Message-ID: <20250131192912.133796-9-ameryhung@gmail.com>
Date: Fri, 31 Jan 2025 11:28:47 -0800
From: Amery Hung <ameryhung@...il.com>
To: netdev@...r.kernel.org
Cc: bpf@...r.kernel.org,
	daniel@...earbox.net,
	andrii@...nel.org,
	alexei.starovoitov@...il.com,
	martin.lau@...nel.org,
	kuba@...nel.org,
	edumazet@...gle.com,
	xiyou.wangcong@...il.com,
	cong.wang@...edance.com,
	jhs@...atatu.com,
	sinquersw@...il.com,
	toke@...hat.com,
	jiri@...nulli.us,
	stfomichev@...il.com,
	ekarani.silvestre@....ufcg.edu.br,
	yangpeihao@...u.edu.cn,
	yepeilin.cs@...il.com,
	ameryhung@...il.com,
	ming.lei@...hat.com,
	kernel-team@...a.com
Subject: [PATCH bpf-next v3 08/18] bpf: net_sched: Support implementation of Qdisc_ops in bpf

From: Amery Hung <amery.hung@...edance.com>

Enable users to implement a classless qdisc using bpf. The last few
patches in this series has prepared struct_ops to support core operators
in Qdisc_ops. The recent advancement in bpf such as allocated
objects, bpf list and bpf rbtree has also provided powerful and flexible
building blocks to realize sophisticated scheduling algorithms. Therefore,
in this patch, we start allowing qdisc to be implemented using bpf
struct_ops. Users can implement Qdisc_ops.{enqueue, dequeue, init, reset,
and .destroy in Qdisc_ops in bpf and register the qdisc dynamically into
the kernel.

We do not allow users to attach bpf qdiscs to classful qdiscs. This is to
prevent accidentally breaking existings clasful qdiscs if they rely on
some data in the child qdisc. This restrication can potentially be lifted
in the future. Note that, we still allow bpf qdisc to be attached to mq.

Co-developed-by: Cong Wang <cong.wang@...edance.com>
Signed-off-by: Cong Wang <cong.wang@...edance.com>
Signed-off-by: Amery Hung <amery.hung@...edance.com>
---
 net/sched/Kconfig       |  12 +++
 net/sched/Makefile      |   1 +
 net/sched/bpf_qdisc.c   | 210 ++++++++++++++++++++++++++++++++++++++++
 net/sched/sch_api.c     |  14 ++-
 net/sched/sch_generic.c |   3 +-
 5 files changed, 236 insertions(+), 4 deletions(-)
 create mode 100644 net/sched/bpf_qdisc.c

diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 8180d0c12fce..ccd0255da5a5 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -403,6 +403,18 @@ config NET_SCH_ETS
 
 	  If unsure, say N.
 
+config NET_SCH_BPF
+	bool "BPF-based Qdisc"
+	depends on BPF_SYSCALL && BPF_JIT && DEBUG_INFO_BTF
+	help
+	  This option allows BPF-based queueing disiplines. With BPF struct_ops,
+	  users can implement supported operators in Qdisc_ops using BPF programs.
+	  The queue holding skb can be built with BPF maps or graphs.
+
+	  Say Y here if you want to use BPF-based Qdisc.
+
+	  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
index 82c3f78ca486..904d784902d1 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -62,6 +62,7 @@ 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)	+= bpf_qdisc.o
 
 obj-$(CONFIG_NET_CLS_U32)	+= cls_u32.o
 obj-$(CONFIG_NET_CLS_ROUTE4)	+= cls_route.o
diff --git a/net/sched/bpf_qdisc.c b/net/sched/bpf_qdisc.c
new file mode 100644
index 000000000000..00f3232f4a98
--- /dev/null
+++ b/net/sched/bpf_qdisc.c
@@ -0,0 +1,210 @@
+#include <linux/types.h>
+#include <linux/bpf_verifier.h>
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/filter.h>
+#include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
+
+static struct bpf_struct_ops bpf_Qdisc_ops;
+
+struct bpf_sk_buff_ptr {
+	struct sk_buff *skb;
+};
+
+static int bpf_qdisc_init(struct btf *btf)
+{
+	return 0;
+}
+
+static const struct bpf_func_proto *
+bpf_qdisc_get_func_proto(enum bpf_func_id func_id,
+			 const struct bpf_prog *prog)
+{
+	/* Tail call is disabled since there is no gaurantee valid refcounted
+	 * kptrs will always be passed to another bpf program with __ref arguments.
+	 */
+	switch (func_id) {
+	case BPF_FUNC_tail_call:
+		return NULL;
+	default:
+		return bpf_base_func_proto(func_id, prog);
+	}
+}
+
+BTF_ID_LIST_SINGLE(bpf_sk_buff_ids, struct, sk_buff)
+BTF_ID_LIST_SINGLE(bpf_sk_buff_ptr_ids, struct, bpf_sk_buff_ptr)
+
+static bool bpf_qdisc_is_valid_access(int off, int size,
+				      enum bpf_access_type type,
+				      const struct bpf_prog *prog,
+				      struct bpf_insn_access_aux *info)
+{
+	struct btf *btf = prog->aux->attach_btf;
+	u32 arg;
+
+	arg = btf_ctx_arg_idx(btf, prog->aux->attach_func_proto, off);
+	if (bpf_struct_ops_prog_moff(prog) == offsetof(struct Qdisc_ops, enqueue)) {
+		if (arg == 2 && type == BPF_READ) {
+			info->reg_type = PTR_TO_BTF_ID | PTR_TRUSTED;
+			info->btf = btf;
+			info->btf_id = bpf_sk_buff_ptr_ids[0];
+			return true;
+		}
+	}
+
+	return bpf_tracing_btf_ctx_access(off, size, type, prog, info);
+}
+
+static int bpf_qdisc_btf_struct_access(struct bpf_verifier_log *log,
+					const struct bpf_reg_state *reg,
+					int off, int size)
+{
+	const struct btf_type *t, *skbt;
+	size_t end;
+
+	skbt = btf_type_by_id(reg->btf, bpf_sk_buff_ids[0]);
+	t = btf_type_by_id(reg->btf, reg->btf_id);
+	if (t != skbt) {
+		bpf_log(log, "only read is supported\n");
+		return -EACCES;
+	}
+
+	switch (off) {
+	case offsetof(struct sk_buff, tstamp):
+		end = offsetofend(struct sk_buff, tstamp);
+		break;
+	case offsetof(struct sk_buff, priority):
+		end = offsetofend(struct sk_buff, priority);
+		break;
+	case offsetof(struct sk_buff, mark):
+		end = offsetofend(struct sk_buff, mark);
+		break;
+	case offsetof(struct sk_buff, queue_mapping):
+		end = offsetofend(struct sk_buff, queue_mapping);
+		break;
+	case offsetof(struct sk_buff, cb) + offsetof(struct qdisc_skb_cb, tc_classid):
+		end = offsetof(struct sk_buff, cb) +
+		      offsetofend(struct qdisc_skb_cb, tc_classid);
+		break;
+	case offsetof(struct sk_buff, cb) + offsetof(struct qdisc_skb_cb, data[0]) ...
+	     offsetof(struct sk_buff, cb) + offsetof(struct qdisc_skb_cb,
+						     data[QDISC_CB_PRIV_LEN - 1]):
+		end = offsetof(struct sk_buff, cb) +
+		      offsetofend(struct qdisc_skb_cb, data[QDISC_CB_PRIV_LEN - 1]);
+		break;
+	case offsetof(struct sk_buff, tc_index):
+		end = offsetofend(struct sk_buff, tc_index);
+		break;
+	default:
+		bpf_log(log, "no write support to sk_buff at off %d\n", off);
+		return -EACCES;
+	}
+
+	if (off + size > end) {
+		bpf_log(log,
+			"write access at off %d with size %d beyond the member of sk_buff ended at %zu\n",
+			off, size, end);
+		return -EACCES;
+	}
+
+	return 0;
+}
+
+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,
+	.btf_struct_access	= bpf_qdisc_btf_struct_access,
+};
+
+static int bpf_qdisc_init_member(const struct btf_type *t,
+				 const struct btf_member *member,
+				 void *kdata, const void *udata)
+{
+	const struct Qdisc_ops *uqdisc_ops;
+	struct Qdisc_ops *qdisc_ops;
+	u32 moff;
+
+	uqdisc_ops = (const struct Qdisc_ops *)udata;
+	qdisc_ops = (struct Qdisc_ops *)kdata;
+
+	moff = __btf_member_bit_offset(t, member) / 8;
+	switch (moff) {
+	case offsetof(struct Qdisc_ops, peek):
+		qdisc_ops->peek = qdisc_peek_dequeued;
+		return 0;
+	case offsetof(struct Qdisc_ops, id):
+		if (bpf_obj_name_cpy(qdisc_ops->id, uqdisc_ops->id,
+				     sizeof(qdisc_ops->id)) <= 0)
+			return -EINVAL;
+		return 1;
+	}
+
+	return 0;
+}
+
+static int bpf_qdisc_reg(void *kdata, struct bpf_link *link)
+{
+	return register_qdisc(kdata);
+}
+
+static void bpf_qdisc_unreg(void *kdata, struct bpf_link *link)
+{
+	return unregister_qdisc(kdata);
+}
+
+static int Qdisc_ops__enqueue(struct sk_buff *skb__ref, struct Qdisc *sch,
+			      struct sk_buff **to_free)
+{
+	return 0;
+}
+
+static struct sk_buff *Qdisc_ops__dequeue(struct Qdisc *sch)
+{
+	return NULL;
+}
+
+static struct sk_buff *Qdisc_ops__peek(struct Qdisc *sch)
+{
+	return NULL;
+}
+
+static int Qdisc_ops__init(struct Qdisc *sch, struct nlattr *arg,
+			   struct netlink_ext_ack *extack)
+{
+	return 0;
+}
+
+static void Qdisc_ops__reset(struct Qdisc *sch)
+{
+}
+
+static void Qdisc_ops__destroy(struct Qdisc *sch)
+{
+}
+
+static struct Qdisc_ops __bpf_ops_qdisc_ops = {
+	.enqueue = Qdisc_ops__enqueue,
+	.dequeue = Qdisc_ops__dequeue,
+	.peek = Qdisc_ops__peek,
+	.init = Qdisc_ops__init,
+	.reset = Qdisc_ops__reset,
+	.destroy = Qdisc_ops__destroy,
+};
+
+static struct bpf_struct_ops bpf_Qdisc_ops = {
+	.verifier_ops = &bpf_qdisc_verifier_ops,
+	.reg = bpf_qdisc_reg,
+	.unreg = bpf_qdisc_unreg,
+	.init_member = bpf_qdisc_init_member,
+	.init = bpf_qdisc_init,
+	.name = "Qdisc_ops",
+	.cfi_stubs = &__bpf_ops_qdisc_ops,
+	.owner = THIS_MODULE,
+};
+
+static int __init bpf_qdisc_kfunc_init(void)
+{
+	return register_bpf_struct_ops(&bpf_Qdisc_ops, Qdisc_ops);
+}
+late_initcall(bpf_qdisc_kfunc_init);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index e3e91cf867eb..c8057e0692a6 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -25,6 +25,7 @@
 #include <linux/hrtimer.h>
 #include <linux/slab.h>
 #include <linux/hashtable.h>
+#include <linux/bpf.h>
 
 #include <net/net_namespace.h>
 #include <net/sock.h>
@@ -358,7 +359,7 @@ static struct Qdisc_ops *qdisc_lookup_ops(struct nlattr *kind)
 		read_lock(&qdisc_mod_lock);
 		for (q = qdisc_base; q; q = q->next) {
 			if (nla_strcmp(kind, q->id) == 0) {
-				if (!try_module_get(q->owner))
+				if (!bpf_try_module_get(q, q->owner))
 					q = NULL;
 				break;
 			}
@@ -1200,6 +1201,13 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
 			return -EINVAL;
 		}
 
+		if (new &&
+		    !(parent->flags & TCQ_F_MQROOT) &&
+		    new->ops->owner == BPF_MODULE_OWNER) {
+			NL_SET_ERR_MSG(extack, "BPF qdisc not supported on a non root");
+			return -EINVAL;
+		}
+
 		if (new &&
 		    !(parent->flags & TCQ_F_MQROOT) &&
 		    rcu_access_pointer(new->stab)) {
@@ -1287,7 +1295,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev,
 				/* We will try again qdisc_lookup_ops,
 				 * so don't keep a reference.
 				 */
-				module_put(ops->owner);
+				bpf_module_put(ops, ops->owner);
 				err = -EAGAIN;
 				goto err_out;
 			}
@@ -1398,7 +1406,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev,
 	netdev_put(dev, &sch->dev_tracker);
 	qdisc_free(sch);
 err_out2:
-	module_put(ops->owner);
+	bpf_module_put(ops, ops->owner);
 err_out:
 	*errp = err;
 	return NULL;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 14ab2f4c190a..e6fda9f20272 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -24,6 +24,7 @@
 #include <linux/if_vlan.h>
 #include <linux/skb_array.h>
 #include <linux/if_macvlan.h>
+#include <linux/bpf.h>
 #include <net/sch_generic.h>
 #include <net/pkt_sched.h>
 #include <net/dst.h>
@@ -1078,7 +1079,7 @@ static void __qdisc_destroy(struct Qdisc *qdisc)
 		ops->destroy(qdisc);
 
 	lockdep_unregister_key(&qdisc->root_lock_key);
-	module_put(ops->owner);
+	bpf_module_put(ops, ops->owner);
 	netdev_put(dev, &qdisc->dev_tracker);
 
 	trace_qdisc_destroy(qdisc);
-- 
2.47.1

Powered by blists - more mailing lists