netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Eric Dumazet <eric.dumazet@gmail.com>
To: Jakub Sitnicki <jakub@cloudflare.com>, bpf@vger.kernel.org
Cc: netdev@vger.kernel.org, kernel-team@cloudflare.com,
	John Fastabend <john.fastabend@gmail.com>,
	Lorenz Bauer <lmb@cloudflare.com>, Martin Lau <kafai@fb.com>
Subject: Re: [PATCH bpf-next v4 02/12] net, sk_msg: Annotate lockless access to sk_prot on clone
Date: Thu, 23 Jan 2020 09:18:39 -0800	[thread overview]
Message-ID: <a6bf279e-a998-84ab-4371-cd6c1ccbca5d@gmail.com> (raw)
In-Reply-To: <20200123155534.114313-3-jakub@cloudflare.com>



On 1/23/20 7:55 AM, Jakub Sitnicki wrote:
> sk_msg and ULP frameworks override protocol callbacks pointer in
> sk->sk_prot, while tcp accesses it locklessly when cloning the listening
> socket, that is with neither sk_lock nor sk_callback_lock held.
> 
> Once we enable use of listening sockets with sockmap (and hence sk_msg),
> there will be shared access to sk->sk_prot if socket is getting cloned
> while being inserted/deleted to/from the sockmap from another CPU:
> 
> Read side:
> 
> tcp_v4_rcv
>   sk = __inet_lookup_skb(...)
>   tcp_check_req(sk)
>     inet_csk(sk)->icsk_af_ops->syn_recv_sock
>       tcp_v4_syn_recv_sock
>         tcp_create_openreq_child
>           inet_csk_clone_lock
>             sk_clone_lock
>               READ_ONCE(sk->sk_prot)
> 
> Write side:
> 
> sock_map_ops->map_update_elem
>   sock_map_update_elem
>     sock_map_update_common
>       sock_map_link_no_progs
>         tcp_bpf_init
>           tcp_bpf_update_sk_prot
>             sk_psock_update_proto
>               WRITE_ONCE(sk->sk_prot, ops)
> 
> sock_map_ops->map_delete_elem
>   sock_map_delete_elem
>     __sock_map_delete
>      sock_map_unref
>        sk_psock_put
>          sk_psock_drop
>            sk_psock_restore_proto
>              tcp_update_ulp
>                WRITE_ONCE(sk->sk_prot, proto)
> 
> Mark the shared access with READ_ONCE/WRITE_ONCE annotations.
> 
> Acked-by: Martin KaFai Lau <kafai@fb.com>
> Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
> ---
>  include/linux/skmsg.h | 3 ++-
>  net/core/sock.c       | 5 +++--
>  net/ipv4/tcp_bpf.c    | 4 +++-
>  net/ipv4/tcp_ulp.c    | 3 ++-
>  net/tls/tls_main.c    | 3 ++-
>  5 files changed, 12 insertions(+), 6 deletions(-)
> 
> diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
> index 41ea1258d15e..55c834a5c25e 100644
> --- a/include/linux/skmsg.h
> +++ b/include/linux/skmsg.h
> @@ -352,7 +352,8 @@ static inline void sk_psock_update_proto(struct sock *sk,
>  	psock->saved_write_space = sk->sk_write_space;
>  
>  	psock->sk_proto = sk->sk_prot;
> -	sk->sk_prot = ops;
> +	/* Pairs with lockless read in sk_clone_lock() */
> +	WRITE_ONCE(sk->sk_prot, ops);


Note there are dozens of calls like

if (sk->sk_prot->handler)
    sk->sk_prot->handler(...);

Some of them being done lockless.

I know it is painful, but presumably we need

const struct proto *ops = READ_ONCE(sk->sk_prot);

if (ops->handler)
    ops->handler(....);


  reply	other threads:[~2020-01-23 17:18 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-01-23 15:55 [PATCH bpf-next v4 00/12] Extend SOCKMAP to store listening sockets Jakub Sitnicki
2020-01-23 15:55 ` [PATCH bpf-next v4 01/12] bpf, sk_msg: Don't clear saved sock proto on restore Jakub Sitnicki
2020-01-23 15:55 ` [PATCH bpf-next v4 02/12] net, sk_msg: Annotate lockless access to sk_prot on clone Jakub Sitnicki
2020-01-23 17:18   ` Eric Dumazet [this message]
2020-01-23 18:56     ` Jakub Sitnicki
2020-01-23 19:15       ` John Fastabend
2020-01-27  9:36         ` Jakub Sitnicki
2020-01-23 15:55 ` [PATCH bpf-next v4 03/12] net, sk_msg: Clear sk_user_data pointer on clone if tagged Jakub Sitnicki
2020-01-23 15:55 ` [PATCH bpf-next v4 04/12] tcp_bpf: Don't let child socket inherit parent protocol ops on copy Jakub Sitnicki
2020-01-23 15:55 ` [PATCH bpf-next v4 05/12] bpf, sockmap: Allow inserting listening TCP sockets into sockmap Jakub Sitnicki
2020-01-23 15:55 ` [PATCH bpf-next v4 06/12] bpf, sockmap: Don't set up sockmap progs for listening sockets Jakub Sitnicki
2020-01-23 15:55 ` [PATCH bpf-next v4 07/12] bpf, sockmap: Return socket cookie on lookup from syscall Jakub Sitnicki
2020-01-23 15:55 ` [PATCH bpf-next v4 08/12] bpf, sockmap: Let all kernel-land lookup values in SOCKMAP Jakub Sitnicki
2020-01-23 15:55 ` [PATCH bpf-next v4 09/12] bpf: Allow selecting reuseport socket from a SOCKMAP Jakub Sitnicki
2020-01-23 15:55 ` [PATCH bpf-next v4 10/12] net: Generate reuseport group ID on group creation Jakub Sitnicki
2020-01-23 17:02   ` Martin Lau
2020-01-23 15:55 ` [PATCH bpf-next v4 11/12] selftests/bpf: Extend SK_REUSEPORT tests to cover SOCKMAP Jakub Sitnicki
2020-01-23 15:55 ` [PATCH bpf-next v4 12/12] selftests/bpf: Tests for SOCKMAP holding listening sockets Jakub Sitnicki
2020-01-27 11:13 ` [PATCH bpf-next v4 00/12] Extend SOCKMAP to store " Daniel Borkmann
2020-01-27 13:03   ` Jakub Sitnicki

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=a6bf279e-a998-84ab-4371-cd6c1ccbca5d@gmail.com \
    --to=eric.dumazet@gmail.com \
    --cc=bpf@vger.kernel.org \
    --cc=jakub@cloudflare.com \
    --cc=john.fastabend@gmail.com \
    --cc=kafai@fb.com \
    --cc=kernel-team@cloudflare.com \
    --cc=lmb@cloudflare.com \
    --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).