_len;
+ /* At the same time we need to parse through the mask
+ * in order to verify exact and mask attribute lengths.
+ */
+ mask->enc_opts.dst_opt_type = TUNNEL_GTP_OPT;
+ option_len = fl_set_gtp_opt(nla_opt_msk, mask,
+ msk_depth, option_len,
+ extack);
+ if (option_len < 0)
+ return option_len;
+
+ mask->enc_opts.len += option_len;
+ if (key->enc_opts.len != mask->enc_opts.len) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Key and mask miss aligned");
+ return -EINVAL;
+ }
+ break;
default:
NL_SET_ERR_MSG(extack, "Unknown tunnel option type");
return -EINVAL;
@@ -2761,6 +2844,34 @@ nla_put_failure:
return -EMSGSIZE;
}
+static int fl_dump_key_gtp_opt(struct sk_buff *skb,
+ struct flow_dissector_key_enc_opts *enc_opts)
+
+{
+ struct gtp_pdu_session_info *session_info;
+ struct nlattr *nest;
+
+ nest = nla_nest_start_noflag(skb, TCA_FLOWER_KEY_ENC_OPTS_GTP);
+ if (!nest)
+ goto nla_put_failure;
+
+ session_info = (struct gtp_pdu_session_info *)&enc_opts->data[0];
+
+ if (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_GTP_PDU_TYPE,
+ session_info->pdu_type))
+ goto nla_put_failure;
+
+ if (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_GTP_QFI, session_info->qfi))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, nest);
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(skb, nest);
+ return -EMSGSIZE;
+}
+
static int fl_dump_key_ct(struct sk_buff *skb,
struct flow_dissector_key_ct *key,
struct flow_dissector_key_ct *mask)
@@ -2824,6 +2935,11 @@ static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type,
if (err)
goto nla_put_failure;
break;
+ case TUNNEL_GTP_OPT:
+ err = fl_dump_key_gtp_opt(skb, enc_opts);
+ if (err)
+ goto nla_put_failure;
+ break;
default:
goto nla_put_failure;
}
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 179825a3b2fd..e3c0e8ea2dbb 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -301,7 +301,7 @@ struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle)
if (!handle)
return NULL;
- q = qdisc_match_from_root(dev->qdisc, handle);
+ q = qdisc_match_from_root(rtnl_dereference(dev->qdisc), handle);
if (q)
goto out;
@@ -320,7 +320,7 @@ struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle)
if (!handle)
return NULL;
- q = qdisc_match_from_root(dev->qdisc, handle);
+ q = qdisc_match_from_root(rcu_dereference(dev->qdisc), handle);
if (q)
goto out;
@@ -1082,10 +1082,10 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
skip:
if (!ingress) {
notify_and_destroy(net, skb, n, classid,
- dev->qdisc, new);
+ rtnl_dereference(dev->qdisc), new);
if (new && !new->ops->attach)
qdisc_refcount_inc(new);
- dev->qdisc = new ? : &noop_qdisc;
+ rcu_assign_pointer(dev->qdisc, new ? : &noop_qdisc);
if (new && new->ops->attach)
new->ops->attach(new);
@@ -1451,7 +1451,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
q = dev_ingress_queue(dev)->qdisc_sleeping;
}
} else {
- q = dev->qdisc;
+ q = rtnl_dereference(dev->qdisc);
}
if (!q) {
NL_SET_ERR_MSG(extack, "Cannot find specified qdisc on specified device");
@@ -1540,7 +1540,7 @@ replay:
q = dev_ingress_queue(dev)->qdisc_sleeping;
}
} else {
- q = dev->qdisc;
+ q = rtnl_dereference(dev->qdisc);
}
/* It may be default qdisc, ignore it */
@@ -1762,7 +1762,8 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb)
s_q_idx = 0;
q_idx = 0;
- if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx,
+ if (tc_dump_qdisc_root(rtnl_dereference(dev->qdisc),
+ skb, cb, &q_idx, s_q_idx,
true, tca[TCA_DUMP_INVISIBLE]) < 0)
goto done;
@@ -2033,7 +2034,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n,
} else if (qid1) {
qid = qid1;
} else if (qid == 0)
- qid = dev->qdisc->handle;
+ qid = rtnl_dereference(dev->qdisc)->handle;
/* Now qid is genuine qdisc handle consistent
* both with parent and child.
@@ -2044,7 +2045,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n,
portid = TC_H_MAKE(qid, portid);
} else {
if (qid == 0)
- qid = dev->qdisc->handle;
+ qid = rtnl_dereference(dev->qdisc)->handle;
}
/* OK. Locate qdisc */
@@ -2205,7 +2206,8 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb)
s_t = cb->args[0];
t = 0;
- if (tc_dump_tclass_root(dev->qdisc, skb, tcm, cb, &t, s_t, true) < 0)
+ if (tc_dump_tclass_root(rtnl_dereference(dev->qdisc),
+ skb, tcm, cb, &t, s_t, true) < 0)
goto done;
dev_queue = dev_ingress_queue(dev);
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index f893d9a81b01..5bab9f8b8f45 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -1164,30 +1164,33 @@ static void attach_default_qdiscs(struct net_device *dev)
if (!netif_is_multiqueue(dev) ||
dev->priv_flags & IFF_NO_QUEUE) {
netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL);
- dev->qdisc = txq->qdisc_sleeping;
- qdisc_refcount_inc(dev->qdisc);
+ qdisc = txq->qdisc_sleeping;
+ rcu_assign_pointer(dev->qdisc, qdisc);
+ qdisc_refcount_inc(qdisc);
} else {
qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT, NULL);
if (qdisc) {
- dev->qdisc = qdisc;
+ rcu_assign_pointer(dev->qdisc, qdisc);
qdisc->ops->attach(qdisc);
}
}
+ qdisc = rtnl_dereference(dev->qdisc);
/* Detect default qdisc setup/init failed and fallback to "noqueue" */
- if (dev->qdisc == &noop_qdisc) {
+ if (qdisc == &noop_qdisc) {
netdev_warn(dev, "default qdisc (%s) fail, fallback to %s\n",
default_qdisc_ops->id, noqueue_qdisc_ops.id);
dev->priv_flags |= IFF_NO_QUEUE;
netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL);
- dev->qdisc = txq->qdisc_sleeping;
- qdisc_refcount_inc(dev->qdisc);
+ qdisc = txq->qdisc_sleeping;
+ rcu_assign_pointer(dev->qdisc, qdisc);
+ qdisc_refcount_inc(qdisc);
dev->priv_flags ^= IFF_NO_QUEUE;
}
#ifdef CONFIG_NET_SCHED
- if (dev->qdisc != &noop_qdisc)
- qdisc_hash_add(dev->qdisc, false);
+ if (qdisc != &noop_qdisc)
+ qdisc_hash_add(qdisc, false);
#endif
}
@@ -1217,7 +1220,7 @@ void dev_activate(struct net_device *dev)
* and noqueue_qdisc for virtual interfaces
*/
- if (dev->qdisc == &noop_qdisc)
+ if (rtnl_dereference(dev->qdisc) == &noop_qdisc)
attach_default_qdiscs(dev);
if (!netif_carrier_ok(dev))
@@ -1383,7 +1386,7 @@ static int qdisc_change_tx_queue_len(struct net_device *dev,
void dev_qdisc_change_real_num_tx(struct net_device *dev,
unsigned int new_real_tx)
{
- struct Qdisc *qdisc = dev->qdisc;
+ struct Qdisc *qdisc = rtnl_dereference(dev->qdisc);
if (qdisc->ops->change_real_num_tx)
qdisc->ops->change_real_num_tx(qdisc, new_real_tx);
@@ -1447,7 +1450,7 @@ static void dev_init_scheduler_queue(struct net_device *dev,
void dev_init_scheduler(struct net_device *dev)
{
- dev->qdisc = &noop_qdisc;
+ rcu_assign_pointer(dev->qdisc, &noop_qdisc);
netdev_for_each_tx_queue(dev, dev_init_scheduler_queue, &noop_qdisc);
if (dev_ingress_queue(dev))
dev_init_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc);
@@ -1475,8 +1478,8 @@ void dev_shutdown(struct net_device *dev)
netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc);
if (dev_ingress_queue(dev))
shutdown_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc);
- qdisc_put(dev->qdisc);
- dev->qdisc = &noop_qdisc;
+ qdisc_put(rtnl_dereference(dev->qdisc));
+ rcu_assign_pointer(dev->qdisc, &noop_qdisc);
WARN_ON(timer_pending(&dev->watchdog_timer));
}
generated by cgit v1.2.3 (git 2.46.0) at 2025-11-28 23:08:39 +0000