Netdev List
 help / color / mirror / Atom feed
From: Eric Dumazet <eric.dumazet@gmail.com>
To: Stephen Hemminger <shemminger@vyatta.com>
Cc: Patrick McHardy <kaber@trash.net>,
	David Miller <davem@davemloft.net>,
	netdev@vger.kernel.org
Subject: Re: [PATCH] CHOKe flow scheduler (0.9)
Date: Tue, 18 Jan 2011 20:34:17 +0100	[thread overview]
Message-ID: <1295379257.9097.9.camel@edumazet-laptop> (raw)
In-Reply-To: <20110118110634.7386c757@nehalam>

Le mardi 18 janvier 2011 à 11:06 -0800, Stephen Hemminger a écrit :

> +static bool choke_match_flow(struct sk_buff *skb1, struct sk_buff *skb2)
> +{
> +	int off1, off2, poff;
> +	u8 ip_proto;
> +	u32 ihl;
> +
> +	if (skb1->protocol != skb2->protocol)
> +		return false;
> +
> +	off1 = skb_network_offset(skb1);
> +	off2 = skb_network_offset(skb2);

> +
> +	switch (skb1->protocol) {
> +	case __constant_htons(ETH_P_IP): {
> +		struct iphdr *ip1, *ip2;
> +
> +		if (!pskb_may_pull(skb1, sizeof(struct iphdr) + off1))
> +			return false;
> +
	pskb_network_may_pull() might be cleaner


> +		ip1 = (struct iphdr *) (skb1->data + off1);
	ip1 = ip_hdr(skb);

> +		if (ip1->frag_off & htons(IP_MF | IP_OFFSET))
> +			return false;	/* don't compare fragments */
> +

Hmm, we should compare fragments if possible.

saddr/daddr are available, not the ports.

> +		if (!pskb_may_pull(skb2, sizeof(struct iphdr) + off2))
> +			return false;
> +
> +		ip2 = (struct iphdr *) (skb2->data + off2);
> +		if (ip2->frag_off & htons(IP_MF | IP_OFFSET))
> +			return false;
> +
> +		if (ip1->protocol != ip2->protocol ||
> +		    ip1->saddr != ip2->saddr || ip1->daddr != ip2->daddr)
> +			return false;
> +


	What happens if ip1->ihl != ip2->ihl  here ?

Here I would add the fragment test :

	if ((ip1->frag_off | ip2->frag_off)) & htons(IP_MF | IP_OFFSET))
		return true;

> +		ip_proto = ip1->protocol;
> +		ihl = ip1->ihl;
> +		break;
> +	}
> +
> +	case __constant_htons(ETH_P_IPV6): {
> +		struct ipv6hdr *ip1, *ip2;
> +
> +		if (!pskb_may_pull(skb1, sizeof(struct ipv6hdr *) + off1))
> +			return false;

ouch... sizeof(sizeof(struct ipv6hdr *) is not what you want but
sizeof(struct ipv6hdr) is.

So just use :

	pskb_network_may_pull(skb1, sizeof(*ip1))
> +
> +		if (!pskb_may_pull(skb2, sizeof(struct ipv6hdr *) + off2))
> +			return false;
> +
> +		ip1 = (struct ipv6hdr *) (skb1->data + off1);
	ip1 = ipv6_hdr(skb1);
> +		ip2 = (struct ipv6hdr *) (skb2->data + off2);
> +
> +		if (ip1->nexthdr != ip2->nexthdr ||
> +		    ipv6_addr_cmp(&ip1->saddr, &ip2->saddr) != 0 ||
> +		    ipv6_addr_cmp(&ip1->daddr, &ip2->daddr))
> +			return false;
> +
> +		ihl = (40 >> 2);
> +		ip_proto = ip1->nexthdr;
> +		break;
> +	}
> +
> +	default:
> +		return false;
> +	}
> +




  reply	other threads:[~2011-01-18 19:35 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-01-13 17:27 [PATCH] CHOKe flow scheduler (0.7) Stephen Hemminger
2011-01-13 17:48 ` [PATCH] CHOKe flow scheduler (iproute) Stephen Hemminger
2011-01-13 21:01   ` Eric Dumazet
2011-01-13 18:00 ` [PATCH] CHOKe flow scheduler (0.7) Eric Dumazet
2011-01-13 18:02   ` Eric Dumazet
2011-01-13 20:37 ` Eric Dumazet
2011-01-13 23:34   ` [PATCH] CHOKe flow scheduler (0.8) Stephen Hemminger
2011-01-14  3:29     ` Eric Dumazet
2011-01-14  3:34       ` Eric Dumazet
2011-01-14  3:58         ` Eric Dumazet
2011-01-14 11:32           ` Eric Dumazet
2011-01-14 13:54     ` Patrick McHardy
2011-01-14 13:55       ` Patrick McHardy
2011-01-14 14:24         ` Eric Dumazet
2011-01-14 23:45           ` [PATCH] CHOKe flow scheduler (0.9) Stephen Hemminger
2011-01-15  7:45             ` Eric Dumazet
2011-01-17 17:25               ` Stephen Hemminger
2011-01-17 17:54                 ` Eric Dumazet
2011-01-18 19:06                   ` Stephen Hemminger
2011-01-18 19:34                     ` Eric Dumazet [this message]
2011-01-20 17:38                       ` [PATCH] CHOKe flow scheduler (0.10) Stephen Hemminger
2011-01-20 18:19                         ` Eric Dumazet
2011-01-20 22:46                           ` Eric Dumazet
2011-02-03  1:21                             ` [PATCH net-next] CHOKe flow scheduler (0.11) Stephen Hemminger
2011-02-03  1:59                               ` Eric Dumazet
2011-02-03  4:53                                 ` 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=1295379257.9097.9.camel@edumazet-laptop \
    --to=eric.dumazet@gmail.com \
    --cc=davem@davemloft.net \
    --cc=kaber@trash.net \
    --cc=netdev@vger.kernel.org \
    --cc=shemminger@vyatta.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