public inbox for netdev@vger.kernel.org 
 help / color / mirror / Atom feed
From: Evgeniy Polyakov <zbr@ioremap•net>
To: Eric Dumazet <dada1@cosmosbay•com>
Cc: Stephen Hemminger <shemminger@vyatta•com>,
	Herbert Xu <herbert@gondor•apana.org.au>,
	berrange@redhat•com, et-mgmt-tools@redhat•com,
	davem@davemloft•net, netdev@vger•kernel.org
Subject: Re: virt-manager broken by bind(0) in net-next.
Date: Sat, 31 Jan 2009 00:50:08 +0300	[thread overview]
Message-ID: <20090130215008.GB12210@ioremap.net> (raw)
In-Reply-To: <498349F7.4050300@cosmosbay.com>

On Fri, Jan 30, 2009 at 07:41:59PM +0100, Eric Dumazet (dada1@cosmosbay•com) wrote:
> Reviewing commit a9d8f9110d7e953c2f2b521087a4179677843c2a
> 
> I see use of a hashinfo->bsockets field that :
> 
> - lacks proper lock/synchronization

It should contain rough number of sockets, there is no need to be very
precise because of this hueristic.

> - suffers from cache line ping pongs on SMP

I used free alignment slot so that socket structure would not be
icreased.

> Also there might be a problem at line 175
> 
> if (sk->sk_reuse && sk->sk_state != TCP_LISTEN && --attempts >= 0) { 
> 	spin_unlock(&head->lock);
> 	goto again;
> 
> If we entered inet_csk_get_port() with a non null snum, we can "goto again"
> while it was not expected.
> 
> diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
> index df8e72f..752c6b2 100644
> --- a/net/ipv4/inet_connection_sock.c
> +++ b/net/ipv4/inet_connection_sock.c
> @@ -172,7 +172,8 @@ tb_found:
>  		} else {
>  			ret = 1;
>  			if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) {
> -				if (sk->sk_reuse && sk->sk_state != TCP_LISTEN && --attempts >= 0) {
> +				if (sk->sk_reuse && sk->sk_state != TCP_LISTEN &&
> +					smallest_size == -1 &&  --attempts >= 0) {

I think it should be smallest_size != -1, since we really want to goto
to the again label when hueristic is used, which in turn changes
smallest_size.

-- 
	Evgeniy Polyakov

  reply	other threads:[~2009-01-30 21:50 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20090128212114.38be3e8c@extreme>
     [not found] ` <20090129103544.GC22110@redhat.com>
2009-01-30  5:35   ` virt-manager broken by bind(0) in net-next Stephen Hemminger
2009-01-30  8:16     ` Evgeniy Polyakov
     [not found]       ` <20090130081600.GA2717-i6C2adt8DTjR7s880joybQ@public.gmane.org>
2009-01-30 10:27         ` Daniel P. Berrange
2009-01-30 11:21           ` Evgeniy Polyakov
2009-01-30 12:53             ` Herbert Xu
     [not found]               ` <20090130125337.GA7155-lOAM2aK0SrRLBo1qDEOMRrpzq4S04n8Q@public.gmane.org>
2009-01-30 17:57                 ` Stephen Hemminger
2009-01-30 18:41                   ` Eric Dumazet
2009-01-30 21:50                     ` Evgeniy Polyakov [this message]
2009-01-30 22:30                       ` Eric Dumazet
2009-01-30 22:51                         ` Evgeniy Polyakov
     [not found]                           ` <20090130225113.GA13977-i6C2adt8DTjR7s880joybQ@public.gmane.org>
2009-01-31  0:36                             ` Stephen Hemminger
2009-01-31  8:35                               ` Evgeniy Polyakov
2009-01-31  2:52                             ` Stephen Hemminger
2009-01-31  8:37                               ` Evgeniy Polyakov
2009-01-31  9:17                                 ` Eric Dumazet
2009-01-31  9:31                                   ` Evgeniy Polyakov
2009-01-31  9:49                                     ` Eric Dumazet
2009-01-31  9:56                                       ` Evgeniy Polyakov
2009-01-31 10:17                                         ` Eric Dumazet
2009-02-01 12:42                                           ` Evgeniy Polyakov
2009-02-01 16:12                                             ` Eric Dumazet
2009-02-01 17:40                                               ` Evgeniy Polyakov
2009-02-01 20:31                                                 ` David Miller
     [not found]                       ` <20090130215008.GB12210-i6C2adt8DTjR7s880joybQ@public.gmane.org>
2009-02-01  5:58                         ` Stephen Hemminger
2009-02-01  9:07                           ` David Miller
2009-02-01 12:44                           ` Evgeniy Polyakov
     [not found]                     ` <498349F7.4050300-fPLkHRcR87vqlBn2x/YWAg@public.gmane.org>
2009-02-01  5:29                       ` Stephen Hemminger
2009-01-30  6:50   ` Stephen Hemminger

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=20090130215008.GB12210@ioremap.net \
    --to=zbr@ioremap$(echo .)net \
    --cc=berrange@redhat$(echo .)com \
    --cc=dada1@cosmosbay$(echo .)com \
    --cc=davem@davemloft$(echo .)net \
    --cc=et-mgmt-tools@redhat$(echo .)com \
    --cc=herbert@gondor$(echo .)apana.org.au \
    --cc=netdev@vger$(echo .)kernel.org \
    --cc=shemminger@vyatta$(echo .)com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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