Netdev List
 help / color / mirror / Atom feed
From: Eric Dumazet <eric.dumazet@gmail.com>
To: David Miller <davem@davemloft.net>
Cc: subramanian.vijay@gmail.com, therbert@google.com, netdev@vger.kernel.org
Subject: Re: Bug in computing data_len in tcp_sendmsg?
Date: Fri, 02 Dec 2011 21:48:00 +0100	[thread overview]
Message-ID: <1322858880.2762.69.camel@edumazet-laptop> (raw)
In-Reply-To: <1322858756.2762.68.camel@edumazet-laptop>

Le vendredi 02 décembre 2011 à 21:45 +0100, Eric Dumazet a écrit :
> Le vendredi 02 décembre 2011 à 15:24 -0500, David Miller a écrit :
> > From: Eric Dumazet <eric.dumazet@gmail.com>
> > Date: Fri, 02 Dec 2011 21:22:49 +0100
> > 
> > > Le vendredi 02 décembre 2011 à 13:40 -0500, David Miller a écrit :
> > > 
> > >> Yes, for non-SG this always was technically possible.
> > >> 
> > > 
> > > Yes this can, I reproduced it very easily.
> > > 
> > > I find this hard to believe...
> > 
> > Grrr :-)
> > 
> > Ok, I'll think about this some more.
> 
> Maybe a quick fix would be to trim not len bytes but (len & ~3) bytes ?
> 
> This avoid reallocations and complex code for a 'should never happen in
> normal circumstances'...
> 
> Retransmits could transmits 3 bytes already ACKed, is it a big deal ?
> 
> patch on top of linux/net tree :
> 
> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
> index 63170e2..4e108c5 100644
> --- a/net/ipv4/tcp_output.c
> +++ b/net/ipv4/tcp_output.c
> @@ -1126,7 +1126,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
>  
>  	/* If len == headlen, we avoid __skb_pull to preserve alignment. */
>  	if (unlikely(len < skb_headlen(skb)))
> -		__skb_pull(skb, len);
> +		__skb_pull(skb, len & ~3); /* preserve alignement of tcp/ip headers */
>  	else
>  		__pskb_trim_head(skb, len - skb_headlen(skb));
>  
> 


oops, thats the wrong version, here is it again :

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 63170e2..492b917 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1125,11 +1125,12 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
 		return -ENOMEM;
 
 	/* If len == headlen, we avoid __skb_pull to preserve alignment. */
-	if (unlikely(len < skb_headlen(skb)))
+	if (unlikely(len < skb_headlen(skb))) {
+		len &= ~3;
 		__skb_pull(skb, len);
-	else
+	} else {
 		__pskb_trim_head(skb, len - skb_headlen(skb));
-
+	}
 	TCP_SKB_CB(skb)->seq += len;
 	skb->ip_summed = CHECKSUM_PARTIAL;
 

  reply	other threads:[~2011-12-02 20:48 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-12-01  1:48 Bug in computing data_len in tcp_sendmsg? Tom Herbert
2011-12-01  3:42 ` Eric Dumazet
2011-12-01  4:06   ` Tom Herbert
2011-12-01  4:16     ` David Miller
2011-12-01  4:17     ` Eric Dumazet
2011-12-01  5:09       ` Tom Herbert
2011-12-01  9:15         ` Eric Dumazet
2011-12-01 17:29           ` Jesse Brandeburg
2011-12-01 18:04             ` David Miller
2011-12-01 20:37             ` Eric Dumazet
2011-12-01 22:18       ` Vijay Subramanian
2011-12-01 22:30         ` Eric Dumazet
2011-12-02  6:18           ` Vijay Subramanian
2011-12-02 11:59             ` Eric Dumazet
2011-12-02 15:44               ` Eric Dumazet
2011-12-02 16:05                 ` Eric Dumazet
2011-12-02 18:13                   ` David Miller
2011-12-02 18:36                     ` Eric Dumazet
2011-12-02 18:40                       ` David Miller
2011-12-02 20:22                         ` Eric Dumazet
2011-12-02 20:24                           ` David Miller
2011-12-02 20:45                             ` Eric Dumazet
2011-12-02 20:48                               ` Eric Dumazet [this message]
2011-12-02 21:30                               ` David Miller
2011-12-03 15:09                                 ` Eric Dumazet
2011-12-04  7:39                                   ` [PATCH] tcp: take care of misalignments Eric Dumazet
2011-12-04 18:21                                     ` David Miller
2011-12-04 18:51                                       ` Eric Dumazet
2011-12-05 23:45                                         ` David Miller

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=1322858880.2762.69.camel@edumazet-laptop \
    --to=eric.dumazet@gmail.com \
    --cc=davem@davemloft.net \
    --cc=netdev@vger.kernel.org \
    --cc=subramanian.vijay@gmail.com \
    --cc=therbert@google.com \
    /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