net_sched: introduce eBPF based Qdisc

Signed-off-by: Cong Wang <cong.wang@bytedance.com>

include/linux/bpf_types.h

@@ -8,6 +8,8 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act,
 	      struct __sk_buff, struct sk_buff)
 BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act,
 	      struct __sk_buff, struct sk_buff)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_QDISC, tc_qdisc,
+	      struct __sk_buff, struct sk_buff)
 BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp,
 	      struct xdp_md, struct xdp_buff)
 #ifdef CONFIG_CGROUP_BPF

include/uapi/linux/bpf.h

@@ -953,6 +953,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_LSM,
 	BPF_PROG_TYPE_SK_LOOKUP,
 	BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */
+	BPF_PROG_TYPE_SCHED_QDISC,
 };
 
 enum bpf_attach_type {
@@ -6679,4 +6680,18 @@ struct bpf_core_relo {
 	enum bpf_core_relo_kind kind;
 };
 
+struct sch_bpf_ctx {
+	struct __sk_buff *skb;
+	__u32 classid;
+	__u64 delay;
+};
+
+enum {
+	SCH_BPF_OK,
+	SCH_BPF_QUEUED,
+	SCH_BPF_DROP,
+	SCH_BPF_THROTTLE,
+	SCH_BPF_CONTINUE,
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */

include/uapi/linux/pkt_sched.h

@@ -1267,4 +1267,21 @@ enum {
 
 #define TCA_ETS_MAX (__TCA_ETS_MAX - 1)
 
+#define TCA_SCH_BPF_FLAG_DIRECT _BITUL(0)
+enum {
+	TCA_SCH_BPF_UNSPEC,
+	TCA_SCH_BPF_FLAGS,		/* u32 */
+	TCA_SCH_BPF_ENQUEUE_PROG_NAME,	/* string */
+	TCA_SCH_BPF_ENQUEUE_PROG_FD,	/* u32 */
+	TCA_SCH_BPF_ENQUEUE_PROG_ID,	/* u32 */
+	TCA_SCH_BPF_ENQUEUE_PROG_TAG,	/* data */
+	TCA_SCH_BPF_DEQUEUE_PROG_NAME,	/* string */
+	TCA_SCH_BPF_DEQUEUE_PROG_FD,	/* u32 */
+	TCA_SCH_BPF_DEQUEUE_PROG_ID,	/* u32 */
+	TCA_SCH_BPF_DEQUEUE_PROG_TAG,	/* data */
+	__TCA_SCH_BPF_MAX,
+};
+
+#define TCA_SCH_BPF_MAX (__TCA_SCH_BPF_MAX - 1)
+
 #endif

net/core/filter.c

@@ -7813,6 +7813,19 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	}
 }
 
+static const struct bpf_func_proto *
+tc_qdisc_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+	switch (func_id) {
+	case BPF_FUNC_skb_map_push:
+		return &bpf_skb_map_push_proto;
+	case BPF_FUNC_skb_map_pop:
+		return &bpf_skb_map_pop_proto;
+	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)
 {
@@ -10476,6 +10489,18 @@ const struct bpf_prog_ops tc_cls_act_prog_ops = {
 	.test_run		= bpf_prog_test_run_skb,
 };
 
+const struct bpf_verifier_ops tc_qdisc_verifier_ops = {
+	.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,
+	.gen_ld_abs		= bpf_gen_ld_abs,
+};
+
+const struct bpf_prog_ops tc_qdisc_prog_ops = {
+	.test_run		= bpf_prog_test_run_skb,
+};
+
 const struct bpf_verifier_ops xdp_verifier_ops = {
 	.get_func_proto		= xdp_func_proto,
 	.is_valid_access	= xdp_is_valid_access,

net/sched/Kconfig

@@ -439,6 +439,21 @@ config NET_SCH_ETS
 
 	  If unsure, say N.
 
+config NET_SCH_BPF
+	tristate "eBPF based programmable queue discipline"
+	help
+	  This eBPF based queue discipline offers a way to program your
+	  own packet scheduling algorithm. This is a classful qdisc which
+	  also allows you to decide the hierarchy.
+
+	  Say Y here if you want to use the eBPF based programmable queue
+	  discipline.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called sch_bpf.
+
+	  If unsure, say N.
+
 menuconfig NET_SCH_DEFAULT
 	bool "Allow override default queue discipline"
 	help

net/sched/Makefile

@@ -65,6 +65,7 @@ obj-$(CONFIG_NET_SCH_FQ_PIE)	+= sch_fq_pie.o
 obj-$(CONFIG_NET_SCH_CBS)	+= sch_cbs.o
 obj-$(CONFIG_NET_SCH_ETF)	+= sch_etf.o
 obj-$(CONFIG_NET_SCH_TAPRIO)	+= sch_taprio.o
+obj-$(CONFIG_NET_SCH_BPF)	+= sch_bpf.o
 
 obj-$(CONFIG_NET_CLS_U32)	+= cls_u32.o
 obj-$(CONFIG_NET_CLS_ROUTE4)	+= cls_route.o