[bpf-next,v4,11/19] bpf: net_sched: Add a qdisc watchdog timer

Commit Message

Amery Hung Feb. 10, 2025, 5:43 p.m. UTC

From: Amery Hung <[e-mail]>

Add a watchdog timer to bpf qdisc. The watchdog can be used to schedule
the execution of qdisc through kfunc, bpf_qdisc_schedule(). It can be
useful for building traffic shaping scheduling algorithm, where the time
the next packet will be dequeued is known.

Signed-off-by: Amery Hung <[e-mail]>
---
 include/linux/filter.h | 10 +++++
 net/sched/bpf_qdisc.c  | 92 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 102 insertions(+)

Patch

diff --git a/include/linux/filter.h b/include/linux/filter.h
index a3ea46281595..3ed6eb9e7c73 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -469,6 +469,16 @@  static inline bool insn_is_cast_user(const struct bpf_insn *insn)
 		.off   = 0,					\
 		.imm   = BPF_CALL_IMM(FUNC) })
 
+/* Kfunc call */
+
+#define BPF_CALL_KFUNC(OFF, IMM)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_JMP | BPF_CALL,			\
+		.dst_reg = 0,					\
+		.src_reg = BPF_PSEUDO_KFUNC_CALL,		\
+		.off   = OFF,					\
+		.imm   = IMM })
+
 /* Raw code statement block */
 
 #define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM)			\
diff --git a/net/sched/bpf_qdisc.c b/net/sched/bpf_qdisc.c
index 69a1d547390c..ae06637f4bab 100644
--- a/net/sched/bpf_qdisc.c
+++ b/net/sched/bpf_qdisc.c
@@ -8,6 +8,10 @@ 
 
 static struct bpf_struct_ops bpf_Qdisc_ops;
 
+struct bpf_sched_data {
+	struct qdisc_watchdog watchdog;
+};
+
 struct bpf_sk_buff_ptr {
 	struct sk_buff *skb;
 };
@@ -111,6 +115,46 @@  static int bpf_qdisc_btf_struct_access(struct bpf_verifier_log *log,
 	return 0;
 }
 
+BTF_ID_LIST(bpf_qdisc_init_prologue_ids)
+BTF_ID(func, bpf_qdisc_init_prologue)
+
+static int bpf_qdisc_gen_prologue(struct bpf_insn *insn_buf, bool direct_write,
+				  const struct bpf_prog *prog)
+{
+	struct bpf_insn *insn = insn_buf;
+
+	if (bpf_struct_ops_prog_moff(prog) != offsetof(struct Qdisc_ops, init))
+		return 0;
+
+	*insn++ = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1);
+	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 0);
+	*insn++ = BPF_CALL_KFUNC(0, bpf_qdisc_init_prologue_ids[0]);
+	*insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6);
+	*insn++ = prog->insnsi[0];
+
+	return insn - insn_buf;
+}
+
+BTF_ID_LIST(bpf_qdisc_reset_destroy_epilogue_ids)
+BTF_ID(func, bpf_qdisc_reset_destroy_epilogue)
+
+static int bpf_qdisc_gen_epilogue(struct bpf_insn *insn_buf, const struct bpf_prog *prog,
+				  s16 ctx_stack_off)
+{
+	struct bpf_insn *insn = insn_buf;
+
+	if (bpf_struct_ops_prog_moff(prog) != offsetof(struct Qdisc_ops, reset) &&
+	    bpf_struct_ops_prog_moff(prog) != offsetof(struct Qdisc_ops, destroy))
+		return 0;
+
+	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_FP, ctx_stack_off);
+	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 0);
+	*insn++ = BPF_CALL_KFUNC(0, bpf_qdisc_reset_destroy_epilogue_ids[0]);
+	*insn++ = BPF_EXIT_INSN();
+
+	return insn - insn_buf;
+}
+
 __bpf_kfunc_start_defs();
 
 /* bpf_skb_get_hash - Get the flow hash of an skb.
@@ -139,6 +183,36 @@  __bpf_kfunc void bpf_qdisc_skb_drop(struct sk_buff *skb,
 	__qdisc_drop(skb, (struct sk_buff **)to_free_list);
 }
 
+/* bpf_qdisc_watchdog_schedule - Schedule a qdisc to a later time using a timer.
+ * @sch: The qdisc to be scheduled.
+ * @expire: The expiry time of the timer.
+ * @delta_ns: The slack range of the timer.
+ */
+__bpf_kfunc void bpf_qdisc_watchdog_schedule(struct Qdisc *sch, u64 expire, u64 delta_ns)
+{
+	struct bpf_sched_data *q = qdisc_priv(sch);
+
+	qdisc_watchdog_schedule_range_ns(&q->watchdog, expire, delta_ns);
+}
+
+/* bpf_qdisc_init_prologue - Hidden kfunc called in prologue of .init. */
+__bpf_kfunc void bpf_qdisc_init_prologue(struct Qdisc *sch)
+{
+	struct bpf_sched_data *q = qdisc_priv(sch);
+
+	qdisc_watchdog_init(&q->watchdog, sch);
+}
+
+/* bpf_qdisc_reset_destroy_epilogue - Hidden kfunc called in epilogue of .reset
+ * and .destroy
+ */
+__bpf_kfunc void bpf_qdisc_reset_destroy_epilogue(struct Qdisc *sch)
+{
+	struct bpf_sched_data *q = qdisc_priv(sch);
+
+	qdisc_watchdog_cancel(&q->watchdog);
+}
+
 __bpf_kfunc_end_defs();
 
 BTF_KFUNCS_START(qdisc_kfunc_ids)
@@ -146,6 +220,9 @@  BTF_ID_FLAGS(func, bpf_skb_get_hash, KF_TRUSTED_ARGS)
 BTF_ID_FLAGS(func, bpf_kfree_skb, KF_RELEASE)
 BTF_ID_FLAGS(func, bpf_qdisc_skb_drop, KF_RELEASE)
 BTF_ID_FLAGS(func, bpf_dynptr_from_skb, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_qdisc_watchdog_schedule, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_qdisc_init_prologue, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_qdisc_reset_destroy_epilogue, KF_TRUSTED_ARGS)
 BTF_KFUNCS_END(qdisc_kfunc_ids)
 
 BTF_SET_START(qdisc_common_kfunc_set)
@@ -156,8 +233,13 @@  BTF_SET_END(qdisc_common_kfunc_set)
 
 BTF_SET_START(qdisc_enqueue_kfunc_set)
 BTF_ID(func, bpf_qdisc_skb_drop)
+BTF_ID(func, bpf_qdisc_watchdog_schedule)
 BTF_SET_END(qdisc_enqueue_kfunc_set)
 
+BTF_SET_START(qdisc_dequeue_kfunc_set)
+BTF_ID(func, bpf_qdisc_watchdog_schedule)
+BTF_SET_END(qdisc_dequeue_kfunc_set)
+
 static int bpf_qdisc_kfunc_filter(const struct bpf_prog *prog, u32 kfunc_id)
 {
 	if (bpf_Qdisc_ops.type != btf_type_by_id(prog->aux->attach_btf,
@@ -174,6 +256,9 @@  static int bpf_qdisc_kfunc_filter(const struct bpf_prog *prog, u32 kfunc_id)
 	if (bpf_struct_ops_prog_moff(prog) == offsetof(struct Qdisc_ops, enqueue)) {
 		if (btf_id_set_contains(&qdisc_enqueue_kfunc_set, kfunc_id))
 			return 0;
+	} else if (bpf_struct_ops_prog_moff(prog) == offsetof(struct Qdisc_ops, dequeue)) {
+		if (btf_id_set_contains(&qdisc_dequeue_kfunc_set, kfunc_id))
+			return 0;
 	}
 
 	return btf_id_set_contains(&qdisc_common_kfunc_set, kfunc_id) ? 0 : -EACCES;
@@ -189,6 +274,8 @@  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,
+	.gen_prologue		= bpf_qdisc_gen_prologue,
+	.gen_epilogue		= bpf_qdisc_gen_epilogue,
 };
 
 static int bpf_qdisc_init_member(const struct btf_type *t,
@@ -204,6 +291,11 @@  static int bpf_qdisc_init_member(const struct btf_type *t,
 
 	moff = __btf_member_bit_offset(t, member) / 8;
 	switch (moff) {
+	case offsetof(struct Qdisc_ops, priv_size):
+		if (uqdisc_ops->priv_size)
+			return -EINVAL;
+		qdisc_ops->priv_size = sizeof(struct bpf_sched_data);
+		return 1;
 	case offsetof(struct Qdisc_ops, peek):
 		qdisc_ops->peek = qdisc_peek_dequeued;
 		return 0;