From: Haiyang Zhang <haiyangz@microsoft.com>
To: Eric Dumazet <eric.dumazet@gmail.com>,
David Miller <davem@davemloft.net>
Cc: "edumazet@google.com" <edumazet@google.com>,
"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
KY Srinivasan <kys@microsoft.com>
Subject: RE: [PATCH v2 net-next] net: make skb_set_owner_w() more robust
Date: Mon, 2 Nov 2015 20:05:12 +0000 [thread overview]
Message-ID: <BN1PR0301MB0770C038C9E0F34EBCCB605FCA2C0@BN1PR0301MB0770.namprd03.prod.outlook.com> (raw)
In-Reply-To: <1446421015.6254.106.camel@edumazet-glaptop2.roam.corp.google.com>
> -----Original Message-----
> From: Eric Dumazet [mailto:eric.dumazet@gmail.com]
> Sent: Sunday, November 1, 2015 6:37 PM
> To: David Miller <davem@davemloft.net>
> Cc: Haiyang Zhang <haiyangz@microsoft.com>; edumazet@google.com;
> netdev@vger.kernel.org; KY Srinivasan <kys@microsoft.com>
> Subject: [PATCH v2 net-next] net: make skb_set_owner_w() more robust
>
> From: Eric Dumazet <edumazet@google.com>
>
> skb_set_owner_w() is called from various places that assume
> skb->sk always point to a full blown socket (as it changes
> sk->sk_wmem_alloc)
>
> We'd like to attach skb to request sockets, and in the future
> to timewait sockets as well. For these kind of pseudo sockets,
> we need to take a traditional refcount and use sock_edemux()
> as the destructor.
>
> It is now time to un-inline skb_set_owner_w(), being too big.
>
> Fixes: ca6fb0651883 ("tcp: attach SYNACK messages to request sockets
> instead of listener")
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> Bisected-by: Haiyang Zhang <haiyangz@microsoft.com>
> ---
> v2: sock_edemux() must be guarded by CONFIG_INET
>
> include/net/sock.h | 17 ++---------------
> net/core/sock.c | 22 ++++++++++++++++++++++
> net/ipv4/tcp_output.c | 4 +---
> 3 files changed, 25 insertions(+), 18 deletions(-)
>
> diff --git a/include/net/sock.h b/include/net/sock.h
> index aeed5c95f3ca..f570e75e3da9 100644
> --- a/include/net/sock.h
> +++ b/include/net/sock.h
> @@ -1951,6 +1951,8 @@ static inline void skb_set_hash_from_sk(struct
> sk_buff *skb, struct sock *sk)
> }
> }
>
> +void skb_set_owner_w(struct sk_buff *skb, struct sock *sk);
> +
> /*
> * Queue a received datagram if it will fit. Stream and sequenced
> * protocols can't normally use this as they need to fit buffers in
> @@ -1959,21 +1961,6 @@ static inline void skb_set_hash_from_sk(struct
> sk_buff *skb, struct sock *sk)
> * Inlined as it's very short and called for pretty much every
> * packet ever received.
> */
> -
> -static inline void skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
> -{
> - skb_orphan(skb);
> - skb->sk = sk;
> - skb->destructor = sock_wfree;
> - skb_set_hash_from_sk(skb, sk);
> - /*
> - * We used to take a refcount on sk, but following operation
> - * is enough to guarantee sk_free() wont free this sock until
> - * all in-flight packets are completed
> - */
> - atomic_add(skb->truesize, &sk->sk_wmem_alloc);
> -}
> -
> static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
> {
> skb_orphan(skb);
> diff --git a/net/core/sock.c b/net/core/sock.c
> index 0ef30aa90132..7529eb9463be 100644
> --- a/net/core/sock.c
> +++ b/net/core/sock.c
> @@ -1656,6 +1656,28 @@ void sock_wfree(struct sk_buff *skb)
> }
> EXPORT_SYMBOL(sock_wfree);
>
> +void skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
> +{
> + skb_orphan(skb);
> + skb->sk = sk;
> +#ifdef CONFIG_INET
> + if (unlikely(!sk_fullsock(sk))) {
Thanks for the fix!
For some driver, like ours, this condition may not be "unlikely".
So could you remove the "unlikely"?
Thanks,
- Haiyang
next prev parent reply other threads:[~2015-11-02 20:05 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-10-29 21:49 [patch] tcp: attach SYNACK messages to request sockets instead of listener Haiyang Zhang
2015-10-29 22:58 ` Eric Dumazet
2015-10-30 19:38 ` Haiyang Zhang
2015-10-30 20:02 ` Eric Dumazet
2015-10-30 20:18 ` Eric Dumazet
2015-10-30 21:42 ` Haiyang Zhang
2015-10-30 23:52 ` Eric Dumazet
2015-11-01 17:20 ` [PATCH net-next] net: increase LL_MAX_HEADER if HYPERV_NET is enabled Eric Dumazet
2015-11-01 20:58 ` David Miller
2015-11-01 22:36 ` Eric Dumazet
2015-11-01 22:58 ` [PATCH net-next] net: make skb_set_owner_w() more robust Eric Dumazet
2015-11-01 23:18 ` kbuild test robot
2015-11-01 23:27 ` Eric Dumazet
2015-11-01 23:36 ` [PATCH v2 " Eric Dumazet
2015-11-02 20:05 ` Haiyang Zhang [this message]
2015-11-02 20:09 ` Eric Dumazet
2015-11-02 20:26 ` David Miller
2015-11-02 21:29 ` David Miller
2015-11-03 7:59 ` [PATCH net-next] net: increase LL_MAX_HEADER if HYPERV_NET is enabled KY Srinivasan
2015-11-03 15:33 ` David Miller
2015-11-03 16:37 ` Eric Dumazet
2015-11-03 17:34 ` Haiyang Zhang
2015-11-03 18:20 ` David Miller
2015-11-03 18:49 ` Haiyang Zhang
2015-11-03 19:50 ` David Miller
2015-11-03 21:00 ` Haiyang Zhang
2015-11-03 18:09 ` KY Srinivasan
2015-10-30 20:28 ` [patch] tcp: attach SYNACK messages to request sockets instead of listener KY Srinivasan
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=BN1PR0301MB0770C038C9E0F34EBCCB605FCA2C0@BN1PR0301MB0770.namprd03.prod.outlook.com \
--to=haiyangz@microsoft.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=eric.dumazet@gmail.com \
--cc=kys@microsoft.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).