Re: [PATCH 2/2] packet: Add fanout support.

[Eric Dumazet <eric.dumazet@gmail.com>]

Le lundi 04 juillet 2011 à 21:20 -0700, David Miller a écrit :
> Fanouts allow packet capturing to be demuxed to a set of AF_PACKET
> sockets.  Two fanout policies are implemented:
> 
> 1) Hashing based upon skb->rxhash
> 
> 2) Pure round-robin
> 
> An AF_PACKET socket must be fully bound before it tries to add itself
> to a fanout.  All AF_PACKET sockets trying to join the same fanout
> must all have the same bind settings.
> 
> Fanouts are identified (within a network namespace) by a 16-bit ID.
> The first socket to try to add itself to a fanout with a particular
> ID, creates that fanout.  When the last socket leaves the fanout
> (which happens only when the socket is closed), that fanout is
> destroyed.
> 
> Signed-off-by: David S. Miller <davem@davemloft.net>
> ---
>  include/linux/if_packet.h |    4 +
>  net/packet/af_packet.c    |  250 ++++++++++++++++++++++++++++++++++++++++++++-
>  2 files changed, 249 insertions(+), 5 deletions(-)
> 
> diff --git a/include/linux/if_packet.h b/include/linux/if_packet.h
> index 7b31863..1efa1cb 100644
> --- a/include/linux/if_packet.h
> +++ b/include/linux/if_packet.h
> @@ -49,6 +49,10 @@ struct sockaddr_ll {
>  #define PACKET_VNET_HDR			15
>  #define PACKET_TX_TIMESTAMP		16
>  #define PACKET_TIMESTAMP		17
> +#define PACKET_FANOUT			18
> +
> +#define PACKET_FANOUT_HASH		0
> +#define PACKET_FANOUT_LB		1
>  
>  struct tpacket_stats {
>  	unsigned int	tp_packets;
> diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
> index bb281bf..7db1e12 100644
> --- a/net/packet/af_packet.c
> +++ b/net/packet/af_packet.c
> @@ -187,9 +187,11 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg);
>  
>  static void packet_flush_mclist(struct sock *sk);
>  
> +struct packet_fanout;
>  struct packet_sock {
>  	/* struct sock has to be the first member of packet_sock */
>  	struct sock		sk;
> +	struct packet_fanout	*fanout;
>  	struct tpacket_stats	stats;
>  	struct packet_ring_buffer	rx_ring;
>  	struct packet_ring_buffer	tx_ring;
> @@ -212,6 +214,24 @@ struct packet_sock {
>  	struct packet_type	prot_hook ____cacheline_aligned_in_smp;
>  };
>  
> +#define PACKET_FANOUT_MAX	2048
> +
> +struct packet_fanout {
> +#ifdef CONFIG_NET_NS
> +	struct net		*net;
> +#endif
> +	int			num_members;
> +	u16			id;
> +	u8			type;
> +	u8			pad;
> +	atomic_t		rr_cur;
> +	struct list_head	list;
> +	struct sock		*arr[PACKET_FANOUT_MAX];

Thats about 16Kbytes, yet you use kzalloc()

> +	spinlock_t		lock;
> +	atomic_t		sk_ref;
> +	struct packet_type	prot_hook ____cacheline_aligned_in_smp;
> +};
> +

Maybe use a dynamic array ? I suspect most uses wont even reach 16
sockets anyway...