Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Kuniyuki Iwashima <kuniyu@amazon.co.jp>
To:     "David S . Miller" <davem@davemloft.net>,
        Jakub Kicinski <kuba@kernel.org>,
        Eric Dumazet <edumazet@google.com>,
        Neal Cardwell <ncardwell@google.com>,
        Yuchung Cheng <ycheng@google.com>,
        Alexei Starovoitov <ast@kernel.org>,
        Daniel Borkmann <daniel@iogearbox.net>,
        Andrii Nakryiko <andrii@kernel.org>,
        Martin KaFai Lau <kafai@fb.com>
CC:     Benjamin Herrenschmidt <benh@amazon.com>,
        Kuniyuki Iwashima <kuniyu@amazon.co.jp>,
        Kuniyuki Iwashima <kuni1840@gmail.com>, <bpf@vger.kernel.org>,
        <netdev@vger.kernel.org>, <linux-kernel@vger.kernel.org>
Subject: [PATCH v8 bpf-next 08/11] bpf: Support BPF_FUNC_get_socket_cookie() for BPF_PROG_TYPE_SK_REUSEPORT.
Date:   Sat, 12 Jun 2021 21:32:21 +0900
Message-ID: <20210612123224.12525-9-kuniyu@amazon.co.jp>
In-Reply-To: <20210612123224.12525-1-kuniyu@amazon.co.jp>
References: <20210612123224.12525-1-kuniyu@amazon.co.jp>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
Precedence: bulk

We will call sock_reuseport.prog for socket migration in the next commit,
so the eBPF program has to know which listener is closing to select a new
listener.

We can currently get a unique ID of each listener in the userspace by
calling bpf_map_lookup_elem() for BPF_MAP_TYPE_REUSEPORT_SOCKARRAY map.

This patch makes the pointer of sk available in sk_reuseport_md so that we
can get the ID by BPF_FUNC_get_socket_cookie() in the eBPF program.

Link: https://lore.kernel.org/netdev/20201119001154.kapwihc2plp4f7zc@kafai-mbp.dhcp.thefacebook.com/
Suggested-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Acked-by: Martin KaFai Lau <kafai@fb.com>
---
 include/uapi/linux/bpf.h       |  1 +
 net/core/filter.c              | 10 ++++++++++
 tools/include/uapi/linux/bpf.h |  1 +
 3 files changed, 12 insertions(+)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 2c1ba70abbf1..f3b72588442b 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5416,6 +5416,7 @@ struct sk_reuseport_md {
 	__u32 ip_protocol;	/* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */
 	__u32 bind_inany;	/* Is sock bound to an INANY address? */
 	__u32 hash;		/* A hash of the packet 4 tuples */
+	__bpf_md_ptr(struct bpf_sock *, sk);
 };
 
 #define BPF_TAG_SIZE	8
diff --git a/net/core/filter.c b/net/core/filter.c
index caa88955562e..f753ab550525 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -10172,6 +10172,8 @@ sk_reuseport_func_proto(enum bpf_func_id func_id,
 		return &sk_reuseport_load_bytes_proto;
 	case BPF_FUNC_skb_load_bytes_relative:
 		return &sk_reuseport_load_bytes_relative_proto;
+	case BPF_FUNC_get_socket_cookie:
+		return &bpf_get_socket_ptr_cookie_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -10201,6 +10203,10 @@ sk_reuseport_is_valid_access(int off, int size,
 	case offsetof(struct sk_reuseport_md, hash):
 		return size == size_default;
 
+	case offsetof(struct sk_reuseport_md, sk):
+		info->reg_type = PTR_TO_SOCKET;
+		return size == sizeof(__u64);
+
 	/* Fields that allow narrowing */
 	case bpf_ctx_range(struct sk_reuseport_md, eth_protocol):
 		if (size < sizeof_field(struct sk_buff, protocol))
@@ -10273,6 +10279,10 @@ static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type,
 	case offsetof(struct sk_reuseport_md, bind_inany):
 		SK_REUSEPORT_LOAD_FIELD(bind_inany);
 		break;
+
+	case offsetof(struct sk_reuseport_md, sk):
+		SK_REUSEPORT_LOAD_FIELD(sk);
+		break;
 	}
 
 	return insn - insn_buf;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 2c1ba70abbf1..f3b72588442b 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5416,6 +5416,7 @@ struct sk_reuseport_md {
 	__u32 ip_protocol;	/* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */
 	__u32 bind_inany;	/* Is sock bound to an INANY address? */
 	__u32 hash;		/* A hash of the packet 4 tuples */
+	__bpf_md_ptr(struct bpf_sock *, sk);
 };
 
 #define BPF_TAG_SIZE	8
-- 
2.30.2