netdev - [RFC PATCH v7 2/8] net_sched: Add kfuncs for working with skb

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <2d31261b245828d09d2f80e0953e911a9c38573a.1705432850.git.amery.hung@bytedance.com>
Date: Wed, 17 Jan 2024 21:56:18 +0000
From: Amery Hung <ameryhung@...il.com>
To: netdev@...r.kernel.org
Cc: bpf@...r.kernel.org,
	yangpeihao@...u.edu.cn,
	toke@...hat.com,
	jhs@...atatu.com,
	jiri@...nulli.us,
	sdf@...gle.com,
	xiyou.wangcong@...il.com,
	yepeilin.cs@...il.com
Subject: [RFC PATCH v7 2/8] net_sched: Add kfuncs for working with skb

From: Cong Wang <cong.wang@...edance.com>

This patch introduces four kfuncs available to developers:

struct sk_buff *bpf_skb_acquire(struct sk_buff *skb);
void bpf_skb_release(struct sk_buff *skb);
bool bpf_qdisc_set_skb_dequeue(struct sk_buff *skb);
u32 bpf_skb_get_hash(struct sk_buff *skb)

kptr is used to ensure the vailidility of skbs throughout their lifetime
in eBPF qdiscs. First, in the enqueue program, bpf_skb_acquire() can be
used to acquire a referenced kptr to an skb from ctx->skb. Then, it can
be stored in bpf maps or allocated objects serving as queues. Otherwise,
the program should call bpf_skb_release() to release the reference.
Finally, in the dequeue program, a skb kptr can be exchanged out of
queues and passed to bpf_qdisc_set_skb_dequeue() to set the skb to be
dequeued. The kfunc will also release the reference.

Since skb kptr is incompatible with helpers taking __sk_buff,
bpf_skb_get_hash() is added for now for the ease of implementing
flow-based queueing algorithms.

Signed-off-by: Cong Wang <cong.wang@...edance.com>
Co-developed-by: Amery Hung <amery.hung@...edance.com>
Signed-off-by: Amery Hung <amery.hung@...edance.com>
---
 net/sched/sch_bpf.c | 83 ++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 82 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_bpf.c b/net/sched/sch_bpf.c
index 56f3ab9c6059..b0e7c3a19c30 100644
--- a/net/sched/sch_bpf.c
+++ b/net/sched/sch_bpf.c
@@ -15,6 +15,7 @@
 #include <linux/slab.h>
 #include <linux/filter.h>
 #include <linux/bpf.h>
+#include <linux/btf_ids.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
 #include <net/pkt_cls.h>
@@ -520,9 +521,89 @@ static struct Qdisc_ops sch_bpf_qdisc_ops __read_mostly = {
 	.owner		=	THIS_MODULE,
 };
 
+__diag_push();
+__diag_ignore_all("-Wmissing-prototypes",
+		  "Global functions as their definitions will be in vmlinux BTF");
+
+/* bpf_skb_acquire - Acquire a reference to an skb. An skb acquired by this
+ * kfunc which is not stored in a map as a kptr, must be released by calling
+ * bpf_skb_release().
+ * @skb: The skb on which a reference is being acquired.
+ */
+__bpf_kfunc struct sk_buff *bpf_skb_acquire(struct sk_buff *skb)
+{
+	return skb_get(skb);
+}
+
+/* bpf_skb_release - Release the reference acquired on an skb.
+ * @skb: The skb on which a reference is being released.
+ */
+__bpf_kfunc void bpf_skb_release(struct sk_buff *skb)
+{
+	skb_unref(skb);
+}
+
+/* bpf_skb_destroy - Release an skb reference acquired and exchanged into
+ * an allocated object or a map.
+ * @skb: The skb on which a reference is being released.
+ */
+__bpf_kfunc void bpf_skb_destroy(struct sk_buff *skb)
+{
+	skb_unref(skb);
+	consume_skb(skb);
+}
+
+/* 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_qdisc_set_skb_dequeue - Set the skb to be dequeued. This will also
+ * release the reference to the skb.
+ * @skb: The skb to be dequeued by the qdisc.
+ */
+__bpf_kfunc void bpf_qdisc_set_skb_dequeue(struct sk_buff *skb)
+{
+	consume_skb(skb);
+	__this_cpu_write(bpf_skb_dequeue, skb);
+}
+
+__diag_pop();
+
+BTF_SET8_START(skb_kfunc_btf_ids)
+BTF_ID_FLAGS(func, bpf_skb_acquire, KF_ACQUIRE)
+BTF_ID_FLAGS(func, bpf_skb_release, KF_RELEASE)
+BTF_ID_FLAGS(func, bpf_skb_get_hash)
+BTF_ID_FLAGS(func, bpf_qdisc_set_skb_dequeue, KF_RELEASE)
+BTF_SET8_END(skb_kfunc_btf_ids)
+
+static const struct btf_kfunc_id_set skb_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set   = &skb_kfunc_btf_ids,
+};
+
+BTF_ID_LIST(skb_kfunc_dtor_ids)
+BTF_ID(struct, sk_buff)
+BTF_ID_FLAGS(func, bpf_skb_destroy, KF_RELEASE)
+
 static int __init sch_bpf_mod_init(void)
 {
-	return register_qdisc(&sch_bpf_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_QDISC, &skb_kfunc_set);
+	ret = ret ?: register_btf_id_dtor_kfuncs(skb_kfunc_dtors,
+						 ARRAY_SIZE(skb_kfunc_dtors),
+						 THIS_MODULE);
+	return ret ?: register_qdisc(&sch_bpf_qdisc_ops);
 }
 
 static void __exit sch_bpf_mod_exit(void)
-- 
2.20.1