From: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
To: "David S . Miller" <davem@davemloft.net>,
Jakub Kicinski <kuba@kernel.org>,
Eric Dumazet <edumazet@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 v2 bpf-next 11/13] bpf: Support BPF_FUNC_get_socket_cookie() for BPF_PROG_TYPE_SK_REUSEPORT.
Date: Mon, 7 Dec 2020 22:24:54 +0900 [thread overview]
Message-ID: <20201207132456.65472-12-kuniyu@amazon.co.jp> (raw)
In-Reply-To: <20201207132456.65472-1-kuniyu@amazon.co.jp>
We will call sock_reuseport.prog for socket migration in the next commit,
so the eBPF program has to know which listener is closing in order to
select the new listener.
Currently, we can get a unique ID for each listener in the userspace by
calling bpf_map_lookup_elem() for BPF_MAP_TYPE_REUSEPORT_SOCKARRAY map.
This patch makes the sk pointer 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>
---
include/uapi/linux/bpf.h | 8 ++++++++
net/core/filter.c | 22 ++++++++++++++++++++++
tools/include/uapi/linux/bpf.h | 8 ++++++++
3 files changed, 38 insertions(+)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index cf518e83df5c..a688a7a4fe85 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1655,6 +1655,13 @@ union bpf_attr {
* A 8-byte long non-decreasing number on success, or 0 if the
* socket field is missing inside *skb*.
*
+ * u64 bpf_get_socket_cookie(struct bpf_sock *sk)
+ * Description
+ * Equivalent to bpf_get_socket_cookie() helper that accepts
+ * *skb*, but gets socket from **struct bpf_sock** context.
+ * Return
+ * A 8-byte long non-decreasing number.
+ *
* u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx)
* Description
* Equivalent to bpf_get_socket_cookie() helper that accepts
@@ -4463,6 +4470,7 @@ struct sk_reuseport_md {
__u32 bind_inany; /* Is sock bound to an INANY address? */
__u32 hash; /* A hash of the packet 4 tuples */
__u8 migration; /* Migration type */
+ __bpf_md_ptr(struct bpf_sock *, sk); /* Current listening socket */
};
#define BPF_TAG_SIZE 8
diff --git a/net/core/filter.c b/net/core/filter.c
index 7bdf62f24044..9f7018e3f545 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4631,6 +4631,18 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = {
.arg1_type = ARG_PTR_TO_CTX,
};
+BPF_CALL_1(bpf_get_socket_pointer_cookie, struct sock *, sk)
+{
+ return __sock_gen_cookie(sk);
+}
+
+static const struct bpf_func_proto bpf_get_socket_pointer_cookie_proto = {
+ .func = bpf_get_socket_pointer_cookie,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_SOCKET,
+};
+
BPF_CALL_1(bpf_get_socket_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx)
{
return __sock_gen_cookie(ctx->sk);
@@ -9989,6 +10001,8 @@ 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_pointer_cookie_proto;
default:
return bpf_base_func_proto(func_id);
}
@@ -10022,6 +10036,10 @@ sk_reuseport_is_valid_access(int off, int size,
return prog->expected_attach_type == BPF_SK_REUSEPORT_SELECT_OR_MIGRATE &&
size == sizeof(__u8);
+ 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))
@@ -10098,6 +10116,10 @@ static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type,
case offsetof(struct sk_reuseport_md, migration):
SK_REUSEPORT_LOAD_FIELD(migration);
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 cf518e83df5c..a688a7a4fe85 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1655,6 +1655,13 @@ union bpf_attr {
* A 8-byte long non-decreasing number on success, or 0 if the
* socket field is missing inside *skb*.
*
+ * u64 bpf_get_socket_cookie(struct bpf_sock *sk)
+ * Description
+ * Equivalent to bpf_get_socket_cookie() helper that accepts
+ * *skb*, but gets socket from **struct bpf_sock** context.
+ * Return
+ * A 8-byte long non-decreasing number.
+ *
* u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx)
* Description
* Equivalent to bpf_get_socket_cookie() helper that accepts
@@ -4463,6 +4470,7 @@ struct sk_reuseport_md {
__u32 bind_inany; /* Is sock bound to an INANY address? */
__u32 hash; /* A hash of the packet 4 tuples */
__u8 migration; /* Migration type */
+ __bpf_md_ptr(struct bpf_sock *, sk); /* Current listening socket */
};
#define BPF_TAG_SIZE 8
--
2.17.2 (Apple Git-113)
next prev parent reply other threads:[~2020-12-07 13:29 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-12-07 13:24 [PATCH v2 bpf-next 00/13] Socket migration for SO_REUSEPORT Kuniyuki Iwashima
2020-12-07 13:24 ` [PATCH v2 bpf-next 01/13] tcp: Allow TCP_CLOSE sockets to hold the reuseport group Kuniyuki Iwashima
2020-12-07 13:24 ` [PATCH v2 bpf-next 02/13] bpf: Define migration types for SO_REUSEPORT Kuniyuki Iwashima
2020-12-07 13:24 ` [PATCH v2 bpf-next 03/13] Revert "locking/spinlocks: Remove the unused spin_lock_bh_nested() API" Kuniyuki Iwashima
2020-12-07 16:25 ` Waiman Long
2020-12-07 13:24 ` [PATCH v2 bpf-next 04/13] tcp: Introduce inet_csk_reqsk_queue_migrate() Kuniyuki Iwashima
2020-12-07 13:24 ` [PATCH v2 bpf-next 05/13] tcp: Set the new listener to migrated TFO requests Kuniyuki Iwashima
2020-12-07 13:24 ` [PATCH v2 bpf-next 06/13] tcp: Migrate TCP_ESTABLISHED/TCP_SYN_RECV sockets in accept queues Kuniyuki Iwashima
2020-12-07 13:24 ` [PATCH v2 bpf-next 07/13] tcp: Migrate TCP_NEW_SYN_RECV requests Kuniyuki Iwashima
2020-12-07 13:24 ` [PATCH v2 bpf-next 08/13] bpf: Introduce two attach types for BPF_PROG_TYPE_SK_REUSEPORT Kuniyuki Iwashima
2020-12-07 13:24 ` [PATCH v2 bpf-next 09/13] libbpf: Set expected_attach_type " Kuniyuki Iwashima
2020-12-07 13:24 ` [PATCH v2 bpf-next 10/13] bpf: Add migration to sk_reuseport_(kern|md) Kuniyuki Iwashima
2020-12-07 13:24 ` Kuniyuki Iwashima [this message]
2020-12-07 13:24 ` [PATCH v2 bpf-next 12/13] bpf: Call bpf_run_sk_reuseport() for socket migration Kuniyuki Iwashima
2020-12-07 13:24 ` [PATCH v2 bpf-next 13/13] bpf: Test BPF_SK_REUSEPORT_SELECT_OR_MIGRATE 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=20201207132456.65472-12-kuniyu@amazon.co.jp \
--to=kuniyu@amazon.co.jp \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=benh@amazon.com \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=kafai@fb.com \
--cc=kuba@kernel.org \
--cc=kuni1840@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
/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).