bpf: tcp: Support bpf_(get|set)sockopt in bpf tcp iter

This patch allows bpf tcp iter to call bpf_(get|set)sockopt.
To allow a specific bpf iter (tcp here) to call a set of helpers,
get_func_proto function pointer is added to bpf_iter_reg.
The bpf iter is a tracing prog which currently requires
CAP_PERFMON or CAP_SYS_ADMIN, so this patch does not
impose other capability checks for bpf_(get|set)sockopt.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210701200619.1036715-1-kafai@fb.com

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 978ebd1..c8cc090 100644 (file)
--- 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);

diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 2d4fbdb..2e9d47b 100644 (file)
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -360,6 +360,28 @@ bool bpf_iter_prog_supported(struct bpf_prog *prog)
        return supported;
 }
 
+const struct bpf_func_proto *
+bpf_iter_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+       const struct bpf_iter_target_info *tinfo;
+       const struct bpf_func_proto *fn = NULL;
+
+       mutex_lock(&targets_mutex);
+       list_for_each_entry(tinfo, &targets, list) {
+               if (tinfo->btf_id == prog->aux->attach_btf_id) {
+                       const struct bpf_iter_reg *reg_info;
+
+                       reg_info = tinfo->reg_info;
+                       if (reg_info->get_func_proto)
+                               fn = reg_info->get_func_proto(func_id, prog);
+                       break;
+               }
+       }
+       mutex_unlock(&targets_mutex);
+
+       return fn;
+}
+
 static void bpf_iter_link_release(struct bpf_link *link)
 {
        struct bpf_iter_link *iter_link =

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 1f22ce1..c5e0b6a 100644 (file)
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1461,6 +1461,8 @@ raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 const struct bpf_func_proto *
 tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
+       const struct bpf_func_proto *fn;
+
        switch (func_id) {
 #ifdef CONFIG_NET
        case BPF_FUNC_skb_output:
@@ -1501,7 +1503,10 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
        case BPF_FUNC_d_path:
                return &bpf_d_path_proto;
        default:
-               return raw_tp_prog_func_proto(func_id, prog);
+               fn = raw_tp_prog_func_proto(func_id, prog);
+               if (!fn && prog->expected_attach_type == BPF_TRACE_ITER)
+                       fn = bpf_iter_get_func_proto(func_id, prog);
+               return fn;
        }
 }
 

diff --git a/net/core/filter.c b/net/core/filter.c
index 3b4986e..faf29fd 100644 (file)
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5016,6 +5016,40 @@ err_clear:
        return -EINVAL;
 }
 
+BPF_CALL_5(bpf_sk_setsockopt, struct sock *, sk, int, level,
+          int, optname, char *, optval, int, optlen)
+{
+       return _bpf_setsockopt(sk, level, optname, optval, optlen);
+}
+
+const struct bpf_func_proto bpf_sk_setsockopt_proto = {
+       .func           = bpf_sk_setsockopt,
+       .gpl_only       = false,
+       .ret_type       = RET_INTEGER,
+       .arg1_type      = ARG_PTR_TO_BTF_ID_SOCK_COMMON,
+       .arg2_type      = ARG_ANYTHING,
+       .arg3_type      = ARG_ANYTHING,
+       .arg4_type      = ARG_PTR_TO_MEM,
+       .arg5_type      = ARG_CONST_SIZE,
+};
+
+BPF_CALL_5(bpf_sk_getsockopt, struct sock *, sk, int, level,
+          int, optname, char *, optval, int, optlen)
+{
+       return _bpf_getsockopt(sk, level, optname, optval, optlen);
+}
+
+const struct bpf_func_proto bpf_sk_getsockopt_proto = {
+       .func           = bpf_sk_getsockopt,
+       .gpl_only       = false,
+       .ret_type       = RET_INTEGER,
+       .arg1_type      = ARG_PTR_TO_BTF_ID_SOCK_COMMON,
+       .arg2_type      = ARG_ANYTHING,
+       .arg3_type      = ARG_ANYTHING,
+       .arg4_type      = ARG_PTR_TO_UNINIT_MEM,
+       .arg5_type      = ARG_CONST_SIZE,
+};
+
 BPF_CALL_5(bpf_sock_addr_setsockopt, struct bpf_sock_addr_kern *, ctx,
           int, level, int, optname, char *, optval, int, optlen)
 {

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 84ac013..f9c6e47 100644 (file)
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -3259,6 +3259,20 @@ static const struct bpf_iter_seq_info tcp_seq_info = {
        .seq_priv_size          = sizeof(struct bpf_tcp_iter_state),
 };
 
+static const struct bpf_func_proto *
+bpf_iter_tcp_get_func_proto(enum bpf_func_id func_id,
+                           const struct bpf_prog *prog)
+{
+       switch (func_id) {
+       case BPF_FUNC_setsockopt:
+               return &bpf_sk_setsockopt_proto;
+       case BPF_FUNC_getsockopt:
+               return &bpf_sk_getsockopt_proto;
+       default:
+               return NULL;
+       }
+}
+
 static struct bpf_iter_reg tcp_reg_info = {
        .target                 = "tcp",
        .ctx_arg_info_size      = 1,
@@ -3266,6 +3280,7 @@ static struct bpf_iter_reg tcp_reg_info = {
                { offsetof(struct bpf_iter__tcp, sk_common),
                  PTR_TO_BTF_ID_OR_NULL },
        },
+       .get_func_proto         = bpf_iter_tcp_get_func_proto,
        .seq_info               = &tcp_seq_info,
 };