From: Amery Hung <amery.hung@xxxxxxxxxxxxx> This selftest shows a bare minimum fifo qdisc, which simply enqueues skbs into the back of a bpf list and dequeues from the front of the list. Signed-off-by: Amery Hung <amery.hung@xxxxxxxxxxxxx> --- tools/testing/selftests/bpf/config | 1 + .../selftests/bpf/prog_tests/bpf_qdisc.c | 161 ++++++++++++++++++ .../selftests/bpf/progs/bpf_qdisc_common.h | 27 +++ .../selftests/bpf/progs/bpf_qdisc_fifo.c | 117 +++++++++++++ 4 files changed, 306 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/bpf_qdisc.c create mode 100644 tools/testing/selftests/bpf/progs/bpf_qdisc_common.h create mode 100644 tools/testing/selftests/bpf/progs/bpf_qdisc_fifo.c diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index c378d5d07e02..6b0cab55bd2d 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -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 diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_qdisc.c b/tools/testing/selftests/bpf/prog_tests/bpf_qdisc.c new file mode 100644 index 000000000000..295d0216e70f --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_qdisc.c @@ -0,0 +1,161 @@ +#include <linux/pkt_sched.h> +#include <linux/rtnetlink.h> +#include <test_progs.h> + +#include "network_helpers.h" +#include "bpf_qdisc_fifo.skel.h" + +#ifndef ENOTSUPP +#define ENOTSUPP 524 +#endif + +#define LO_IFINDEX 1 + +static const unsigned int total_bytes = 10 * 1024 * 1024; +static int stop; + +static void *server(void *arg) +{ + int lfd = (int)(long)arg, err = 0, fd; + ssize_t nr_sent = 0, bytes = 0; + char batch[1500]; + + fd = accept(lfd, NULL, NULL); + while (fd == -1) { + if (errno == EINTR) + continue; + err = -errno; + goto done; + } + + if (settimeo(fd, 0)) { + err = -errno; + goto done; + } + + while (bytes < total_bytes && !READ_ONCE(stop)) { + nr_sent = send(fd, &batch, + MIN(total_bytes - bytes, sizeof(batch)), 0); + if (nr_sent == -1 && errno == EINTR) + continue; + if (nr_sent == -1) { + err = -errno; + break; + } + bytes += nr_sent; + } + + ASSERT_EQ(bytes, total_bytes, "send"); + +done: + if (fd >= 0) + close(fd); + if (err) { + WRITE_ONCE(stop, 1); + return ERR_PTR(err); + } + return NULL; +} + +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); + struct sockaddr_in6 sa6 = {}; + ssize_t nr_recv = 0, bytes = 0; + int lfd = -1, fd = -1; + pthread_t srv_thread; + socklen_t addrlen = sizeof(sa6); + void *thread_ret; + char batch[1500]; + int err; + + WRITE_ONCE(stop, 0); + + err = bpf_tc_hook_create(&hook); + if (!ASSERT_OK(err, "attach qdisc")) + return; + + lfd = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0); + if (!ASSERT_NEQ(lfd, -1, "socket")) { + bpf_tc_hook_destroy(&hook); + return; + } + + fd = socket(AF_INET6, SOCK_STREAM, 0); + if (!ASSERT_NEQ(fd, -1, "socket")) { + bpf_tc_hook_destroy(&hook); + close(lfd); + return; + } + + if (settimeo(lfd, 0) || settimeo(fd, 0)) + goto done; + + err = getsockname(lfd, (struct sockaddr *)&sa6, &addrlen); + if (!ASSERT_NEQ(err, -1, "getsockname")) + goto done; + + /* connect to server */ + err = connect(fd, (struct sockaddr *)&sa6, addrlen); + if (!ASSERT_NEQ(err, -1, "connect")) + goto done; + + err = pthread_create(&srv_thread, NULL, server, (void *)(long)lfd); + if (!ASSERT_OK(err, "pthread_create")) + goto done; + + /* recv total_bytes */ + while (bytes < total_bytes && !READ_ONCE(stop)) { + nr_recv = recv(fd, &batch, + MIN(total_bytes - bytes, sizeof(batch)), 0); + if (nr_recv == -1 && errno == EINTR) + continue; + if (nr_recv == -1) + break; + bytes += nr_recv; + } + + ASSERT_EQ(bytes, total_bytes, "recv"); + + WRITE_ONCE(stop, 1); + pthread_join(srv_thread, &thread_ret); + ASSERT_OK(IS_ERR(thread_ret), "thread_ret"); + +done: + close(lfd); + close(fd); + + bpf_tc_hook_destroy(&hook); + return; +} + +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) +{ + if (test__start_subtest("fifo")) + test_fifo(); +} diff --git a/tools/testing/selftests/bpf/progs/bpf_qdisc_common.h b/tools/testing/selftests/bpf/progs/bpf_qdisc_common.h new file mode 100644 index 000000000000..62a778f94908 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_qdisc_common.h @@ -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 diff --git a/tools/testing/selftests/bpf/progs/bpf_qdisc_fifo.c b/tools/testing/selftests/bpf/progs/bpf_qdisc_fifo.c new file mode 100644 index 000000000000..705e7da325da --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_qdisc_fifo.c @@ -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", +}; + -- 2.47.0