PERFORCE change 125169 for review

[Julian Elischer]

Marko Zec wrote:
> http://perforce.freebsd.org/chv.cgi?CH=125169
> 
> Change 125169 by zec at zec_tpx32 on 2007/08/15 11:28:57
> 
> 	Defer dispatching of netisr handlers for mbufs which have
> 	crossed a boundary between two vnets.  Direct dispatching
> 	in such cases could lead to various LORs, or in most
> 	extreme circumstances cause the kernel stack to overflow.
> 	
> 	This is accomplished by the introduction of a new mbuf
> 	flag, M_REMOTE_VNET, which must be set by any kernel entity
> 	moving a mbuf from one vnet context to another.  So far
> 	only ng_eiface and ng_wormhole can operate across a
> 	boundary between vnets, so update those two accordingly.
> 	The flag is then evaluated in netisr_dispatch(), and if
> 	set, the mbuf is queued for later processing instead of
> 	direct dispatching of netisr handler.
> 


Is it not possible for unix domain sockets to do so if the file
descriptor as an a part of the filesystem that is shared?

I hope soon (within a year) to have several vimages from a 
networking perspective but with a common filesystem root.
the processes will communicate between themselves using 
Unix domain sockets. (That's what they currently do but I want to
make them have separate routing tables etc.



> Affected files ...
> 
> .. //depot/projects/vimage/src/sys/net/netisr.c#6 edit
> .. //depot/projects/vimage/src/sys/netgraph/ng_eiface.c#7 edit
> .. //depot/projects/vimage/src/sys/netgraph/ng_wormhole.c#2 edit
> .. //depot/projects/vimage/src/sys/sys/mbuf.h#6 edit
> 
> Differences ...
> 
> ==== //depot/projects/vimage/src/sys/net/netisr.c#6 (text+ko) ====
> 
> @@ -178,8 +178,19 @@
>  	 * from an interface but does not guarantee ordering
>  	 * between multiple places in the system (e.g. IP
>  	 * dispatched from interfaces vs. IP queued from IPSec).
> +	 *
> +	 * If the kernel was compiled with options VIMAGE, also defer
> +	 * dispatch of netisr handlers for mbufs that have crossed a
> +	 * boundary between two vnets.  Direct dispatching in such
> +	 * cases could lead to various LORs, or in most extreme
> +	 * circumstances cause the kernel stack to overflow.
>  	 */
> +#ifndef VIMAGE
>  	if (netisr_direct && (ni->ni_flags & NETISR_MPSAFE)) {
> +#else
> +	if (netisr_direct && (ni->ni_flags & NETISR_MPSAFE) &&
> +	    !(m->m_flags & M_REMOTE_VNET)) {
> +#endif
>  		isrstat.isrs_directed++;
>  		/*
>  		 * NB: We used to drain the queue before handling
> 
> ==== //depot/projects/vimage/src/sys/netgraph/ng_eiface.c#7 (text+ko) ====
> 
> @@ -253,6 +253,12 @@
>  			continue;
>  		}
>  
> +#ifdef VIMAGE
> +		/* Mark up the mbuf if crossing vnet boundary */
> +		if (ifp->if_vnet != node->nd_vnet)
> +			m->m_flags |= M_REMOTE_VNET;
> +#endif
> +
>  		/*
>  		 * Send packet; if hook is not connected, mbuf will get
>  		 * freed.
> @@ -542,6 +548,12 @@
>  	/* Update interface stats */
>  	ifp->if_ipackets++;
>  
> +#ifdef VIMAGE
> +	/* Mark up the mbuf if crossing vnet boundary */
> +	if (ifp->if_vnet != hook->hk_node->nd_vnet)
> +		m->m_flags |= M_REMOTE_VNET;
> +#endif
> +
>  	(*ifp->if_input)(ifp, m);
>  
>  	/* Done */
> 
> ==== //depot/projects/vimage/src/sys/netgraph/ng_wormhole.c#2 (text+ko) ====
> 
> @@ -378,11 +378,14 @@
>          priv_p priv = NG_NODE_PRIVATE(NG_HOOK_NODE(hook));
>  	int error = 0;
>  	priv_p remote_priv = priv->remote_priv;
> +	struct mbuf *m;
>  
>  	if (priv->status != NG_WORMHOLE_ACTIVE) {
>  		NG_FREE_ITEM(item);
>  		error = ENOTCONN;
>  	} else {
> +		m = NGI_M(item);
> +		m->m_flags |= M_REMOTE_VNET;
>  		CURVNET_SET_QUIET(remote_priv->vnet);
>                  NG_FWD_ITEM_HOOK(error, item, remote_priv->hook);
>  		CURVNET_RESTORE();
> 
> ==== //depot/projects/vimage/src/sys/sys/mbuf.h#6 (text+ko) ====
> 
> @@ -192,6 +192,7 @@
>  #define	M_LASTFRAG	0x2000	/* packet is last fragment */
>  #define	M_VLANTAG	0x10000	/* ether_vtag is valid */
>  #define	M_PROMISC	0x20000	/* packet was not for us */
> +#define	M_REMOTE_VNET	0x40000	/* mbuf crossed boundary between two vnets */
>  
>  /*
>   * External buffer types: identify ext_buf type.
> @@ -214,7 +215,7 @@
>  #define	M_COPYFLAGS	(M_PKTHDR|M_EOR|M_RDONLY|M_PROTO1|M_PROTO1|M_PROTO2|\
>  			    M_PROTO3|M_PROTO4|M_PROTO5|M_SKIP_FIREWALL|\
>  			    M_BCAST|M_MCAST|M_FRAG|M_FIRSTFRAG|M_LASTFRAG|\
> -			    M_VLANTAG|M_PROMISC)
> +			    M_VLANTAG|M_PROMISC|M_REMOTE_VNET)
>  
>  /*
>   * Flags to purge when crossing layers.