[RFC PATCH 12/17] bpf: Add helper to schedule an interface for TX dequeue

["Toke Høiland-Jørgensen" <toke@redhat.com>]

This adds a helper that a BPF program can call to schedule an interface for
transmission. The helper can be used from both a regular XDP program (to
schedule transmission after queueing a packet), and from a dequeue program
to (re-)schedule transmission after a dequeue operation. In particular, the
latter use can be combined with BPF timers to schedule delayed
transmission, for instance to implement traffic shaping.

The helper always schedules transmission on the interface on the current
CPU. For cross-CPU operation, it is up to the BPF program to arrange for
the helper to be called on the appropriate CPU, either by configuring
hardware RSS appropriately, or by using a cpumap. Likewise, it is up to the
BPF programs to decide whether to use separate queues per CPU (by using
multiple maps to queue packets in), or accept the lock contention of using
a single map across CPUs.

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
---
 include/uapi/linux/bpf.h       | 11 +++++++
 net/core/filter.c              | 52 ++++++++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h | 11 +++++++
 3 files changed, 74 insertions(+)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d44382644391..b352ecc280f4 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5358,6 +5358,16 @@ union bpf_attr {
  *		*bpf_packet_dequeue()* (and checked to not be NULL).
  *	Return
  *		This always succeeds and returns zero.
+ *
+ * long bpf_schedule_iface_dequeue(void *ctx, int ifindex, int flags)
+ *	Description
+ *		Schedule the interface with index *ifindex* for transmission from
+ *		its dequeue program as soon as possible. The *flags* argument
+ *		must be zero.
+ *
+ *	Return
+ *		Returns zero on success, or -ENOENT if no dequeue program is
+ *		loaded on the interface.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5570,6 +5580,7 @@ union bpf_attr {
 	FN(tcp_raw_check_syncookie_ipv6),	\
 	FN(packet_dequeue),		\
 	FN(packet_drop),		\
+	FN(schedule_iface_dequeue),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/net/core/filter.c b/net/core/filter.c
index 7c89eaa01c29..bb556d873b52 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4431,6 +4431,54 @@ static const struct bpf_func_proto bpf_xdp_redirect_map_proto = {
 	.arg3_type      = ARG_ANYTHING,
 };
 
+static int bpf_schedule_iface_dequeue(struct net *net, int ifindex, int flags)
+{
+	struct net_device *dev;
+	struct bpf_prog *prog;
+
+	if (flags)
+		return -EINVAL;
+
+	dev = dev_get_by_index_rcu(net, ifindex);
+	if (!dev)
+		return -ENODEV;
+
+	prog = rcu_dereference(dev->xdp_dequeue_prog);
+	if (!prog)
+		return -ENOENT;
+
+	dev_schedule_xdp_dequeue(dev);
+	return 0;
+}
+
+BPF_CALL_3(bpf_xdp_schedule_iface_dequeue, struct xdp_buff *, ctx, int, ifindex, int, flags)
+{
+	return bpf_schedule_iface_dequeue(dev_net(ctx->rxq->dev), ifindex, flags);
+}
+
+static const struct bpf_func_proto bpf_xdp_schedule_iface_dequeue_proto = {
+	.func           = bpf_xdp_schedule_iface_dequeue,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_ANYTHING,
+	.arg3_type      = ARG_ANYTHING,
+};
+
+BPF_CALL_3(bpf_dequeue_schedule_iface_dequeue, struct dequeue_data *, ctx, int, ifindex, int, flags)
+{
+	return bpf_schedule_iface_dequeue(dev_net(ctx->txq->dev), ifindex, flags);
+}
+
+static const struct bpf_func_proto bpf_dequeue_schedule_iface_dequeue_proto = {
+	.func           = bpf_dequeue_schedule_iface_dequeue,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_ANYTHING,
+	.arg3_type      = ARG_ANYTHING,
+};
+
 BTF_ID_LIST_SINGLE(xdp_md_btf_ids, struct, xdp_md)
 
 BPF_CALL_4(bpf_packet_dequeue, struct dequeue_data *, ctx, struct bpf_map *, map,
@@ -8068,6 +8116,8 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_xdp_fib_lookup_proto;
 	case BPF_FUNC_check_mtu:
 		return &bpf_xdp_check_mtu_proto;
+	case BPF_FUNC_schedule_iface_dequeue:
+		return &bpf_xdp_schedule_iface_dequeue_proto;
 #ifdef CONFIG_INET
 	case BPF_FUNC_sk_lookup_udp:
 		return &bpf_xdp_sk_lookup_udp_proto;
@@ -8105,6 +8155,8 @@ dequeue_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_packet_dequeue_proto;
 	case BPF_FUNC_packet_drop:
 		return &bpf_packet_drop_proto;
+	case BPF_FUNC_schedule_iface_dequeue:
+		return &bpf_dequeue_schedule_iface_dequeue_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 1dab68a89e18..9eb9a5b52c76 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5358,6 +5358,16 @@ union bpf_attr {
  *		*bpf_packet_dequeue()* (and checked to not be NULL).
  *	Return
  *		This always succeeds and returns zero.
+ *
+ * long bpf_schedule_iface_dequeue(void *ctx, int ifindex, int flags)
+ *	Description
+ *		Schedule the interface with index *ifindex* for transmission from
+ *		its dequeue program as soon as possible. The *flags* argument
+ *		must be zero.
+ *
+ *	Return
+ *		Returns zero on success, or -ENOENT if no dequeue program is
+ *		loaded on the interface.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5570,6 +5580,7 @@ union bpf_attr {
 	FN(tcp_raw_check_syncookie_ipv6),	\
 	FN(packet_dequeue),		\
 	FN(packet_drop),		\
+	FN(schedule_iface_dequeue),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
2.37.0