From mboxrd@z Thu Jan 1 00:00:00 1970 From: Wei Yongjun Subject: Re: [PATCH net-next-2.6 v4 1/5] sctp: Add Auto-ASCONF support Date: Thu, 21 Apr 2011 12:52:43 +0800 Message-ID: <4DAFB81B.8080308@cn.fujitsu.com> References: <0F65CB0F-7945-4E22-8003-A30EC2C653B5@sfc.wide.ad.jp> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: netdev@vger.kernel.org, lksctp-developers@lists.sourceforge.net To: Michio Honda Return-path: Received: from cn.fujitsu.com ([222.73.24.84]:51616 "EHLO song.cn.fujitsu.com" rhost-flags-OK-FAIL-OK-OK) by vger.kernel.org with ESMTP id S1750858Ab1DUEwu (ORCPT ); Thu, 21 Apr 2011 00:52:50 -0400 In-Reply-To: <0F65CB0F-7945-4E22-8003-A30EC2C653B5@sfc.wide.ad.jp> Sender: netdev-owner@vger.kernel.org List-ID: comment inline. > 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, and this patch implement the latter. > > Signed-off-by: Michio Honda > --- > diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h > index 505845d..8678cbd 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(struct sctp_sockaddr_entry *, int); > > /* > * sctp/socket.c > @@ -135,6 +136,7 @@ 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_sock *, struct sctp_sockaddr_entry *); > > /* > * sctp/primitive.c > diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h > index cc9185c..80974c3 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_splist; > + 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_splist (sctp_globals.auto_asconf_splist) > +#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) > @@ -341,6 +351,8 @@ struct sctp_sock { > atomic_t pd_mode; > /* Receive to here while partial delivery is in effect. */ > struct sk_buff_head pd_lobby; > + struct list_head auto_asconf_list; > + int do_auto_asconf; > }; > > static inline struct sctp_sock *sctp_sk(const struct sock *sk) > @@ -796,6 +808,10 @@ struct sctp_sockaddr_entry { > __u8 valid; > }; > > +#define SCTP_NEWADDR 1 > +#define SCTP_DELADDR 2 We can use exist SCTP_ADDR_NEW and SCTP_ADDR_DEL. > +#define SCTP_ADDRESS_TICK_DELAY 500 > + > typedef struct sctp_chunk *(sctp_packet_phandler_t)(struct sctp_association *); > > /* This structure holds lists of chunks as we are assembling for > @@ -1239,6 +1255,7 @@ 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? */ > diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c > index faf71d1..869267b 100644 > --- a/net/sctp/bind_addr.c > +++ b/net/sctp/bind_addr.c > @@ -536,6 +536,21 @@ 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; > + } > + return 0; > +} > + > /******************************************************************** > * 3rd Level Abstractions > ********************************************************************/ > diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c > index 865ce7b..0ba27b9 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, 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, SCTP_DELADDR); > found = 1; > addr->valid = 0; > list_del_rcu(&addr->list); > diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c > index 152976e..d8442a4 100644 > --- a/net/sctp/protocol.c > +++ b/net/sctp/protocol.c > @@ -636,6 +636,164 @@ static void sctp_v4_ecn_capable(struct sock *sk) > INET_ECN_xmit(sk); > } > > +void sctp_addr_wq_timeout_handler(unsigned long arg) > +{ > + struct sctp_sockaddr_entry *addrw = NULL; > + union sctp_addr *addr = NULL; > + struct sctp_sock *sp = NULL; > + > + 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_sockaddr_entry, > + list); > + 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->state, > + 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 sockets\n"); > + list_del(&addrw->list); > + kfree(addrw); > + goto retry_wq; > + } > + if (ipv6_chk_addr(&init_net, in6, NULL, 0) == 0 && > + addrw->state == 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); > + mod_timer(&sctp_addr_wq_timer, timeo_val); > + spin_unlock_bh(&sctp_addr_wq_lock); > + return; > + } > + } > + list_for_each_entry(sp, &sctp_auto_asconf_splist, auto_asconf_list) { > + struct sock *sk; > + > + if (sp == NULL) { > + SCTP_DEBUG_PRINTK("addrwq_timo_handler: no socket\n"); > + continue; > + } sp should never be NULL? > + sk = sctp_opt2sk(sp); > + if (!sctp_is_ep_boundall(sk)) > + /* ignore bound-specific endpoints */ > + continue; better to comment before if (!sctp_is_ep_boundall(sk)) /* ignore bound-specific endpoints */ if (!sctp_is_ep_boundall(sk)) continue; > + sctp_bh_lock_sock(sk); > + if (sctp_asconf_mgmt(sp, addrw) < 0) { > + SCTP_DEBUG_PRINTK("sctp_addrwq_timo_handler: sctp_asconf_mgmt failed\n"); > + sctp_bh_unlock_sock(sk); > + continue; > + } > + sctp_bh_unlock_sock(sk); > + } > + > + list_del(&addrw->list); > + kfree(addrw); > + > + if (!list_empty(&sctp_addr_waitq)) > + goto retry_wq; > + > + spin_unlock_bh(&sctp_addr_wq_lock); > +} > + > +static void sctp_free_addr_wq() > +{ > + struct sctp_sockaddr_entry *addrw = NULL; > + struct sctp_sockaddr_entry *temp = NULL; > + > + spin_lock_bh(&sctp_addr_wq_lock); > + del_timer(&sctp_addr_wq_timer); > + list_for_each_entry_safe(addrw, temp, &sctp_addr_waitq, list) { > + list_del(&addrw->list); > + kfree(addrw); > + } > + spin_unlock_bh(&sctp_addr_wq_lock); > +} > + > +/* lookup the entry for the same address in the addr_waitq > + * sctp_addr_wq MUST be locked > + */ > +static struct sctp_sockaddr_entry *sctp_addr_wq_lookup(struct sctp_sockaddr_entry *addr) > +{ > + struct sctp_sockaddr_entry *addrw; > + > + list_for_each_entry(addrw, &sctp_addr_waitq, list) { > + if (addrw->a.sa.sa_family != addr->a.sa.sa_family) > + continue; > + if (addrw->a.sa.sa_family == AF_INET) { > + if (addrw->a.v4.sin_addr.s_addr == > + addr->a.v4.sin_addr.s_addr) > + return addrw; > + } else if (addrw->a.sa.sa_family == AF_INET6) { > + if (ipv6_addr_equal(&addrw->a.v6.sin6_addr, > + &addr->a.v6.sin6_addr)) > + return addrw; > + } > + } > + return NULL; > +} > + > +void sctp_addr_wq_mgmt(struct sctp_sockaddr_entry *addr, int cmd) > +{ > + struct sctp_sockaddr_entry *addrw = 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 > + */ > + > + spin_lock_bh(&sctp_addr_wq_lock); > + /* Offsets existing events in addr_wq */ > + addrw = sctp_addr_wq_lookup(addr); > + tmpaddr = &addrw->a; > + if (addrw) { > + if (addrw->state != cmd) { > + SCTP_DEBUG_PRINTK_IPADDR("sctp_addr_wq_mgmt offsets existing entry for %d ", > + " in wq %p\n", addrw->state, 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 = kmemdup(addr, sizeof(struct sctp_sockaddr_entry), GFP_ATOMIC); > + if (addrw == NULL) { > + spin_unlock_bh(&sctp_addr_wq_lock); > + return; > + } > + addrw->state = cmd; > + list_add_tail(&addrw->list, &sctp_addr_waitq); > + tmpaddr = &addrw->a; > + SCTP_DEBUG_PRINTK_IPADDR("sctp_addr_wq_mgmt add new entry for cmd:%d ", > + " in wq %p\n", addrw->state, tmpaddr, &sctp_addr_waitq); > + > + if (!timer_pending(&sctp_addr_wq_timer)) { > + timeo_val = jiffies; > + timeo_val += msecs_to_jiffies(SCTP_ADDRESS_TICK_DELAY); > + 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 +821,7 @@ 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, SCTP_NEWADDR); > spin_unlock_bh(&sctp_local_addr_lock); > } > break; > @@ -673,6 +832,7 @@ 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, SCTP_DELADDR); > found = 1; > addr->valid = 0; > list_del_rcu(&addr->list); > @@ -1256,6 +1416,7 @@ SCTP_STATIC __init int sctp_init(void) > /* Disable ADDIP by default. */ > sctp_addip_enable = 0; > sctp_addip_noauth = 0; > + sctp_auto_asconf_enable = 0; > > /* Enable PR-SCTP by default. */ > sctp_prsctp_enable = 1; > @@ -1280,6 +1441,13 @@ SCTP_STATIC __init int sctp_init(void) > spin_lock_init(&sctp_local_addr_lock); > sctp_get_local_addr_list(); > > + /* Initialize the address event list */ > + INIT_LIST_HEAD(&sctp_addr_waitq); > + INIT_LIST_HEAD(&sctp_auto_asconf_splist); > + spin_lock_init(&sctp_addr_wq_lock); > + sctp_addr_wq_timer.expires = 0; > + setup_timer(&sctp_addr_wq_timer, sctp_addr_wq_timeout_handler, 0); > + > status = sctp_v4_protosw_init(); > > if (status) > @@ -1344,6 +1512,7 @@ err_chunk_cachep: > /* Exit handler for the SCTP protocol. */ > SCTP_STATIC __exit void sctp_exit(void) > { > + sctp_free_addr_wq(); Not sure whether is the best place to free wq, NETDEV event may not disabled? > /* BUG. This should probably do something useful like clean > * up all the remaining associations and all that memory. > */ > diff --git a/net/sctp/socket.c b/net/sctp/socket.c > index 3951a10..29f2b1f 100644 > --- a/net/sctp/socket.c > +++ b/net/sctp/socket.c > @@ -807,6 +807,37 @@ out: > return retval; > } > > +/* set addr events to assocs in the endpoint. ep and addr_wq must be locked */ > +int > +sctp_asconf_mgmt(struct sctp_sock *sp, struct sctp_sockaddr_entry *addrw) > +{ > + struct sock *sk = sctp_opt2sk(sp); > + union sctp_addr *addr = NULL; > + int cmd; > + int error = 0; > + > + addr = &addrw->a; > + addr->v4.sin_port = htons(sp->ep->base.bind_addr.port); > + cmd = addrw->state; > + > + SCTP_DEBUG_PRINTK("sctp_asconf_mgmt sp:%p\n", sp); > + 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 > @@ -3770,6 +3801,13 @@ 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(&sp->auto_asconf_list, > + &sctp_auto_asconf_splist); > + sp->do_auto_asconf = 1; > + } else > + sp->do_auto_asconf = 0; > + SCTP_DEBUG_PRINTK("sctp_init_sk sk:%p ep:%p\n", sk, ep); > local_bh_enable(); > > return 0; > @@ -3779,11 +3817,17 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk) > SCTP_STATIC void sctp_destroy_sock(struct sock *sk) > { > struct sctp_endpoint *ep; > + struct sctp_sock *sp; > > SCTP_DEBUG_PRINTK("sctp_destroy_sock(sk: %p)\n", sk); > > /* Release our hold on the endpoint. */ > - ep = sctp_sk(sk)->ep; > + sp = sctp_sk(sk); > + ep = sp->ep; > + if (sp->do_auto_asconf) { > + sp->do_auto_asconf = 0; > + list_del(&sp->auto_asconf_list); > + } > sctp_endpoint_free(ep); > local_bh_disable(); > percpu_counter_dec(&sctp_sockets_allocated); > > -- > 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 >