diff mbox series

[bpf-next,v1,05/13] bpf: net_sched: Support implementation of Qdisc_ops in bpf

Message ID 20241213232958.2388301-6-amery.hung@bytedance.com (mailing list archive)
State Changes Requested
Delegated to: BPF
Headers show
Series bpf qdisc | expand

Checks

Context Check Description
netdev/tree_selection success Clearly marked for bpf-next, async
netdev/apply fail Patch does not apply to bpf-next-0
bpf/vmtest-bpf-net-VM_Test-0 success Logs for Lint
bpf/vmtest-bpf-net-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-net-VM_Test-3 success Logs for Validate matrix.py
bpf/vmtest-bpf-net-VM_Test-2 success Logs for Unittests
bpf/vmtest-bpf-net-VM_Test-5 success Logs for aarch64-gcc / build-release
bpf/vmtest-bpf-net-VM_Test-9 success Logs for aarch64-gcc / test (test_verifier, false, 360) / test_verifier on aarch64 with gcc
bpf/vmtest-bpf-net-VM_Test-10 success Logs for aarch64-gcc / veristat-kernel
bpf/vmtest-bpf-net-VM_Test-4 success Logs for aarch64-gcc / build / build for aarch64 with gcc
bpf/vmtest-bpf-net-VM_Test-11 success Logs for aarch64-gcc / veristat-meta
bpf/vmtest-bpf-net-VM_Test-13 success Logs for s390x-gcc / build-release
bpf/vmtest-bpf-net-VM_Test-6 success Logs for aarch64-gcc / test (test_maps, false, 360) / test_maps on aarch64 with gcc
bpf/vmtest-bpf-net-VM_Test-12 success Logs for s390x-gcc / build / build for s390x with gcc
bpf/vmtest-bpf-net-VM_Test-16 success Logs for s390x-gcc / test (test_verifier, false, 360) / test_verifier on s390x with gcc
bpf/vmtest-bpf-net-VM_Test-17 success Logs for s390x-gcc / veristat-kernel
bpf/vmtest-bpf-net-VM_Test-18 success Logs for s390x-gcc / veristat-meta
bpf/vmtest-bpf-net-VM_Test-19 success Logs for set-matrix
bpf/vmtest-bpf-net-VM_Test-20 success Logs for x86_64-gcc / build / build for x86_64 with gcc
bpf/vmtest-bpf-net-VM_Test-21 success Logs for x86_64-gcc / build-release
bpf/vmtest-bpf-net-VM_Test-22 success Logs for x86_64-gcc / test (test_maps, false, 360) / test_maps on x86_64 with gcc
bpf/vmtest-bpf-net-VM_Test-25 success Logs for x86_64-gcc / test (test_progs_no_alu32_parallel, true, 30) / test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-net-VM_Test-26 success Logs for x86_64-gcc / test (test_progs_parallel, true, 30) / test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-net-VM_Test-27 success Logs for x86_64-gcc / test (test_verifier, false, 360) / test_verifier on x86_64 with gcc
bpf/vmtest-bpf-net-VM_Test-28 success Logs for x86_64-gcc / veristat-kernel / x86_64-gcc veristat_kernel
bpf/vmtest-bpf-net-VM_Test-29 fail Logs for x86_64-gcc / veristat-meta / x86_64-gcc veristat_meta
bpf/vmtest-bpf-net-VM_Test-30 success Logs for x86_64-llvm-17 / build / build for x86_64 with llvm-17
bpf/vmtest-bpf-net-VM_Test-31 success Logs for x86_64-llvm-17 / build-release / build for x86_64 with llvm-17-O2
bpf/vmtest-bpf-net-VM_Test-32 success Logs for x86_64-llvm-17 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-17
bpf/vmtest-bpf-net-VM_Test-33 success Logs for x86_64-llvm-17 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-17
bpf/vmtest-bpf-net-VM_Test-34 success Logs for x86_64-llvm-17 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-17
bpf/vmtest-bpf-net-VM_Test-35 success Logs for x86_64-llvm-17 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-17
bpf/vmtest-bpf-net-VM_Test-36 success Logs for x86_64-llvm-17 / veristat-kernel
bpf/vmtest-bpf-net-VM_Test-37 success Logs for x86_64-llvm-17 / veristat-meta
bpf/vmtest-bpf-net-VM_Test-38 success Logs for x86_64-llvm-18 / build / build for x86_64 with llvm-18
bpf/vmtest-bpf-net-VM_Test-39 success Logs for x86_64-llvm-18 / build-release / build for x86_64 with llvm-18-O2
bpf/vmtest-bpf-net-VM_Test-40 success Logs for x86_64-llvm-18 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-18
bpf/vmtest-bpf-net-VM_Test-44 success Logs for x86_64-llvm-18 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-18
bpf/vmtest-bpf-net-VM_Test-45 success Logs for x86_64-llvm-18 / veristat-kernel
bpf/vmtest-bpf-net-VM_Test-46 success Logs for x86_64-llvm-18 / veristat-meta
bpf/vmtest-bpf-net-VM_Test-7 success Logs for aarch64-gcc / test (test_progs, false, 360) / test_progs on aarch64 with gcc
bpf/vmtest-bpf-net-VM_Test-8 success Logs for aarch64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-net-VM_Test-15 success Logs for s390x-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on s390x with gcc
bpf/vmtest-bpf-net-VM_Test-23 success Logs for x86_64-gcc / test (test_progs, false, 360) / test_progs on x86_64 with gcc
bpf/vmtest-bpf-net-VM_Test-24 success Logs for x86_64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-net-VM_Test-41 success Logs for x86_64-llvm-18 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-18
bpf/vmtest-bpf-net-VM_Test-42 success Logs for x86_64-llvm-18 / test (test_progs_cpuv4, false, 360) / test_progs_cpuv4 on x86_64 with llvm-18
bpf/vmtest-bpf-net-VM_Test-43 success Logs for x86_64-llvm-18 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-18
bpf/vmtest-bpf-net-PR fail PR summary
bpf/vmtest-bpf-net-VM_Test-14 success Logs for s390x-gcc / test (test_progs, false, 360) / test_progs on s390x with gcc

Commit Message

Amery Hung Dec. 13, 2024, 11:29 p.m. UTC 
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.

Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Co-developed-by: Amery Hung <amery.hung@bytedance.com>
Signed-off-by: Amery Hung <amery.hung@bytedance.com>
---
 include/linux/btf.h     |   1 +
 kernel/bpf/btf.c        |   4 +-
 net/sched/Kconfig       |  12 +++
 net/sched/Makefile      |   1 +
 net/sched/bpf_qdisc.c   | 214 ++++++++++++++++++++++++++++++++++++++++
 net/sched/sch_api.c     |   7 +-
 net/sched/sch_generic.c |   3 +-
 7 files changed, 236 insertions(+), 6 deletions(-)
 create mode 100644 net/sched/bpf_qdisc.c

Comments

Cong Wang Dec. 14, 2024, 4:51 a.m. UTC | #1 
On Fri, Dec 13, 2024 at 11:29:50PM +0000, Amery Hung wrote:
> diff --git a/include/linux/btf.h b/include/linux/btf.h
> index 4214e76c9168..eb16218fdf52 100644
> --- a/include/linux/btf.h
> +++ b/include/linux/btf.h
> @@ -563,6 +563,7 @@ const char *btf_name_by_offset(const struct btf *btf, u32 offset);
>  const char *btf_str_by_offset(const struct btf *btf, u32 offset);
>  struct btf *btf_parse_vmlinux(void);
>  struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog);
> +u32 get_ctx_arg_idx(struct btf *btf, const struct btf_type *func_proto, int off);
>  u32 *btf_kfunc_id_set_contains(const struct btf *btf, u32 kfunc_btf_id,
>  			       const struct bpf_prog *prog);
>  u32 *btf_kfunc_is_modify_return(const struct btf *btf, u32 kfunc_btf_id,
> diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
> index a05ccf9ee032..f733dbf24261 100644
> --- a/kernel/bpf/btf.c
> +++ b/kernel/bpf/btf.c
> @@ -6375,8 +6375,8 @@ static bool is_int_ptr(struct btf *btf, const struct btf_type *t)
>  	return btf_type_is_int(t);
>  }
>  
> -static u32 get_ctx_arg_idx(struct btf *btf, const struct btf_type *func_proto,
> -			   int off)
> +u32 get_ctx_arg_idx(struct btf *btf, const struct btf_type *func_proto,
> +		    int off)
>  {
>  	const struct btf_param *args;
>  	const struct btf_type *t;

Maybe separate this piece out as a separate patch?


> 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

I think new features should be default to n, unless you have reasons not
to do so.

> +	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/sch_api.c b/net/sched/sch_api.c
> index 2eefa4783879..f074053c4232 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;
>  			}
> @@ -1287,7 +1288,7 @@ 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 +1399,7 @@ 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 38ec18f73de4..1e770ec251a0 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>
> @@ -1083,7 +1084,7 @@ 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);

Maybe this piece should be separated out too? Ideally this patch should
only have bpf_qdisc.c and its Makefile and Kconfig changes.

Regards.
Martin KaFai Lau Dec. 18, 2024, 11:37 p.m. UTC | #2 
On 12/13/24 3:29 PM, Amery Hung wrote:
> +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, priv_size):
> +		if (uqdisc_ops->priv_size)

bpf_struct_ops_map_update_elem() has enforced non function pointer member must 
be zero if ->init_member() returns 0, so this check is unnecessary.

> +			return -EINVAL;
> +		return 1;
> +	case offsetof(struct Qdisc_ops, static_flags):
> +		if (uqdisc_ops->static_flags)

Same here.

case priv_size and static_flags should be not needed, just return 0.

> +			return -EINVAL;
> +		return 1;
> +	case offsetof(struct Qdisc_ops, peek):
> +		if (!uqdisc_ops->peek)

bpf_struct_ops_map_update_elem() will assign the trampoline (that will call the 
bpf prog) to qdisc_ops->peek if the "u"qdisc_ops->peek has the prog fd.

This test is not necessary also.

> +			qdisc_ops->peek = qdisc_peek_dequeued;

Always do this assignment



> +		return 1;

and return 0 here. Allow the bpf_struct_ops_map_update_elem() to do the needed 
fd testing instead and reassign the qdisc_ops->peek with the trampoline if needed.

> +	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;
> +}
diff mbox series

Patch

diff --git a/include/linux/btf.h b/include/linux/btf.h
index 4214e76c9168..eb16218fdf52 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -563,6 +563,7 @@  const char *btf_name_by_offset(const struct btf *btf, u32 offset);
 const char *btf_str_by_offset(const struct btf *btf, u32 offset);
 struct btf *btf_parse_vmlinux(void);
 struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog);
+u32 get_ctx_arg_idx(struct btf *btf, const struct btf_type *func_proto, int off);
 u32 *btf_kfunc_id_set_contains(const struct btf *btf, u32 kfunc_btf_id,
 			       const struct bpf_prog *prog);
 u32 *btf_kfunc_is_modify_return(const struct btf *btf, u32 kfunc_btf_id,
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index a05ccf9ee032..f733dbf24261 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6375,8 +6375,8 @@  static bool is_int_ptr(struct btf *btf, const struct btf_type *t)
 	return btf_type_is_int(t);
 }
 
-static u32 get_ctx_arg_idx(struct btf *btf, const struct btf_type *func_proto,
-			   int off)
+u32 get_ctx_arg_idx(struct btf *btf, const struct btf_type *func_proto,
+		    int off)
 {
 	const struct btf_param *args;
 	const struct btf_type *t;
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..a2e2db29e5fc
--- /dev/null
+++ b/net/sched/bpf_qdisc.c
@@ -0,0 +1,214 @@ 
+#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)
+{
+	switch (func_id) {
+	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 = get_ctx_arg_idx(btf, prog->aux->attach_func_proto, off);
+	if (!strcmp(prog->aux->attach_func_name, "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, priv_size):
+		if (uqdisc_ops->priv_size)
+			return -EINVAL;
+		return 1;
+	case offsetof(struct Qdisc_ops, static_flags):
+		if (uqdisc_ops->static_flags)
+			return -EINVAL;
+		return 1;
+	case offsetof(struct Qdisc_ops, peek):
+		if (!uqdisc_ops->peek)
+			qdisc_ops->peek = qdisc_peek_dequeued;
+		return 1;
+	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 2eefa4783879..f074053c4232 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;
 			}
@@ -1287,7 +1288,7 @@  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 +1399,7 @@  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 38ec18f73de4..1e770ec251a0 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>
@@ -1083,7 +1084,7 @@  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);