Merge branch 'bpf_iter_tcp_udp'

Yonghong Song says:

====================
bpf iterator implments traversal of kernel data structures and these
data structures are passed to a bpf program for processing.
This gives great flexibility for users to examine kernel data
structure without using e.g. /proc/net which has limited and
fixed format.

Commit 138d0be35b14 ("net: bpf: Add netlink and ipv6_route bpf_iter targets")
implemented bpf iterators for netlink and ipv6_route.
This patch set intends to implement bpf iterators for tcp and udp.

Currently, /proc/net/tcp is used to print tcp4 stats and /proc/net/tcp6
is used to print tcp6 stats. /proc/net/udp[6] have similar usage model.
In contrast, only one tcp iterator is implemented and it is bpf program
resposibility to filter based on socket family. The same is for udp.
This will avoid another unnecessary traversal pass if users want
to check both tcp4 and tcp6.

Several helpers are also implemented in this patch
  bpf_skc_to_{tcp, tcp6, tcp_timewait, tcp_request, udp6}_sock
The argument for these helpers is not a fixed btf_id. For example,
  bpf_skc_to_tcp(struct sock_common *), or
  bpf_skc_to_tcp(struct sock *), or
  bpf_skc_to_tcp(struct inet_sock *), ...
are all valid. At runtime, the helper will check whether pointer cast
is legal or not. Please see Patch #5 for details.

Since btf_id's for both arguments and return value are known at
build time, the btf_id's are pre-computed once vmlinux btf becomes
valid. Jiri's "adding d_path helper" patch set
  https://lore.kernel.org/bpf/20200616100512.2168860-1-jolsa@kernel.org/T/
provides a way to pre-compute btf id during vmlinux build time.
This can be applied here as well. A followup patch can convert
to build time btf id computation after Jiri's patch landed.

Changelogs:
  v4 -> v5:
    - fix bpf_skc_to_udp6_sock helper as besides sk_protocol, sk_family,
      sk_type == SOCK_DGRAM is also needed to differentiate from
      SOCK_RAW (Eric)
  v3 -> v4:
    - fix bpf_skc_to_{tcp_timewait, tcp_request}_sock helper implementation
      as just checking sk->sk_state is not enough (Martin)
    - fix a few kernel test robot reported failures
    - move bpf_tracing_net.h from libbpf to selftests (Andrii)
    - remove __weak attribute from selftests CONFIG_HZ variables (Andrii)
  v2 -> v3:
    - change sock_cast*/SOCK_CAST* names to btf_sock* names for generality (Martin)
    - change gpl_license to false (Martin)
    - fix helper to cast to tcp timewait/request socket. (Martin)
  v1 -> v2:
    - guard init_sock_cast_types() defination properly with CONFIG_NET (Martin)
    - reuse the btf_ids, computed for new helper argument, for return
      values (Martin)
    - using BTF_TYPE_EMIT to express intent of btf type generation (Andrii)
    - abstract out common net macros into bpf_tracing_net.h (Andrii)
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 80 insertions, 0 deletions

diff --git a/tools/testing/selftests/bpf/progs/bpf_iter.h b/tools/testing/selftests/bpf/progs/bpf_iter.h
new file mode 100644
index 000000000000..17db3bac518b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2020 Facebook */
+/* "undefine" structs in vmlinux.h, because we "override" them below */
+#define bpf_iter_meta bpf_iter_meta___not_used
+#define bpf_iter__bpf_map bpf_iter__bpf_map___not_used
+#define bpf_iter__ipv6_route bpf_iter__ipv6_route___not_used
+#define bpf_iter__netlink bpf_iter__netlink___not_used
+#define bpf_iter__task bpf_iter__task___not_used
+#define bpf_iter__task_file bpf_iter__task_file___not_used
+#define bpf_iter__tcp bpf_iter__tcp___not_used
+#define tcp6_sock tcp6_sock___not_used
+#define bpf_iter__udp bpf_iter__udp___not_used
+#define udp6_sock udp6_sock___not_used
+#include "vmlinux.h"
+#undef bpf_iter_meta
+#undef bpf_iter__bpf_map
+#undef bpf_iter__ipv6_route
+#undef bpf_iter__netlink
+#undef bpf_iter__task
+#undef bpf_iter__task_file
+#undef bpf_iter__tcp
+#undef tcp6_sock
+#undef bpf_iter__udp
+#undef udp6_sock
+
+struct bpf_iter_meta {
+	struct seq_file *seq;
+	__u64 session_id;
+	__u64 seq_num;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__ipv6_route {
+	struct bpf_iter_meta *meta;
+	struct fib6_info *rt;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__netlink {
+	struct bpf_iter_meta *meta;
+	struct netlink_sock *sk;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__task {
+	struct bpf_iter_meta *meta;
+	struct task_struct *task;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__task_file {
+	struct bpf_iter_meta *meta;
+	struct task_struct *task;
+	__u32 fd;
+	struct file *file;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__bpf_map {
+	struct bpf_iter_meta *meta;
+	struct bpf_map *map;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__tcp {
+	struct bpf_iter_meta *meta;
+	struct sock_common *sk_common;
+	uid_t uid;
+} __attribute__((preserve_access_index));
+
+struct tcp6_sock {
+	struct tcp_sock	tcp;
+	struct ipv6_pinfo inet6;
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__udp {
+	struct bpf_iter_meta *meta;
+	struct udp_sock *udp_sk;
+	uid_t uid __attribute__((aligned(8)));
+	int bucket __attribute__((aligned(8)));
+} __attribute__((preserve_access_index));
+
+struct udp6_sock {
+	struct udp_sock	udp;
+	struct ipv6_pinfo inet6;
+} __attribute__((preserve_access_index));