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 10/13] bpf: Add migration to sk_reuseport_(kern|md).
Date: Mon, 7 Dec 2020 22:24:53 +0900 [thread overview]
Message-ID: <20201207132456.65472-11-kuniyu@amazon.co.jp> (raw)
In-Reply-To: <20201207132456.65472-1-kuniyu@amazon.co.jp>
This patch adds u8 migration field to sk_reuseport_kern and sk_reuseport_md
to signal the eBPF program if the kernel calls it for selecting a listener
for SYN or migrating sockets in the accept queue or an immature socket
during 3WHS.
Note that this field is accessible only if the attached type is
BPF_SK_REUSEPORT_SELECT_OR_MIGRATE.
Link: https://lore.kernel.org/netdev/20201123003828.xjpjdtk4ygl6tg6h@kafai-mbp.dhcp.thefacebook.com/
Suggested-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
---
include/linux/bpf.h | 1 +
include/linux/filter.h | 4 ++--
include/uapi/linux/bpf.h | 1 +
net/core/filter.c | 15 ++++++++++++---
net/core/sock_reuseport.c | 2 +-
tools/include/uapi/linux/bpf.h | 1 +
6 files changed, 18 insertions(+), 6 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index d05e75ed8c1b..cdeb27f4ad63 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1914,6 +1914,7 @@ struct sk_reuseport_kern {
u32 hash;
u32 reuseport_id;
bool bind_inany;
+ u8 migration;
};
bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type,
struct bpf_insn_access_aux *info);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 1b62397bd124..15d5bf13a905 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -967,12 +967,12 @@ void bpf_warn_invalid_xdp_action(u32 act);
#ifdef CONFIG_INET
struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
struct bpf_prog *prog, struct sk_buff *skb,
- u32 hash);
+ u32 hash, u8 migration);
#else
static inline struct sock *
bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
struct bpf_prog *prog, struct sk_buff *skb,
- u32 hash)
+ u32 hash, u8 migration)
{
return NULL;
}
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c7f6848c0226..cf518e83df5c 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4462,6 +4462,7 @@ 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 */
+ __u8 migration; /* Migration type */
};
#define BPF_TAG_SIZE 8
diff --git a/net/core/filter.c b/net/core/filter.c
index 77001a35768f..7bdf62f24044 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -9860,7 +9860,7 @@ int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf,
static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern,
struct sock_reuseport *reuse,
struct sock *sk, struct sk_buff *skb,
- u32 hash)
+ u32 hash, u8 migration)
{
reuse_kern->skb = skb;
reuse_kern->sk = sk;
@@ -9869,16 +9869,17 @@ static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern,
reuse_kern->hash = hash;
reuse_kern->reuseport_id = reuse->reuseport_id;
reuse_kern->bind_inany = reuse->bind_inany;
+ reuse_kern->migration = migration;
}
struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
struct bpf_prog *prog, struct sk_buff *skb,
- u32 hash)
+ u32 hash, u8 migration)
{
struct sk_reuseport_kern reuse_kern;
enum sk_action action;
- bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, hash);
+ bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, hash, migration);
action = BPF_PROG_RUN(prog, &reuse_kern);
if (action == SK_PASS)
@@ -10017,6 +10018,10 @@ sk_reuseport_is_valid_access(int off, int size,
case offsetof(struct sk_reuseport_md, hash):
return size == size_default;
+ case bpf_ctx_range(struct sk_reuseport_md, migration):
+ return prog->expected_attach_type == BPF_SK_REUSEPORT_SELECT_OR_MIGRATE &&
+ size == sizeof(__u8);
+
/* Fields that allow narrowing */
case bpf_ctx_range(struct sk_reuseport_md, eth_protocol):
if (size < sizeof_field(struct sk_buff, protocol))
@@ -10089,6 +10094,10 @@ 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, migration):
+ SK_REUSEPORT_LOAD_FIELD(migration);
+ break;
}
return insn - insn_buf;
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index 1011c3756c92..b877c8e552d2 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -313,7 +313,7 @@ static struct sock *__reuseport_select_sock(struct sock *sk, u32 hash,
goto select_by_hash;
if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT)
- sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, hash);
+ sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, hash, migration);
else
sk2 = run_bpf_filter(reuse, socks, prog, skb, hdr_len);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index c7f6848c0226..cf518e83df5c 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4462,6 +4462,7 @@ 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 */
+ __u8 migration; /* Migration type */
};
#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 ` Kuniyuki Iwashima [this message]
2020-12-07 13:24 ` [PATCH v2 bpf-next 11/13] bpf: Support BPF_FUNC_get_socket_cookie() " Kuniyuki Iwashima
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=20201207132456.65472-11-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).