On Wed, Apr 8, 2020 at 4:26 PM Yonghong Song <yhs@xxxxxx> wrote:
>
> Two bpf programs are added in this patch for netlink and ipv6_route
> target. On my VM, I am able to achieve identical
> results compared to /proc/net/netlink and /proc/net/ipv6_route.
>
> $ cat /proc/net/netlink
> sk Eth Pid Groups Rmem Wmem Dump Locks Drops Inode
> 000000002c42d58b 0 0 00000000 0 0 0 2 0 7
> 00000000a4e8b5e1 0 1 00000551 0 0 0 2 0 18719
> 00000000e1b1c195 4 0 00000000 0 0 0 2 0 16422
> 000000007e6b29f9 6 0 00000000 0 0 0 2 0 16424
> ....
> 00000000159a170d 15 1862 00000002 0 0 0 2 0 1886
> 000000009aca4bc9 15 3918224839 00000002 0 0 0 2 0 19076
> 00000000d0ab31d2 15 1 00000002 0 0 0 2 0 18683
> 000000008398fb08 16 0 00000000 0 0 0 2 0 27
> $ cat /sys/kernel/bpfdump/netlink/my1
> sk Eth Pid Groups Rmem Wmem Dump Locks Drops Inode
> 000000002c42d58b 0 0 00000000 0 0 0 2 0 7
> 00000000a4e8b5e1 0 1 00000551 0 0 0 2 0 18719
> 00000000e1b1c195 4 0 00000000 0 0 0 2 0 16422
> 000000007e6b29f9 6 0 00000000 0 0 0 2 0 16424
> ....
> 00000000159a170d 15 1862 00000002 0 0 0 2 0 1886
> 000000009aca4bc9 15 3918224839 00000002 0 0 0 2 0 19076
> 00000000d0ab31d2 15 1 00000002 0 0 0 2 0 18683
> 000000008398fb08 16 0 00000000 0 0 0 2 0 27
>
> $ cat /proc/net/ipv6_route
> fe800000000000000000000000000000 40 00000000000000000000000000000000 00 00000000000000000000000000000000 00000100 00000001 00000000 00000001 eth0
> 00000000000000000000000000000000 00 00000000000000000000000000000000 00 00000000000000000000000000000000 ffffffff 00000001 00000000 00200200 lo
> 00000000000000000000000000000001 80 00000000000000000000000000000000 00 00000000000000000000000000000000 00000000 00000003 00000000 80200001 lo
> fe80000000000000c04b03fffe7827ce 80 00000000000000000000000000000000 00 00000000000000000000000000000000 00000000 00000002 00000000 80200001 eth0
> ff000000000000000000000000000000 08 00000000000000000000000000000000 00 00000000000000000000000000000000 00000100 00000003 00000000 00000001 eth0
> 00000000000000000000000000000000 00 00000000000000000000000000000000 00 00000000000000000000000000000000 ffffffff 00000001 00000000 00200200 lo
> $ cat /sys/kernel/bpfdump/ipv6_route/my1
> fe800000000000000000000000000000 40 00000000000000000000000000000000 00 00000000000000000000000000000000 00000100 00000001 00000000 00000001 eth0
> 00000000000000000000000000000000 00 00000000000000000000000000000000 00 00000000000000000000000000000000 ffffffff 00000001 00000000 00200200 lo
> 00000000000000000000000000000001 80 00000000000000000000000000000000 00 00000000000000000000000000000000 00000000 00000003 00000000 80200001 lo
> fe80000000000000c04b03fffe7827ce 80 00000000000000000000000000000000 00 00000000000000000000000000000000 00000000 00000002 00000000 80200001 eth0
> ff000000000000000000000000000000 08 00000000000000000000000000000000 00 00000000000000000000000000000000 00000100 00000003 00000000 00000001 eth0
> 00000000000000000000000000000000 00 00000000000000000000000000000000 00 00000000000000000000000000000000 ffffffff 00000001 00000000 00200200 lo
>
> Signed-off-by: Yonghong Song <yhs@xxxxxx>
> ---
> .../selftests/bpf/progs/bpfdump_ipv6_route.c | 63 ++++++++++++++++
> .../selftests/bpf/progs/bpfdump_netlink.c | 74 +++++++++++++++++++
> 2 files changed, 137 insertions(+)
> create mode 100644 tools/testing/selftests/bpf/progs/bpfdump_ipv6_route.c
> create mode 100644 tools/testing/selftests/bpf/progs/bpfdump_netlink.c
>
> diff --git a/tools/testing/selftests/bpf/progs/bpfdump_ipv6_route.c b/tools/testing/selftests/bpf/progs/bpfdump_ipv6_route.c
> new file mode 100644
> index 000000000000..590e56791052
> --- /dev/null
> +++ b/tools/testing/selftests/bpf/progs/bpfdump_ipv6_route.c
> @@ -0,0 +1,63 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/* Copyright (c) 2020 Facebook */
> +#include "vmlinux.h"
> +#include <bpf/bpf_helpers.h>
> +#include <bpf/bpf_tracing.h>
> +#include <bpf/bpf_endian.h>
> +
> +char _license[] SEC("license") = "GPL";
> +
> +extern bool CONFIG_IPV6_SUBTREES __kconfig __weak;
> +
> +#define RTF_GATEWAY 0x0002
> +#define IFNAMSIZ 16
> +#define fib_nh_gw_family nh_common.nhc_gw_family
> +#define fib_nh_gw6 nh_common.nhc_gw.ipv6
> +#define fib_nh_dev nh_common.nhc_dev
> +
> +SEC("dump//sys/kernel/bpfdump/ipv6_route")
> +int BPF_PROG(dump_ipv6_route, struct fib6_info *rt, struct seq_file *seq, u64 seq_num)
> +{
> + struct fib6_nh *fib6_nh = &rt->fib6_nh[0];
> + unsigned int flags = rt->fib6_flags;
> + const struct net_device *dev;
> + struct nexthop *nh;
> + static const char fmt1[] = "%pi6 %02x ";
> + static const char fmt2[] = "%pi6 ";
> + static const char fmt3[] = "00000000000000000000000000000000 ";
> + static const char fmt4[] = "%08x %08x ";
> + static const char fmt5[] = "%8s\n";
> + static const char fmt6[] = "\n";
> + static const char fmt7[] = "00000000000000000000000000000000 00 ";
> +
> + /* FIXME: nexthop_is_multipath is not handled here. */
> + nh = rt->nh;
> + if (rt->nh)
> + fib6_nh = &nh->nh_info->fib6_nh;
> +
> + bpf_seq_printf(seq, fmt1, sizeof(fmt1), &rt->fib6_dst.addr,
> + rt->fib6_dst.plen);
> +
> + if (CONFIG_IPV6_SUBTREES)
> + bpf_seq_printf(seq, fmt1, sizeof(fmt1), &rt->fib6_src.addr,
> + rt->fib6_src.plen);
> + else
> + bpf_seq_printf(seq, fmt7, sizeof(fmt7));
> +
> + if (fib6_nh->fib_nh_gw_family) {
> + flags |= RTF_GATEWAY;
> + bpf_seq_printf(seq, fmt2, sizeof(fmt2), &fib6_nh->fib_nh_gw6);
> + } else {
> + bpf_seq_printf(seq, fmt3, sizeof(fmt3));
> + }
> +
> + dev = fib6_nh->fib_nh_dev;
> + bpf_seq_printf(seq, fmt4, sizeof(fmt4), rt->fib6_metric, rt->fib6_ref.refs.counter);
> + bpf_seq_printf(seq, fmt4, sizeof(fmt4), 0, flags);
> + if (dev)
> + bpf_seq_printf(seq, fmt5, sizeof(fmt5), dev->name);
> + else
> + bpf_seq_printf(seq, fmt6, sizeof(fmt6));
> +
> + return 0;
> +}
> diff --git a/tools/testing/selftests/bpf/progs/bpfdump_netlink.c b/tools/testing/selftests/bpf/progs/bpfdump_netlink.c
> new file mode 100644
> index 000000000000..37c9be546b99
> --- /dev/null
> +++ b/tools/testing/selftests/bpf/progs/bpfdump_netlink.c
> @@ -0,0 +1,74 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/* Copyright (c) 2020 Facebook */
> +#include "vmlinux.h"
> +#include <bpf/bpf_helpers.h>
> +#include <bpf/bpf_tracing.h>
> +#include <bpf/bpf_endian.h>
> +
> +char _license[] SEC("license") = "GPL";
> +
> +#define sk_rmem_alloc sk_backlog.rmem_alloc
> +#define sk_refcnt __sk_common.skc_refcnt
> +
> +#define offsetof(TYPE, MEMBER) ((size_t)&((TYPE *)0)->MEMBER)
> +#define container_of(ptr, type, member) ({ \
> + void *__mptr = (void *)(ptr); \
> + ((type *)(__mptr - offsetof(type, member))); })
> +
> +static inline struct inode *SOCK_INODE(struct socket *socket)
> +{
> + return &container_of(socket, struct socket_alloc, socket)->vfs_inode;
> +}
> +
> +SEC("dump//sys/kernel/bpfdump/netlink")
We discussed already on previous patch, but just to put it visually
into comparison:
SEC("dump/netlink")
looks so much nicer :)
> +int BPF_PROG(dump_netlink, struct netlink_sock *nlk, struct seq_file *seq, u64 seq_num)
> +{
> + static const char banner[] =
> + "sk Eth Pid Groups "
> + "Rmem Wmem Dump Locks Drops Inode\n";
> + static const char fmt1[] = "%pK %-3d ";
> + static const char fmt2[] = "%-10u %08x ";
> + static const char fmt3[] = "%-8d %-8d ";
> + static const char fmt4[] = "%-5d %-8d ";
> + static const char fmt5[] = "%-8u %-8lu\n";
> + struct sock *s = &nlk->sk;
> + unsigned long group, ino;
> + struct inode *inode;
> + struct socket *sk;
> +
> + if (seq_num == 0)
> + bpf_seq_printf(seq, banner, sizeof(banner));
> +
> + bpf_seq_printf(seq, fmt1, sizeof(fmt1), s, s->sk_protocol);
> +
> + if (!nlk->groups) {
> + group = 0;
> + } else {
> + /* FIXME: temporary use bpf_probe_read here, needs
> + * verifier support to do direct access.
> + */
> + bpf_probe_read(&group, sizeof(group), &nlk->groups[0]);
Is this what's being fixed by patch #10?
> + }
> + bpf_seq_printf(seq, fmt2, sizeof(fmt2), nlk->portid, (u32)group);
> +
> +
> + bpf_seq_printf(seq, fmt3, sizeof(fmt3), s->sk_rmem_alloc.counter,
> + s->sk_wmem_alloc.refs.counter - 1);
> + bpf_seq_printf(seq, fmt4, sizeof(fmt4), nlk->cb_running,
> + s->sk_refcnt.refs.counter);
> +
> + sk = s->sk_socket;
> + if (!sk) {
> + ino = 0;
> + } else {
> + /* FIXME: container_of inside SOCK_INODE has a forced
> + * type conversion, and direct access cannot be used
> + * with current verifier.
> + */
> + inode = SOCK_INODE(sk);
> + bpf_probe_read(&ino, sizeof(ino), &inode->i_ino);
> + }
> + bpf_seq_printf(seq, fmt5, sizeof(fmt5), s->sk_drops.counter, ino);
> +
> + return 0;
> +}
> --
> 2.24.1
>
