diff options
author | Linus Torvalds <torvalds@woody.linux-foundation.org> | 2007-10-18 14:40:30 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@woody.linux-foundation.org> | 2007-10-18 14:40:30 -0700 |
commit | a57793651ff1a09ef18bade998632435ca2dc13f (patch) | |
tree | fffc839d7b001f196421f09f0a06491588835fe1 /net | |
parent | 9cf52b2921fbe62566b6b2ee79f71203749c9e5e (diff) | |
parent | 52f095ee88d8851866bc7694ab991ca5abf21d5e (diff) |
Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6
* 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6: (51 commits)
[IPV6]: Fix again the fl6_sock_lookup() fixed locking
[NETFILTER]: nf_conntrack_tcp: fix connection reopening fix
[IPV6]: Fix race in ipv6_flowlabel_opt() when inserting two labels
[IPV6]: Lost locking in fl6_sock_lookup
[IPV6]: Lost locking when inserting a flowlabel in ipv6_fl_list
[NETFILTER]: xt_sctp: fix mistake to pass a pointer where array is required
[NET]: Fix OOPS due to missing check in dev_parse_header().
[TCP]: Remove lost_retrans zero seqno special cases
[NET]: fix carrier-on bug?
[NET]: Fix uninitialised variable in ip_frag_reasm()
[IPSEC]: Rename mode to outer_mode and add inner_mode
[IPSEC]: Disallow combinations of RO and AH/ESP/IPCOMP
[IPSEC]: Use the top IPv4 route's peer instead of the bottom
[IPSEC]: Store afinfo pointer in xfrm_mode
[IPSEC]: Add missing BEET checks
[IPSEC]: Move type and mode map into xfrm_state.c
[IPSEC]: Fix length check in xfrm_parse_spi
[IPSEC]: Move ip_summed zapping out of xfrm6_rcv_spi
[IPSEC]: Get nexthdr from caller in xfrm6_rcv_spi
[IPSEC]: Move tunnel parsing for IPv4 out of xfrm4_input
...
Diffstat (limited to 'net')
43 files changed, 661 insertions, 806 deletions
diff --git a/net/atm/br2684.c b/net/atm/br2684.c index c742d37bfb9..ba6428f204f 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -24,16 +24,6 @@ Author: Marcell GAL, 2000, XDSL Ltd, Hungary #include "common.h" -/* - * Define this to use a version of the code which interacts with the higher - * layers in a more intellegent way, by always reserving enough space for - * our header at the begining of the packet. However, there may still be - * some problems with programs like tcpdump. In 2.5 we'll sort out what - * we need to do to get this perfect. For now we just will copy the packet - * if we need space for the header - */ -/* #define FASTER_VERSION */ - #ifdef SKB_DEBUG static void skb_debug(const struct sk_buff *skb) { @@ -69,9 +59,7 @@ struct br2684_vcc { #ifdef CONFIG_ATM_BR2684_IPFILTER struct br2684_filter filter; #endif /* CONFIG_ATM_BR2684_IPFILTER */ -#ifndef FASTER_VERSION unsigned copies_needed, copies_failed; -#endif /* FASTER_VERSION */ }; struct br2684_dev { @@ -147,13 +135,6 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct br2684_dev *brdev, struct br2684_vcc *brvcc) { struct atm_vcc *atmvcc; -#ifdef FASTER_VERSION - if (brvcc->encaps == e_llc) - memcpy(skb_push(skb, 8), llc_oui_pid_pad, 8); - /* last 2 bytes of llc_oui_pid_pad are managed by header routines; - yes, you got it: 8 + 2 = sizeof(llc_oui_pid_pad) - */ -#else int minheadroom = (brvcc->encaps == e_llc) ? 10 : 2; if (skb_headroom(skb) < minheadroom) { struct sk_buff *skb2 = skb_realloc_headroom(skb, minheadroom); @@ -170,7 +151,6 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct br2684_dev *brdev, skb_copy_to_linear_data(skb, llc_oui_pid_pad, 10); else memset(skb->data, 0, 2); -#endif /* FASTER_VERSION */ skb_debug(skb); ATM_SKB(skb)->vcc = atmvcc = brvcc->atmvcc; @@ -237,87 +217,6 @@ static struct net_device_stats *br2684_get_stats(struct net_device *dev) return &BRPRIV(dev)->stats; } -#ifdef FASTER_VERSION -/* - * These mirror eth_header and eth_header_cache. They are not usually - * exported for use in modules, so we grab them from net_device - * after ether_setup() is done with it. Bit of a hack. - */ -static int (*my_eth_header)(struct sk_buff *, struct net_device *, - unsigned short, void *, void *, unsigned); -static int (*my_eth_header_cache)(struct neighbour *, struct hh_cache *); - -static int -br2684_header(struct sk_buff *skb, struct net_device *dev, - unsigned short type, void *daddr, void *saddr, unsigned len) -{ - u16 *pad_before_eth; - int t = my_eth_header(skb, dev, type, daddr, saddr, len); - if (t > 0) { - pad_before_eth = (u16 *) skb_push(skb, 2); - *pad_before_eth = 0; - return dev->hard_header_len; /* or return 16; ? */ - } else - return t; -} - -static int -br2684_header_cache(struct neighbour *neigh, struct hh_cache *hh) -{ -/* hh_data is 16 bytes long. if encaps is ether-llc we need 24, so -xmit will add the additional header part in that case */ - u16 *pad_before_eth = (u16 *)(hh->hh_data); - int t = my_eth_header_cache(neigh, hh); - DPRINTK("br2684_header_cache, neigh=%p, hh_cache=%p\n", neigh, hh); - if (t < 0) - return t; - else { - *pad_before_eth = 0; - hh->hh_len = PADLEN + ETH_HLEN; - } - return 0; -} - -/* - * This is similar to eth_type_trans, which cannot be used because of - * our dev->hard_header_len - */ -static inline __be16 br_type_trans(struct sk_buff *skb, struct net_device *dev) -{ - struct ethhdr *eth; - unsigned char *rawp; - eth = eth_hdr(skb); - - if (is_multicast_ether_addr(eth->h_dest)) { - if (!compare_ether_addr(eth->h_dest, dev->broadcast)) - skb->pkt_type = PACKET_BROADCAST; - else - skb->pkt_type = PACKET_MULTICAST; - } - - else if (compare_ether_addr(eth->h_dest, dev->dev_addr)) - skb->pkt_type = PACKET_OTHERHOST; - - if (ntohs(eth->h_proto) >= 1536) - return eth->h_proto; - - rawp = skb->data; - - /* - * This is a magic hack to spot IPX packets. Older Novell breaks - * the protocol design and runs IPX over 802.3 without an 802.2 LLC - * layer. We look for FFFF which isn't a used 802.2 SSAP/DSAP. This - * won't work for fault tolerant netware but does for the rest. - */ - if (*(unsigned short *) rawp == 0xFFFF) - return htons(ETH_P_802_3); - - /* - * Real 802.2 LLC - */ - return htons(ETH_P_802_2); -} -#endif /* FASTER_VERSION */ /* * We remember when the MAC gets set, so we don't override it later with @@ -448,17 +347,8 @@ static void br2684_push(struct atm_vcc *atmvcc, struct sk_buff *skb) return; } -#ifdef FASTER_VERSION - /* FIXME: tcpdump shows that pointer to mac header is 2 bytes earlier, - than should be. What else should I set? */ - skb_pull(skb, plen); - skb_set_mac_header(skb, -ETH_HLEN); - skb->pkt_type = PACKET_HOST; - skb->protocol = br_type_trans(skb, net_dev); -#else skb_pull(skb, plen - ETH_HLEN); skb->protocol = eth_type_trans(skb, net_dev); -#endif /* FASTER_VERSION */ #ifdef CONFIG_ATM_BR2684_IPFILTER if (unlikely(packet_fails_filter(skb->protocol, brvcc, skb))) { brdev->stats.rx_dropped++; @@ -584,13 +474,6 @@ static void br2684_setup(struct net_device *netdev) ether_setup(netdev); brdev->net_dev = netdev; -#ifdef FASTER_VERSION - my_eth_header = netdev->hard_header; - netdev->hard_header = br2684_header; - my_eth_header_cache = netdev->hard_header_cache; - netdev->hard_header_cache = br2684_header_cache; - netdev->hard_header_len = sizeof(llc_oui_pid_pad) + ETH_HLEN; /* 10 + 14 */ -#endif my_eth_mac_addr = netdev->set_mac_address; netdev->set_mac_address = br2684_mac_addr; netdev->hard_start_xmit = br2684_start_xmit; @@ -719,16 +602,12 @@ static int br2684_seq_show(struct seq_file *seq, void *v) list_for_each_entry(brvcc, &brdev->brvccs, brvccs) { seq_printf(seq, " vcc %d.%d.%d: encaps=%s" -#ifndef FASTER_VERSION ", failed copies %u/%u" -#endif /* FASTER_VERSION */ "\n", brvcc->atmvcc->dev->number, brvcc->atmvcc->vpi, brvcc->atmvcc->vci, (brvcc->encaps == e_llc) ? "LLC" : "VC" -#ifndef FASTER_VERSION , brvcc->copies_failed , brvcc->copies_needed -#endif /* FASTER_VERSION */ ); #ifdef CONFIG_ATM_BR2684_IPFILTER #define b1(var, byte) ((u8 *) &brvcc->filter.var)[byte] diff --git a/net/core/filter.c b/net/core/filter.c index bd903aaf7aa..1f0068eae50 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -387,6 +387,25 @@ int sk_chk_filter(struct sock_filter *filter, int flen) } /** + * sk_filter_rcu_release: Release a socket filter by rcu_head + * @rcu: rcu_head that contains the sk_filter to free + */ +static void sk_filter_rcu_release(struct rcu_head *rcu) +{ + struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu); + + sk_filter_release(fp); +} + +static void sk_filter_delayed_uncharge(struct sock *sk, struct sk_filter *fp) +{ + unsigned int size = sk_filter_len(fp); + + atomic_sub(size, &sk->sk_omem_alloc); + call_rcu_bh(&fp->rcu, sk_filter_rcu_release); +} + +/** * sk_attach_filter - attach a socket filter * @fprog: the filter program * @sk: the socket to use @@ -398,7 +417,7 @@ int sk_chk_filter(struct sock_filter *filter, int flen) */ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) { - struct sk_filter *fp; + struct sk_filter *fp, *old_fp; unsigned int fsize = sizeof(struct sock_filter) * fprog->len; int err; @@ -418,19 +437,34 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) fp->len = fprog->len; err = sk_chk_filter(fp->insns, fp->len); - if (!err) { - struct sk_filter *old_fp; - - rcu_read_lock_bh(); - old_fp = rcu_dereference(sk->sk_filter); - rcu_assign_pointer(sk->sk_filter, fp); - rcu_read_unlock_bh(); - fp = old_fp; + if (err) { + sk_filter_uncharge(sk, fp); + return err; } - if (fp) - sk_filter_release(sk, fp); - return err; + rcu_read_lock_bh(); + old_fp = rcu_dereference(sk->sk_filter); + rcu_assign_pointer(sk->sk_filter, fp); + rcu_read_unlock_bh(); + + sk_filter_delayed_uncharge(sk, old_fp); + return 0; +} + +int sk_detach_filter(struct sock *sk) +{ + int ret = -ENOENT; + struct sk_filter *filter; + + rcu_read_lock_bh(); + filter = rcu_dereference(sk->sk_filter); + if (filter) { + rcu_assign_pointer(sk->sk_filter, NULL); + sk_filter_delayed_uncharge(sk, filter); + ret = 0; + } + rcu_read_unlock_bh(); + return ret; } EXPORT_SYMBOL(sk_chk_filter); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 2100c734b10..8cae60c5338 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2454,7 +2454,7 @@ static int pktgen_output_ipsec(struct sk_buff *skb, struct pktgen_dev *pkt_dev) spin_lock(&x->lock); iph = ip_hdr(skb); - err = x->mode->output(x, skb); + err = x->outer_mode->output(x, skb); if (err) goto error; err = x->type->output(x, skb); diff --git a/net/core/sock.c b/net/core/sock.c index d45ecdccc6a..d292b4113d6 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -428,7 +428,6 @@ int sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen) { struct sock *sk=sock->sk; - struct sk_filter *filter; int val; int valbool; struct linger ling; @@ -652,16 +651,7 @@ set_rcvbuf: break; case SO_DETACH_FILTER: - rcu_read_lock_bh(); - filter = rcu_dereference(sk->sk_filter); - if (filter) { - rcu_assign_pointer(sk->sk_filter, NULL); - sk_filter_release(sk, filter); - rcu_read_unlock_bh(); - break; - } - rcu_read_unlock_bh(); - ret = -ENONET; + ret = sk_detach_filter(sk); break; case SO_PASSSEC: @@ -925,7 +915,7 @@ void sk_free(struct sock *sk) filter = rcu_dereference(sk->sk_filter); if (filter) { - sk_filter_release(sk, filter); + sk_filter_uncharge(sk, filter); rcu_assign_pointer(sk->sk_filter, NULL); } diff --git a/net/dccp/input.c b/net/dccp/input.c index 19d7e1dbd87..3560a2a875a 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -19,6 +19,9 @@ #include "ccid.h" #include "dccp.h" +/* rate-limit for syncs in reply to sequence-invalid packets; RFC 4340, 7.5.4 */ +int sysctl_dccp_sync_ratelimit __read_mostly = HZ / 8; + static void dccp_fin(struct sock *sk, struct sk_buff *skb) { sk->sk_shutdown |= RCV_SHUTDOWN; diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c index 9364b2fb4db..c62c05039f6 100644 --- a/net/dccp/sysctl.c +++ b/net/dccp/sysctl.c @@ -18,9 +18,6 @@ #error This file should not be compiled without CONFIG_SYSCTL defined #endif -/* rate-limit for syncs in reply to sequence-invalid packets; RFC 4340, 7.5.4 */ -int sysctl_dccp_sync_ratelimit __read_mostly = HZ / 8; - static struct ctl_table dccp_default_table[] = { { .procname = "seq_window", diff --git a/net/ieee80211/ieee80211_crypt_tkip.c b/net/ieee80211/ieee80211_crypt_tkip.c index 6cc54eeca3e..72e6ab66834 100644 --- a/net/ieee80211/ieee80211_crypt_tkip.c +++ b/net/ieee80211/ieee80211_crypt_tkip.c @@ -586,7 +586,7 @@ static void michael_mic_hdr(struct sk_buff *skb, u8 * hdr) if (stype & IEEE80211_STYPE_QOS_DATA) { const struct ieee80211_hdr_3addrqos *qoshdr = (struct ieee80211_hdr_3addrqos *)skb->data; - hdr[12] = qoshdr->qos_ctl & cpu_to_le16(IEEE80211_QCTL_TID); + hdr[12] = le16_to_cpu(qoshdr->qos_ctl) & IEEE80211_QCTL_TID; } else hdr[12] = 0; /* priority */ diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 484cf512858..e15e04fc666 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -136,7 +136,9 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f, *work -= f->qsize; atomic_sub(f->qsize, &f->mem); - f->destructor(q); + if (f->destructor) + f->destructor(q); + kfree(q); } EXPORT_SYMBOL(inet_frag_destroy); @@ -172,3 +174,88 @@ int inet_frag_evictor(struct inet_frags *f) return evicted; } EXPORT_SYMBOL(inet_frag_evictor); + +static struct inet_frag_queue *inet_frag_intern(struct inet_frag_queue *qp_in, + struct inet_frags *f, unsigned int hash, void *arg) +{ + struct inet_frag_queue *qp; +#ifdef CONFIG_SMP + struct hlist_node *n; +#endif + + write_lock(&f->lock); +#ifdef CONFIG_SMP + /* With SMP race we have to recheck hash table, because + * such entry could be created on other cpu, while we + * promoted read lock to write lock. + */ + hlist_for_each_entry(qp, n, &f->hash[hash], list) { + if (f->match(qp, arg)) { + atomic_inc(&qp->refcnt); + write_unlock(&f->lock); + qp_in->last_in |= COMPLETE; + inet_frag_put(qp_in, f); + return qp; + } + } +#endif + qp = qp_in; + if (!mod_timer(&qp->timer, jiffies + f->ctl->timeout)) + atomic_inc(&qp->refcnt); + + atomic_inc(&qp->refcnt); + hlist_add_head(&qp->list, &f->hash[hash]); + list_add_tail(&qp->lru_list, &f->lru_list); + f->nqueues++; + write_unlock(&f->lock); + return qp; +} + +static struct inet_frag_queue *inet_frag_alloc(struct inet_frags *f, void *arg) +{ + struct inet_frag_queue *q; + + q = kzalloc(f->qsize, GFP_ATOMIC); + if (q == NULL) + return NULL; + + f->constructor(q, arg); + atomic_add(f->qsize, &f->mem); + setup_timer(&q->timer, f->frag_expire, (unsigned long)q); + spin_lock_init(&q->lock); + atomic_set(&q->refcnt, 1); + + return q; +} + +static struct inet_frag_queue *inet_frag_create(struct inet_frags *f, + void *arg, unsigned int hash) +{ + struct inet_frag_queue *q; + + q = inet_frag_alloc(f, arg); + if (q == NULL) + return NULL; + + return inet_frag_intern(q, f, hash, arg); +} + +struct inet_frag_queue *inet_frag_find(struct inet_frags *f, void *key, + unsigned int hash) +{ + struct inet_frag_queue *q; + struct hlist_node *n; + + read_lock(&f->lock); + hlist_for_each_entry(q, n, &f->hash[hash], list) { + if (f->match(q, key)) { + atomic_inc(&q->refcnt); + read_unlock(&f->lock); + return q; + } + } + read_unlock(&f->lock); + + return inet_frag_create(f, key, hash); +} +EXPORT_SYMBOL(inet_frag_find); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 443b3f89192..2143bf30597 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -108,6 +108,11 @@ int ip_frag_mem(void) static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, struct net_device *dev); +struct ip4_create_arg { + struct iphdr *iph; + u32 user; +}; + static unsigned int ipqhashfn(__be16 id, __be32 saddr, __be32 daddr, u8 prot) { return jhash_3words((__force u32)id << 16 | prot, @@ -123,6 +128,19 @@ static unsigned int ip4_hashfn(struct inet_frag_queue *q) return ipqhashfn(ipq->id, ipq->saddr, ipq->daddr, ipq->protocol); } +static int ip4_frag_match(struct inet_frag_queue *q, void *a) +{ + struct ipq *qp; + struct ip4_create_arg *arg = a; + + qp = container_of(q, struct ipq, q); + return (qp->id == arg->iph->id && + qp->saddr == arg->iph->saddr && + qp->daddr == arg->iph->daddr && + qp->protocol == arg->iph->protocol && + qp->user == arg->user); +} + /* Memory Tracking Functions. */ static __inline__ void frag_kfree_skb(struct sk_buff *skb, int *work) { @@ -132,6 +150,20 @@ static __inline__ void frag_kfree_skb(struct sk_buff *skb, int *work) kfree_skb(skb); } +static void ip4_frag_init(struct inet_frag_queue *q, void *a) +{ + struct ipq *qp = container_of(q, struct ipq, q); + struct ip4_create_arg *arg = a; + + qp->protocol = arg->iph->protocol; + qp->id = arg->iph->id; + qp->saddr = arg->iph->saddr; + qp->daddr = arg->iph->daddr; + qp->user = arg->user; + qp->peer = sysctl_ipfrag_max_dist ? + inet_getpeer(arg->iph->saddr, 1) : NULL; +} + static __inline__ void ip4_frag_free(struct inet_frag_queue *q) { struct ipq *qp; @@ -139,17 +171,6 @@ static __inline__ void ip4_frag_free(struct inet_frag_queue *q) qp = container_of(q, struct ipq, q); if (qp->peer) inet_putpeer(qp->peer); - kfree(qp); -} - -static __inline__ struct ipq *frag_alloc_queue(void) -{ - struct ipq *qp = kzalloc(sizeof(struct ipq), GFP_ATOMIC); - - if (!qp) - return NULL; - atomic_add(sizeof(struct ipq), &ip4_frags.mem); - return qp; } @@ -185,7 +206,9 @@ static void ip_evictor(void) */ static void ip_expire(unsigned long arg) { - struct ipq *qp = (struct ipq *) arg; + struct ipq *qp; + + qp = container_of((struct inet_frag_queue *) arg, struct ipq, q); spin_lock(&qp->q.lock); @@ -210,112 +233,30 @@ out: ipq_put(qp); } -/* Creation primitives. */ - -static struct ipq *ip_frag_intern(struct ipq *qp_in) +/* Find the correct entry in the "incomplete datagrams" queue for + * this IP datagram, and create new one, if nothing is found. + */ +static inline struct ipq *ip_find(struct iphdr *iph, u32 user) { - struct ipq *qp; -#ifdef CONFIG_SMP - struct hlist_node *n; -#endif + struct inet_frag_queue *q; + struct ip4_create_arg arg; unsigned int hash; - write_lock(&ip4_frags.lock); - hash = ipqhashfn(qp_in->id, qp_in->saddr, qp_in->daddr, - qp_in->protocol); -#ifdef CONFIG_SMP - /* With SMP race we have to recheck hash table, because - * such entry could be created on other cpu, while we - * promoted read lock to write lock. - */ - hlist_for_each_entry(qp, n, &ip4_frags.hash[hash], q.list) { - if (qp->id == qp_in->id && - qp->saddr == qp_in->saddr && - qp->daddr == qp_in->daddr && - qp->protocol == qp_in->protocol && - qp->user == qp_in->user) { - atomic_inc(&qp->q.refcnt); - write_unlock(&ip4_frags.lock); - qp_in->q.last_in |= COMPLETE; - ipq_put(qp_in); - return qp; - } - } -#endif - qp = qp_in; - - if (!mod_timer(&qp->q.timer, jiffies + ip4_frags_ctl.timeout)) - atomic_inc(&qp->q.refcnt); + arg.iph = iph; + arg.user = user; + hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol); - atomic_inc(&qp->q.refcnt); - hlist_add_head(&qp->q.list, &ip4_frags.hash[hash]); - INIT_LIST_HEAD(&qp->q.lru_list); - list_add_tail(&qp->q.lru_list, &ip4_frags.lru_list); - ip4_frags.nqueues++; - write_unlock(&ip4_frags.lock); - return qp; -} - -/* Add an entry to the 'ipq' queue for a newly received IP datagram. */ -static struct ipq *ip_frag_create(struct iphdr *iph, u32 user) -{ - struct ipq *qp; - - if ((qp = frag_alloc_queue()) == NULL) + q = inet_frag_find(&ip4_frags, &arg, hash); + if (q == NULL) goto out_nomem; - qp->protocol = iph->protocol; - qp->id = iph->id; - qp->saddr = iph->saddr; - qp->daddr = iph->daddr; - qp->user = user; - qp->peer = sysctl_ipfrag_max_dist ? inet_getpeer(iph->saddr, 1) : NULL; - - /* Initialize a timer for this entry. */ - init_timer(&qp->q.timer); - qp->q.timer.data = (unsigned long) qp; /* pointer to queue */ - qp->q.timer.function = ip_expire; /* expire function */ - spin_lock_init(&qp->q.lock); - atomic_set(&qp->q.refcnt, 1); - - return ip_frag_intern(qp); + return container_of(q, struct ipq, q); out_nomem: LIMIT_NETDEBUG(KERN_ERR "ip_frag_create: no memory left !\n"); return NULL; } -/* Find the correct entry in the "incomplete datagrams" queue for - * this IP datagram, and create new one, if nothing is found. - */ -static inline struct ipq *ip_find(struct iphdr *iph, u32 user) -{ - __be16 id = iph->id; - __be32 saddr = iph->saddr; - __be32 daddr = iph->daddr; - __u8 protocol = iph->protocol; - unsigned int hash; - struct ipq *qp; - struct hlist_node *n; - - read_lock(&ip4_frags.lock); - hash = ipqhashfn(id, saddr, daddr, protocol); - hlist_for_each_entry(qp, n, &ip4_frags.hash[hash], q.list) { - if (qp->id == id && - qp->saddr == saddr && - qp->daddr == daddr && - qp->protocol == protocol && - qp->user == user) { - atomic_inc(&qp->q.refcnt); - read_unlock(&ip4_frags.lock); - return qp; - } - } - read_unlock(&ip4_frags.lock); - - return ip_frag_create(iph, user); -} - /* Is the fragment too far ahead to be part of ipq? */ static inline int ip_frag_too_far(struct ipq *qp) { @@ -545,7 +486,6 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, if (prev) { head = prev->next; fp = skb_clone(head, GFP_ATOMIC); - if (!fp) goto out_nomem; @@ -571,7 +511,6 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, goto out_oversize; /* Head of list must not be cloned. */ - err = -ENOMEM; if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC)) goto out_nomem; @@ -627,6 +566,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, out_nomem: LIMIT_NETDEBUG(KERN_ERR "IP: queue_glue: no memory for gluing " "queue %p\n", qp); + err = -ENOMEM; goto out_fail; out_oversize: if (net_ratelimit()) @@ -671,9 +611,12 @@ void __init ipfrag_init(void) { ip4_frags.ctl = &ip4_frags_ctl; ip4_frags.hashfn = ip4_hashfn; + ip4_frags.constructor = ip4_frag_init; ip4_frags.destructor = ip4_frag_free; ip4_frags.skb_free = NULL; ip4_frags.qsize = sizeof(struct ipq); + ip4_frags.match = ip4_frag_match; + ip4_frags.frag_expire = ip_expire; inet_frags_init(&ip4_frags); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 0f00966b178..9288220b73a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1121,7 +1121,7 @@ static int tcp_mark_lost_retrans(struct sock *sk, u32 received_upto) struct sk_buff *skb; int flag = 0; int cnt = 0; - u32 new_low_seq = 0; + u32 new_low_seq = tp->snd_nxt; tcp_for_write_queue(skb, sk) { u32 ack_seq = TCP_SKB_CB(skb)->ack_seq; @@ -1153,7 +1153,7 @@ static int tcp_mark_lost_retrans(struct sock *sk, u32 received_upto) NET_INC_STATS_BH(LINUX_MIB_TCPLOSTRETRANSMIT); } } else { - if (!new_low_seq || before(ack_seq, new_low_seq)) + if (before(ack_seq, new_low_seq)) new_low_seq = ack_seq; cnt += tcp_skb_pcount(skb); } @@ -1242,7 +1242,7 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_ int num_sacks = (ptr[1] - TCPOLEN_SACK_BASE)>>3; int reord = tp->packets_out; int prior_fackets; - u32 highest_sack_end_seq = 0; + u32 highest_sack_end_seq = tp->lost_retrans_low; int flag = 0; int found_dup_sack = 0; int cached_fack_count; diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index e9bbfde19ac..5e95c8a07ef 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -16,19 +16,6 @@ #include <net/ip.h> #include <net/xfrm.h> -static int xfrm4_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq) -{ - switch (nexthdr) { - case IPPROTO_IPIP: - case IPPROTO_IPV6: - *spi = ip_hdr(skb)->saddr; - *seq = 0; - return 0; - } - - return xfrm_parse_spi(skb, nexthdr, spi, seq); -} - #ifdef CONFIG_NETFILTER static inline int xfrm4_rcv_encap_finish(struct sk_buff *skb) { @@ -46,28 +33,29 @@ drop: } #endif -static int xfrm4_rcv_encap(struct sk_buff *skb, __u16 encap_type) +int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type) { - __be32 spi, seq; + int err; + __be32 seq; struct xfrm_state *xfrm_vec[XFRM_MAX_DEPTH]; struct xfrm_state *x; int xfrm_nr = 0; int decaps = 0; - int err = xfrm4_parse_spi(skb, ip_hdr(skb)->protocol, &spi, &seq); unsigned int nhoff = offsetof(struct iphdr, protocol); - if (err != 0) + seq = 0; + if (!spi && (err = xfrm_parse_spi(skb, nexthdr, &spi, &seq)) != 0) goto drop; do { const struct iphdr *iph = ip_hdr(skb); - int nexthdr; if (xfrm_nr == XFRM_MAX_DEPTH) goto drop; x = xfrm_state_lookup((xfrm_address_t *)&iph->daddr, spi, - iph->protocol != IPPROTO_IPV6 ? iph->protocol : IPPROTO_IPIP, AF_INET); + nexthdr, AF_INET); if (x == NULL) goto drop; @@ -103,15 +91,15 @@ static int xfrm4_rcv_encap(struct sk_buff *skb, __u16 encap_type) xfrm_vec[xfrm_nr++] = x; - if (x->mode->input(x, skb)) + if (x->outer_mode->input(x, skb)) goto drop; - if (x->props.mode == XFRM_MODE_TUNNEL) { + if (x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL) { decaps = 1; break; } - err = xfrm_parse_spi(skb, ip_hdr(skb)->protocol, &spi, &seq); + err = xfrm_parse_spi(skb, nexthdr, &spi, &seq); if (err < 0) goto drop; } while (!err); @@ -165,6 +153,7 @@ drop: kfree_skb(skb); return 0; } +EXPORT_SYMBOL(xfrm4_rcv_encap); /* If it's a keepalive packet, then just eat it. * If it's an encapsulated packet, then pass it to the @@ -252,11 +241,8 @@ int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb) __skb_pull(skb, len); skb_reset_transport_header(skb); - /* modify the protocol (it's ESP!) */ - iph->protocol = IPPROTO_ESP; - /* process ESP */ - ret = xfrm4_rcv_encap(skb, encap_type); + ret = xfrm4_rcv_encap(skb, IPPROTO_ESP, 0, encap_type); return ret; drop: @@ -266,7 +252,7 @@ drop: int xfrm4_rcv(struct sk_buff *skb) { - return xfrm4_rcv_encap(skb, 0); + return xfrm4_rcv_spi(skb, ip_hdr(skb)->protocol, 0); } EXPORT_SYMBOL(xfrm4_rcv); diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c index 73d2338bec5..e42e122414b 100644 --- a/net/ipv4/xfrm4_mode_beet.c +++ b/net/ipv4/xfrm4_mode_beet.c @@ -114,6 +114,7 @@ static struct xfrm_mode xfrm4_beet_mode = { .output = xfrm4_beet_output, .owner = THIS_MODULE, .encap = XFRM_MODE_BEET, + .flags = XFRM_MODE_FLAG_TUNNEL, }; static int __init xfrm4_beet_init(void) diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 1ae9d32276f..e4deecba6dd 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -139,6 +139,7 @@ static struct xfrm_mode xfrm4_tunnel_mode = { .output = xfrm4_tunnel_output, .owner = THIS_MODULE, .encap = XFRM_MODE_TUNNEL, + .flags = XFRM_MODE_FLAG_TUNNEL, }; static int __init xfrm4_tunnel_init(void) diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index a4edd666318..c4a7156962b 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -47,7 +47,7 @@ static inline int xfrm4_output_one(struct sk_buff *skb) struct iphdr *iph; int err; - if (x->props.mode == XFRM_MODE_TUNNEL) { + if (x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL) { err = xfrm4_tunnel_check_size(skb); if (err) goto error_nolock; diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 329825ca68f..cc86fb110dd 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -117,7 +117,7 @@ __xfrm4_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int header_len += xfrm[i]->props.header_len; trailer_len += xfrm[i]->props.trailer_len; - if (xfrm[i]->props.mode == XFRM_MODE_TUNNEL) { + if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) { unsigned short encap_family = xfrm[i]->props.family; switch (encap_family) { case AF_INET: @@ -151,7 +151,6 @@ __xfrm4_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int i = 0; for (; dst_prev != &rt->u.dst; dst_prev = dst_prev->child) { struct xfrm_dst *x = (struct xfrm_dst*)dst_prev; - struct xfrm_state_afinfo *afinfo; x->u.rt.fl = *fl; dst_prev->xfrm = xfrm[i++]; @@ -169,27 +168,17 @@ __xfrm4_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int /* Copy neighbout for reachability confirmation */ dst_prev->neighbour = neigh_clone(rt->u.dst.neighbour); dst_prev->input = rt->u.dst.input; - /* XXX: When IPv6 module can be unloaded, we should manage reference - * to xfrm6_output in afinfo->output. Miyazawa - * */ - afinfo = xfrm_state_get_afinfo(dst_prev->xfrm->props.family); - if (!afinfo) { - dst = *dst_p; - err = -EAFNOSUPPORT; - goto error; - } - dst_prev->output = afinfo->output; - xfrm_state_put_afinfo(afinfo); - if (dst_prev->xfrm->props.family == AF_INET && rt->peer) - atomic_inc(&rt->peer->refcnt); - x->u.rt.peer = rt->peer; + dst_prev->output = dst_prev->xfrm->outer_mode->afinfo->output; + if (rt0->peer) + atomic_inc(&rt0->peer->refcnt); + x->u.rt.peer = rt0->peer; /* Sheit... I remember I did this right. Apparently, * it was magically lost, so this code needs audit */ x->u.rt.rt_flags = rt0->rt_flags&(RTCF_BROADCAST|RTCF_MULTICAST|RTCF_LOCAL); - x->u.rt.rt_type = rt->rt_type; + x->u.rt.rt_type = rt0->rt_type; x->u.rt.rt_src = rt0->rt_src; x->u.rt.rt_dst = rt0->rt_dst; - x->u.rt.rt_gateway = rt->rt_gateway; + x->u.rt.rt_gateway = rt0->rt_gateway; x->u.rt.rt_spec_dst = rt0->rt_spec_dst; x->u.rt.idev = rt0->idev; in_dev_hold(rt0->idev); @@ -291,7 +280,7 @@ static void xfrm4_dst_destroy(struct dst_entry *dst) if (likely(xdst->u.rt.idev)) in_dev_put(xdst->u.rt.idev); - if (dst->xfrm && dst->xfrm->props.family == AF_INET && likely(xdst->u.rt.peer)) + if (likely(xdst->u.rt.peer)) inet_putpeer(xdst->u.rt.peer); xfrm_dst_destroy(xdst); } diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index 93e2c061cdd..13d54a1c333 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -49,6 +49,7 @@ __xfrm4_init_tempsel(struct xfrm_state *x, struct flowi *fl, static struct xfrm_state_afinfo xfrm4_state_afinfo = { .family = AF_INET, + .owner = THIS_MODULE, .init_flags = xfrm4_init_flags, .init_tempsel = __xfrm4_init_tempsel, .output = xfrm4_output, diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c index 1312417608e..32684519562 100644 --- a/net/ipv4/xfrm4_tunnel.c +++ b/net/ipv4/xfrm4_tunnel.c @@ -18,7 +18,7 @@ static int ipip_output(struct xfrm_state *x, struct sk_buff *skb) static int ipip_xfrm_rcv(struct xfrm_state *x, struct sk_buff *skb) { - return IPPROTO_IP; + return ip_hdr(skb)->protocol; } static int ipip_init_state(struct xfrm_state *x) @@ -48,20 +48,25 @@ static struct xfrm_type ipip_type = { .output = ipip_output }; +static int xfrm_tunnel_rcv(struct sk_buff *skb) +{ + return xfrm4_rcv_spi(skb, IPPROTO_IP, ip_hdr(skb)->saddr); +} + static int xfrm_tunnel_err(struct sk_buff *skb, u32 info) { return -ENOENT; } static struct xfrm_tunnel xfrm_tunnel_handler = { - .handler = xfrm4_rcv, + .handler = xfrm_tunnel_rcv, .err_handler = xfrm_tunnel_err, .priority = 2, }; #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) static struct xfrm_tunnel xfrm64_tunnel_handler = { - .handler = xfrm4_rcv, + .handler = xfrm_tunnel_rcv, .err_handler = xfrm_tunnel_err, .priority = 2, }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 52d10d21321..348bd8d0611 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -255,11 +255,6 @@ static void addrconf_mod_timer(struct inet6_ifaddr *ifp, static int snmp6_alloc_dev(struct inet6_dev *idev) { - int err = -ENOMEM; - - if (!idev || !idev->dev) - return -EINVAL; - if (snmp_mib_init((void **)idev->stats.ipv6, sizeof(struct ipstats_mib), __alignof__(struct ipstats_mib)) < 0) @@ -280,15 +275,14 @@ err_icmpmsg: err_icmp: snmp_mib_free((void **)idev->stats.ipv6); err_ip: - return err; + return -ENOMEM; } -static int snmp6_free_dev(struct inet6_dev *idev) +static void snmp6_free_dev(struct inet6_dev *idev) { snmp_mib_free((void **)idev->stats.icmpv6msg); snmp_mib_free((void **)idev->stats.icmpv6); snmp_mib_free((void **)idev->stats.ipv6); - return 0; } /* Nobody refers to this device, we may destroy it. */ diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index bc929381fa4..1b1caf3aa1c 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -747,6 +747,7 @@ static void cleanup_ipv6_mibs(void) { snmp_mib_free((void **)ipv6_statistics); snmp_mib_free((void **)icmpv6_statistics); + snmp_mib_free((void **)icmpv6msg_statistics); snmp_mib_free((void **)udp_stats_in6); snmp_mib_free((void **)udplite_stats_in6); } diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index f9f68916269..67cd06613a2 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -344,6 +344,8 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) goto out; + skb->ip_summed = CHECKSUM_NONE; + hdr_len = skb->data - skb_network_header(skb); ah = (struct ip_auth_hdr *)skb->data; ahp = x->data; @@ -475,8 +477,15 @@ static int ah6_init_state(struct xfrm_state *x) x->props.header_len = XFRM_ALIGN8(sizeof(struct ip_auth_hdr) + ahp->icv_trunc_len); - if (x->props.mode == XFRM_MODE_TUNNEL) + switch (x->props.mode) { + case XFRM_MODE_BEET: + case XFRM_MODE_TRANSPORT: + break; + case XFRM_MODE_TUNNEL: x->props.header_len += sizeof(struct ipv6hdr); + default: + goto error; + } x->data = ahp; return 0; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 9eb92859835..b0715432e45 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -354,8 +354,15 @@ static int esp6_init_state(struct xfrm_state *x) (x->ealg->alg_key_len + 7) / 8)) goto error; x->props.header_len = sizeof(struct ip_esp_hdr) + esp->conf.ivlen; - if (x->props.mode == XFRM_MODE_TUNNEL) + switch (x->props.mode) { + case XFRM_MODE_BEET: + case XFRM_MODE_TRANSPORT: + break; + case XFRM_MODE_TUNNEL: x->props.header_len += sizeof(struct ipv6hdr); + default: + goto error; + } x->data = esp; return 0; diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 217d60f9fc8..b12cc22e774 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -154,8 +154,10 @@ static void ip6_fl_gc(unsigned long dummy) write_unlock(&ip6_fl_lock); } -static int fl_intern(struct ip6_flowlabel *fl, __be32 label) +static struct ip6_flowlabel *fl_intern(struct ip6_flowlabel *fl, __be32 label) { + struct ip6_flowlabel *lfl; + fl->label = label & IPV6_FLOWLABEL_MASK; write_lock_bh(&ip6_fl_lock); @@ -163,12 +165,26 @@ static int fl_intern(struct ip6_flowlabel *fl, __be32 label) for (;;) { fl->label = htonl(net_random())&IPV6_FLOWLABEL_MASK; if (fl->label) { - struct ip6_flowlabel *lfl; lfl = __fl_lookup(fl->label); if (lfl == NULL) break; } } + } else { + /* + * we dropper the ip6_fl_lock, so this entry could reappear + * and we need to recheck with it. + * + * OTOH no need to search the active socket first, like it is + * done in ipv6_flowlabel_opt - sock is locked, so new entry + * with the same label can only appear on another sock + */ + lfl = __fl_lookup(fl->label); + if (lfl != NULL) { + atomic_inc(&lfl->users); + write_unlock_bh(&ip6_fl_lock); + return lfl; + } } fl->lastuse = jiffies; @@ -176,7 +192,7 @@ static int fl_intern(struct ip6_flowlabel *fl, __be32 label) fl_ht[FL_HASH(fl->label)] = fl; atomic_inc(&fl_size); write_unlock_bh(&ip6_fl_lock); - return 0; + return NULL; } @@ -190,14 +206,17 @@ struct ip6_flowlabel * fl6_sock_lookup(struct sock *sk, __be32 label) label &= IPV6_FLOWLABEL_MASK; + read_lock_bh(&ip6_sk_fl_lock); for (sfl=np->ipv6_fl_list; sfl; sfl = sfl->next) { struct ip6_flowlabel *fl = sfl->fl; if (fl->label == label) { fl->lastuse = jiffies; atomic_inc(&fl->users); + read_unlock_bh(&ip6_sk_fl_lock); return fl; } } + read_unlock_bh(&ip6_sk_fl_lock); return NULL; } @@ -409,6 +428,16 @@ static int ipv6_opt_cmp(struct ipv6_txoptions *o1, struct ipv6_txoptions *o2) return 0; } +static inline void fl_link(struct ipv6_pinfo *np, struct ipv6_fl_socklist *sfl, + struct ip6_flowlabel *fl) +{ + write_lock_bh(&ip6_sk_fl_lock); + sfl->fl = fl; + sfl->next = np->ipv6_fl_list; + np->ipv6_fl_list = sfl; + write_unlock_bh(&ip6_sk_fl_lock); +} + int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) { int err; @@ -416,7 +445,8 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) struct in6_flowlabel_req freq; struct ipv6_fl_socklist *sfl1=NULL; struct ipv6_fl_socklist *sfl, **sflp; - struct ip6_flowlabel *fl; + struct ip6_flowlabel *fl, *fl1 = NULL; + if (optlen < sizeof(freq)) return -EINVAL; @@ -472,8 +502,6 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) sfl1 = kmalloc(sizeof(*sfl1), GFP_KERNEL); if (freq.flr_label) { - struct ip6_flowlabel *fl1 = NULL; - err = -EEXIST; read_lock_bh(&ip6_sk_fl_lock); for (sfl = np->ipv6_fl_list; sfl; sfl = sfl->next) { @@ -492,6 +520,7 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) if (fl1 == NULL) fl1 = fl_lookup(freq.flr_label); if (fl1) { +recheck: err = -EEXIST; if (freq.flr_flags&IPV6_FL_F_EXCL) goto release; @@ -513,11 +542,7 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) fl1->linger = fl->linger; if ((long)(fl->expires - fl1->expires) > 0) fl1->expires = fl->expires; - write_lock_bh(&ip6_sk_fl_lock); - sfl1->fl = fl1; - sfl1->next = np->ipv6_fl_list; - np->ipv6_fl_list = sfl1; - write_unlock_bh(&ip6_sk_fl_lock); + fl_link(np, sfl1, fl1); fl_free(fl); return 0; @@ -534,9 +559,9 @@ release: if (sfl1 == NULL || (err = mem_check(sk)) != 0) goto done; - err = fl_intern(fl, freq.flr_label); - if (err) - goto done; + fl1 = fl_intern(fl, freq.flr_label); + if (fl1 != NULL) + goto recheck; if (!freq.flr_label) { if (copy_to_user(&((struct in6_flowlabel_req __user *) optval)->flr_label, @@ -545,9 +570,7 @@ release: } } - sfl1->fl = fl; - sfl1->next = np->ipv6_fl_list; - np->ipv6_fl_list = sfl1; + fl_link(np, sfl1, fl); return 0; default: diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 28fc8edfdc3..80ef2a1d39f 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -411,8 +411,15 @@ static int ipcomp6_init_state(struct xfrm_state *x) goto out; x->props.header_len = 0; - if (x->props.mode == XFRM_MODE_TUNNEL) + switch (x->props.mode) { + case XFRM_MODE_BEET: + case XFRM_MODE_TRANSPORT: + break; + case XFRM_MODE_TUNNEL: x->props.header_len += sizeof(struct ipv6hdr); + default: + goto error; + } mutex_lock(&ipcomp6_resource_mutex); if (!ipcomp6_alloc_scratches()) diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 726fafd4196..e170c67c47a 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -130,22 +130,6 @@ static inline void frag_kfree_skb(struct sk_buff *skb, unsigned int *work) kfree_skb(skb); } -static void nf_frag_free(struct inet_frag_queue *q) -{ - kfree(container_of(q, struct nf_ct_frag6_queue, q)); -} - -static inline struct nf_ct_frag6_queue *frag_alloc_queue(void) -{ - struct nf_ct_frag6_queue *fq; - - fq = kzalloc(sizeof(struct nf_ct_frag6_queue), GFP_ATOMIC); - if (fq == NULL) - return NULL; - atomic_add(sizeof(struct nf_ct_frag6_queue), &nf_frags.mem); - return fq; -} - /* Destruction primitives. */ static __inline__ void fq_put(struct nf_ct_frag6_queue *fq) @@ -168,7 +152,10 @@ static void nf_ct_frag6_evictor(void) static void nf_ct_frag6_expire(unsigned long data) { - struct nf_ct_frag6_queue *fq = (struct nf_ct_frag6_queue *) data; + struct nf_ct_frag6_queue *fq; + + fq = container_of((struct inet_frag_queue *)data, + struct nf_ct_frag6_queue, q); spin_lock(&fq->q.lock); @@ -184,89 +171,29 @@ out: /* Creation primitives. */ -static struct nf_ct_frag6_queue *nf_ct_frag6_intern(unsigned int hash, - struct nf_ct_frag6_queue *fq_in) +static __inline__ struct nf_ct_frag6_queue * +fq_find(__be32 id, struct in6_addr *src, struct in6_addr *dst) { - struct nf_ct_frag6_queue *fq; -#ifdef CONFIG_SMP - struct hlist_node *n; -#endif - - write_lock(&nf_frags.lock); -#ifdef CONFIG_SMP - hlist_for_each_entry(fq, n, &nf_frags.hash[hash], q.list) { - if (fq->id == fq_in->id && - ipv6_addr_equal(&fq_in->saddr, &fq->saddr) && - ipv6_addr_equal(&fq_in->daddr, &fq->daddr)) { - atomic_inc(&fq->q.refcnt); - write_unlock(&nf_frags.lock); - fq_in->q.last_in |= COMPLETE; - fq_put(fq_in); - return fq; - } - } -#endif - fq = fq_in; - - if (!mod_timer(&fq->q.timer, jiffies + nf_frags_ctl.timeout)) - atomic_inc(&fq->q.refcnt); - - atomic_inc(&fq->q.refcnt); - hlist_add_head(&fq->q.list, &nf_frags.hash[hash]); - INIT_LIST_HEAD(&fq->q.lru_list); - list_add_tail(&fq->q.lru_list, &nf_frags.lru_list); - nf_frags.nqueues++; - write_unlock(&nf_frags.lock); - return fq; -} + struct inet_frag_queue *q; + struct ip6_create_arg arg; + unsigned int hash; + arg.id = id; + arg.src = src; + arg.dst = dst; + hash = ip6qhashfn(id, src, dst); -static struct nf_ct_frag6_queue * -nf_ct_frag6_create(unsigned int hash, __be32 id, struct in6_addr *src, struct in6_addr *dst) -{ - struct nf_ct_frag6_queue *fq; - - if ((fq = frag_alloc_queue()) == NULL) { - pr_debug("Can't alloc new queue\n"); + q = inet_frag_find(&nf_frags, &arg, hash); + if (q == NULL) goto oom; - } - - fq->id = id; - ipv6_addr_copy(&fq->saddr, src); - ipv6_addr_copy(&fq->daddr, dst); - - setup_timer(&fq->q.timer, nf_ct_frag6_expire, (unsigned long)fq); - spin_lock_init(&fq->q.lock); - atomic_set(&fq->q.refcnt, 1); - return nf_ct_frag6_intern(hash, fq); + return container_of(q, struct nf_ct_frag6_queue, q); oom: + pr_debug("Can't alloc new queue\n"); return NULL; } -static __inline__ struct nf_ct_frag6_queue * -fq_find(__be32 id, struct in6_addr *src, struct in6_addr *dst) -{ - struct nf_ct_frag6_queue *fq; - struct hlist_node *n; - unsigned int hash = ip6qhashfn(id, src, dst); - - read_lock(&nf_frags.lock); - hlist_for_each_entry(fq, n, &nf_frags.hash[hash], q.list) { - if (fq->id == id && - ipv6_addr_equal(src, &fq->saddr) && - ipv6_addr_equal(dst, &fq->daddr)) { - atomic_inc(&fq->q.refcnt); - read_unlock(&nf_frags.lock); - return fq; - } - } - read_unlock(&nf_frags.lock); - - return nf_ct_frag6_create(hash, id, src, dst); -} - static int nf_ct_frag6_queue(struct nf_ct_frag6_queue *fq, struct sk_buff *skb, struct frag_hdr *fhdr, int nhoff) @@ -749,9 +676,12 @@ int nf_ct_frag6_init(void) { nf_frags.ctl = &nf_frags_ctl; nf_frags.hashfn = nf_hashfn; - nf_frags.destructor = nf_frag_free; + nf_frags.constructor = ip6_frag_init; + nf_frags.destructor = NULL; nf_frags.skb_free = nf_skb_free; nf_frags.qsize = sizeof(struct nf_ct_frag6_queue); + nf_frags.match = ip6_frag_match; + nf_frags.frag_expire = nf_ct_frag6_expire; inet_frags_init(&nf_frags); return 0; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 6ad19cfc202..76c88a93b9b 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -143,6 +143,18 @@ static unsigned int ip6_hashfn(struct inet_frag_queue *q) return ip6qhashfn(fq->id, &fq->saddr, &fq->daddr); } +int ip6_frag_match(struct inet_frag_queue *q, void *a) +{ + struct frag_queue *fq; + struct ip6_create_arg *arg = a; + + fq = container_of(q, struct frag_queue, q); + return (fq->id == arg->id && + ipv6_addr_equal(&fq->saddr, arg->src) && + ipv6_addr_equal(&fq->daddr, arg->dst)); +} +EXPORT_SYMBOL(ip6_frag_match); + /* Memory Tracking Functions. */ static inline void frag_kfree_skb(struct sk_buff *skb, int *work) { @@ -152,20 +164,16 @@ static inline void frag_kfree_skb(struct sk_buff *skb, int *work) kfree_skb(skb); } -static void ip6_frag_free(struct inet_frag_queue *fq) +void ip6_frag_init(struct inet_frag_queue *q, void *a) { - kfree(container_of(fq, struct frag_queue, q)); -} - -static inline struct frag_queue *frag_alloc_queue(void) -{ - struct frag_queue *fq = kzalloc(sizeof(struct frag_queue), GFP_ATOMIC); + struct frag_queue *fq = container_of(q, struct frag_queue, q); + struct ip6_create_arg *arg = a; - if(!fq) - return NULL; - atomic_add(sizeof(struct frag_queue), &ip6_frags.mem); - return fq; + fq->id = arg->id; + ipv6_addr_copy(&fq->saddr, arg->src); + ipv6_addr_copy(&fq->daddr, arg->dst); } +EXPORT_SYMBOL(ip6_frag_init); /* Destruction primitives. */ @@ -193,9 +201,11 @@ static void ip6_evictor(struct inet6_dev *idev) static void ip6_frag_expire(unsigned long data) { - struct frag_queue *fq = (struct frag_queue *) data; + struct frag_queue *fq; struct net_device *dev = NULL; + fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q); + spin_lock(&fq->q.lock); if (fq->q.last_in & COMPLETE) @@ -230,98 +240,30 @@ out: fq_put(fq); } -/* Creation primitives. */ - - -static struct frag_queue *ip6_frag_intern(struct frag_queue *fq_in) +static __inline__ struct frag_queue * +fq_find(__be32 id, struct in6_addr *src, struct in6_addr *dst, + struct inet6_dev *idev) { - struct frag_queue *fq; + struct inet_frag_queue *q; + struct ip6_create_arg arg; unsigned int hash; -#ifdef CONFIG_SMP - struct hlist_node *n; -#endif - write_lock(&ip6_frags.lock); - hash = ip6qhashfn(fq_in->id, &fq_in->saddr, &fq_in->daddr); -#ifdef CONFIG_SMP - hlist_for_each_entry(fq, n, &ip6_frags.hash[hash], q.list) { - if (fq->id == fq_in->id && - ipv6_addr_equal(&fq_in->saddr, &fq->saddr) && - ipv6_addr_equal(&fq_in->daddr, &fq->daddr)) { - atomic_inc(&fq->q.refcnt); - write_unlock(&ip6_frags.lock); - fq_in->q.last_in |= COMPLETE; - fq_put(fq_in); - return fq; - } - } -#endif - fq = fq_in; - - if (!mod_timer(&fq->q.timer, jiffies + ip6_frags_ctl.timeout)) - atomic_inc(&fq->q.refcnt); - - atomic_inc(&fq->q.refcnt); - hlist_add_head(&fq->q.list, &ip6_frags.hash[hash]); - INIT_LIST_HEAD(&fq->q.lru_list); - list_add_tail(&fq->q.lru_list, &ip6_frags.lru_list); - ip6_frags.nqueues++; - write_unlock(&ip6_frags.lock); - return fq; -} - - -static struct frag_queue * -ip6_frag_create(__be32 id, struct in6_addr *src, struct in6_addr *dst, - struct inet6_dev *idev) -{ - struct frag_queue *fq; + arg.id = id; + arg.src = src; + arg.dst = dst; + hash = ip6qhashfn(id, src, dst); - if ((fq = frag_alloc_queue()) == NULL) + q = inet_frag_find(&ip6_frags, &arg, hash); + if (q == NULL) goto oom; - fq->id = id; - ipv6_addr_copy(&fq->saddr, src); - ipv6_addr_copy(&fq->daddr, dst); - - init_timer(&fq->q.timer); - fq->q.timer.function = ip6_frag_expire; - fq->q.timer.data = (long) fq; - spin_lock_init(&fq->q.lock); - atomic_set(&fq->q.refcnt, 1); - - return ip6_frag_intern(fq); + return container_of(q, struct frag_queue, q); oom: IP6_INC_STATS_BH(idev, IPSTATS_MIB_REASMFAILS); return NULL; } -static __inline__ struct frag_queue * -fq_find(__be32 id, struct in6_addr *src, struct in6_addr *dst, - struct inet6_dev *idev) -{ - struct frag_queue *fq; - struct hlist_node *n; - unsigned int hash; - - read_lock(&ip6_frags.lock); - hash = ip6qhashfn(id, src, dst); - hlist_for_each_entry(fq, n, &ip6_frags.hash[hash], q.list) { - if (fq->id == id && - ipv6_addr_equal(src, &fq->saddr) && - ipv6_addr_equal(dst, &fq->daddr)) { - atomic_inc(&fq->q.refcnt); - read_unlock(&ip6_frags.lock); - return fq; - } - } - read_unlock(&ip6_frags.lock); - - return ip6_frag_create(id, src, dst, idev); -} - - static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, struct frag_hdr *fhdr, int nhoff) { @@ -697,8 +639,11 @@ void __init ipv6_frag_init(void) ip6_frags.ctl = &ip6_frags_ctl; ip6_frags.hashfn = ip6_hashfn; - ip6_frags.destructor = ip6_frag_free; + ip6_frags.constructor = ip6_frag_init; + ip6_frags.destructor = NULL; ip6_frags.skb_free = NULL; ip6_frags.qsize = sizeof(struct frag_queue); + ip6_frags.match = ip6_frag_match; + ip6_frags.frag_expire = ip6_frag_expire; inet_frags_init(&ip6_frags); } diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 02f69e544f6..515783707e8 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -16,7 +16,7 @@ #include <net/ipv6.h> #include <net/xfrm.h> -int xfrm6_rcv_spi(struct sk_buff *skb, __be32 spi) +int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi) { int err; __be32 seq; @@ -24,11 +24,9 @@ int xfrm6_rcv_spi(struct sk_buff *skb, __be32 spi) struct xfrm_state *x; int xfrm_nr = 0; int decaps = 0; - int nexthdr; unsigned int nhoff; nhoff = IP6CB(skb)->nhoff; - nexthdr = skb_network_header(skb)[nhoff]; seq = 0; if (!spi && (err = xfrm_parse_spi(skb, nexthdr, &spi, &seq)) != 0) @@ -41,7 +39,7 @@ int xfrm6_rcv_spi(struct sk_buff *skb, __be32 spi) goto drop; x = xfrm_state_lookup((xfrm_address_t *)&iph->daddr, spi, - nexthdr != IPPROTO_IPIP ? nexthdr : IPPROTO_IPV6, AF_INET6); + nexthdr, AF_INET6); if (x == NULL) goto drop; spin_lock(&x->lock); @@ -70,10 +68,10 @@ int xfrm6_rcv_spi(struct sk_buff *skb, __be32 spi) xfrm_vec[xfrm_nr++] = x; - if (x->mode->input(x, skb)) + if (x->outer_mode->input(x, skb)) goto drop; - if (x->props.mode == XFRM_MODE_TUNNEL) { /* XXX */ + if (x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL) { decaps = 1; break; } @@ -99,7 +97,6 @@ int xfrm6_rcv_spi(struct sk_buff *skb, __be32 spi) memcpy(skb->sp->xvec + skb->sp->len, xfrm_vec, xfrm_nr * sizeof(xfrm_vec[0])); skb->sp->len += xfrm_nr; - skb->ip_summed = CHECKSUM_NONE; nf_reset(skb); @@ -135,7 +132,8 @@ EXPORT_SYMBOL(xfrm6_rcv_spi); int xfrm6_rcv(struct sk_buff *skb) { - return xfrm6_rcv_spi(skb, 0); + return xfrm6_rcv_spi(skb, skb_network_header(skb)[IP6CB(skb)->nhoff], + 0); } EXPORT_SYMBOL(xfrm6_rcv); diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c index 13bb1e85676..2bfb4f05c14 100644 --- a/net/ipv6/xfrm6_mode_beet.c +++ b/net/ipv6/xfrm6_mode_beet.c @@ -79,6 +79,7 @@ static struct xfrm_mode xfrm6_beet_mode = { .output = xfrm6_beet_output, .owner = THIS_MODULE, .encap = XFRM_MODE_BEET, + .flags = XFRM_MODE_FLAG_TUNNEL, }; static int __init xfrm6_beet_init(void) diff --git a/net/ipv6/xfrm6_mode_ro.c b/net/ipv6/xfrm6_mode_ro.c index 957ae36b669..a7bc8c62317 100644 --- a/net/ipv6/xfrm6_mode_ro.c +++ b/net/ipv6/xfrm6_mode_ro.c @@ -58,16 +58,7 @@ static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb) return 0; } -/* - * Do nothing about routing optimization header unlike IPsec. - */ -static int xfrm6_ro_input(struct xfrm_state *x, struct sk_buff *skb) -{ - return 0; -} - static struct xfrm_mode xfrm6_ro_mode = { - .input = xfrm6_ro_input, .output = xfrm6_ro_output, .owner = THIS_MODULE, .encap = XFRM_MODE_ROUTEOPTIMIZATION, diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index ea228387911..fd84e221727 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -118,6 +118,7 @@ static struct xfrm_mode xfrm6_tunnel_mode = { .output = xfrm6_tunnel_output, .owner = THIS_MODULE, .encap = XFRM_MODE_TUNNEL, + .flags = XFRM_MODE_FLAG_TUNNEL, }; static int __init xfrm6_tunnel_init(void) diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index a5a32c17249..656976760ad 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -50,7 +50,7 @@ static inline int xfrm6_output_one(struct sk_buff *skb) struct ipv6hdr *iph; int err; - if (x->props.mode == XFRM_MODE_TUNNEL) { + if (x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL) { err = xfrm6_tunnel_check_size(skb); if (err) goto error_nolock; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 15aa4c58c31..82e27b80d07 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -178,8 +178,7 @@ __xfrm6_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int __xfrm6_bundle_len_inc(&header_len, &nfheader_len, xfrm[i]); trailer_len += xfrm[i]->props.trailer_len; - if (xfrm[i]->props.mode == XFRM_MODE_TUNNEL || - xfrm[i]->props.mode == XFRM_MODE_ROUTEOPTIMIZATION) { + if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) { unsigned short encap_family = xfrm[i]->props.family; switch(encap_family) { case AF_INET: @@ -215,7 +214,6 @@ __xfrm6_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int i = 0; for (; dst_prev != &rt->u.dst; dst_prev = dst_prev->child) { struct xfrm_dst *x = (struct xfrm_dst*)dst_prev; - struct xfrm_state_afinfo *afinfo; dst_prev->xfrm = xfrm[i++]; dst_prev->dev = rt->u.dst.dev; @@ -232,18 +230,7 @@ __xfrm6_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int /* Copy neighbour for reachability confirmation */ dst_prev->neighbour = neigh_clone(rt->u.dst.neighbour); dst_prev->input = rt->u.dst.input; - /* XXX: When IPv4 is implemented as module and can be unloaded, - * we should manage reference to xfrm4_output in afinfo->output. - * Miyazawa - */ - afinfo = xfrm_state_get_afinfo(dst_prev->xfrm->props.family); - if (!afinfo) { - dst = *dst_p; - goto error; - } - - dst_prev->output = afinfo->output; - xfrm_state_put_afinfo(afinfo); + dst_prev->output = dst_prev->xfrm->outer_mode->afinfo->output; /* Sheit... I remember I did this right. Apparently, * it was magically lost, so this code needs audit */ x->u.rt6.rt6i_flags = rt0->rt6i_flags&(RTCF_BROADCAST|RTCF_MULTICAST|RTCF_LOCAL); diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index cdadb484746..b392bee396f 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -93,7 +93,8 @@ __xfrm6_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n) /* Rule 4: select IPsec tunnel */ for (i = 0; i < n; i++) { if (src[i] && - src[i]->props.mode == XFRM_MODE_TUNNEL) { + (src[i]->props.mode == XFRM_MODE_TUNNEL || + src[i]->props.mode == XFRM_MODE_BEET)) { dst[j++] = src[i]; src[i] = NULL; } @@ -146,7 +147,8 @@ __xfrm6_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n) /* Rule 3: select IPsec tunnel */ for (i = 0; i < n; i++) { if (src[i] && - src[i]->mode == XFRM_MODE_TUNNEL) { + (src[i]->mode == XFRM_MODE_TUNNEL || + src[i]->mode == XFRM_MODE_BEET)) { dst[j++] = src[i]; src[i] = NULL; } @@ -168,6 +170,7 @@ __xfrm6_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n) static struct xfrm_state_afinfo xfrm6_state_afinfo = { .family = AF_INET6, + .owner = THIS_MODULE, .init_tempsel = __xfrm6_init_tempsel, .tmpl_sort = __xfrm6_tmpl_sort, .state_sort = __xfrm6_state_sort, diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 3f8a3abde67..fae90ff3108 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -248,7 +248,7 @@ static int xfrm6_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm6_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) { - return 0; + return skb_network_header(skb)[IP6CB(skb)->nhoff]; } static int xfrm6_tunnel_rcv(struct sk_buff *skb) @@ -257,7 +257,7 @@ static int xfrm6_tunnel_rcv(struct sk_buff *skb) __be32 spi; spi = xfrm6_tunnel_spi_lookup((xfrm_address_t *)&iph->saddr); - return xfrm6_rcv_spi(skb, spi) > 0 ? : 0; + return xfrm6_rcv_spi(skb, IPPROTO_IPV6, spi) > 0 ? : 0; } static int xfrm6_tunnel_err(struct sk_buff *skb, struct inet6_skb_parm *opt, diff --git a/net/irda/ircomm/ircomm_tty_attach.c b/net/irda/ircomm/ircomm_tty_attach.c index 824309dabfe..b5a13882c92 100644 --- a/net/irda/ircomm/ircomm_tty_attach.c +++ b/net/irda/ircomm/ircomm_tty_attach.c @@ -381,18 +381,9 @@ static void ircomm_tty_discovery_indication(discinfo_t *discovery, info.daddr = discovery->daddr; info.saddr = discovery->saddr; - /* FIXME. We have a locking problem on the hashbin here. - * We probably need to use hashbin_find_next(), but we first - * need to ensure that "line" is unique. - Jean II */ - self = (struct ircomm_tty_cb *) hashbin_get_first(ircomm_tty); - while (self != NULL) { - IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;); - - ircomm_tty_do_event(self, IRCOMM_TTY_DISCOVERY_INDICATION, - NULL, &info); - - self = (struct ircomm_tty_cb *) hashbin_get_next(ircomm_tty); - } + self = (struct ircomm_tty_cb *) priv; + ircomm_tty_do_event(self, IRCOMM_TTY_DISCOVERY_INDICATION, + NULL, &info); } /* diff --git a/net/mac80211/ieee80211_ioctl.c b/net/mac80211/ieee80211_ioctl.c index f0224c2311d..6caa3ec2cff 100644 --- a/net/mac80211/ieee80211_ioctl.c +++ b/net/mac80211/ieee80211_ioctl.c @@ -306,9 +306,12 @@ int ieee80211_set_channel(struct ieee80211_local *local, int channel, int freq) ((chan->chan == channel) || (chan->freq == freq))) { local->oper_channel = chan; local->oper_hw_mode = mode; - set++; + set = 1; + break; } } + if (set) + break; } if (set) { @@ -508,10 +511,11 @@ static int ieee80211_ioctl_giwap(struct net_device *dev, static int ieee80211_ioctl_siwscan(struct net_device *dev, struct iw_request_info *info, - struct iw_point *data, char *extra) + union iwreq_data *wrqu, char *extra) { struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct iw_scan_req *req = NULL; u8 *ssid = NULL; size_t ssid_len = 0; @@ -536,6 +540,14 @@ static int ieee80211_ioctl_siwscan(struct net_device *dev, return -EOPNOTSUPP; } + /* if SSID was specified explicitly then use that */ + if (wrqu->data.length == sizeof(struct iw_scan_req) && + wrqu->data.flags & IW_SCAN_THIS_ESSID) { + req = (struct iw_scan_req *)extra; + ssid = req->essid; + ssid_len = req->essid_len; + } + return ieee80211_sta_req_scan(dev, ssid, ssid_len); } diff --git a/net/mac80211/ieee80211_sta.c b/net/mac80211/ieee80211_sta.c index 1641e8fe44b..db81aef6177 100644 --- a/net/mac80211/ieee80211_sta.c +++ b/net/mac80211/ieee80211_sta.c @@ -12,7 +12,6 @@ */ /* TODO: - * BSS table: use <BSSID,SSID> as the key to support multi-SSID APs * order BSS list by RSSI(?) ("quality of AP") * scan result table filtering (by capability (privacy, IBSS/BSS, WPA/RSN IE, * SSID) @@ -61,7 +60,8 @@ static void ieee80211_send_probe_req(struct net_device *dev, u8 *dst, u8 *ssid, size_t ssid_len); static struct ieee80211_sta_bss * -ieee80211_rx_bss_get(struct net_device *dev, u8 *bssid); +ieee80211_rx_bss_get(struct net_device *dev, u8 *bssid, int channel, + u8 *ssid, u8 ssid_len); static void ieee80211_rx_bss_put(struct net_device *dev, struct ieee80211_sta_bss *bss); static int ieee80211_sta_find_ibss(struct net_device *dev, @@ -427,7 +427,9 @@ static void ieee80211_set_associated(struct net_device *dev, if (sdata->type != IEEE80211_IF_TYPE_STA) return; - bss = ieee80211_rx_bss_get(dev, ifsta->bssid); + bss = ieee80211_rx_bss_get(dev, ifsta->bssid, + local->hw.conf.channel, + ifsta->ssid, ifsta->ssid_len); if (bss) { if (bss->has_erp_value) ieee80211_handle_erp_ie(dev, bss->erp_value); @@ -574,7 +576,8 @@ static void ieee80211_send_assoc(struct net_device *dev, capab |= WLAN_CAPABILITY_SHORT_SLOT_TIME | WLAN_CAPABILITY_SHORT_PREAMBLE; } - bss = ieee80211_rx_bss_get(dev, ifsta->bssid); + bss = ieee80211_rx_bss_get(dev, ifsta->bssid, local->hw.conf.channel, + ifsta->ssid, ifsta->ssid_len); if (bss) { if (bss->capability & WLAN_CAPABILITY_PRIVACY) capab |= WLAN_CAPABILITY_PRIVACY; @@ -722,6 +725,7 @@ static void ieee80211_send_disassoc(struct net_device *dev, static int ieee80211_privacy_mismatch(struct net_device *dev, struct ieee80211_if_sta *ifsta) { + struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); struct ieee80211_sta_bss *bss; int res = 0; @@ -729,7 +733,8 @@ static int ieee80211_privacy_mismatch(struct net_device *dev, ifsta->key_management_enabled) return 0; - bss = ieee80211_rx_bss_get(dev, ifsta->bssid); + bss = ieee80211_rx_bss_get(dev, ifsta->bssid, local->hw.conf.channel, + ifsta->ssid, ifsta->ssid_len); if (!bss) return 0; @@ -1203,15 +1208,11 @@ static void ieee80211_rx_mgmt_assoc_resp(struct net_device *dev, capab_info = le16_to_cpu(mgmt->u.assoc_resp.capab_info); status_code = le16_to_cpu(mgmt->u.assoc_resp.status_code); aid = le16_to_cpu(mgmt->u.assoc_resp.aid); - if ((aid & (BIT(15) | BIT(14))) != (BIT(15) | BIT(14))) - printk(KERN_DEBUG "%s: invalid aid value %d; bits 15:14 not " - "set\n", dev->name, aid); - aid &= ~(BIT(15) | BIT(14)); printk(KERN_DEBUG "%s: RX %sssocResp from %s (capab=0x%x " "status=%d aid=%d)\n", dev->name, reassoc ? "Rea" : "A", print_mac(mac, mgmt->sa), - capab_info, status_code, aid); + capab_info, status_code, aid & ~(BIT(15) | BIT(14))); if (status_code != WLAN_STATUS_SUCCESS) { printk(KERN_DEBUG "%s: AP denied association (code=%d)\n", @@ -1223,6 +1224,11 @@ static void ieee80211_rx_mgmt_assoc_resp(struct net_device *dev, return; } + if ((aid & (BIT(15) | BIT(14))) != (BIT(15) | BIT(14))) + printk(KERN_DEBUG "%s: invalid aid value %d; bits 15:14 not " + "set\n", dev->name, aid); + aid &= ~(BIT(15) | BIT(14)); + pos = mgmt->u.assoc_resp.variable; if (ieee802_11_parse_elems(pos, len - (pos - (u8 *) mgmt), &elems) == ParseFailed) { @@ -1241,7 +1247,9 @@ static void ieee80211_rx_mgmt_assoc_resp(struct net_device *dev, * update our stored copy */ if (elems.erp_info && elems.erp_info_len >= 1) { struct ieee80211_sta_bss *bss - = ieee80211_rx_bss_get(dev, ifsta->bssid); + = ieee80211_rx_bss_get(dev, ifsta->bssid, + local->hw.conf.channel, + ifsta->ssid, ifsta->ssid_len); if (bss) { bss->erp_value = elems.erp_info[0]; bss->has_erp_value = 1; @@ -1271,7 +1279,9 @@ static void ieee80211_rx_mgmt_assoc_resp(struct net_device *dev, " AP\n", dev->name); return; } - bss = ieee80211_rx_bss_get(dev, ifsta->bssid); + bss = ieee80211_rx_bss_get(dev, ifsta->bssid, + local->hw.conf.channel, + ifsta->ssid, ifsta->ssid_len); if (bss) { sta->last_rssi = bss->rssi; sta->last_signal = bss->signal; @@ -1347,7 +1357,8 @@ static void __ieee80211_rx_bss_hash_del(struct net_device *dev, static struct ieee80211_sta_bss * -ieee80211_rx_bss_add(struct net_device *dev, u8 *bssid) +ieee80211_rx_bss_add(struct net_device *dev, u8 *bssid, int channel, + u8 *ssid, u8 ssid_len) { struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); struct ieee80211_sta_bss *bss; @@ -1358,6 +1369,11 @@ ieee80211_rx_bss_add(struct net_device *dev, u8 *bssid) atomic_inc(&bss->users); atomic_inc(&bss->users); memcpy(bss->bssid, bssid, ETH_ALEN); + bss->channel = channel; + if (ssid && ssid_len <= IEEE80211_MAX_SSID_LEN) { + memcpy(bss->ssid, ssid, ssid_len); + bss->ssid_len = ssid_len; + } spin_lock_bh(&local->sta_bss_lock); /* TODO: order by RSSI? */ @@ -1369,7 +1385,8 @@ ieee80211_rx_bss_add(struct net_device *dev, u8 *bssid) static struct ieee80211_sta_bss * -ieee80211_rx_bss_get(struct net_device *dev, u8 *bssid) +ieee80211_rx_bss_get(struct net_device *dev, u8 *bssid, int channel, + u8 *ssid, u8 ssid_len) { struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); struct ieee80211_sta_bss *bss; @@ -1377,7 +1394,10 @@ ieee80211_rx_bss_get(struct net_device *dev, u8 *bssid) spin_lock_bh(&local->sta_bss_lock); bss = local->sta_bss_hash[STA_HASH(bssid)]; while (bss) { - if (memcmp(bss->bssid, bssid, ETH_ALEN) == 0) { + if (!memcmp(bss->bssid, bssid, ETH_ALEN) && + bss->channel == channel && + bss->ssid_len == ssid_len && + (ssid_len == 0 || !memcmp(bss->ssid, ssid, ssid_len))) { atomic_inc(&bss->users); break; } @@ -1545,9 +1565,11 @@ static void ieee80211_rx_bss_info(struct net_device *dev, else channel = rx_status->channel; - bss = ieee80211_rx_bss_get(dev, mgmt->bssid); + bss = ieee80211_rx_bss_get(dev, mgmt->bssid, channel, + elems.ssid, elems.ssid_len); if (!bss) { - bss = ieee80211_rx_bss_add(dev, mgmt->bssid); + bss = ieee80211_rx_bss_add(dev, mgmt->bssid, channel, + elems.ssid, elems.ssid_len); if (!bss) return; } else { @@ -1573,10 +1595,6 @@ static void ieee80211_rx_bss_info(struct net_device *dev, bss->beacon_int = le16_to_cpu(mgmt->u.beacon.beacon_int); bss->capability = le16_to_cpu(mgmt->u.beacon.capab_info); - if (elems.ssid && elems.ssid_len <= IEEE80211_MAX_SSID_LEN) { - memcpy(bss->ssid, elems.ssid, elems.ssid_len); - bss->ssid_len = elems.ssid_len; - } bss->supp_rates_len = 0; if (elems.supp_rates) { @@ -1647,7 +1665,6 @@ static void ieee80211_rx_bss_info(struct net_device *dev, bss->hw_mode = rx_status->phymode; - bss->channel = channel; bss->freq = rx_status->freq; if (channel != rx_status->channel && (bss->hw_mode == MODE_IEEE80211G || @@ -2375,7 +2392,7 @@ static int ieee80211_sta_create_ibss(struct net_device *dev, { struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); struct ieee80211_sta_bss *bss; - struct ieee80211_sub_if_data *sdata; + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_hw_mode *mode; u8 bssid[ETH_ALEN], *pos; int i; @@ -2398,18 +2415,17 @@ static int ieee80211_sta_create_ibss(struct net_device *dev, printk(KERN_DEBUG "%s: Creating new IBSS network, BSSID %s\n", dev->name, print_mac(mac, bssid)); - bss = ieee80211_rx_bss_add(dev, bssid); + bss = ieee80211_rx_bss_add(dev, bssid, local->hw.conf.channel, + sdata->u.sta.ssid, sdata->u.sta.ssid_len); if (!bss) return -ENOMEM; - sdata = IEEE80211_DEV_TO_SUB_IF(dev); mode = local->oper_hw_mode; if (local->hw.conf.beacon_int == 0) local->hw.conf.beacon_int = 100; bss->beacon_int = local->hw.conf.beacon_int; bss->hw_mode = local->hw.conf.phymode; - bss->channel = local->hw.conf.channel; bss->freq = local->hw.conf.freq; bss->last_update = jiffies; bss->capability = WLAN_CAPABILITY_IBSS; @@ -2469,7 +2485,8 @@ static int ieee80211_sta_find_ibss(struct net_device *dev, "%s\n", print_mac(mac, bssid), print_mac(mac2, ifsta->bssid)); #endif /* CONFIG_MAC80211_IBSS_DEBUG */ if (found && memcmp(ifsta->bssid, bssid, ETH_ALEN) != 0 && - (bss = ieee80211_rx_bss_get(dev, bssid))) { + (bss = ieee80211_rx_bss_get(dev, bssid, local->hw.conf.channel, + ifsta->ssid, ifsta->ssid_len))) { printk(KERN_DEBUG "%s: Selected IBSS BSSID %s" " based on configured SSID\n", dev->name, print_mac(mac, bssid)); diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index a127ab32881..7a3f64c1aca 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -834,10 +834,12 @@ static int tcp_packet(struct nf_conn *conntrack, case TCP_CONNTRACK_SYN_SENT: if (old_state < TCP_CONNTRACK_TIME_WAIT) break; - if (conntrack->proto.tcp.seen[!dir].flags & - IP_CT_TCP_FLAG_CLOSE_INIT) { - /* Attempt to reopen a closed connection. - * Delete this connection and look up again. */ + if ((conntrack->proto.tcp.seen[!dir].flags & + IP_CT_TCP_FLAG_CLOSE_INIT) + || (conntrack->proto.tcp.last_dir == dir + && conntrack->proto.tcp.last_index == TCP_RST_SET)) { + /* Attempt to reopen a closed/aborted connection. + * Delete this connection and look up again. */ write_unlock_bh(&tcp_lock); if (del_timer(&conntrack->timeout)) conntrack->timeout.function((unsigned long) @@ -925,6 +927,7 @@ static int tcp_packet(struct nf_conn *conntrack, in_window: /* From now on we have got in-window packets */ conntrack->proto.tcp.last_index = index; + conntrack->proto.tcp.last_dir = dir; pr_debug("tcp_conntracks: "); NF_CT_DUMP_TUPLE(tuple); diff --git a/net/netfilter/xt_sctp.c b/net/netfilter/xt_sctp.c index f907770fd4e..3358273a47b 100644 --- a/net/netfilter/xt_sctp.c +++ b/net/netfilter/xt_sctp.c @@ -42,21 +42,21 @@ match_flags(const struct xt_sctp_flag_info *flag_info, static inline bool match_packet(const struct sk_buff *skb, unsigned int offset, - const u_int32_t *chunkmap, - int chunk_match_type, - const struct xt_sctp_flag_info *flag_info, - const int flag_count, + const struct xt_sctp_info *info, bool *hotdrop) { u_int32_t chunkmapcopy[256 / sizeof (u_int32_t)]; sctp_chunkhdr_t _sch, *sch; + int chunk_match_type = info->chunk_match_type; + const struct xt_sctp_flag_info *flag_info = info->flag_info; + int flag_count = info->flag_count; #ifdef DEBUG_SCTP int i = 0; #endif if (chunk_match_type == SCTP_CHUNK_MATCH_ALL) - SCTP_CHUNKMAP_COPY(chunkmapcopy, chunkmap); + SCTP_CHUNKMAP_COPY(chunkmapcopy, info->chunkmap); do { sch = skb_header_pointer(skb, offset, sizeof(_sch), &_sch); @@ -73,7 +73,7 @@ match_packet(const struct sk_buff *skb, duprintf("skb->len: %d\toffset: %d\n", skb->len, offset); - if (SCTP_CHUNKMAP_IS_SET(chunkmap, sch->type)) { + if (SCTP_CHUNKMAP_IS_SET(info->chunkmap, sch->type)) { switch (chunk_match_type) { case SCTP_CHUNK_MATCH_ANY: if (match_flags(flag_info, flag_count, @@ -104,7 +104,7 @@ match_packet(const struct sk_buff *skb, switch (chunk_match_type) { case SCTP_CHUNK_MATCH_ALL: - return SCTP_CHUNKMAP_IS_CLEAR(chunkmap); + return SCTP_CHUNKMAP_IS_CLEAR(info->chunkmap); case SCTP_CHUNK_MATCH_ANY: return false; case SCTP_CHUNK_MATCH_ONLY: @@ -148,9 +148,7 @@ match(const struct sk_buff *skb, && ntohs(sh->dest) <= info->dpts[1], XT_SCTP_DEST_PORTS, info->flags, info->invflags) && SCCHECK(match_packet(skb, protoff + sizeof (sctp_sctphdr_t), - info->chunkmap, info->chunk_match_type, - info->flag_info, info->flag_count, - hotdrop), + info, hotdrop), XT_SCTP_CHUNK_TYPES, info->flags, info->invflags); } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 95ae11956f3..e01d57692c9 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -249,10 +249,11 @@ static void dev_watchdog_down(struct net_device *dev) */ void netif_carrier_on(struct net_device *dev) { - if (test_and_clear_bit(__LINK_STATE_NOCARRIER, &dev->state)) + if (test_and_clear_bit(__LINK_STATE_NOCARRIER, &dev->state)) { linkwatch_fire_event(dev); - if (netif_running(dev)) - __netdev_watchdog_up(dev); + if (netif_running(dev)) + __netdev_watchdog_up(dev); + } } /** diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 113f4442998..cb97fda1b6d 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -49,13 +49,16 @@ EXPORT_SYMBOL(secpath_dup); int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq) { int offset, offset_seq; + int hlen; switch (nexthdr) { case IPPROTO_AH: + hlen = sizeof(struct ip_auth_hdr); offset = offsetof(struct ip_auth_hdr, spi); offset_seq = offsetof(struct ip_auth_hdr, seq_no); break; case IPPROTO_ESP: + hlen = sizeof(struct ip_esp_hdr); offset = offsetof(struct ip_esp_hdr, spi); offset_seq = offsetof(struct ip_esp_hdr, seq_no); break; @@ -69,7 +72,7 @@ int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq) return 1; } - if (!pskb_may_pull(skb, 16)) + if (!pskb_may_pull(skb, hlen)) return -EINVAL; *spi = *(__be32*)(skb_transport_header(skb) + offset); diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 0eb3377602e..f4bfd6c4565 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -63,7 +63,7 @@ int xfrm_output(struct sk_buff *skb) xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } - err = x->mode->output(x, skb); + err = x->outer_mode->output(x, skb); if (err) goto error; @@ -82,7 +82,7 @@ int xfrm_output(struct sk_buff *skb) } dst = skb->dst; x = dst->xfrm; - } while (x && (x->props.mode != XFRM_MODE_TUNNEL)); + } while (x && !(x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL)); err = 0; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index af27c193697..b702bd8a389 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -49,8 +49,6 @@ static DEFINE_SPINLOCK(xfrm_policy_gc_lock); static struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short family); static void xfrm_policy_put_afinfo(struct xfrm_policy_afinfo *afinfo); -static struct xfrm_policy_afinfo *xfrm_policy_lock_afinfo(unsigned int family); -static void xfrm_policy_unlock_afinfo(struct xfrm_policy_afinfo *afinfo); static inline int __xfrm4_selector_match(struct xfrm_selector *sel, struct flowi *fl) @@ -86,72 +84,6 @@ int xfrm_selector_match(struct xfrm_selector *sel, struct flowi *fl, return 0; } -int xfrm_register_type(struct xfrm_type *type, unsigned short family) -{ - struct xfrm_policy_afinfo *afinfo = xfrm_policy_lock_afinfo(family); - struct xfrm_type **typemap; - int err = 0; - - if (unlikely(afinfo == NULL)) - return -EAFNOSUPPORT; - typemap = afinfo->type_map; - - if (likely(typemap[type->proto] == NULL)) - typemap[type->proto] = type; - else - err = -EEXIST; - xfrm_policy_unlock_afinfo(afinfo); - return err; -} -EXPORT_SYMBOL(xfrm_register_type); - -int xfrm_unregister_type(struct xfrm_type *type, unsigned short family) -{ - struct xfrm_policy_afinfo *afinfo = xfrm_policy_lock_afinfo(family); - struct xfrm_type **typemap; - int err = 0; - - if (unlikely(afinfo == NULL)) - return -EAFNOSUPPORT; - typemap = afinfo->type_map; - - if (unlikely(typemap[type->proto] != type)) - err = -ENOENT; - else - typemap[type->proto] = NULL; - xfrm_policy_unlock_afinfo(afinfo); - return err; -} -EXPORT_SYMBOL(xfrm_unregister_type); - -struct xfrm_type *xfrm_get_type(u8 proto, unsigned short family) -{ - struct xfrm_policy_afinfo *afinfo; - struct xfrm_type **typemap; - struct xfrm_type *type; - int modload_attempted = 0; - -retry: - afinfo = xfrm_policy_get_afinfo(family); - if (unlikely(afinfo == NULL)) - return NULL; - typemap = afinfo->type_map; - - type = typemap[proto]; - if (unlikely(type && !try_module_get(type->owner))) - type = NULL; - if (!type && !modload_attempted) { - xfrm_policy_put_afinfo(afinfo); - request_module("xfrm-type-%d-%d", - (int) family, (int) proto); - modload_attempted = 1; - goto retry; - } - - xfrm_policy_put_afinfo(afinfo); - return type; -} - int xfrm_dst_lookup(struct xfrm_dst **dst, struct flowi *fl, unsigned short family) { @@ -170,94 +102,6 @@ int xfrm_dst_lookup(struct xfrm_dst **dst, struct flowi *fl, } EXPORT_SYMBOL(xfrm_dst_lookup); -void xfrm_put_type(struct xfrm_type *type) -{ - module_put(type->owner); -} - -int xfrm_register_mode(struct xfrm_mode *mode, int family) -{ - struct xfrm_policy_afinfo *afinfo; - struct xfrm_mode **modemap; - int err; - - if (unlikely(mode->encap >= XFRM_MODE_MAX)) - return -EINVAL; - - afinfo = xfrm_policy_lock_afinfo(family); - if (unlikely(afinfo == NULL)) - return -EAFNOSUPPORT; - - err = -EEXIST; - modemap = afinfo->mode_map; - if (likely(modemap[mode->encap] == NULL)) { - modemap[mode->encap] = mode; - err = 0; - } - - xfrm_policy_unlock_afinfo(afinfo); - return err; -} -EXPORT_SYMBOL(xfrm_register_mode); - -int xfrm_unregister_mode(struct xfrm_mode *mode, int family) -{ - struct xfrm_policy_afinfo *afinfo; - struct xfrm_mode **modemap; - int err; - - if (unlikely(mode->encap >= XFRM_MODE_MAX)) - return -EINVAL; - - afinfo = xfrm_policy_lock_afinfo(family); - if (unlikely(afinfo == NULL)) - return -EAFNOSUPPORT; - - err = -ENOENT; - modemap = afinfo->mode_map; - if (likely(modemap[mode->encap] == mode)) { - modemap[mode->encap] = NULL; - err = 0; - } - - xfrm_policy_unlock_afinfo(afinfo); - return err; -} -EXPORT_SYMBOL(xfrm_unregister_mode); - -struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family) -{ - struct xfrm_policy_afinfo *afinfo; - struct xfrm_mode *mode; - int modload_attempted = 0; - - if (unlikely(encap >= XFRM_MODE_MAX)) - return NULL; - -retry: - afinfo = xfrm_policy_get_afinfo(family); - if (unlikely(afinfo == NULL)) - return NULL; - - mode = afinfo->mode_map[encap]; - if (unlikely(mode && !try_module_get(mode->owner))) - mode = NULL; - if (!mode && !modload_attempted) { - xfrm_policy_put_afinfo(afinfo); - request_module("xfrm-mode-%d-%d", family, encap); - modload_attempted = 1; - goto retry; - } - - xfrm_policy_put_afinfo(afinfo); - return mode; -} - -void xfrm_put_mode(struct xfrm_mode *mode) -{ - module_put(mode->owner); -} - static inline unsigned long make_jiffies(long secs) { if (secs >= (MAX_SCHEDULE_TIMEOUT-1)/HZ) @@ -2096,7 +1940,8 @@ int xfrm_bundle_ok(struct xfrm_policy *pol, struct xfrm_dst *first, if (xdst->genid != dst->xfrm->genid) return 0; - if (strict && fl && dst->xfrm->props.mode != XFRM_MODE_TUNNEL && + if (strict && fl && + !(dst->xfrm->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL) && !xfrm_state_addr_flow_check(dst->xfrm, fl, family)) return 0; @@ -2213,23 +2058,6 @@ static void xfrm_policy_put_afinfo(struct xfrm_policy_afinfo *afinfo) read_unlock(&xfrm_policy_afinfo_lock); } -static struct xfrm_policy_afinfo *xfrm_policy_lock_afinfo(unsigned int family) -{ - struct xfrm_policy_afinfo *afinfo; - if (unlikely(family >= NPROTO)) - return NULL; - write_lock_bh(&xfrm_policy_afinfo_lock); - afinfo = xfrm_policy_afinfo[family]; - if (unlikely(!afinfo)) - write_unlock_bh(&xfrm_policy_afinfo_lock); - return afinfo; -} - -static void xfrm_policy_unlock_afinfo(struct xfrm_policy_afinfo *afinfo) -{ - write_unlock_bh(&xfrm_policy_afinfo_lock); -} - static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = ptr; @@ -2464,7 +2292,8 @@ static int xfrm_policy_migrate(struct xfrm_policy *pol, if (!migrate_tmpl_match(mp, &pol->xfrm_vec[i])) continue; n++; - if (pol->xfrm_vec[i].mode != XFRM_MODE_TUNNEL) + if (pol->xfrm_vec[i].mode != XFRM_MODE_TUNNEL && + pol->xfrm_vec[i].mode != XFRM_MODE_BEET) continue; /* update endpoints */ memcpy(&pol->xfrm_vec[i].id.daddr, &mp->new_daddr, diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 344f0a6abec..224b44e31a0 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -57,6 +57,9 @@ static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024; static unsigned int xfrm_state_num; static unsigned int xfrm_state_genid; +static struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family); +static void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo); + static inline unsigned int xfrm_dst_hash(xfrm_address_t *daddr, xfrm_address_t *saddr, u32 reqid, @@ -187,6 +190,184 @@ int __xfrm_state_delete(struct xfrm_state *x); int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol); void km_state_expired(struct xfrm_state *x, int hard, u32 pid); +static struct xfrm_state_afinfo *xfrm_state_lock_afinfo(unsigned int family) +{ + struct xfrm_state_afinfo *afinfo; + if (unlikely(family >= NPROTO)) + return NULL; + write_lock_bh(&xfrm_state_afinfo_lock); + afinfo = xfrm_state_afinfo[family]; + if (unlikely(!afinfo)) + write_unlock_bh(&xfrm_state_afinfo_lock); + return afinfo; +} + +static void xfrm_state_unlock_afinfo(struct xfrm_state_afinfo *afinfo) +{ + write_unlock_bh(&xfrm_state_afinfo_lock); +} + +int xfrm_register_type(struct xfrm_type *type, unsigned short family) +{ + struct xfrm_state_afinfo *afinfo = xfrm_state_lock_afinfo(family); + struct xfrm_type **typemap; + int err = 0; + + if (unlikely(afinfo == NULL)) + return -EAFNOSUPPORT; + typemap = afinfo->type_map; + + if (likely(typemap[type->proto] == NULL)) + typemap[type->proto] = type; + else + err = -EEXIST; + xfrm_state_unlock_afinfo(afinfo); + return err; +} +EXPORT_SYMBOL(xfrm_register_type); + +int xfrm_unregister_type(struct xfrm_type *type, unsigned short family) +{ + struct xfrm_state_afinfo *afinfo = xfrm_state_lock_afinfo(family); + struct xfrm_type **typemap; + int err = 0; + + if (unlikely(afinfo == NULL)) + return -EAFNOSUPPORT; + typemap = afinfo->type_map; + + if (unlikely(typemap[type->proto] != type)) + err = -ENOENT; + else + typemap[type->proto] = NULL; + xfrm_state_unlock_afinfo(afinfo); + return err; +} +EXPORT_SYMBOL(xfrm_unregister_type); + +static struct xfrm_type *xfrm_get_type(u8 proto, unsigned short family) +{ + struct xfrm_state_afinfo *afinfo; + struct xfrm_type **typemap; + struct xfrm_type *type; + int modload_attempted = 0; + +retry: + afinfo = xfrm_state_get_afinfo(family); + if (unlikely(afinfo == NULL)) + return NULL; + typemap = afinfo->type_map; + + type = typemap[proto]; + if (unlikely(type && !try_module_get(type->owner))) + type = NULL; + if (!type && !modload_attempted) { + xfrm_state_put_afinfo(afinfo); + request_module("xfrm-type-%d-%d", family, proto); + modload_attempted = 1; + goto retry; + } + + xfrm_state_put_afinfo(afinfo); + return type; +} + +static void xfrm_put_type(struct xfrm_type *type) +{ + module_put(type->owner); +} + +int xfrm_register_mode(struct xfrm_mode *mode, int family) +{ + struct xfrm_state_afinfo *afinfo; + struct xfrm_mode **modemap; + int err; + + if (unlikely(mode->encap >= XFRM_MODE_MAX)) + return -EINVAL; + + afinfo = xfrm_state_lock_afinfo(family); + if (unlikely(afinfo == NULL)) + return -EAFNOSUPPORT; + + err = -EEXIST; + modemap = afinfo->mode_map; + if (modemap[mode->encap]) + goto out; + + err = -ENOENT; + if (!try_module_get(afinfo->owner)) + goto out; + + mode->afinfo = afinfo; + modemap[mode->encap] = mode; + err = 0; + +out: + xfrm_state_unlock_afinfo(afinfo); + return err; +} +EXPORT_SYMBOL(xfrm_register_mode); + +int xfrm_unregister_mode(struct xfrm_mode *mode, int family) +{ + struct xfrm_state_afinfo *afinfo; + struct xfrm_mode **modemap; + int err; + + if (unlikely(mode->encap >= XFRM_MODE_MAX)) + return -EINVAL; + + afinfo = xfrm_state_lock_afinfo(family); + if (unlikely(afinfo == NULL)) + return -EAFNOSUPPORT; + + err = -ENOENT; + modemap = afinfo->mode_map; + if (likely(modemap[mode->encap] == mode)) { + modemap[mode->encap] = NULL; + module_put(mode->afinfo->owner); + err = 0; + } + + xfrm_state_unlock_afinfo(afinfo); + return err; +} +EXPORT_SYMBOL(xfrm_unregister_mode); + +static struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family) +{ + struct xfrm_state_afinfo *afinfo; + struct xfrm_mode *mode; + int modload_attempted = 0; + + if (unlikely(encap >= XFRM_MODE_MAX)) + return NULL; + +retry: + afinfo = xfrm_state_get_afinfo(family); + if (unlikely(afinfo == NULL)) + return NULL; + + mode = afinfo->mode_map[encap]; + if (unlikely(mode && !try_module_get(mode->owner))) + mode = NULL; + if (!mode && !modload_attempted) { + xfrm_state_put_afinfo(afinfo); + request_module("xfrm-mode-%d-%d", family, encap); + modload_attempted = 1; + goto retry; + } + + xfrm_state_put_afinfo(afinfo); + return mode; +} + +static void xfrm_put_mode(struct xfrm_mode *mode) +{ + module_put(mode->owner); +} + static void xfrm_state_gc_destroy(struct xfrm_state *x) { del_timer_sync(&x->timer); @@ -196,8 +377,10 @@ static void xfrm_state_gc_destroy(struct xfrm_state *x) kfree(x->calg); kfree(x->encap); kfree(x->coaddr); - if (x->mode) - xfrm_put_mode(x->mode); + if (x->inner_mode) + xfrm_put_mode(x->inner_mode); + if (x->outer_mode) + xfrm_put_mode(x->outer_mode); if (x->type) { x->type->destructor(x); xfrm_put_type(x->type); @@ -1699,7 +1882,7 @@ int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo) } EXPORT_SYMBOL(xfrm_state_unregister_afinfo); -struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned short family) +static struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family) { struct xfrm_state_afinfo *afinfo; if (unlikely(family >= NPROTO)) @@ -1711,14 +1894,11 @@ struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned short family) return afinfo; } -void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo) +static void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo) { read_unlock(&xfrm_state_afinfo_lock); } -EXPORT_SYMBOL(xfrm_state_get_afinfo); -EXPORT_SYMBOL(xfrm_state_put_afinfo); - /* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */ void xfrm_state_delete_tunnel(struct xfrm_state *x) { @@ -1769,6 +1949,14 @@ int xfrm_init_state(struct xfrm_state *x) goto error; err = -EPROTONOSUPPORT; + x->inner_mode = xfrm_get_mode(x->props.mode, x->sel.family); + if (x->inner_mode == NULL) + goto error; + + if (!(x->inner_mode->flags & XFRM_MODE_FLAG_TUNNEL) && + family != x->sel.family) + goto error; + x->type = xfrm_get_type(x->id.proto, family); if (x->type == NULL) goto error; @@ -1777,8 +1965,8 @@ int xfrm_init_state(struct xfrm_state *x) if (err) goto error; - x->mode = xfrm_get_mode(x->props.mode, family); - if (x->mode == NULL) + x->outer_mode = xfrm_get_mode(x->props.mode, family); + if (x->outer_mode == NULL) goto error; x->km.state = XFRM_STATE_VALID; |