From: Cong Wang <cong.wang@xxxxxxxxxxxxx>
Introduce an eBPF helper function bpf_skb_tc_classify() to reuse exising
TC filters on *any* Qdisc to classify the skb.
Signed-off-by: Cong Wang <cong.wang@xxxxxxxxxxxxx>
---
include/uapi/linux/bpf.h | 1 +
net/core/filter.c | 17 +++++++++-
net/sched/cls_api.c | 69 ++++++++++++++++++++++++++++++++++++++++
3 files changed, 86 insertions(+), 1 deletion(-)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c21fd1f189bc..7ed04736c4e4 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5650,6 +5650,7 @@ union bpf_attr {
FN(tcp_raw_check_syncookie_ipv6), \
FN(ktime_get_tai_ns), \
FN(user_ringbuf_drain), \
+ FN(skb_tc_classify), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/net/core/filter.c b/net/core/filter.c
index 7a271b77a2cc..d1ed60114794 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7926,6 +7926,21 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
}
}
+const struct bpf_func_proto bpf_skb_tc_classify_proto __weak;
+
+static const struct bpf_func_proto *
+tc_qdisc_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+ switch (func_id) {
+#ifdef CONFIG_NET_CLS_ACT
+ case BPF_FUNC_skb_tc_classify:
+ return &bpf_skb_tc_classify_proto;
+#endif
+ default:
+ return tc_cls_act_func_proto(func_id, prog);
+ }
+}
+
static const struct bpf_func_proto *
xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
@@ -10656,7 +10671,7 @@ const struct bpf_prog_ops tc_cls_act_prog_ops = {
};
const struct bpf_verifier_ops tc_qdisc_verifier_ops = {
- .get_func_proto = tc_cls_act_func_proto,
+ .get_func_proto = tc_qdisc_func_proto,
.is_valid_access = tc_cls_act_is_valid_access,
.convert_ctx_access = tc_cls_act_convert_ctx_access,
.gen_prologue = tc_cls_act_prologue,
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 50566db45949..64470a8947b1 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -22,6 +22,7 @@
#include <linux/idr.h>
#include <linux/jhash.h>
#include <linux/rculist.h>
+#include <linux/filter.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/netlink.h>
@@ -1655,6 +1656,74 @@ int tcf_classify(struct sk_buff *skb,
}
EXPORT_SYMBOL(tcf_classify);
+#ifdef CONFIG_BPF_SYSCALL
+BPF_CALL_3(bpf_skb_tc_classify, struct sk_buff *, skb, int, ifindex, u32, handle)
+{
+ struct net *net = dev_net(skb->dev);
+ const struct Qdisc_class_ops *cops;
+ struct tcf_result res = {};
+ struct tcf_block *block;
+ struct tcf_chain *chain;
+ struct net_device *dev;
+ unsigned long cl = 0;
+ struct Qdisc *q;
+ int result;
+
+ rcu_read_lock();
+ dev = dev_get_by_index_rcu(net, ifindex);
+ if (!dev)
+ goto out;
+ q = qdisc_lookup_rcu(dev, handle);
+ if (!q)
+ goto out;
+
+ cops = q->ops->cl_ops;
+ if (!cops)
+ goto out;
+ if (!cops->tcf_block)
+ goto out;
+ if (TC_H_MIN(handle)) {
+ cl = cops->find(q, handle);
+ if (cl == 0)
+ goto out;
+ }
+ block = cops->tcf_block(q, cl, NULL);
+ if (!block)
+ goto out;
+
+ for (chain = tcf_get_next_chain(block, NULL);
+ chain;
+ chain = tcf_get_next_chain(block, chain)) {
+ struct tcf_proto *tp;
+
+ result = tcf_classify(skb, NULL, tp, &res, false);
+ if (result >= 0) {
+ switch (result) {
+ case TC_ACT_QUEUED:
+ case TC_ACT_STOLEN:
+ case TC_ACT_TRAP:
+ fallthrough;
+ case TC_ACT_SHOT:
+ rcu_read_unlock();
+ return 0;
+ }
+ }
+ }
+out:
+ rcu_read_unlock();
+ return res.class;
+}
+
+const struct bpf_func_proto bpf_skb_tc_classify_proto = {
+ .func = bpf_skb_tc_classify,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_ANYTHING,
+};
+#endif
+
struct tcf_chain_info {
struct tcf_proto __rcu **pprev;
struct tcf_proto __rcu *next;
--
2.34.1
