net_sched: introduce eBPF based Qdisc

Signed-off-by: Cong Wang <cong.wang@bytedance.com>
congwang · Sep 11, 2021 · 4705634 · 4705634
1 parent 90df3fc
commit 4705634
Show file tree

Hide file tree

Showing 7 changed files with 683 additions and 0 deletions.
diff --git a/include/linux/bpf_types.h b/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_cls_act,
+//	      struct __sk_buff, struct sk_buff)
 BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp,
 	      struct xdp_md, struct xdp_buff)
 #ifdef CONFIG_CGROUP_BPF

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
@@ -36,6 +36,7 @@
 #include <linux/splice.h>
 #include <linux/in6.h>
 #include <linux/if_packet.h>
+#include <linux/priority_queue.h>
 #include <net/flow.h>
 #include <net/page_pool.h>
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
@@ -735,6 +736,7 @@ struct sk_buff {
 			};
 		};
 		struct rb_node		rbnode; /* used in netem, ip4 defrag, and tcp stack */
+		struct pq_node		pqnode; /* used in ebpf qdisc */
 		struct list_head	list;
 	};
 

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
@@ -949,6 +949,7 @@ 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 {
@@ -6260,4 +6261,23 @@ enum {
 	BTF_F_ZERO	=	(1ULL << 3),
 };
 
+struct sch_bpf_ctx {
+	/* Input */
+	struct __sk_buff *skb;
+	__u32 nr_flows;
+	__u32 handle;
+
+	/* Output */
+	__u64 rank;
+	__u64 delay;
+	__u32 classid;
+};
+
+enum {
+	SCH_BPF_OK,
+	SCH_BPF_REQUEUE,
+	SCH_BPF_DROP,
+	SCH_BPF_THROTTLE,
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
@@ -1263,4 +1263,25 @@ enum {
 
 #define TCA_ETS_MAX (__TCA_ETS_MAX - 1)
 
+enum {
+	TCA_SCH_BPF_UNSPEC,
+	TCA_SCH_BPF_MODE,		/* 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)
+
+enum {
+	TCA_SCH_BPF_MODE_DEFAULT,
+	__TCA_SCH_BPF_MODE_MAX,
+};
+
 #endif
diff --git a/net/sched/Kconfig b/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

diff --git a/net/sched/Makefile b/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