[net-next-2.6,v1] sctp: Add Auto-ASCONF support

SCTP reconfigure the IP addresses in the association by using ASCONF chunks as mentioned in RFC5061.  
For example, we can start to use the newly configured IP address in the existing association.  
ASCONF operation is invoked in two ways: 
First is done by the application to call sctp_bindx() system call.  
Second is automatic operation in the SCTP stack with address events in the host computer (called auto_asconf) .  
The former is already implemented, but the latter is not yet. This patch enables it with one sysctl parameter and setsockopt() system call.  

Signed-off-by: Michio Honda <micchie@sfc.wide.ad.jp>
---


--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Hi Michio Honda

I try to understand what you are doing now, and some comments inline.

And

this patch is too big for review, you'd better to split it to a patchset:
the improve on orig asconf code, the auto-asconf support, the socket
option etc.

> SCTP reconfigure the IP addresses in the association by using ASCONF chunks as mentioned in RFC5061.  
> For example, we can start to use the newly configured IP address in the existing association.  
> ASCONF operation is invoked in two ways: 
> First is done by the application to call sctp_bindx() system call.  
> Second is automatic operation in the SCTP stack with address events in the host computer (called auto_asconf) .  
> The former is already implemented, but the latter is not yet. This patch enables it with one sysctl parameter and setsockopt() system call.  
>
> Signed-off-by: Michio Honda <micchie@sfc.wide.ad.jp>
> ---
>
> diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
> index 11684d9..11c3060 100644
> --- a/include/linux/sysctl.h
> +++ b/include/linux/sysctl.h
> @@ -767,6 +767,7 @@ enum {
>  	NET_SCTP_SNDBUF_POLICY		 = 15,
>  	NET_SCTP_SACK_TIMEOUT		 = 16,
>  	NET_SCTP_RCVBUF_POLICY		 = 17,
> +	NET_SCTP_AUTO_ASCONF_ENABLE	 = 18,
>  };
>  
>  /* /proc/sys/net/bridge */
> diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h
> index c70d8cc..d7a4ee3 100644
> --- a/include/net/sctp/constants.h
> +++ b/include/net/sctp/constants.h
> @@ -441,4 +441,8 @@ enum {
>   */
>  #define SCTP_AUTH_RANDOM_LENGTH 32
>  
> +/* ASCONF PARAMETERS */
> +#define SCTP_ASCONF_V4_PARAM_LEN 16
> +#define SCTP_ASCONF_V6_PARAM_LEN 28
> +
>  #endif /* __sctp_constants_h__ */
> diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
> index 505845d..7161932 100644
> --- a/include/net/sctp/sctp.h
> +++ b/include/net/sctp/sctp.h
> @@ -121,6 +121,7 @@ extern int sctp_copy_local_addr_list(struct sctp_bind_addr *,
>  				     int flags);
>  extern struct sctp_pf *sctp_get_pf_specific(sa_family_t family);
>  extern int sctp_register_pf(struct sctp_pf *, sa_family_t);
> +void sctp_addr_wq_mgmt(union sctp_addr *, int);
>  
>  /*
>   * sctp/socket.c
> @@ -135,6 +136,8 @@ void sctp_sock_rfree(struct sk_buff *skb);
>  void sctp_copy_sock(struct sock *newsk, struct sock *sk,
>  		    struct sctp_association *asoc);
>  extern struct percpu_counter sctp_sockets_allocated;
> +int sctp_asconf_mgmt(struct sctp_endpoint *, struct sock *sk);
> +void sctp_add_addr_to_laddr(struct sockaddr *, struct sctp_association *);
>  
>  /*
>   * sctp/primitive.c
> diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
> index 9352d12..498a3cf 100644
> --- a/include/net/sctp/sm.h
> +++ b/include/net/sctp/sm.h
> @@ -259,6 +259,7 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc,
>  				       struct sctp_chunk *asconf);
>  int sctp_process_asconf_ack(struct sctp_association *asoc,
>  			    struct sctp_chunk *asconf_ack);
> +void sctp_path_check_and_react(struct sctp_association *, struct sockaddr *);
>  struct sctp_chunk *sctp_make_fwdtsn(const struct sctp_association *asoc,
>  				    __u32 new_cum_tsn, size_t nstreams,
>  				    struct sctp_fwdtsn_skip *skiplist);
> diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
> index cc9185c..0c6a6f4 100644
> --- a/include/net/sctp/structs.h
> +++ b/include/net/sctp/structs.h
> @@ -205,6 +205,11 @@ extern struct sctp_globals {
>  	 * It is a list of sctp_sockaddr_entry.
>  	 */
>  	struct list_head local_addr_list;
> +	int auto_asconf_enable;
> +	struct list_head addr_waitq;
> +	struct timer_list addr_wq_timer;
> +	struct list_head auto_asconf_eplist;
> +	spinlock_t addr_wq_lock;
>  
>  	/* Lock that protects the local_addr_list writers */
>  	spinlock_t addr_list_lock;
> @@ -264,6 +269,11 @@ extern struct sctp_globals {
>  #define sctp_port_hashtable		(sctp_globals.port_hashtable)
>  #define sctp_local_addr_list		(sctp_globals.local_addr_list)
>  #define sctp_local_addr_lock		(sctp_globals.addr_list_lock)
> +#define sctp_auto_asconf_eplist		(sctp_globals.auto_asconf_eplist)
> +#define sctp_addr_waitq			(sctp_globals.addr_waitq)
> +#define sctp_addr_wq_timer		(sctp_globals.addr_wq_timer)
> +#define sctp_addr_wq_lock		(sctp_globals.addr_wq_lock)
> +#define sctp_auto_asconf_enable		(sctp_globals.auto_asconf_enable)
>  #define sctp_scope_policy		(sctp_globals.ipv4_scope_policy)
>  #define sctp_addip_enable		(sctp_globals.addip_enable)
>  #define sctp_addip_noauth		(sctp_globals.addip_noauth_enable)
> @@ -796,6 +806,16 @@ struct sctp_sockaddr_entry {
>  	__u8 valid;
>  };
>  
> +#define SCTP_NEWADDR	1
> +#define SCTP_DELADDR	2
> +#define SCTP_ADDRESS_TICK_DELAY	500
> +struct sctp_addr_wait {
> +	struct list_head list;
> +	struct rcu_head rcu;

rcu is not need?

> +	union sctp_addr a;
> +	int	cmd;
> +};
> +
>  typedef struct sctp_chunk *(sctp_packet_phandler_t)(struct sctp_association *);
>  
>  /* This structure holds lists of chunks as we are assembling for
> @@ -1239,6 +1259,7 @@ sctp_scope_t sctp_scope(const union sctp_addr *);
>  int sctp_in_scope(const union sctp_addr *addr, const sctp_scope_t scope);
>  int sctp_is_any(struct sock *sk, const union sctp_addr *addr);
>  int sctp_addr_is_valid(const union sctp_addr *addr);
> +int sctp_is_ep_boundall(struct sock *sk);
>  
>  
>  /* What type of endpoint?  */
> @@ -1267,6 +1288,7 @@ struct sctp_ep_common {
>  	/* Fields to help us manage our entries in the hash tables. */
>  	struct hlist_node node;
>  	int hashent;
> +	struct list_head auto_asconf_list;
>  
>  	/* Runtime type information.  What kind of endpoint is this? */
>  	sctp_endpoint_type_t type;
> @@ -1901,6 +1923,17 @@ struct sctp_association {
>  	 * after reaching 4294967295.
>  	 */
>  	__u32 addip_serial;
> +	/* list of valid addresses in association local
> +	 * This list is needed to ensure base.bind_addr being a valid address
> +	 * list of the endpoint-wide.  When one of associations receives
> +	 * ASCONF-ACK, that address is added to this list.  When all
> +	 * associations belonging to the same endpoint receive ASCONF-ACKs,
> +	 * that address is added to base.bind_addr
> +	 */
> +	struct list_head asoc_laddr_list;
> +	union sctp_addr *asconf_addr_del_pending;
> +	__u32 asconf_del_pending_cid;
> +	int src_out_of_asoc_ok;
>  
>  	/* SCTP AUTH: list of the endpoint shared keys.  These
>  	 * keys are provided out of band by the user applicaton
> diff --git a/include/net/sctp/user.h b/include/net/sctp/user.h
> index e73ebda..75c96b1 100644
> --- a/include/net/sctp/user.h
> +++ b/include/net/sctp/user.h
> @@ -91,6 +91,7 @@ typedef __s32 sctp_assoc_t;
>  #define SCTP_PEER_AUTH_CHUNKS	26	/* Read only */
>  #define SCTP_LOCAL_AUTH_CHUNKS	27	/* Read only */
>  #define SCTP_GET_ASSOC_NUMBER	28	/* Read only */
> +#define SCTP_AUTO_ASCONF	29
>  
>  /* Internal Socket Options. Some of the sctp library functions are
>   * implemented using these socket options.
> diff --git a/net/sctp/associola.c b/net/sctp/associola.c
> index 6b04287..082f1f0 100644
> --- a/net/sctp/associola.c
> +++ b/net/sctp/associola.c
> @@ -280,6 +280,10 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
>  	if (sctp_addip_noauth)
>  		asoc->peer.asconf_capable = 1;
>  
> +	asoc->asconf_addr_del_pending = NULL;
> +	asoc->asconf_del_pending_cid = 0;
> +	asoc->src_out_of_asoc_ok = 0;
> +	INIT_LIST_HEAD(&asoc->asoc_laddr_list);
>  	/* Create an input queue.  */
>  	sctp_inq_init(&asoc->base.inqueue);
>  	sctp_inq_set_th_handler(&asoc->base.inqueue, sctp_assoc_bh_rcv);
> @@ -446,6 +450,18 @@ void sctp_association_free(struct sctp_association *asoc)
>  	/* Free any cached ASCONF_ACK chunk. */
>  	sctp_assoc_free_asconf_acks(asoc);
>  
> +	/* Free pending address space being deleted */
> +	if (asoc->asconf_addr_del_pending != NULL)
> +		kfree(asoc->asconf_addr_del_pending);
> +	if (!list_empty(&asoc->asoc_laddr_list)) {
> +		struct sctp_sockaddr_entry *laddr, *tmp;
> +		list_for_each_entry_safe(laddr, tmp, &asoc->asoc_laddr_list, \
> +		    list) {
> +			list_del(&laddr->list);
> +			kfree(laddr);
> +		}
> +	}
> +
>  	/* Free any cached ASCONF chunk. */
>  	if (asoc->addip_last_asconf)
>  		sctp_chunk_free(asoc->addip_last_asconf);
> @@ -620,6 +636,7 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc,
>  			if (!mod_timer(&active->T3_rtx_timer,
>  					jiffies + active->rto))
>  				sctp_transport_hold(active);
> +		active->flight_size += peer->flight_size;
>  	}
>  
>  	asoc->peer.transport_count--;
> @@ -1277,7 +1294,7 @@ void sctp_assoc_update(struct sctp_association *asoc,
>   */
>  void sctp_assoc_update_retran_path(struct sctp_association *asoc)
>  {
> -	struct sctp_transport *t, *next;
> +	struct sctp_transport *t, *next, *unconfirmed;
>  	struct list_head *head = &asoc->peer.transport_addr_list;
>  	struct list_head *pos;
>  
> @@ -1287,7 +1304,7 @@ void sctp_assoc_update_retran_path(struct sctp_association *asoc)
>  	/* Find the next transport in a round-robin fashion. */
>  	t = asoc->peer.retran_path;
>  	pos = &t->transports;
> -	next = NULL;
> +	next = unconfirmed = NULL;
>  
>  	while (1) {
>  		/* Skip the head. */
> @@ -1318,11 +1335,15 @@ void sctp_assoc_update_retran_path(struct sctp_association *asoc)
>  			 */
>  			if (t->state != SCTP_UNCONFIRMED && !next)
>  				next = t;
> +			else if (t->state == SCTP_UNCONFIRMED)
> +				unconfirmed = t;
>  		}
>  	}
>  
>  	if (t)
>  		asoc->peer.retran_path = t;
> +	else if (unconfirmed)
> +		asoc->peer.retran_path = t = unconfirmed;
>  
>  	SCTP_DEBUG_PRINTK_IPADDR("sctp_assoc_update_retran_path:association"
>  				 " %p addr: ",
> diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c
> index faf71d1..426715f 100644
> --- a/net/sctp/bind_addr.c
> +++ b/net/sctp/bind_addr.c
> @@ -536,6 +536,23 @@ int sctp_in_scope(const union sctp_addr *addr, sctp_scope_t scope)
>  	return 0;
>  }
>  
> +int sctp_is_ep_boundall(struct sock *sk)
> +{
> +	struct sctp_bind_addr *bp;
> +	struct sctp_sockaddr_entry *addr;
> +
> +	bp = &sctp_sk(sk)->ep->base.bind_addr;
> +	if (sctp_list_single_entry(&bp->address_list)) {
> +		addr = list_entry(bp->address_list.next,
> +				  struct sctp_sockaddr_entry, list);
> +		if (sctp_is_any(sk, &addr->a))
> +			return 1;
> +		else
> +			return 0;
> +	}
> +	return 1;
> +}
> +
>  /********************************************************************
>   * 3rd Level Abstractions
>   ********************************************************************/
> diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
> index 865ce7b..471facd 100644
> --- a/net/sctp/ipv6.c
> +++ b/net/sctp/ipv6.c
> @@ -105,6 +105,7 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev,
>  			addr->valid = 1;
>  			spin_lock_bh(&sctp_local_addr_lock);
>  			list_add_tail_rcu(&addr->list, &sctp_local_addr_list);
> +			sctp_addr_wq_mgmt(&addr->a, SCTP_NEWADDR);
>  			spin_unlock_bh(&sctp_local_addr_lock);
>  		}
>  		break;
> @@ -115,6 +116,7 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev,
>  			if (addr->a.sa.sa_family == AF_INET6 &&
>  					ipv6_addr_equal(&addr->a.v6.sin6_addr,
>  						&ifa->addr)) {
> +				sctp_addr_wq_mgmt(&addr->a, SCTP_DELADDR);
>  				found = 1;
>  				addr->valid = 0;
>  				list_del_rcu(&addr->list);
> @@ -332,8 +334,26 @@ static void sctp_v6_get_saddr(struct sctp_sock *sk,
>  				matchlen = bmatchlen;
>  			}
>  		}
> +		if (laddr->state == SCTP_ADDR_NEW && asoc->src_out_of_asoc_ok) {
> +			bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a);
> +			if (!baddr || (matchlen < bmatchlen)) {
> +				baddr = &laddr->a;
> +				matchlen = bmatchlen;
> +			}
> +		}
> +	}
> +	if (baddr == NULL) {
> +		/* We don't have a valid src addr in "endpoint-wide".
> +		 * Looking up in assoc-locally valid address list.
> +		 */
> +		list_for_each_entry(laddr, &asoc->asoc_laddr_list, list) {
> +			bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a);
> +			if (!baddr || (matchlen < bmatchlen)) {
> +				baddr = &laddr->a;
> +				matchlen = bmatchlen;
> +			}
> +		}
>  	}
> -
>  	if (baddr) {
>  		memcpy(saddr, baddr, sizeof(union sctp_addr));
>  		SCTP_DEBUG_PRINTK("saddr: %pI6\n", &saddr->v6.sin6_addr);
> diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
> index 26dc005..033ea20 100644
> --- a/net/sctp/outqueue.c
> +++ b/net/sctp/outqueue.c
> @@ -344,7 +344,14 @@ int sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk)
>  			break;
>  		}
>  	} else {
> -		list_add_tail(&chunk->list, &q->control_chunk_list);
> +		/* We add the ASCONF for the only one newly added address at
> +		 * the front of the queue
> +		 */
> +		if (q->asoc->src_out_of_asoc_ok && \
> +		    chunk->chunk_hdr->type == SCTP_CID_ASCONF)
> +			list_add(&chunk->list, &q->control_chunk_list);
> +		else
> +			list_add_tail(&chunk->list, &q->control_chunk_list);

Why we need to add at front of the queue?

>  		SCTP_INC_STATS(SCTP_MIB_OUTCTRLCHUNKS);
>  	}
>  
> @@ -850,6 +857,24 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout)
>  		case SCTP_CID_SHUTDOWN:
>  		case SCTP_CID_ECN_ECNE:
>  		case SCTP_CID_ASCONF:
> +			/* RFC 5061, 5.3
> +			 * F1) This means that until such time as the ASCONF
> +			 * containing the add is acknowledged, the sender MUST
> +			 * NOT use the new IP address as a source for ANY SCTP
> +			 * packet except on carrying an ASCONF Chunk.
> +			 */
> +			if (asoc->src_out_of_asoc_ok) {
> +				SCTP_DEBUG_PRINTK("outq_flush: out_of_asoc_ok, transmit chunk type %d\n",
> +				    chunk->chunk_hdr->type);
> +				packet = &transport->packet;
> +				sctp_packet_config(packet, vtag,
> +						asoc->peer.ecn_capable);
> +				sctp_packet_append_chunk(packet, chunk);
> +				error = sctp_packet_transmit(packet);
> +				if (error < 0)
> +					return error;
> +				goto sctp_flush_out;
> +			}
>  		case SCTP_CID_FWD_TSN:
>  			status = sctp_packet_transmit_chunk(packet, chunk,
>  							    one_packet);
> diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
> index 152976e..2859c16 100644
> --- a/net/sctp/protocol.c
> +++ b/net/sctp/protocol.c
> @@ -510,12 +510,20 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc,
>  		sctp_v4_dst_saddr(&dst_saddr, dst, htons(bp->port));
>  		rcu_read_lock();
>  		list_for_each_entry_rcu(laddr, &bp->address_list, list) {
> -			if (!laddr->valid || (laddr->state != SCTP_ADDR_SRC))
> +			if (!laddr->valid || (laddr->state != SCTP_ADDR_SRC &&
> +			    asoc->src_out_of_asoc_ok == 0))
>  				continue;
>  			if (sctp_v4_cmp_addr(&dst_saddr, &laddr->a))
>  				goto out_unlock;
>  		}
>  		rcu_read_unlock();
> +		/* We don't have a valid src addr in "endpoint-wide".
> +		 * Looking up in assoc-locally valid address list.
> +		 */
> +		list_for_each_entry(laddr, &asoc->asoc_laddr_list, list) {
> +			if (sctp_v4_cmp_addr(&dst_saddr, &laddr->a))
> +				goto out_unlock;
> +		}
>  
>  		/* None of the bound addresses match the source address of the
>  		 * dst. So release it.
> @@ -636,6 +644,182 @@ static void sctp_v4_ecn_capable(struct sock *sk)
>  	INET_ECN_xmit(sk);
>  }
>  
> +void sctp_addr_wq_timeout_handler(unsigned long arg)
> +{
> +	struct sctp_addr_wait *addrw = NULL;
> +	union sctp_addr *addr = NULL;
> +	struct sctp_ep_common *epb = NULL;
> +	struct sctp_endpoint *ep = NULL;
> +	int cnt = 0;

cnt is useless

> +
> +	spin_lock_bh(&sctp_addr_wq_lock);
> +retry_wq:
> +	if (list_empty(&sctp_addr_waitq)) {
> +		SCTP_DEBUG_PRINTK("sctp_addrwq_timo_handler: nothing in addr waitq\n");
> +		spin_unlock_bh(&sctp_addr_wq_lock);
> +		return;
> +	}
> +	addrw = list_first_entry(&sctp_addr_waitq, struct sctp_addr_wait, list);
> +	if (addrw->cmd != SCTP_NEWADDR && addrw->cmd != SCTP_DELADDR) {
> +		SCTP_DEBUG_PRINTK("sctp_addrwq_timo_handler: cmd is neither NEWADDR nor DELADDR\n");
> +		list_del(&addrw->list);
> +		kfree(addrw);
> +		goto retry_wq;
> +	}
> +
> +	addr = &addrw->a;
> +	SCTP_DEBUG_PRINTK_IPADDR("sctp_addrwq_timo_handler: the first ent in wq %p is ",
> +	    " for cmd %d at entry %p\n", &sctp_addr_waitq, addr, addrw->cmd,
> +	    addrw);
> +
> +	/* Now we send an ASCONF for each association */
> +	/* Note. we currently don't handle link local IPv6 addressees */
> +	if (addr->sa.sa_family == AF_INET6) {
> +		struct in6_addr *in6 = (struct in6_addr *)&addr->v6.sin6_addr;
> +
> +		if (ipv6_addr_type(&addr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) {
> +			SCTP_DEBUG_PRINTK("sctp_timo_handler: link local, hence don't tell eps\n");
> +			list_del(&addrw->list);
> +			kfree(addrw);
> +			goto retry_wq;
> +		}
> +		if (ipv6_chk_addr(&init_net, in6, NULL, 0) == 0 &&
> +		    addrw->cmd == SCTP_NEWADDR) {
> +			unsigned long timeo_val;
> +
> +			SCTP_DEBUG_PRINTK("sctp_timo_handler: this is on DAD, trying %d sec later\n",
> +			    SCTP_ADDRESS_TICK_DELAY);
> +			timeo_val = jiffies;
> +			timeo_val += msecs_to_jiffies(SCTP_ADDRESS_TICK_DELAY);
> +			(void)mod_timer(&sctp_addr_wq_timer, timeo_val);
> +			spin_unlock_bh(&sctp_addr_wq_lock);
> +			return;
> +		}
> +	}
> +	list_for_each_entry(epb, &sctp_auto_asconf_eplist, auto_asconf_list) {
> +		if (epb == NULL) {
> +			SCTP_DEBUG_PRINTK("addrwq_timo_handler: no epb\n");
> +			continue;
> +		}
> +		if (!sctp_is_ep_boundall(epb->sk))
> +			/* ignore bound-specific endpoints */
> +			continue;
> +		ep = sctp_ep(epb);
> +		sctp_bh_lock_sock(epb->sk);
> +		if (sctp_asconf_mgmt(ep, epb->sk) < 0) {
> +			SCTP_DEBUG_PRINTK("sctp_addrwq_timo_handler: sctp_asconf_mgmt failed\n");
> +			sctp_bh_unlock_sock(epb->sk);
> +			continue;
> +		}
> +		sctp_bh_unlock_sock(epb->sk);
> +		++cnt;
> +	}
> +
> +	list_del(&addrw->list);
> +	kfree(addrw);
> +
> +	if (list_empty(&sctp_addr_waitq)) {
> +		spin_unlock_bh(&sctp_addr_wq_lock);
> +		return;
> +	} else
> +		goto retry_wq;
> +
> +	spin_unlock_bh(&sctp_addr_wq_lock);
> +}
> +
> +void sctp_addr_wq_mgmt(union sctp_addr *reqaddr, int cmd)
> +{
> +	struct sctp_addr_wait *addrw = NULL;
> +	struct sctp_addr_wait *addrw_new = NULL;
> +	unsigned long timeo_val;
> +	union sctp_addr *tmpaddr;
> +
> +	/* first, we check if an opposite message already exist in the queue.
> +	 * If we found such message, it is removed.
> +	 * This operation is a bit stupid, but the DHCP client attaches the
> +	 * new address after a couple of addition and deletion of that address
> +	 */
> +
> +	if (reqaddr == NULL) {
> +		SCTP_DEBUG_PRINTK("sctp_addr_wq_mgmt: no address message?\n");
> +		return;
> +	}
> +
> +	spin_lock_bh(&sctp_addr_wq_lock);
> +	/* Offsets existing events in addr_wq */
> +	list_for_each_entry(addrw, &sctp_addr_waitq, list) {
> +		if (addrw->a.sa.sa_family != reqaddr->sa.sa_family)
> +			continue;
> +		if (reqaddr->sa.sa_family == AF_INET) {
> +			if (reqaddr->v4.sin_addr.s_addr ==
> +			    addrw->a.v4.sin_addr.s_addr) {
> +				if (cmd != addrw->cmd) {
> +					tmpaddr = &addrw->a;
> +					SCTP_DEBUG_PRINTK_IPADDR("sctp_addr_wq_mgmt offsets existing entry for %d ",
> +					    " in waitq %p\n", addrw->cmd,
> +					    tmpaddr, &sctp_addr_waitq);
> +					list_del(&addrw->list);
> +					kfree(addrw);
> +					/* nothing to do anymore */
> +					spin_unlock_bh(&sctp_addr_wq_lock);
> +					return;
> +				}
> +			}
> +		} else if (reqaddr->sa.sa_family == AF_INET6) {
> +			if (ipv6_addr_equal(&reqaddr->v6.sin6_addr,
> +			    &addrw->a.v6.sin6_addr)) {
> +				if (cmd != addrw->cmd) {
> +					tmpaddr = &addrw->a;
> +					SCTP_DEBUG_PRINTK_IPADDR("sctp_addr_wq_mgmt: offsets existing entry for %d ",
> +					    " in waitq %p\n", addrw->cmd,
> +					    tmpaddr, &sctp_addr_waitq);
> +					list_del(&addrw->list);
> +					kfree(addrw);
> +					spin_unlock_bh(&sctp_addr_wq_lock);
> +					return;
> +				}
> +			}
> +		}
> +	}
> +
> +	/* OK, we have to add the new address to the wait queue */
> +	addrw_new = kzalloc(sizeof(struct sctp_addr_wait), GFP_ATOMIC);
> +	if (addrw_new == NULL) {
> +		SCTP_DEBUG_PRINTK("sctp_addr_weitq_mgmt no memory? return\n");
> +		spin_unlock_bh(&sctp_addr_wq_lock);
> +		return;
> +	}
> +	if (reqaddr->sa.sa_family == AF_INET) {
> +		addrw_new->a.v4.sin_family = AF_INET;
> +		addrw_new->a.v4.sin_addr.s_addr = reqaddr->v4.sin_addr.s_addr;
> +	} else if (reqaddr->sa.sa_family == AF_INET6) {
> +		addrw_new->a.v6.sin6_family = AF_INET6;
> +		ipv6_addr_copy(&addrw_new->a.v6.sin6_addr,
> +		    &reqaddr->v6.sin6_addr);
> +	} else {
> +		SCTP_DEBUG_PRINTK("sctp_addr_waitq_mgmt: Unknown family of request addr, return\n");
> +		kfree(addrw_new);
> +		spin_unlock_bh(&sctp_addr_wq_lock);
> +		return;
> +	}
> +	addrw_new->cmd = cmd;
> +	list_add_tail(&addrw_new->list, &sctp_addr_waitq);
> +	tmpaddr = &addrw_new->a;
> +	SCTP_DEBUG_PRINTK_IPADDR("sctp_addr_wq_mgmt add new entry for cmd:%d ",
> +	    " in waitq %p, start a timer\n",
> +	    addrw_new->cmd, tmpaddr, &sctp_addr_waitq);
> +
> +	if (timer_pending(&sctp_addr_wq_timer)) {
> +		SCTP_DEBUG_PRINTK("sctp_addr_wq_mgmt: addr_wq timer is already running\n");
> +		spin_unlock_bh(&sctp_addr_wq_lock);
> +		return;
> +	}
> +	timeo_val = jiffies;
> +	timeo_val += msecs_to_jiffies(SCTP_ADDRESS_TICK_DELAY);
> +	(void)mod_timer(&sctp_addr_wq_timer, timeo_val);
> +	spin_unlock_bh(&sctp_addr_wq_lock);
> +}
> +
>  /* Event handler for inet address addition/deletion events.
>   * The sctp_local_addr_list needs to be protocted by a spin lock since
>   * multiple notifiers (say IPv4 and IPv6) may be running at the same
> @@ -663,6 +847,7 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev,
>  			addr->valid = 1;
>  			spin_lock_bh(&sctp_local_addr_lock);
>  			list_add_tail_rcu(&addr->list, &sctp_local_addr_list);
> +			sctp_addr_wq_mgmt(&addr->a, SCTP_NEWADDR);
>  			spin_unlock_bh(&sctp_local_addr_lock);
>  		}
>  		break;
> @@ -673,6 +858,7 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev,
>  			if (addr->a.sa.sa_family == AF_INET &&
>  					addr->a.v4.sin_addr.s_addr ==
>  					ifa->ifa_local) {
> +				sctp_addr_wq_mgmt(&addr->a, SCTP_DELADDR);
>  				found = 1;
>  				addr->valid = 0;
>  				list_del_rcu(&addr->list);
> @@ -1277,6 +1463,12 @@ SCTP_STATIC __init int sctp_init(void)
>  
>  	/* Initialize the local address list. */
>  	INIT_LIST_HEAD(&sctp_local_addr_list);
> +	INIT_LIST_HEAD(&sctp_addr_waitq);
> +	INIT_LIST_HEAD(&sctp_auto_asconf_eplist);
> +	spin_lock_init(&sctp_addr_wq_lock);
> +	sctp_addr_wq_timer.expires = 0;
> +	setup_timer(&sctp_addr_wq_timer, sctp_addr_wq_timeout_handler,
> +	    (unsigned long)NULL);

We also need to stop the timer when mod is removed.

>  	spin_lock_init(&sctp_local_addr_lock);
>  	sctp_get_local_addr_list();
>  
> diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
> index de98665..b5ca24a 100644
> --- a/net/sctp/sm_make_chunk.c
> +++ b/net/sctp/sm_make_chunk.c
> @@ -2651,6 +2651,61 @@ __u32 sctp_generate_tsn(const struct sctp_endpoint *ep)
>  	return retval;
>  }
>  
> +void
> +sctp_path_check_and_react(struct sctp_association *asoc, struct sockaddr *sa)
> +{
> +	struct sctp_transport *trans;
> +	int addrnum, family;
> +	struct sctp_sockaddr_entry *saddr;
> +	struct sctp_bind_addr *bp;
> +	union sctp_addr *tmpaddr;
> +
> +	family = sa->sa_family;
> +	bp = &asoc->base.bind_addr;
> +	addrnum = 0;
> +	/* count up the number of local addresses in the same family */
> +	list_for_each_entry(saddr, &bp->address_list, list) {
> +		if (saddr->a.sa.sa_family == family) {
> +			tmpaddr = &saddr->a;
> +			if (family == AF_INET6 &&
> +			    ipv6_addr_type(&tmpaddr->v6.sin6_addr) &
> +			    IPV6_ADDR_LINKLOCAL) {
> +				continue;
> +			}
> +			addrnum++;
> +		}
> +	}
> +	if (addrnum == 1) {
> +		union sctp_addr *tmpaddr;
> +		tmpaddr = (union sctp_addr *)sa;
> +		SCTP_DEBUG_PRINTK_IPADDR("pcheck_react: only 1 local addr in asoc %p ",
> +		    " family %d\n", asoc, tmpaddr, family);
> +		list_for_each_entry(trans, &asoc->peer.transport_addr_list,
> +		    transports) {
> +			/* reset path information and release refcount to the
> +			 * dst_entry  based on the src change */
> +			sctp_transport_hold(trans);
> +			trans->cwnd = min(4*asoc->pathmtu,
> +			    max_t(__u32, 2*asoc->pathmtu, 4380));
> +			trans->ssthresh = asoc->peer.i.a_rwnd;
> +			trans->rtt = 0;
> +			trans->srtt = 0;
> +			trans->rttvar = 0;
> +			trans->rto = asoc->rto_initial;
> +			dst_release(trans->dst);
> +			trans->dst = NULL;
> +			memset(&trans->saddr, 0, sizeof(union sctp_addr));
> +			sctp_transport_route(trans, NULL,
> +			    sctp_sk(asoc->base.sk));
> +			SCTP_DEBUG_PRINTK_IPADDR("we freed dst_entry (asoc: %p dst: ",
> +			    " trans: %p)\n", asoc, (&trans->ipaddr), trans);
> +			trans->rto_pending = 1;
> +			sctp_transport_put(trans);
> +		}
> +	}
> +	return;
> +}
> +
>  /*
>   * ADDIP 3.1.1 Address Configuration Change Chunk (ASCONF)
>   *      0                   1                   2                   3
> @@ -2744,11 +2799,29 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *asoc,
>  	int			addr_param_len = 0;
>  	int 			totallen = 0;
>  	int 			i;
> +	sctp_addip_param_t del_param; /* 8 Bytes (Type 0xC002, Len and CrrID) */
> +	sctp_addip_param_t spr_param;
> +	struct sctp_af *del_af;
> +	struct sctp_af *spr_af;
> +	int del_addr_param_len = 0;
> +	int spr_addr_param_len = 0;
> +	int del_paramlen = sizeof(sctp_addip_param_t);
> +	int spr_paramlen = sizeof(sctp_addip_param_t);
> +	union sctp_addr_param del_addr_param; /* (v4) 8 Bytes, (v6) 20 Bytes */
> +	union sctp_addr_param spr_addr_param;
> +	int			v4 = 0;
> +	int			v6 = 0;
>  
>  	/* Get total length of all the address parameters. */
>  	addr_buf = addrs;
>  	for (i = 0; i < addrcnt; i++) {
>  		addr = (union sctp_addr *)addr_buf;
> +		if (addr != NULL) {
> +			if (addr->sa.sa_family == AF_INET)
> +				v4 = 1;
> +			else if (addr->sa.sa_family == AF_INET6)
> +				v6 = 1;
> +		}
>  		af = sctp_get_af_specific(addr->v4.sin_family);
>  		addr_param_len = af->to_addr_param(addr, &addr_param);
>  
> @@ -2757,6 +2830,40 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *asoc,
>  
>  		addr_buf += af->sockaddr_len;
>  	}
> +	/* Add the length of a pending address being deleted */
> +	if (flags == SCTP_PARAM_ADD_IP && asoc->asconf_addr_del_pending) {
> +		if ((asoc->asconf_addr_del_pending->sa.sa_family == AF_INET
> +		    && v4) ||
> +		    (asoc->asconf_addr_del_pending->sa.sa_family == AF_INET6
> +		    && v6)) {
> +			del_af = sctp_get_af_specific(
> +			    asoc->asconf_addr_del_pending->sa.sa_family);
> +			del_addr_param_len = del_af->to_addr_param(
> +			    asoc->asconf_addr_del_pending, &del_addr_param);
> +			totallen += del_paramlen;
> +			totallen += del_addr_param_len;
> +			SCTP_DEBUG_PRINTK("mkasconf_update_ip: now we picked del_pending addr, totallen for all addresses is %d\n",
> +			    totallen);
> +			/* for Set Primary (equal size as del parameters */
> +			totallen += del_paramlen;
> +			totallen += del_addr_param_len;
> +		}
> +		if (v4) {
> +			if (totallen != SCTP_ASCONF_V4_PARAM_LEN * 2 &&
> +			    totallen != SCTP_ASCONF_V4_PARAM_LEN * 3) {
> +				SCTP_DEBUG_PRINTK("mkasconf_update_ip: incorrect total length of ASCONF parameters, del + add MUST be 32 bytes, but %d bytes\n", totallen);
> +			return NULL;
> +			}
> +		} else if (v6) {
> +			if (totallen != SCTP_ASCONF_V6_PARAM_LEN * 2 &&
> +			    totallen != SCTP_ASCONF_V6_PARAM_LEN * 3) {
> +				SCTP_DEBUG_PRINTK("mkasconf_update_ip: incorrect total length of ASCONF parameters, del + add MUST be 56 bytes, but %d bytes\n", totallen);
> +			return NULL;
> +			}
> +		}
> +	}
> +	SCTP_DEBUG_PRINTK("mkasconf_update_ip: call mkasconf() for %d bytes\n",
> +	    totallen);
>  
>  	/* Create an asconf chunk with the required length. */
>  	retval = sctp_make_asconf(asoc, laddr, totallen);
> @@ -2778,6 +2885,32 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *asoc,
>  
>  		addr_buf += af->sockaddr_len;
>  	}
> +	if (flags == SCTP_PARAM_ADD_IP && asoc->asconf_addr_del_pending) {
> +		addr = asoc->asconf_addr_del_pending;
> +		del_af = sctp_get_af_specific(addr->v4.sin_family);
> +		del_addr_param_len = del_af->to_addr_param(addr,
> +		    &del_addr_param);
> +		del_param.param_hdr.type = SCTP_PARAM_DEL_IP;
> +		del_param.param_hdr.length = htons(del_paramlen +
> +		    del_addr_param_len);
> +		del_param.crr_id = i;
> +		asoc->asconf_del_pending_cid = i;
> +
> +		sctp_addto_chunk(retval, del_paramlen, &del_param);
> +		sctp_addto_chunk(retval, del_addr_param_len, &del_addr_param);
> +		/* For SET_PRIMARY */
> +		addr_buf = addrs;
> +		addr = (union sctp_addr *)addr_buf;
> +		spr_af = sctp_get_af_specific(addr->v4.sin_family);
> +		spr_addr_param_len = spr_af->to_addr_param(addr,
> +		    &spr_addr_param);
> +		spr_param.param_hdr.type = SCTP_PARAM_SET_PRIMARY;
> +		spr_param.param_hdr.length = htons(spr_paramlen +
> +		    spr_addr_param_len);
> +		spr_param.crr_id = (i+1);
> +		sctp_addto_chunk(retval, spr_paramlen, &spr_param);
> +		sctp_addto_chunk(retval, spr_addr_param_len, &spr_addr_param);
> +	}
>  	return retval;
>  }
>  
> @@ -2990,7 +3123,7 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc,
>  		 * an Error Cause TLV set to the new error code 'Request to
>  		 * Delete Source IP Address'
>  		 */
> -		if (sctp_cmp_addr_exact(sctp_source(asconf), &addr))
> +		if (sctp_cmp_addr_exact(&asconf->source, &addr))
>  			return SCTP_ERROR_DEL_SRC_IP;
>  
>  		/* Section 4.2.2
> @@ -3171,7 +3304,6 @@ static void sctp_asconf_param_success(struct sctp_association *asoc,
>  	struct sctp_bind_addr *bp = &asoc->base.bind_addr;
>  	union sctp_addr_param *addr_param;
>  	struct sctp_transport *transport;
> -	struct sctp_sockaddr_entry *saddr;
>  
>  	addr_param = (union sctp_addr_param *)
>  			((void *)asconf_param + sizeof(sctp_addip_param_t));
> @@ -3186,9 +3318,16 @@ static void sctp_asconf_param_success(struct sctp_association *asoc,
>  		 * held, so the list can not change.
>  		 */
>  		local_bh_disable();
> -		list_for_each_entry(saddr, &bp->address_list, list) {
> -			if (sctp_cmp_addr_exact(&saddr->a, &addr))
> -				saddr->state = SCTP_ADDR_SRC;
> +		/* Until this ASCONF is acked on all associations, we cannot
> +		 * consider this address as ADDR_SRC
> +		 */
> +		asoc->src_out_of_asoc_ok = 0;
> +		sctp_add_addr_to_laddr(&addr.sa, asoc);
> +		list_for_each_entry(transport, &asoc->peer.transport_addr_list,
> +				transports) {
> +			dst_release(transport->dst);
> +			sctp_transport_route(transport, NULL,
> +					     sctp_sk(asoc->base.sk));
>  		}
>  		local_bh_enable();
>  		list_for_each_entry(transport, &asoc->peer.transport_addr_list,
> @@ -3203,6 +3342,25 @@ static void sctp_asconf_param_success(struct sctp_association *asoc,
>  	case SCTP_PARAM_DEL_IP:
>  		local_bh_disable();
>  		sctp_del_bind_addr(bp, &addr);
> +		if (asoc->asconf_addr_del_pending != NULL) {
> +			if ((addr.sa.sa_family == AF_INET) &&
> +			    (asoc->asconf_addr_del_pending->sa.sa_family ==
> +			     AF_INET)) {
> +				if (asoc->asconf_addr_del_pending->v4.sin_addr.s_addr == addr.v4.sin_addr.s_addr) {
> +					kfree(asoc->asconf_addr_del_pending);
> +					asoc->asconf_del_pending_cid = 0;
> +					asoc->asconf_addr_del_pending = NULL;
> +				}
> +			} else if ((addr.sa.sa_family == AF_INET6) &&
> +				(asoc->asconf_addr_del_pending->sa.sa_family ==
> +				 AF_INET6)) {
> +				if (ipv6_addr_equal(&asoc->asconf_addr_del_pending->v6.sin6_addr, &addr.v6.sin6_addr)) {
> +					kfree(asoc->asconf_addr_del_pending);
> +					asoc->asconf_del_pending_cid = 0;
> +					asoc->asconf_addr_del_pending = NULL;
> +				}
> +			}
> +		}
>  		local_bh_enable();
>  		list_for_each_entry(transport, &asoc->peer.transport_addr_list,
>  				transports) {
> @@ -3293,6 +3451,8 @@ int sctp_process_asconf_ack(struct sctp_association *asoc,
>  	int	no_err = 1;
>  	int	retval = 0;
>  	__be16	err_code = SCTP_ERROR_NO_ERROR;
> +	sctp_addip_param_t *first_asconf_param = NULL;
> +	int first_asconf_paramlen;
>  
>  	/* Skip the chunkhdr and addiphdr from the last asconf sent and store
>  	 * a pointer to address parameter.
> @@ -3307,6 +3467,8 @@ int sctp_process_asconf_ack(struct sctp_association *asoc,
>  	length = ntohs(addr_param->v4.param_hdr.length);
>  	asconf_param = (sctp_addip_param_t *)((void *)addr_param + length);
>  	asconf_len -= length;
> +	first_asconf_param = asconf_param;
> +	first_asconf_paramlen = ntohs(first_asconf_param->param_hdr.length);
>  
>  	/* ADDIP 4.1
>  	 * A8) If there is no response(s) to specific TLV parameter(s), and no
> @@ -3361,6 +3523,35 @@ int sctp_process_asconf_ack(struct sctp_association *asoc,
>  		asconf_len -= length;
>  	}
>  
> +	/* When the source address obviously changes to newly added one, we
> +	   reset the cwnd to re-probe the path condition
> +	*/
> +	if (no_err && first_asconf_param->param_hdr.type == SCTP_PARAM_ADD_IP) {
> +		if (first_asconf_paramlen == SCTP_ASCONF_V4_PARAM_LEN) {
> +			struct sockaddr_in sin;
> +
> +			memset(&sin, 0, sizeof(struct sockaddr_in));
> +			sin.sin_family = AF_INET;
> +			memcpy(&sin.sin_addr.s_addr, first_asconf_param + 1,
> +					sizeof(struct in_addr));
> +			sctp_path_check_and_react(asoc,
> +					(struct sockaddr *)&sin);
> +
> +		} else if (first_asconf_paramlen == SCTP_ASCONF_V6_PARAM_LEN) {
> +			struct sockaddr_in6 sin6;
> +
> +			memset(&sin6, 0, sizeof(struct sockaddr_in6));
> +			sin6.sin6_family = AF_INET6;
> +			memcpy(&sin6.sin6_addr, first_asconf_param + 1,
> +					sizeof(struct in6_addr));
> +			sctp_path_check_and_react(asoc,
> +					(struct sockaddr *)&sin6);
> +		} else {
> +			SCTP_DEBUG_PRINTK("funny asconf_paramlen? (%d)\n",
> +			    first_asconf_paramlen);
> +		}
> +	}
> +
>  	/* Free the cached last sent asconf chunk. */
>  	list_del_init(&asconf->transmitted_list);
>  	sctp_chunk_free(asconf);
> diff --git a/net/sctp/socket.c b/net/sctp/socket.c
> index 3951a10..9bc5e98 100644
> --- a/net/sctp/socket.c
> +++ b/net/sctp/socket.c
> @@ -527,6 +527,7 @@ static int sctp_send_asconf_add_ip(struct sock		*sk,
>  	struct list_head		*p;
>  	int 				i;
>  	int 				retval = 0;
> +	struct sctp_transport		*trans = NULL;
>  
>  	if (!sctp_addip_enable)
>  		return retval;
> @@ -583,13 +584,10 @@ static int sctp_send_asconf_add_ip(struct sock		*sk,
>  			goto out;
>  		}
>  
> -		retval = sctp_send_asconf(asoc, chunk);
> -		if (retval)
> -			goto out;
> -
>  		/* Add the new addresses to the bind address list with
>  		 * use_as_src set to 0.
>  		 */
> +		SCTP_DEBUG_PRINTK("snd_asconf_addip: next, add_bind_addr with ADDR_NEW flag\n");
>  		addr_buf = addrs;
>  		for (i = 0; i < addrcnt; i++) {
>  			addr = (union sctp_addr *)addr_buf;
> @@ -599,6 +597,28 @@ static int sctp_send_asconf_add_ip(struct sock		*sk,
>  						    SCTP_ADDR_NEW, GFP_ATOMIC);
>  			addr_buf += af->sockaddr_len;
>  		}
> +		list_for_each_entry(trans, &asoc->peer.transport_addr_list,
> +		    transports) {
> +			if (asoc->asconf_addr_del_pending != NULL)
> +				/* This ADDIP ASCONF piggybacks DELIP for the
> +				 * last address, so need to select src addr
> +				 * from the out_of_asoc addrs
> +				 */
> +				asoc->src_out_of_asoc_ok = 1;
> +			/* Clear the source and route cache in the path */
> +			memset(&trans->saddr, 0, sizeof(union sctp_addr));
> +			dst_release(trans->dst);
> +			trans->cwnd = min(4*asoc->pathmtu, max_t(__u32,
> +			    2*asoc->pathmtu, 4380));
> +			trans->ssthresh = asoc->peer.i.a_rwnd;
> +			trans->rto = asoc->rto_initial;
> +			trans->rtt = 0;
> +			trans->srtt = 0;
> +			trans->rttvar = 0;
> +			sctp_transport_route(trans, NULL,
> +			    sctp_sk(asoc->base.sk));
> +		}
> +		retval = sctp_send_asconf(asoc, chunk);

We need to do this really?

>  	}
>  
>  out:
> @@ -711,7 +731,9 @@ static int sctp_send_asconf_del_ip(struct sock		*sk,
>  	struct sctp_sockaddr_entry *saddr;
>  	int 			i;
>  	int 			retval = 0;
> +	int			stored = 0;
>  
> +	chunk = NULL;
>  	if (!sctp_addip_enable)
>  		return retval;
>  
> @@ -762,8 +784,42 @@ static int sctp_send_asconf_del_ip(struct sock		*sk,
>  		bp = &asoc->base.bind_addr;
>  		laddr = sctp_find_unmatch_addr(bp, (union sctp_addr *)addrs,
>  					       addrcnt, sp);
> -		if (!laddr)
> -			continue;
> +		if ((laddr == NULL) && (addrcnt == 1)) {
> +			union sctp_addr *sa_addr = NULL;
> +
> +			if (asoc->asconf_addr_del_pending == NULL) {
> +				asoc->asconf_addr_del_pending =
> +				    kmalloc(sizeof(union sctp_addr),
> +				    GFP_ATOMIC);
> +				memset(asoc->asconf_addr_del_pending, 0,
> +						sizeof(union sctp_addr));
> +				if (addrs->sa_family == AF_INET) {
> +					struct sockaddr_in *sin;
> +
> +					sin = (struct sockaddr_in *)addrs;
> +					asoc->asconf_addr_del_pending->v4.sin_family = AF_INET;
> +					memcpy(&asoc->asconf_addr_del_pending->v4.sin_addr, &sin->sin_addr, sizeof(struct in_addr));
> +				} else if (addrs->sa_family == AF_INET6) {
> +					struct sockaddr_in6 *sin6;
> +
> +					sin6 = (struct sockaddr_in6 *)addrs;
> +					asoc->asconf_addr_del_pending->v6.sin6_family = AF_INET6;
> +					memcpy(&asoc->asconf_addr_del_pending->v6.sin6_addr, &sin6->sin6_addr, sizeof(struct in6_addr));
> +				}
> +				sa_addr = (union sctp_addr *)addrs;
> +				SCTP_DEBUG_PRINTK_IPADDR("send_asconf_del_ip: keep the last address asoc: %p ",
> +				    " at %p\n", asoc, sa_addr,
> +				    asoc->asconf_addr_del_pending);
> +				stored = 1;
> +				goto skip_mkasconf;
> +			} else {
> +				SCTP_DEBUG_PRINTK_IPADDR("send_asconf_del_ip: asoc %p, deleting last address ",
> +				    " is already stored at %p\n", asoc,
> +				    asoc->asconf_addr_del_pending,
> +				    asoc->asconf_addr_del_pending);
> +				continue;
> +			}
> +		}
>  
>  		/* We do not need RCU protection throughout this loop
>  		 * because this is done under a socket lock from the
> @@ -776,6 +832,7 @@ static int sctp_send_asconf_del_ip(struct sock		*sk,
>  			goto out;
>  		}
>  
> +skip_mkasconf:
>  		/* Reset use_as_src flag for the addresses in the bind address
>  		 * list that are to be deleted.
>  		 */
> @@ -797,16 +854,205 @@ static int sctp_send_asconf_del_ip(struct sock		*sk,
>  		list_for_each_entry(transport, &asoc->peer.transport_addr_list,
>  					transports) {
>  			dst_release(transport->dst);
> +			/* Clear source address cache */
> +			memset(&transport->saddr, 0, sizeof(union sctp_addr));
>  			sctp_transport_route(transport, NULL,
>  					     sctp_sk(asoc->base.sk));
>  		}
>  
> +		if (stored) {
> +			/* We don't need to transmit ASCONF */
> +			continue;
> +		}
>  		retval = sctp_send_asconf(asoc, chunk);
>  	}
>  out:
>  	return retval;
>  }
>  
> +/* Add a new address to the list contains available addresses only in the
> + * association.  If the new address is also available on the other associations
> + * on the endpoint, it is marked as SCTP_ADDR_SRC in the bind address list on
> + * the endpoint.  This situation is possible when some of associations receive
> + * ASCONF-ACK for ADD_IP at the endpoint
> + */
> +void
> +sctp_add_addr_to_laddr(struct sockaddr *sa, struct sctp_association *asoc)
> +{
> +	struct sctp_endpoint *ep = asoc->ep;
> +	struct sctp_association *tmp = NULL;
> +	struct sctp_bind_addr *bp;
> +	struct sctp_sockaddr_entry *addr;
> +	struct sockaddr_in *sin = NULL;
> +	struct sockaddr_in6 *sin6 = NULL;
> +	int local;
> +	int found;
> +
> +	union sctp_addr *tmpaddr = NULL;
> +	tmpaddr = (union sctp_addr *)sa;
> +	SCTP_DEBUG_PRINTK_IPADDR("add_addr_to_laddr: asoc: %p ", " ep: %p",
> +	    asoc, tmpaddr, ep);
> +	if (sa->sa_family == AF_INET)
> +		sin = (struct sockaddr_in *)sa;
> +	else if (sa->sa_family == AF_INET6)
> +		sin6 = (struct sockaddr_in6 *)sa;
> +
> +	/* Check if this address is locally available in the other asocs */
> +	local = 0;
> +	list_for_each_entry(tmp, &ep->asocs, asocs) {
> +		if (tmp == asoc)
> +			continue;
> +		found = 0;
> +		list_for_each_entry(addr, &tmp->asoc_laddr_list, list) {
> +			tmpaddr = &addr->a;
> +			if (sa->sa_family != addr->a.sa.sa_family)
> +				continue;
> +			if (sa->sa_family == AF_INET) {
> +				if (sin->sin_addr.s_addr ==
> +				    addr->a.v4.sin_addr.s_addr)
> +					found = 1;
> +			} else if (sa->sa_family == AF_INET6) {
> +				if (ipv6_addr_equal(&sin6->sin6_addr,
> +				    &addr->a.v6.sin6_addr))
> +					found = 1;
> +
> +			}
> +		}
> +		if (!found) {
> +			SCTP_DEBUG_PRINTK("add_addr_to_laddr: not found in asoc %p\n", tmp);
> +			local = 1;
> +			break;
> +		}
> +	}
> +	addr = NULL;
> +
> +	if (local) {
> +		/* this address is not available in some of the other
> +		 * associations.  So add as locally-available in this
> +		 * asocciation
> +		 */
> +		addr = kmalloc(sizeof(struct sctp_sockaddr_entry), GFP_ATOMIC);
> +		if  (addr == NULL) {
> +			SCTP_DEBUG_PRINTK("add_addr_to_laddr: failed to allocate memory for this address\n");
> +			return;
> +		}
> +		memset(addr, 0, sizeof(struct sctp_sockaddr_entry));
> +		if (sa->sa_family == AF_INET) {
> +			addr->a.sa.sa_family = AF_INET;
> +			addr->a.v4.sin_port = sin->sin_port;
> +			addr->a.v4.sin_addr.s_addr = sin->sin_addr.s_addr;
> +		} else if (sa->sa_family == AF_INET6) {
> +			addr->a.sa.sa_family = AF_INET6;
> +			addr->a.v6.sin6_port = sin6->sin6_port;
> +			memcpy(&addr->a.v6.sin6_addr, &sin6->sin6_addr,
> +			    sizeof(struct in6_addr));
> +		}
> +		list_add_tail(&addr->list, &asoc->asoc_laddr_list);
> +		SCTP_DEBUG_PRINTK("add_addr_to_laddr: now we added this address to the local list on asoc %p\n", asoc);
> +	} else {
> +		/* this address is also available in all other asocs.  So set
> +		 * it as ADDR_SRC in the bind-addr list in the endpoint, then
> +		 * remove from the asoc_laddr_list on the associations.
> +		 */
> +		SCTP_DEBUG_PRINTK("add_addr_to_laddr: this address is available in all other asocs\n");
> +		bp = &asoc->base.bind_addr;
> +
> +		/* change state of the new address in the bind list */
> +		list_for_each_entry(addr, &bp->address_list, list) {
> +			if (addr->state != SCTP_ADDR_NEW)
> +				continue;
> +			if (addr->a.sa.sa_family != sa->sa_family)
> +				continue;
> +			if (addr->a.sa.sa_family == AF_INET) {
> +				if (sin->sin_port != addr->a.v4.sin_port)
> +					continue;
> +				if (sin->sin_addr.s_addr !=
> +				    addr->a.v4.sin_addr.s_addr)
> +					continue;
> +			} else if (addr->a.sa.sa_family == AF_INET6) {
> +				if (sin6->sin6_port != addr->a.v6.sin6_port)
> +					continue;
> +				if (!ipv6_addr_equal(&sin6->sin6_addr,
> +				    &addr->a.v6.sin6_addr))
> +					continue;
> +			}
> +			SCTP_DEBUG_PRINTK("add_addr_to_laddr: found the entry for this address with ADDR_NEW flag, set to ADDR_SRC\n");
> +			addr->state = SCTP_ADDR_SRC;
> +		}
> +
> +		/* remove the entry of this address from the asoc-local list */
> +		list_for_each_entry(tmp, &ep->asocs, asocs) {
> +			if (tmp == asoc)
> +				continue;
> +			addr = NULL;
> +			list_for_each_entry(addr, &tmp->asoc_laddr_list, list) {
> +				if (sa->sa_family != addr->a.sa.sa_family)
> +					continue;
> +				if (sa->sa_family == AF_INET) {
> +					if (sin->sin_addr.s_addr !=
> +					    addr->a.v4.sin_addr.s_addr)
> +						continue;
> +				} else if (sa->sa_family == AF_INET6) {
> +					if (!ipv6_addr_equal(&sin6->sin6_addr,
> +					    &addr->a.v6.sin6_addr))
> +						continue;
> +				}
> +				break;
> +			}
> +			if (addr == NULL) {
> +				SCTP_DEBUG_PRINTK("add_addr_to_laddr: Huh, asoc %p doesn't have the entry for this address?\n", asoc);
> +				continue;
> +			}
> +			list_del(&addr->list);
> +			kfree(addr);
> +		}
> +	}
> +}
> +
> +/* set addr events to assocs in the endpoint.  ep and addr_wq must be locked */
> +int
> +sctp_asconf_mgmt(struct sctp_endpoint *ep, struct sock *sk)

only the ep param is necessary, sk should be fetch from ep.

> +{
> +	struct sctp_addr_wait *addrw = NULL;
> +	union sctp_addr *addr = NULL;
> +	int cmd;
> +	int error = 0;
> +
> +	if (ep == NULL || sk == NULL)
> +		return -EINVAL;
> +	if (list_empty(&sctp_addr_waitq)) {
> +		SCTP_DEBUG_PRINTK("asconf_mgmt: nothing in the wq\n");
> +		return -EINVAL;
> +	}
> +	addrw = list_first_entry(&sctp_addr_waitq, struct sctp_addr_wait, list);
> +	if (addrw->cmd != SCTP_NEWADDR && addrw->cmd != SCTP_DELADDR)
> +		return -EINVAL;
> +	addr = &addrw->a;
> +	cmd = addrw->cmd;
> +
> +	if (addr->sa.sa_family == AF_INET)
> +		addr->v4.sin_port = htons(ep->base.bind_addr.port);
> +	else if (addr->sa.sa_family == AF_INET6)
> +		addr->v6.sin6_port = htons(ep->base.bind_addr.port);

use addr->v4.sin_port = htons(ep->base.bind_addr.port) is enough,
no need to check the family.

> +
> +	SCTP_DEBUG_PRINTK("sctp_asconf_mgmt sk:%p ep:%p\n", sk, ep);
> +	if (cmd == SCTP_NEWADDR) {
> +		error = sctp_send_asconf_add_ip(sk, (struct sockaddr *)addr, 1);
> +		if (error) {
> +			SCTP_DEBUG_PRINTK("asconf_mgmt: send_asconf_add_ip returns %d\n", error);
> +			return error;
> +		}
> +	} else if (cmd == SCTP_DELADDR) {
> +		error = sctp_send_asconf_del_ip(sk, (struct sockaddr *)addr, 1);
> +		if (error) {
> +			SCTP_DEBUG_PRINTK("asconf_mgmt: send_asconf_del_ip returns %d\n", error);
> +			return error;
> +		}
> +	}
> +
> +	return 0;
> +}
> +
>  /* Helper for tunneling sctp_bindx() requests through sctp_setsockopt()
>   *
>   * API 8.1
> @@ -3341,6 +3587,44 @@ static int sctp_setsockopt_del_key(struct sock *sk,
>  
>  }
>  
> +/*
> + * 8.1.23 SCTP_AUTO_ASCONF
> + *
> + * This option will enable or disable the use of the automatic generation of
> + * ASCONF chunks to add and delete addresses to an existing association.  Note
> + * that this option has two caveats namely: a) it only affects sockets that
> + * are bound to all addresses available to the SCTP stack, and b) the system
> + * administrator may have an overriding control that turns the ASCONF feature
> + * off no matter what setting the socket option may have.
> + * This option expects an integer boolean flag, where a non-zero value turns on
> + * the option, and a zero value turns off the option.
> + * Note. In this implementation, socket operation overrides default parameter
> + * being set by sysctl as well as FreeBSD implementation
> + */
> +static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval,
> +					unsigned int optlen)
> +{
> +	int val;
> +	struct sctp_ep_common *epb;
> +
> +	if (optlen < sizeof(int))
> +		return -EINVAL;
> +	if (get_user(val, (int __user *)optval))
> +		return -EFAULT;
> +	if (!sctp_is_ep_boundall(sk) && val)
> +		return -EINVAL;
> +	list_for_each_entry(epb, &sctp_auto_asconf_eplist, auto_asconf_list) {
> +		if (epb->sk == sk) {
> +			if (val == 0)
> +				list_del(&epb->auto_asconf_list);
> +			return 0;
> +		}
> +	}
> +	if (val)
> +		list_add_tail(&sctp_sk(sk)->ep->base.auto_asconf_list,
> +		    &sctp_auto_asconf_eplist);
> +	return 0;
> +}

The sctp_setsockopt_auto_asconf is not correct, if we enable this option
twice, the list will be broken.

We'd better to introcude a auto_asconf flag to ep, and then, we do not
need to scanf the asconf_list.
If auto_asconf flag is true, it is exists in the list, otherwise, not.

>  
>  /* API 6.2 setsockopt(), getsockopt()
>   *
> @@ -3488,6 +3772,9 @@ SCTP_STATIC int sctp_setsockopt(struct sock *sk, int level, int optname,
>  	case SCTP_AUTH_DELETE_KEY:
>  		retval = sctp_setsockopt_del_key(sk, optval, optlen);
>  		break;
> +	case SCTP_AUTO_ASCONF:
> +		retval = sctp_setsockopt_auto_asconf(sk, optval, optlen);
> +		break;
>  	default:
>  		retval = -ENOPROTOOPT;
>  		break;
> @@ -3770,6 +4057,10 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk)
>  	local_bh_disable();
>  	percpu_counter_inc(&sctp_sockets_allocated);
>  	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
> +	if (sctp_auto_asconf_enable)
> +		list_add_tail(&ep->base.auto_asconf_list,
> +		    &sctp_auto_asconf_eplist);
> +	SCTP_DEBUG_PRINTK("sctp_init_sk sk:%p ep:%p\n", sk, ep);

All of the sctp sockets are added to sctp_auto_asconf_eplist.
I think none of the sockets should exists in this list by default,
only after we enable AUTO_ASCONF, we should add it to this list.

>  	local_bh_enable();
>  
>  	return 0;
> @@ -3779,11 +4070,18 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk)
>  SCTP_STATIC void sctp_destroy_sock(struct sock *sk)
>  {
>  	struct sctp_endpoint *ep;
> +	struct sctp_ep_common *epb;
>  
>  	SCTP_DEBUG_PRINTK("sctp_destroy_sock(sk: %p)\n", sk);
>  
>  	/* Release our hold on the endpoint. */
>  	ep = sctp_sk(sk)->ep;
> +	list_for_each_entry(epb, &sctp_auto_asconf_eplist, auto_asconf_list) {
> +		if (epb->sk == sk) {
> +			list_del(&epb->auto_asconf_list);
> +			break;
> +		}
> +	}
>  	sctp_endpoint_free(ep);
>  	local_bh_disable();
>  	percpu_counter_dec(&sctp_sockets_allocated);
> @@ -5283,6 +5581,31 @@ static int sctp_getsockopt_assoc_number(struct sock *sk, int len,
>  	return 0;
>  }
>  
> +/*
> + * 8.1.23 SCTP_AUTO_ASCONF
> + * See the corresponding setsockopt entry as description
> + */
> +static int sctp_getsockopt_auto_asconf(struct sock *sk, int len,
> +				   char __user *optval, int __user *optlen)
> +{
> +	int val = 0;
> +	struct sctp_ep_common *epb;
> +
> +	if (len < sizeof(int))
> +		return -EINVAL;
> +
> +	len = sizeof(int);
> +	list_for_each_entry(epb, &sctp_auto_asconf_eplist, auto_asconf_list) {
> +		if (epb->sk == sk)
> +			val = 1;
> +	}
> +	if (put_user(len, optlen))
> +		return -EFAULT;
> +	if (copy_to_user(optval, &val, len))
> +		return -EFAULT;
> +	return 0;
> +}
> +
>  SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname,
>  				char __user *optval, int __user *optlen)
>  {
> @@ -5415,6 +5738,9 @@ SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname,
>  	case SCTP_GET_ASSOC_NUMBER:
>  		retval = sctp_getsockopt_assoc_number(sk, len, optval, optlen);
>  		break;
> +	case SCTP_AUTO_ASCONF:
> +		retval = sctp_getsockopt_auto_asconf(sk, len, optval, optlen);
> +		break;
>  	default:
>  		retval = -ENOPROTOOPT;
>  		break;
> diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
> index 50cb57f..df39789 100644
> --- a/net/sctp/sysctl.c
> +++ b/net/sctp/sysctl.c
> @@ -183,6 +183,13 @@ static ctl_table sctp_table[] = {
>  		.proc_handler	= proc_dointvec,
>  	},
>  	{
> +		.procname	= "auto_asconf_enable",
> +		.data		= &sctp_auto_asconf_enable,
> +		.maxlen		= sizeof(int),
> +		.mode		= 0644,
> +		.proc_handler	= proc_dointvec,
> +	},
> +	{
>  		.procname	= "prsctp_enable",
>  		.data		= &sctp_prsctp_enable,
>  		.maxlen		= sizeof(int),
>

Is the sysctl parameter necessary, since auto_asconf is disabled
by default, and we need to set the option to enabled it.



--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Hi, 

Thanks for your comments.  
I would like to discuss some of them in-line before resubmission.  

Cheers,
- Michio

On Mar 31, 2011, at 15:45 , Wei Yongjun wrote:

> Hi Michio Honda
> 
> I try to understand what you are doing now, and some comments inline.
> 
> And
> 
> this patch is too big for review, you'd better to split it to a patchset:
> the improve on orig asconf code, the auto-asconf support, the socket
> option etc.
> 
>> @@ -599,6 +597,28 @@ static int sctp_send_asconf_add_ip(struct sock		*sk,
>> 						    SCTP_ADDR_NEW, GFP_ATOMIC);
>> 			addr_buf += af->sockaddr_len;
>> 		}
>> +		list_for_each_entry(trans, &asoc->peer.transport_addr_list,
>> +		    transports) {
>> +			if (asoc->asconf_addr_del_pending != NULL)
>> +				/* This ADDIP ASCONF piggybacks DELIP for the
>> +				 * last address, so need to select src addr
>> +				 * from the out_of_asoc addrs
>> +				 */
>> +				asoc->src_out_of_asoc_ok = 1;
>> +			/* Clear the source and route cache in the path */
>> +			memset(&trans->saddr, 0, sizeof(union sctp_addr));
>> +			dst_release(trans->dst);
>> +			trans->cwnd = min(4*asoc->pathmtu, max_t(__u32,
>> +			    2*asoc->pathmtu, 4380));
>> +			trans->ssthresh = asoc->peer.i.a_rwnd;
>> +			trans->rto = asoc->rto_initial;
>> +			trans->rtt = 0;
>> +			trans->srtt = 0;
>> +			trans->rttvar = 0;
>> +			sctp_transport_route(trans, NULL,
>> +			    sctp_sk(asoc->base.sk));
>> +		}
>> +		retval = sctp_send_asconf(asoc, chunk);
> 
> We need to do this really?
We have to reset path information before transmitting ASCONF from the new source address.  
Because when we obviously change the source address (i.e., deletion of the last local address), we don't know any information of the path (e.g., RTT) between the new source address and the existing destination address.  
> 
>> 
>> @@ -3341,6 +3587,44 @@ static int sctp_setsockopt_del_key(struct sock *sk,
>> 
>> +static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval,
>> +					unsigned int optlen)
>> +{
>> +	int val;
>> +	struct sctp_ep_common *epb;
>> +
>> +	if (optlen < sizeof(int))
>> +		return -EINVAL;
>> +	if (get_user(val, (int __user *)optval))
>> +		return -EFAULT;
>> +	if (!sctp_is_ep_boundall(sk) && val)
>> +		return -EINVAL;
>> +	list_for_each_entry(epb, &sctp_auto_asconf_eplist, auto_asconf_list) {
>> +		if (epb->sk == sk) {
>> +			if (val == 0)
>> +				list_del(&epb->auto_asconf_list);
>> +			return 0;
>> +		}
>> +	}
>> +	if (val)
>> +		list_add_tail(&sctp_sk(sk)->ep->base.auto_asconf_list,
>> +		    &sctp_auto_asconf_eplist);
>> +	return 0;
>> +}
> 
> The sctp_setsockopt_auto_asconf is not correct, if we enable this option
> twice, the list will be broken.
Oops, I fix, thanks!
> 
> We'd better to introcude a auto_asconf flag to ep, and then, we do not
> need to scanf the asconf_list.
> If auto_asconf flag is true, it is exists in the list, otherwise, not.
Agreed, it's more simple.   
> 
> All of the sctp sockets are added to sctp_auto_asconf_eplist.
> I think none of the sockets should exists in this list by default,
> only after we enable AUTO_ASCONF, we should add it to this list.
Sockets are added to auto_asconf_eplist only when the sysctl parameter is on.   
> 
>> 
> 
> Is the sysctl parameter necessary, since auto_asconf is disabled
> by default, and we need to set the option to enabled it.
I believe auto_asconf should be enabled by both of sysctl and setsockopt as well as FreeBSD implementation does.  
Adopting the same methods could be helpful for applications concerning auto_asconf availability.  
I agree to set the sysctl parameter to 0 by default.    

> 
> 
> 


--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

> Hi, 
>
> Thanks for your comments.  
> I would like to discuss some of them in-line before resubmission.  
>
> Cheers,
> - Michio
>
> On Mar 31, 2011, at 15:45 , Wei Yongjun wrote:
>
>> Hi Michio Honda
>>
>> I try to understand what you are doing now, and some comments inline.
>>
>> And
>>
>> this patch is too big for review, you'd better to split it to a patchset:
>> the improve on orig asconf code, the auto-asconf support, the socket
>> option etc.
>>
>>> @@ -599,6 +597,28 @@ static int sctp_send_asconf_add_ip(struct sock		*sk,
>>> 						    SCTP_ADDR_NEW, GFP_ATOMIC);
>>> 			addr_buf += af->sockaddr_len;
>>> 		}
>>> +		list_for_each_entry(trans, &asoc->peer.transport_addr_list,
>>> +		    transports) {
>>> +			if (asoc->asconf_addr_del_pending != NULL)
>>> +				/* This ADDIP ASCONF piggybacks DELIP for the
>>> +				 * last address, so need to select src addr
>>> +				 * from the out_of_asoc addrs
>>> +				 */
>>> +				asoc->src_out_of_asoc_ok = 1;
>>> +			/* Clear the source and route cache in the path */
>>> +			memset(&trans->saddr, 0, sizeof(union sctp_addr));
>>> +			dst_release(trans->dst);
>>> +			trans->cwnd = min(4*asoc->pathmtu, max_t(__u32,
>>> +			    2*asoc->pathmtu, 4380));
>>> +			trans->ssthresh = asoc->peer.i.a_rwnd;
>>> +			trans->rto = asoc->rto_initial;
>>> +			trans->rtt = 0;
>>> +			trans->srtt = 0;
>>> +			trans->rttvar = 0;
>>> +			sctp_transport_route(trans, NULL,
>>> +			    sctp_sk(asoc->base.sk));
>>> +		}
>>> +		retval = sctp_send_asconf(asoc, chunk);
>> We need to do this really?
> We have to reset path information before transmitting ASCONF from the new source address.  
> Because when we obviously change the source address (i.e., deletion of the last local address), we don't know any information of the path (e.g., RTT) between the new source address and the existing destination address.  

Do you means we deleted all of the local address? This is prohibit
by rfc5061. If we have other address, we can use it.

   F5)  An endpoint MUST NOT delete its last remaining IP address from
        an association.  In other words, if an endpoint is NOT multi-
        homed, it MUST NOT use the delete IP address without an Add IP
        Address preceding the delete parameter in the ASCONF Chunk.  Or,
        if an endpoint sends multiple requests to delete IP addresses,
        it MUST NOT delete all of the IP addresses that the peer has
        listed for the requester.


But the rfc does not said what we should do if all of the local addresses
are invalid.


>>> @@ -3341,6 +3587,44 @@ static int sctp_setsockopt_del_key(struct sock *sk,
>>>
>>> +static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval,
>>> +					unsigned int optlen)
>>> +{
>>> +	int val;
>>> +	struct sctp_ep_common *epb;
>>> +
>>> +	if (optlen < sizeof(int))
>>> +		return -EINVAL;
>>> +	if (get_user(val, (int __user *)optval))
>>> +		return -EFAULT;
>>> +	if (!sctp_is_ep_boundall(sk) && val)
>>> +		return -EINVAL;
>>> +	list_for_each_entry(epb, &sctp_auto_asconf_eplist, auto_asconf_list) {
>>> +		if (epb->sk == sk) {
>>> +			if (val == 0)
>>> +				list_del(&epb->auto_asconf_list);
>>> +			return 0;
>>> +		}
>>> +	}
>>> +	if (val)
>>> +		list_add_tail(&sctp_sk(sk)->ep->base.auto_asconf_list,
>>> +		    &sctp_auto_asconf_eplist);
>>> +	return 0;
>>> +}
>> The sctp_setsockopt_auto_asconf is not correct, if we enable this option
>> twice, the list will be broken.
> Oops, I fix, thanks!
>> We'd better to introcude a auto_asconf flag to ep, and then, we do not
>> need to scanf the asconf_list.
>> If auto_asconf flag is true, it is exists in the list, otherwise, not.
> Agreed, it's more simple.   
>> All of the sctp sockets are added to sctp_auto_asconf_eplist.
>> I think none of the sockets should exists in this list by default,
>> only after we enable AUTO_ASCONF, we should add it to this list.
> Sockets are added to auto_asconf_eplist only when the sysctl parameter is on.   

If so, the SCTP_AUTO_ASCONF will be broken.

I think before SCTP_AUTO_ASCONF be document, the sysctl parameter
is used to enable/disable the auto asconf, but after SCTP_AUTO_ASCONF
defined, sysctl parameter should be deprecated.

>> Is the sysctl parameter necessary, since auto_asconf is disabled
>> by default, and we need to set the option to enabled it.
> I believe auto_asconf should be enabled by both of sysctl and setsockopt as well as FreeBSD implementation does.  
> Adopting the same methods could be helpful for applications concerning auto_asconf availability.  
> I agree to set the sysctl parameter to 0 by default.    
>
>>
>>
>
>
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

On Apr 1, 2011, at 10:25 , Wei Yongjun wrote:

> 
>> Hi, 
>> 
>> Thanks for your comments.  
>> I would like to discuss some of them in-line before resubmission.  
>> 
>> Cheers,
>> - Michio
>> 
>> On Mar 31, 2011, at 15:45 , Wei Yongjun wrote:
>> 
>>> Hi Michio Honda
>>> 
>>> I try to understand what you are doing now, and some comments inline.
>>> 
>>> And
>>> 
>>> this patch is too big for review, you'd better to split it to a patchset:
>>> the improve on orig asconf code, the auto-asconf support, the socket
>>> option etc.
>>> 
>>>> @@ -599,6 +597,28 @@ static int sctp_send_asconf_add_ip(struct sock		*sk,
>>>> 						    SCTP_ADDR_NEW, GFP_ATOMIC);
>>>> 			addr_buf += af->sockaddr_len;
>>>> 		}
>>>> +		list_for_each_entry(trans, &asoc->peer.transport_addr_list,
>>>> +		    transports) {
>>>> +			if (asoc->asconf_addr_del_pending != NULL)
>>>> +				/* This ADDIP ASCONF piggybacks DELIP for the
>>>> +				 * last address, so need to select src addr
>>>> +				 * from the out_of_asoc addrs
>>>> +				 */
>>>> +				asoc->src_out_of_asoc_ok = 1;
>>>> +			/* Clear the source and route cache in the path */
>>>> +			memset(&trans->saddr, 0, sizeof(union sctp_addr));
>>>> +			dst_release(trans->dst);
>>>> +			trans->cwnd = min(4*asoc->pathmtu, max_t(__u32,
>>>> +			    2*asoc->pathmtu, 4380));
>>>> +			trans->ssthresh = asoc->peer.i.a_rwnd;
>>>> +			trans->rto = asoc->rto_initial;
>>>> +			trans->rtt = 0;
>>>> +			trans->srtt = 0;
>>>> +			trans->rttvar = 0;
>>>> +			sctp_transport_route(trans, NULL,
>>>> +			    sctp_sk(asoc->base.sk));
>>>> +		}
>>>> +		retval = sctp_send_asconf(asoc, chunk);
>>> We need to do this really?
>> We have to reset path information before transmitting ASCONF from the new source address.  
>> Because when we obviously change the source address (i.e., deletion of the last local address), we don't know any information of the path (e.g., RTT) between the new source address and the existing destination address.  
> 
> Do you means we deleted all of the local address? This is prohibit
> by rfc5061. If we have other address, we can use it.
> 
>   F5)  An endpoint MUST NOT delete its last remaining IP address from
>        an association.  In other words, if an endpoint is NOT multi-
>        homed, it MUST NOT use the delete IP address without an Add IP
>        Address preceding the delete parameter in the ASCONF Chunk.  Or,
>        if an endpoint sends multiple requests to delete IP addresses,
>        it MUST NOT delete all of the IP addresses that the peer has
>        listed for the requester.
> 
> 
> But the rfc does not said what we should do if all of the local addresses
> are invalid.
Sorry for my bad description, I mean, suppose the host having one local IP address changes the IP address to new one.   
The host will remove the old address, and configure the new IP address.  
Then, I believe following steps in SCTP implementation could make sense.  
1. When the host removes the local address, SCTP implementation postpones to remove the local address from the association, because it is the last local address in the association.    
2. After the configuration of the new IP address, the SCTP implementation tries to send an ASCONF with ADD_IP_ADDRESS from the newly configured address.  This address can be used for ASCONF while it cannot be used for the other chunks.  This ASCONF also contains DELETE_IP_ADDRESS for the old address.  (This is allowed as Sec.5.3 F5 describes)
Then, the path where the ASCONF goes is obviously new path because of the new source address, thus we should reset old path parameters, otherwise the SCTP implementation might set wrong RTO and estimate wrong RTT for that ASCONF.    


> 
> 
>>>> @@ -3341,6 +3587,44 @@ static int sctp_setsockopt_del_key(struct sock *sk,
>>>> 
>>>> +static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval,
>>>> +					unsigned int optlen)
>>>> +{
>>>> +	int val;
>>>> +	struct sctp_ep_common *epb;
>>>> +
>>>> +	if (optlen < sizeof(int))
>>>> +		return -EINVAL;
>>>> +	if (get_user(val, (int __user *)optval))
>>>> +		return -EFAULT;
>>>> +	if (!sctp_is_ep_boundall(sk) && val)
>>>> +		return -EINVAL;
>>>> +	list_for_each_entry(epb, &sctp_auto_asconf_eplist, auto_asconf_list) {
>>>> +		if (epb->sk == sk) {
>>>> +			if (val == 0)
>>>> +				list_del(&epb->auto_asconf_list);
>>>> +			return 0;
>>>> +		}
>>>> +	}
>>>> +	if (val)
>>>> +		list_add_tail(&sctp_sk(sk)->ep->base.auto_asconf_list,
>>>> +		    &sctp_auto_asconf_eplist);
>>>> +	return 0;
>>>> +}
>>> The sctp_setsockopt_auto_asconf is not correct, if we enable this option
>>> twice, the list will be broken.
>> Oops, I fix, thanks!
>>> We'd better to introcude a auto_asconf flag to ep, and then, we do not
>>> need to scanf the asconf_list.
>>> If auto_asconf flag is true, it is exists in the list, otherwise, not.
>> Agreed, it's more simple.   
>>> All of the sctp sockets are added to sctp_auto_asconf_eplist.
>>> I think none of the sockets should exists in this list by default,
>>> only after we enable AUTO_ASCONF, we should add it to this list.
>> Sockets are added to auto_asconf_eplist only when the sysctl parameter is on.   
> 
> If so, the SCTP_AUTO_ASCONF will be broken.
> 
> I think before SCTP_AUTO_ASCONF be document, the sysctl parameter
> is used to enable/disable the auto asconf, but after SCTP_AUTO_ASCONF
> defined, sysctl parameter should be deprecated.
Mmm, not sure, we should ask Randy and Michael.  I'll send separate email soon.  
> 
>>> Is the sysctl parameter necessary, since auto_asconf is disabled
>>> by default, and we need to set the option to enabled it.
>> I believe auto_asconf should be enabled by both of sysctl and setsockopt as well as FreeBSD implementation does.  
>> Adopting the same methods could be helpful for applications concerning auto_asconf availability.  
>> I agree to set the sysctl parameter to 0 by default.    
>> 
>>> 
>>> 
>> 
>> 

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html