Merge branch 'bpf: Allow bpf tcp iter to do bpf_(get|set)sockopt'

Martin KaFai says:

====================

This set is to allow bpf tcp iter to call bpf_(get|set)sockopt.

With bpf-tcp-cc, new algo rollout happens more often.  Instead of
restarting the applications to pick up the new tcp-cc, this set
allows the bpf tcp iter to call bpf_(get|set)sockopt(TCP_CONGESTION).
It is not limited to TCP_CONGESTION, the bpf tcp iter can call
bpf_(get|set)sockopt() with other options.  The bpf tcp iter can read
into all the fields of a tcp_sock, so there is a lot of flexibility
to select the desired sk to do setsockopt(), e.g. it can test for
TCP_LISTEN only and leave the established connections untouched,
or check the addr/port, or check the current tcp-cc name, ...etc.

Patch 1-4 are some cleanup and prep work in the tcp and bpf seq_file.

Patch 5 is to have the tcp seq_file iterate on the
port+addr lhash2 instead of the port only listening_hash.

Patch 6 is to have the bpf tcp iter doing batching which
then allows lock_sock.  lock_sock is needed for setsockopt.

Patch 7 allows the bpf tcp iter to call bpf_(get|set)sockopt.

v2:
- Use __GFP_NOWARN in patch 6
- Add bpf_getsockopt() in patch 7 to give a symmetrical user experience.
  selftest in patch 8 is changed to also cover bpf_getsockopt().
- Remove CAP_NET_ADMIN check in patch 7. Tracing bpf prog has already
  required CAP_SYS_ADMIN or CAP_PERFMON.
- Move some def macros to bpf_tracing_net.h in patch 8
====================

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>

1 files changed, 8 insertions, 0 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 978ebd16ae60..c8cc09013210 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1442,6 +1442,9 @@ typedef void (*bpf_iter_show_fdinfo_t) (const struct bpf_iter_aux_info *aux,
 					struct seq_file *seq);
 typedef int (*bpf_iter_fill_link_info_t)(const struct bpf_iter_aux_info *aux,
 					 struct bpf_link_info *info);
+typedef const struct bpf_func_proto *
+(*bpf_iter_get_func_proto_t)(enum bpf_func_id func_id,
+			     const struct bpf_prog *prog);
 
 enum bpf_iter_feature {
 	BPF_ITER_RESCHED	= BIT(0),
@@ -1454,6 +1457,7 @@ struct bpf_iter_reg {
 	bpf_iter_detach_target_t detach_target;
 	bpf_iter_show_fdinfo_t show_fdinfo;
 	bpf_iter_fill_link_info_t fill_link_info;
+	bpf_iter_get_func_proto_t get_func_proto;
 	u32 ctx_arg_info_size;
 	u32 feature;
 	struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX];
@@ -1476,6 +1480,8 @@ struct bpf_iter__bpf_map_elem {
 int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info);
 void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info);
 bool bpf_iter_prog_supported(struct bpf_prog *prog);
+const struct bpf_func_proto *
+bpf_iter_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog);
 int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, struct bpf_prog *prog);
 int bpf_iter_new_fd(struct bpf_link *link);
 bool bpf_link_is_iter(struct bpf_link *link);
@@ -2050,6 +2056,8 @@ extern const struct bpf_func_proto bpf_task_storage_get_proto;
 extern const struct bpf_func_proto bpf_task_storage_delete_proto;
 extern const struct bpf_func_proto bpf_for_each_map_elem_proto;
 extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto;
+extern const struct bpf_func_proto bpf_sk_setsockopt_proto;
+extern const struct bpf_func_proto bpf_sk_getsockopt_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);