public inbox for netdev@vger.kernel.org
 help / color / mirror / Atom feed
From: Eric Dumazet <eric.dumazet@gmail.com>
To: Jiri Pirko <jpirko@redhat.com>
Cc: netdev@vger.kernel.org, davem@davemloft.net,
	shemminger@vyatta.com, kaber@trash.net
Subject: Re: [PATCH net-next-2.6] net: replace hooks in __netif_receive_skb V3
Date: Fri, 28 May 2010 09:02:43 +0200	[thread overview]
Message-ID: <1275030163.2650.3.camel@edumazet-laptop> (raw)
In-Reply-To: <20100528061241.GC2823@psychotron.redhat.com>

Le vendredi 28 mai 2010 à 08:12 +0200, Jiri Pirko a écrit :

> diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
> index a1bff65..f54b97d 100644
> --- a/include/linux/netdevice.h
> +++ b/include/linux/netdevice.h
> @@ -254,6 +254,16 @@ struct netdev_hw_addr_list {
>  #define netdev_for_each_mc_addr(ha, dev) \
>  	netdev_hw_addr_list_for_each(ha, &(dev)->mc)
>  
> +
> +struct netdev_rx_handler {
> +	struct list_head	list;
> +	unsigned int		order;
> +#define NETDEV_RX_HANDLER_ORDER_BRIDGE	1
> +#define NETDEV_RX_HANDLER_ORDER_MACVLAN	2
> +	struct sk_buff		*(*callback)(struct sk_buff *skb);
> +	struct rcu_head		rcu;
> +};
> +
>  struct hh_cache {
>  	struct hh_cache *hh_next;	/* Next entry			     */
>  	atomic_t	hh_refcnt;	/* number of users                   */
> @@ -1031,6 +1041,9 @@ struct net_device {
>  	/* GARP */
>  	struct garp_port	*garp_port;
>  
> +	/* receive handlers (hooks) list */
> +	struct list_head	rx_handlers;
> +
>  	/* class/net/name entry */
>  	struct device		dev;
>  	/* space for optional device, statistics, and wireless sysfs groups */
> @@ -1685,6 +1698,11 @@ static inline void napi_free_frags(struct napi_struct *napi)
>  	napi->skb = NULL;
>  }
>  

Please chose another place to hold rx_handlers, to keep rx path memory
needs to minimum cache lines. Somewhere in the following section :

/*
 * Cache line mostly used on receive path (including eth_type_trans())
 */
        unsigned long           last_rx;        /* Time of last Rx      */
        /* Interface address info used in eth_type_trans() */
        unsigned char           *dev_addr;      /* hw address, (before bcast
                                                   because most packets are
                                                   unicast) */

        struct netdev_hw_addr_list      dev_addrs; /* list of device
                                                      hw addresses */

        unsigned char           broadcast[MAX_ADDR_LEN];        /* hw bcast add */

#ifdef CONFIG_RPS
        struct kset             *queues_kset;

        struct netdev_rx_queue  *_rx;

        /* Number of RX queues allocated at alloc_netdev_mq() time  */
        unsigned int            num_rx_queues;
#endif

        struct netdev_queue     rx_queue;


and before the :

	struct netdev_queue     *_tx ____cacheline_aligned_in_smp;




  reply	other threads:[~2010-05-28  7:02 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-05-27 18:08 [PATCH net-next-2.6] net: replace hooks in __netif_receive_skb V2 Jiri Pirko
2010-05-27 20:08 ` Stephen Hemminger
2010-05-28  5:51   ` Jiri Pirko
2010-05-28  6:12     ` [PATCH net-next-2.6] net: replace hooks in __netif_receive_skb V3 Jiri Pirko
2010-05-28  7:02       ` Eric Dumazet [this message]
2010-05-28  7:33         ` [PATCH net-next-2.6] net: replace hooks in __netif_receive_skb V4 Jiri Pirko
2010-06-01 15:28           ` net: replace hooks in __netif_receive_skb (v4) Stephen Hemminger
2010-06-01 15:41             ` Jiri Pirko
2010-06-01 16:10               ` Stephen Hemminger
2010-06-02  7:02                 ` Jiri Pirko
2010-06-01 16:13             ` Fischer, Anna
2010-06-02  6:50               ` Jiri Pirko
2010-06-02  7:24             ` net: " Jiri Pirko
2010-06-02  7:52             ` [PATCH net-next-2.6] net: replace hooks in __netif_receive_skb V5 Jiri Pirko
2010-06-02 14:11               ` David Miller
2010-06-02 15:07               ` Stephen Hemminger
2010-06-02 15:15                 ` Eric Dumazet
2010-06-02 20:43                   ` Paul E. McKenney
2010-06-02 16:20               ` Fischer, Anna

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=1275030163.2650.3.camel@edumazet-laptop \
    --to=eric.dumazet@gmail.com \
    --cc=davem@davemloft.net \
    --cc=jpirko@redhat.com \
    --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