Add kfuncs for working on skb in qdisc.
Both bpf_qdisc_skb_drop() and bpf_skb_release() can be used to release
a reference to an skb. However, bpf_qdisc_skb_drop() can only be called
in .enqueue where a to_free skb list is available from kernel to defer
the release. Otherwise, bpf_skb_release() should be used elsewhere. It
is also used in bpf_obj_free_fields() when cleaning up skb in maps and
collections.
bpf_qdisc_schedule() can be used to schedule the execution of the qdisc.
An example use case is to throttle a qdisc if the time to dequeue the
next packet is known.
bpf_skb_get_hash() returns the flow hash of an skb, which can be used
to build flow-based queueing algorithms.
Signed-off-by: Amery Hung <amery.hung@xxxxxxxxxxxxx>
---
net/sched/bpf_qdisc.c | 74 ++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 73 insertions(+), 1 deletion(-)
diff --git a/net/sched/bpf_qdisc.c b/net/sched/bpf_qdisc.c
index a68fc115d8f8..eff7559aa346 100644
--- a/net/sched/bpf_qdisc.c
+++ b/net/sched/bpf_qdisc.c
@@ -148,6 +148,64 @@ static int bpf_qdisc_btf_struct_access(struct bpf_verifier_log *log,
return 0;
}
+__bpf_kfunc_start_defs();
+
+/* bpf_skb_get_hash - Get the flow hash of an skb.
+ * @skb: The skb to get the flow hash from.
+ */
+__bpf_kfunc u32 bpf_skb_get_hash(struct sk_buff *skb)
+{
+ return skb_get_hash(skb);
+}
+
+/* bpf_skb_release - Release an skb reference acquired on an skb immediately.
+ * @skb: The skb on which a reference is being released.
+ */
+__bpf_kfunc void bpf_skb_release(struct sk_buff *skb)
+{
+ consume_skb(skb);
+}
+
+/* bpf_qdisc_skb_drop - Add an skb to be dropped later to a list.
+ * @skb: The skb on which a reference is being released and dropped.
+ * @to_free_list: The list of skbs to be dropped.
+ */
+__bpf_kfunc void bpf_qdisc_skb_drop(struct sk_buff *skb,
+ struct bpf_sk_buff_ptr *to_free_list)
+{
+ __qdisc_drop(skb, (struct sk_buff **)to_free_list);
+}
+
+/* bpf_qdisc_watchdog_schedule - Schedule a qdisc to a later time using a timer.
+ * @sch: The qdisc to be scheduled.
+ * @expire: The expiry time of the timer.
+ * @delta_ns: The slack range of the timer.
+ */
+__bpf_kfunc void bpf_qdisc_watchdog_schedule(struct Qdisc *sch, u64 expire, u64 delta_ns)
+{
+ struct bpf_sched_data *q = qdisc_priv(sch);
+
+ qdisc_watchdog_schedule_range_ns(&q->watchdog, expire, delta_ns);
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(bpf_qdisc_kfunc_ids)
+BTF_ID_FLAGS(func, bpf_skb_get_hash)
+BTF_ID_FLAGS(func, bpf_skb_release, KF_RELEASE)
+BTF_ID_FLAGS(func, bpf_qdisc_skb_drop, KF_RELEASE)
+BTF_ID_FLAGS(func, bpf_qdisc_watchdog_schedule)
+BTF_KFUNCS_END(bpf_qdisc_kfunc_ids)
+
+static const struct btf_kfunc_id_set bpf_qdisc_kfunc_set = {
+ .owner = THIS_MODULE,
+ .set = &bpf_qdisc_kfunc_ids,
+};
+
+BTF_ID_LIST(skb_kfunc_dtor_ids)
+BTF_ID(struct, sk_buff)
+BTF_ID_FLAGS(func, bpf_skb_release, KF_RELEASE)
+
static const struct bpf_verifier_ops bpf_qdisc_verifier_ops = {
.get_func_proto = bpf_qdisc_get_func_proto,
.is_valid_access = bpf_qdisc_is_valid_access,
@@ -347,6 +405,20 @@ static struct bpf_struct_ops bpf_Qdisc_ops = {
static int __init bpf_qdisc_kfunc_init(void)
{
- return register_bpf_struct_ops(&bpf_Qdisc_ops, Qdisc_ops);
+ int ret;
+ const struct btf_id_dtor_kfunc skb_kfunc_dtors[] = {
+ {
+ .btf_id = skb_kfunc_dtor_ids[0],
+ .kfunc_btf_id = skb_kfunc_dtor_ids[1]
+ },
+ };
+
+ ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_qdisc_kfunc_set);
+ ret = ret ?: register_btf_id_dtor_kfuncs(skb_kfunc_dtors,
+ ARRAY_SIZE(skb_kfunc_dtors),
+ THIS_MODULE);
+ ret = ret ?: register_bpf_struct_ops(&bpf_Qdisc_ops, Qdisc_ops);
+
+ return ret;
}
late_initcall(bpf_qdisc_kfunc_init);
--
2.20.1
