@@ -71,6 +71,7 @@ CONFIG_NET_IPGRE=y
CONFIG_NET_IPGRE_DEMUX=y
CONFIG_NET_IPIP=y
CONFIG_NET_MPLS_GSO=y
+CONFIG_NET_SCH_BPF=y
CONFIG_NET_SCH_FQ=y
CONFIG_NET_SCH_INGRESS=y
CONFIG_NET_SCHED=y
new file mode 100644
@@ -0,0 +1,79 @@
+#include <linux/pkt_sched.h>
+#include <linux/rtnetlink.h>
+#include <test_progs.h>
+
+#include "network_helpers.h"
+#include "bpf_qdisc_fifo.skel.h"
+
+#define LO_IFINDEX 1
+
+static const unsigned int total_bytes = 10 * 1024 * 1024;
+
+static void do_test(char *qdisc)
+{
+ DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = LO_IFINDEX,
+ .attach_point = BPF_TC_QDISC,
+ .parent = TC_H_ROOT,
+ .handle = 0x8000000,
+ .qdisc = qdisc);
+ int srv_fd = -1, cli_fd = -1;
+ int err;
+
+ err = bpf_tc_hook_create(&hook);
+ if (!ASSERT_OK(err, "attach qdisc"))
+ return;
+
+ srv_fd = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0);
+ if (!ASSERT_OK_FD(srv_fd, "start server"))
+ goto done;
+
+ cli_fd = connect_to_fd(srv_fd, 0);
+ if (!ASSERT_OK_FD(cli_fd, "connect to client"))
+ goto done;
+
+ err = send_recv_data(srv_fd, cli_fd, total_bytes);
+ ASSERT_OK(err, "send_recv_data");
+
+done:
+ if (srv_fd != -1)
+ close(srv_fd);
+ if (cli_fd != -1)
+ close(cli_fd);
+
+ bpf_tc_hook_destroy(&hook);
+}
+
+static void test_fifo(void)
+{
+ struct bpf_qdisc_fifo *fifo_skel;
+ struct bpf_link *link;
+
+ fifo_skel = bpf_qdisc_fifo__open_and_load();
+ if (!ASSERT_OK_PTR(fifo_skel, "bpf_qdisc_fifo__open_and_load"))
+ return;
+
+ link = bpf_map__attach_struct_ops(fifo_skel->maps.fifo);
+ if (!ASSERT_OK_PTR(link, "bpf_map__attach_struct_ops")) {
+ bpf_qdisc_fifo__destroy(fifo_skel);
+ return;
+ }
+
+ do_test("bpf_fifo");
+
+ bpf_link__destroy(link);
+ bpf_qdisc_fifo__destroy(fifo_skel);
+}
+
+void test_bpf_qdisc(void)
+{
+ struct netns_obj *netns;
+
+ netns = netns_new("bpf_qdisc_ns", true);
+ if (!ASSERT_OK_PTR(netns, "netns_new"))
+ return;
+
+ if (test__start_subtest("fifo"))
+ test_fifo();
+
+ netns_free(netns);
+}
new file mode 100644
@@ -0,0 +1,27 @@
+#ifndef _BPF_QDISC_COMMON_H
+#define _BPF_QDISC_COMMON_H
+
+#define NET_XMIT_SUCCESS 0x00
+#define NET_XMIT_DROP 0x01 /* skb dropped */
+#define NET_XMIT_CN 0x02 /* congestion notification */
+
+#define TC_PRIO_CONTROL 7
+#define TC_PRIO_MAX 15
+
+u32 bpf_skb_get_hash(struct sk_buff *p) __ksym;
+void bpf_kfree_skb(struct sk_buff *p) __ksym;
+void bpf_qdisc_skb_drop(struct sk_buff *p, struct bpf_sk_buff_ptr *to_free) __ksym;
+void bpf_qdisc_watchdog_schedule(struct Qdisc *sch, u64 expire, u64 delta_ns) __ksym;
+void bpf_qdisc_bstats_update(struct Qdisc *sch, const struct sk_buff *skb) __ksym;
+
+static struct qdisc_skb_cb *qdisc_skb_cb(const struct sk_buff *skb)
+{
+ return (struct qdisc_skb_cb *)skb->cb;
+}
+
+static inline unsigned int qdisc_pkt_len(const struct sk_buff *skb)
+{
+ return qdisc_skb_cb(skb)->pkt_len;
+}
+
+#endif
new file mode 100644
@@ -0,0 +1,117 @@
+#include <vmlinux.h>
+#include "bpf_experimental.h"
+#include "bpf_qdisc_common.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct skb_node {
+ struct sk_buff __kptr * skb;
+ struct bpf_list_node node;
+};
+
+#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8)))
+
+private(A) struct bpf_spin_lock q_fifo_lock;
+private(A) struct bpf_list_head q_fifo __contains(skb_node, node);
+
+SEC("struct_ops/bpf_fifo_enqueue")
+int BPF_PROG(bpf_fifo_enqueue, struct sk_buff *skb, struct Qdisc *sch,
+ struct bpf_sk_buff_ptr *to_free)
+{
+ struct skb_node *skbn;
+ u32 pkt_len;
+
+ if (sch->q.qlen == sch->limit)
+ goto drop;
+
+ skbn = bpf_obj_new(typeof(*skbn));
+ if (!skbn)
+ goto drop;
+
+ pkt_len = qdisc_pkt_len(skb);
+
+ sch->q.qlen++;
+ skb = bpf_kptr_xchg(&skbn->skb, skb);
+ if (skb)
+ bpf_qdisc_skb_drop(skb, to_free);
+
+ bpf_spin_lock(&q_fifo_lock);
+ bpf_list_push_back(&q_fifo, &skbn->node);
+ bpf_spin_unlock(&q_fifo_lock);
+
+ sch->qstats.backlog += pkt_len;
+ return NET_XMIT_SUCCESS;
+drop:
+ bpf_qdisc_skb_drop(skb, to_free);
+ return NET_XMIT_DROP;
+}
+
+SEC("struct_ops/bpf_fifo_dequeue")
+struct sk_buff *BPF_PROG(bpf_fifo_dequeue, struct Qdisc *sch)
+{
+ struct bpf_list_node *node;
+ struct sk_buff *skb = NULL;
+ struct skb_node *skbn;
+
+ bpf_spin_lock(&q_fifo_lock);
+ node = bpf_list_pop_front(&q_fifo);
+ bpf_spin_unlock(&q_fifo_lock);
+ if (!node)
+ return NULL;
+
+ skbn = container_of(node, struct skb_node, node);
+ skb = bpf_kptr_xchg(&skbn->skb, skb);
+ bpf_obj_drop(skbn);
+ if (!skb)
+ return NULL;
+
+ sch->qstats.backlog -= qdisc_pkt_len(skb);
+ bpf_qdisc_bstats_update(sch, skb);
+ sch->q.qlen--;
+
+ return skb;
+}
+
+SEC("struct_ops/bpf_fifo_init")
+int BPF_PROG(bpf_fifo_init, struct Qdisc *sch, struct nlattr *opt,
+ struct netlink_ext_ack *extack)
+{
+ sch->limit = 1000;
+ return 0;
+}
+
+SEC("struct_ops/bpf_fifo_reset")
+void BPF_PROG(bpf_fifo_reset, struct Qdisc *sch)
+{
+ struct bpf_list_node *node;
+ struct skb_node *skbn;
+ int i;
+
+ bpf_for(i, 0, sch->q.qlen) {
+ struct sk_buff *skb = NULL;
+
+ bpf_spin_lock(&q_fifo_lock);
+ node = bpf_list_pop_front(&q_fifo);
+ bpf_spin_unlock(&q_fifo_lock);
+
+ if (!node)
+ break;
+
+ skbn = container_of(node, struct skb_node, node);
+ skb = bpf_kptr_xchg(&skbn->skb, skb);
+ if (skb)
+ bpf_kfree_skb(skb);
+ bpf_obj_drop(skbn);
+ }
+ sch->q.qlen = 0;
+}
+
+SEC(".struct_ops")
+struct Qdisc_ops fifo = {
+ .enqueue = (void *)bpf_fifo_enqueue,
+ .dequeue = (void *)bpf_fifo_dequeue,
+ .init = (void *)bpf_fifo_init,
+ .reset = (void *)bpf_fifo_reset,
+ .id = "bpf_fifo",
+};
+