bpf.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Martin KaFai Lau <kafai@fb.com>
To: <bpf@vger.kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Eric Dumazet <edumazet@google.com>, <kernel-team@fb.com>,
	Neal Cardwell <ncardwell@google.com>, <netdev@vger.kernel.org>,
	Yonghong Song <yhs@fb.com>, Yuchung Cheng <ycheng@google.com>
Subject: [PATCH v2 bpf-next 7/8] bpf: tcp: Support bpf_(get|set)sockopt in bpf tcp iter
Date: Thu, 1 Jul 2021 13:06:19 -0700	[thread overview]
Message-ID: <20210701200619.1036715-1-kafai@fb.com> (raw)
In-Reply-To: <20210701200535.1033513-1-kafai@fb.com>

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.

Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
---
 include/linux/bpf.h      |  8 ++++++++
 kernel/bpf/bpf_iter.c    | 22 ++++++++++++++++++++++
 kernel/trace/bpf_trace.c |  7 ++++++-
 net/core/filter.c        | 34 ++++++++++++++++++++++++++++++++++
 net/ipv4/tcp_ipv4.c      | 15 +++++++++++++++
 5 files changed, 85 insertions(+), 1 deletion(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f309fc1509f2..b9a62b805a99 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1397,6 +1397,9 @@ 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),
@@ -1409,6 +1412,7 @@ 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];
@@ -1431,6 +1435,8 @@ 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);
@@ -1997,6 +2003,8 @@ 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 2d4fbdbb194e..2e9d47bb40ff 100644
--- 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 64bd2d84367f..a137494f2505 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1430,6 +1430,8 @@ 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:
@@ -1470,7 +1472,10 @@ 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 d70187ce851b..61f8121f205f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5012,6 +5012,40 @@ static int _bpf_getsockopt(struct sock *sk, int level, int optname,
 	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 3e1afab26381..6ea47850e1fa 100644
--- 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,
 };
 
-- 
2.30.2


  parent reply	other threads:[~2021-07-01 20:07 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-01 20:05 [PATCH v2 bpf-next 0/8] bpf: Allow bpf tcp iter to do bpf_(get|set)sockopt Martin KaFai Lau
2021-07-01 20:05 ` [PATCH v2 bpf-next 1/8] tcp: seq_file: Avoid skipping sk during tcp_seek_last_pos Martin KaFai Lau
2021-07-22 14:16   ` Kuniyuki Iwashima
2021-07-22 15:08     ` Kuniyuki Iwashima
2021-07-22 21:42       ` Martin KaFai Lau
2021-07-22 22:06         ` Kuniyuki Iwashima
2021-07-01 20:05 ` [PATCH v2 bpf-next 2/8] tcp: seq_file: Refactor net and family matching Martin KaFai Lau
2021-07-01 20:05 ` [PATCH v2 bpf-next 3/8] bpf: tcp: seq_file: Remove bpf_seq_afinfo from tcp_iter_state Martin KaFai Lau
2021-07-01 20:06 ` [PATCH v2 bpf-next 4/8] tcp: seq_file: Add listening_get_first() Martin KaFai Lau
2021-07-01 20:06 ` [PATCH v2 bpf-next 5/8] tcp: seq_file: Replace listening_hash with lhash2 Martin KaFai Lau
2021-07-01 20:06 ` [PATCH v2 bpf-next 6/8] bpf: tcp: bpf iter batching and lock_sock Martin KaFai Lau
2021-07-01 20:06 ` Martin KaFai Lau [this message]
2021-07-01 20:06 ` [PATCH v2 bpf-next 8/8] bpf: selftest: Test batching and bpf_(get|set)sockopt in bpf tcp iter Martin KaFai Lau
2021-07-02 10:50 ` [PATCH v2 bpf-next 0/8] bpf: Allow bpf tcp iter to do bpf_(get|set)sockopt David Laight
2021-07-06 15:44   ` Martin KaFai Lau
2021-07-15  1:29 ` Alexei Starovoitov
2021-07-20 18:05   ` Alexei Starovoitov
2021-07-20 18:42     ` Eric Dumazet
2021-07-22 13:25 ` Eric Dumazet
2021-07-22 21:01   ` Martin KaFai Lau
2021-07-22 14:53 ` Kuniyuki Iwashima

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210701200619.1036715-1-kafai@fb.com \
    --to=kafai@fb.com \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=edumazet@google.com \
    --cc=kernel-team@fb.com \
    --cc=ncardwell@google.com \
    --cc=netdev@vger.kernel.org \
    --cc=ycheng@google.com \
    --cc=yhs@fb.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).