diff options
author | Ingo Molnar <mingo@elte.hu> | 2010-10-07 09:43:38 +0200 |
---|---|---|
committer | Ingo Molnar <mingo@elte.hu> | 2010-10-07 09:43:45 +0200 |
commit | 556ef63255f1a6f82910a637c4164dbf7d3d1af2 (patch) | |
tree | ae209fe4959e0837bf4eb72abc6e02c8a82179a1 /net | |
parent | d4f8f217b8a5d5bd02af979650418dca4caec472 (diff) | |
parent | cb655d0f3d57c23db51b981648e452988c0223f9 (diff) | |
download | linux-556ef63255f1a6f82910a637c4164dbf7d3d1af2.tar.gz linux-556ef63255f1a6f82910a637c4164dbf7d3d1af2.tar.xz |
Merge commit 'v2.6.36-rc7' into core/rcu
Merge reason: Update from -rc3 to -rc7.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'net')
68 files changed, 500 insertions, 416 deletions
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 01ddb0472f86..0eb96f7e44be 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -24,8 +24,11 @@ int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp, if (vlan_dev) skb->dev = vlan_dev; - else if (vlan_id) - goto drop; + else if (vlan_id) { + if (!(skb->dev->flags & IFF_PROMISC)) + goto drop; + skb->pkt_type = PACKET_OTHERHOST; + } return (polling ? netif_receive_skb(skb) : netif_rx(skb)); @@ -102,8 +105,11 @@ vlan_gro_common(struct napi_struct *napi, struct vlan_group *grp, if (vlan_dev) skb->dev = vlan_dev; - else if (vlan_id) - goto drop; + else if (vlan_id) { + if (!(skb->dev->flags & IFF_PROMISC)) + goto drop; + skb->pkt_type = PACKET_OTHERHOST; + } for (p = napi->gro_list; p; p = p->next) { NAPI_GRO_CB(p)->same_flow = diff --git a/net/9p/client.c b/net/9p/client.c index dc6f2f26d023..9eb72505308f 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -331,8 +331,10 @@ static void p9_tag_cleanup(struct p9_client *c) } } - if (c->tagpool) + if (c->tagpool) { + p9_idpool_put(0, c->tagpool); /* free reserved tag 0 */ p9_idpool_destroy(c->tagpool); + } /* free requests associated with tags */ for (row = 0; row < (c->max_tag/P9_ROW_MAXTAG); row++) { @@ -944,6 +946,7 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, int nwname, char **wnames, int16_t nwqids, count; err = 0; + wqids = NULL; clnt = oldfid->clnt; if (clone) { fid = p9_fid_create(clnt); @@ -994,9 +997,11 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, int nwname, char **wnames, else fid->qid = oldfid->qid; + kfree(wqids); return fid; clunk_fid: + kfree(wqids); p9_client_clunk(fid); fid = NULL; diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 0ea20c30466c..17c5ba7551a5 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -426,8 +426,10 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req) /* Allocate an fcall for the reply */ rpl_context = kmalloc(sizeof *rpl_context, GFP_KERNEL); - if (!rpl_context) + if (!rpl_context) { + err = -ENOMEM; goto err_close; + } /* * If the request has a buffer, steal it, otherwise @@ -445,8 +447,8 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req) } rpl_context->rc = req->rc; if (!rpl_context->rc) { - kfree(rpl_context); - goto err_close; + err = -ENOMEM; + goto err_free2; } /* @@ -458,11 +460,8 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req) */ if (atomic_inc_return(&rdma->rq_count) <= rdma->rq_depth) { err = post_recv(client, rpl_context); - if (err) { - kfree(rpl_context->rc); - kfree(rpl_context); - goto err_close; - } + if (err) + goto err_free1; } else atomic_dec(&rdma->rq_count); @@ -471,8 +470,10 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req) /* Post the request */ c = kmalloc(sizeof *c, GFP_KERNEL); - if (!c) - goto err_close; + if (!c) { + err = -ENOMEM; + goto err_free1; + } c->req = req; c->busa = ib_dma_map_single(rdma->cm_id->device, @@ -499,9 +500,15 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req) return ib_post_send(rdma->qp, &wr, &bad_wr); error: + kfree(c); + kfree(rpl_context->rc); + kfree(rpl_context); P9_DPRINTK(P9_DEBUG_ERROR, "EIO\n"); return -EIO; - + err_free1: + kfree(rpl_context->rc); + err_free2: + kfree(rpl_context); err_close: spin_lock_irqsave(&rdma->req_lock, flags); if (rdma->state < P9_RDMA_CLOSING) { diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index dcfbe99ff81c..b88515936e4b 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -329,7 +329,8 @@ p9_virtio_create(struct p9_client *client, const char *devname, char *args) mutex_lock(&virtio_9p_lock); list_for_each_entry(chan, &virtio_chan_list, chan_list) { - if (!strncmp(devname, chan->tag, chan->tag_len)) { + if (!strncmp(devname, chan->tag, chan->tag_len) && + strlen(devname) == chan->tag_len) { if (!chan->inuse) { chan->inuse = true; found = 1; diff --git a/net/Kconfig b/net/Kconfig index e330594d3709..e926884c1675 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -217,7 +217,7 @@ source "net/dns_resolver/Kconfig" config RPS boolean - depends on SMP && SYSFS + depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS default y menu "Network testing" diff --git a/net/atm/br2684.c b/net/atm/br2684.c index 651babdfab38..ad2b232a2055 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -399,12 +399,6 @@ static void br2684_push(struct atm_vcc *atmvcc, struct sk_buff *skb) unregister_netdev(net_dev); free_netdev(net_dev); } - read_lock_irq(&devs_lock); - if (list_empty(&br2684_devs)) { - /* last br2684 device */ - unregister_atmdevice_notifier(&atm_dev_notifier); - } - read_unlock_irq(&devs_lock); return; } @@ -675,7 +669,6 @@ static int br2684_create(void __user *arg) if (list_empty(&br2684_devs)) { /* 1st br2684 device */ - register_atmdevice_notifier(&atm_dev_notifier); brdev->number = 1; } else brdev->number = BRPRIV(list_entry_brdev(br2684_devs.prev))->number + 1; @@ -815,6 +808,7 @@ static int __init br2684_init(void) return -ENOMEM; #endif register_atm_ioctl(&br2684_ioctl_ops); + register_atmdevice_notifier(&atm_dev_notifier); return 0; } @@ -830,9 +824,7 @@ static void __exit br2684_exit(void) #endif - /* if not already empty */ - if (!list_empty(&br2684_devs)) - unregister_atmdevice_notifier(&atm_dev_notifier); + unregister_atmdevice_notifier(&atm_dev_notifier); while (!list_empty(&br2684_devs)) { net_dev = list_entry_brdev(br2684_devs.next); diff --git a/net/core/dev.c b/net/core/dev.c index 3721fbb9a83c..660dd41aaaa6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2058,16 +2058,16 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev, struct sk_buff *skb) { int queue_index; - struct sock *sk = skb->sk; + const struct net_device_ops *ops = dev->netdev_ops; - queue_index = sk_tx_queue_get(sk); - if (queue_index < 0) { - const struct net_device_ops *ops = dev->netdev_ops; + if (ops->ndo_select_queue) { + queue_index = ops->ndo_select_queue(dev, skb); + queue_index = dev_cap_txqueue(dev, queue_index); + } else { + struct sock *sk = skb->sk; + queue_index = sk_tx_queue_get(sk); + if (queue_index < 0) { - if (ops->ndo_select_queue) { - queue_index = ops->ndo_select_queue(dev, skb); - queue_index = dev_cap_txqueue(dev, queue_index); - } else { queue_index = 0; if (dev->real_num_tx_queues > 1) queue_index = skb_tx_hash(dev, skb); @@ -4845,7 +4845,7 @@ static void rollback_registered_many(struct list_head *head) dev = list_first_entry(head, struct net_device, unreg_list); call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); - synchronize_net(); + rcu_barrier(); list_for_each_entry(dev, head, unreg_list) dev_put(dev); diff --git a/net/core/iovec.c b/net/core/iovec.c index 1cd98df412df..e6b133b77ccb 100644 --- a/net/core/iovec.c +++ b/net/core/iovec.c @@ -35,9 +35,10 @@ * in any case. */ -int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode) +long verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode) { - int size, err, ct; + int size, ct; + long err; if (m->msg_namelen) { if (mode == VERIFY_READ) { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 26396ff67cf9..c83b421341c0 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2706,7 +2706,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) } else if (skb_gro_len(p) != pinfo->gso_size) return -E2BIG; - headroom = NET_SKB_PAD + NET_IP_ALIGN; + headroom = skb_headroom(p); nskb = alloc_skb(headroom + skb_gro_offset(p), GFP_ATOMIC); if (unlikely(!nskb)) return -ENOMEM; diff --git a/net/core/sock.c b/net/core/sock.c index b05b9b6ddb87..ef30e9d286e7 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1351,9 +1351,9 @@ int sock_i_uid(struct sock *sk) { int uid; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : 0; - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); return uid; } EXPORT_SYMBOL(sock_i_uid); @@ -1362,9 +1362,9 @@ unsigned long sock_i_ino(struct sock *sk) { unsigned long ino; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0; - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); return ino; } EXPORT_SYMBOL(sock_i_ino); diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 571f8950ed06..72380a30d1c8 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -217,6 +217,7 @@ config NET_IPIP config NET_IPGRE tristate "IP: GRE tunnels over IP" + depends on IPV6 || IPV6=n help Tunneling means encapsulating data of one protocol type within another protocol and sending it over a channel that understands the diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index f0550941df7b..721a8a37b45c 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -62,8 +62,11 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) } if (!inet->inet_saddr) inet->inet_saddr = rt->rt_src; /* Update source address */ - if (!inet->inet_rcv_saddr) + if (!inet->inet_rcv_saddr) { inet->inet_rcv_saddr = rt->rt_src; + if (sk->sk_prot->rehash) + sk->sk_prot->rehash(sk); + } inet->inet_daddr = rt->rt_dst; inet->inet_dport = usin->sin_port; sk->sk_state = TCP_ESTABLISHED; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index a43968918350..7d02a9f999fa 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -246,6 +246,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, struct fib_result res; int no_addr, rpf, accept_local; + bool dev_match; int ret; struct net *net; @@ -273,12 +274,22 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, } *spec_dst = FIB_RES_PREFSRC(res); fib_combine_itag(itag, &res); + dev_match = false; + #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (FIB_RES_DEV(res) == dev || res.fi->fib_nhs > 1) + for (ret = 0; ret < res.fi->fib_nhs; ret++) { + struct fib_nh *nh = &res.fi->fib_nh[ret]; + + if (nh->nh_dev == dev) { + dev_match = true; + break; + } + } #else if (FIB_RES_DEV(res) == dev) + dev_match = true; #endif - { + if (dev_match) { ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST; fib_res_put(&res); return ret; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 79d057a939ba..4a8e370862bc 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -186,7 +186,9 @@ static inline struct tnode *node_parent_rcu(struct node *node) { struct tnode *ret = node_parent(node); - return rcu_dereference(ret); + return rcu_dereference_check(ret, + rcu_read_lock_held() || + lockdep_rtnl_is_held()); } /* Same as rcu_assign_pointer @@ -1753,7 +1755,9 @@ static struct leaf *leaf_walk_rcu(struct tnode *p, struct node *c) static struct leaf *trie_firstleaf(struct trie *t) { - struct tnode *n = (struct tnode *) rcu_dereference(t->trie); + struct tnode *n = (struct tnode *) rcu_dereference_check(t->trie, + rcu_read_lock_held() || + lockdep_rtnl_is_held()); if (!n) return NULL; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index a1ad0e7180d2..1fdcacd36ce7 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -834,7 +834,7 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, int mark = 0; - if (len == 8) { + if (len == 8 || IGMP_V2_SEEN(in_dev)) { if (ih->code == 0) { /* Alas, old v1 router presents here. */ diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 945b20a5ad50..35c93e8b6a46 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -45,7 +45,7 @@ #include <net/netns/generic.h> #include <net/rtnetlink.h> -#ifdef CONFIG_IPV6 +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> @@ -699,7 +699,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if ((dst = rt->rt_gateway) == 0) goto tx_error_icmp; } -#ifdef CONFIG_IPV6 +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) else if (skb->protocol == htons(ETH_P_IPV6)) { struct in6_addr *addr6; int addr_type; @@ -774,7 +774,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev goto tx_error; } } -#ifdef CONFIG_IPV6 +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) else if (skb->protocol == htons(ETH_P_IPV6)) { struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb); @@ -850,7 +850,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if ((iph->ttl = tiph->ttl) == 0) { if (skb->protocol == htons(ETH_P_IP)) iph->ttl = old_iph->ttl; -#ifdef CONFIG_IPV6 +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) else if (skb->protocol == htons(ETH_P_IPV6)) iph->ttl = ((struct ipv6hdr *)old_iph)->hop_limit; #endif diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 04b69896df5f..7649d7750075 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -488,9 +488,8 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) * we can switch to copy when see the first bad fragment. */ if (skb_has_frags(skb)) { - struct sk_buff *frag; + struct sk_buff *frag, *frag2; int first_len = skb_pagelen(skb); - int truesizes = 0; if (first_len - hlen > mtu || ((first_len - hlen) & 7) || @@ -503,18 +502,18 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) if (frag->len > mtu || ((frag->len & 7) && frag->next) || skb_headroom(frag) < hlen) - goto slow_path; + goto slow_path_clean; /* Partially cloned skb? */ if (skb_shared(frag)) - goto slow_path; + goto slow_path_clean; BUG_ON(frag->sk); if (skb->sk) { frag->sk = skb->sk; frag->destructor = sock_wfree; } - truesizes += frag->truesize; + skb->truesize -= frag->truesize; } /* Everything is OK. Generate! */ @@ -524,7 +523,6 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) frag = skb_shinfo(skb)->frag_list; skb_frag_list_init(skb); skb->data_len = first_len - skb_headlen(skb); - skb->truesize -= truesizes; skb->len = first_len; iph->tot_len = htons(first_len); iph->frag_off = htons(IP_MF); @@ -576,6 +574,15 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) } IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS); return err; + +slow_path_clean: + skb_walk_frags(skb, frag2) { + if (frag2 == frag) + break; + frag2->sk = NULL; + frag2->destructor = NULL; + skb->truesize += frag2->truesize; + } } slow_path: diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 6c40a8c46e79..64b70ad162e3 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1129,6 +1129,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_HDRINCL: val = inet->hdrincl; break; + case IP_NODEFRAG: + val = inet->nodefrag; + break; case IP_MTU_DISCOVER: val = inet->pmtudisc; break; diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index b254dafaf429..43eec80c0e7c 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -112,6 +112,7 @@ static void send_reset(struct sk_buff *oldskb, int hook) /* ip_route_me_harder expects skb->dst to be set */ skb_dst_set_noref(nskb, skb_dst(oldskb)); + nskb->protocol = htons(ETH_P_IP); if (ip_route_me_harder(nskb, addr_type)) goto free_nskb; diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index eab8de32f200..f3a9b42b16c6 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -66,9 +66,11 @@ static unsigned int ipv4_conntrack_defrag(unsigned int hooknum, const struct net_device *out, int (*okfn)(struct sk_buff *)) { + struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(skb->sk); - if (inet && inet->nodefrag) + if (sk && (sk->sk_family == PF_INET) && + inet->nodefrag) return NF_ACCEPT; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index 1679e2c0963d..ee5f419d0a56 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -893,13 +893,15 @@ static void fast_csum(__sum16 *csum, unsigned char s[4]; if (offset & 1) { - s[0] = s[2] = 0; + s[0] = ~0; s[1] = ~*optr; + s[2] = 0; s[3] = *nptr; } else { - s[1] = s[3] = 0; s[0] = ~*optr; + s[1] = ~0; s[2] = *nptr; + s[3] = 0; } *csum = csum_fold(csum_partial(s, 4, ~csum_unfold(*csum))); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 3f56b6e6c6aa..ac6559cb54f9 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1231,7 +1231,7 @@ restart: } if (net_ratelimit()) - printk(KERN_WARNING "Neighbour table overflow.\n"); + printk(KERN_WARNING "ipv4: Neighbour table overflow.\n"); rt_drop(rt); return -ENOBUFS; } @@ -2738,6 +2738,11 @@ slow_output: } EXPORT_SYMBOL_GPL(__ip_route_output_key); +static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie) +{ + return NULL; +} + static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) { } @@ -2746,7 +2751,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = { .family = AF_INET, .protocol = cpu_to_be16(ETH_P_IP), .destroy = ipv4_dst_destroy, - .check = ipv4_dst_check, + .check = ipv4_blackhole_dst_check, .update_pmtu = ipv4_rt_blackhole_update_pmtu, .entries = ATOMIC_INIT(0), }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3fb1428e526e..f115ea68a4ef 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -386,8 +386,6 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) */ mask = 0; - if (sk->sk_err) - mask = POLLERR; /* * POLLHUP is certainly not done right. But poll() doesn't @@ -457,6 +455,11 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) if (tp->urg_data & TCP_URG_VALID) mask |= POLLPRI; } + /* This barrier is coupled with smp_wmb() in tcp_reset() */ + smp_rmb(); + if (sk->sk_err) + mask |= POLLERR; + return mask; } EXPORT_SYMBOL(tcp_poll); @@ -940,7 +943,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, sg = sk->sk_route_caps & NETIF_F_SG; while (--iovlen >= 0) { - int seglen = iov->iov_len; + size_t seglen = iov->iov_len; unsigned char __user *from = iov->iov_base; iov++; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e663b78a2ef6..b55f60f6fcbe 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2545,7 +2545,8 @@ static void tcp_mark_head_lost(struct sock *sk, int packets) cnt += tcp_skb_pcount(skb); if (cnt > packets) { - if (tcp_is_sack(tp) || (oldcnt >= packets)) + if ((tcp_is_sack(tp) && !tcp_is_fack(tp)) || + (oldcnt >= packets)) break; mss = skb_shinfo(skb)->gso_size; @@ -4048,6 +4049,8 @@ static void tcp_reset(struct sock *sk) default: sk->sk_err = ECONNRESET; } + /* This barrier is coupled with smp_rmb() in tcp_poll() */ + smp_wmb(); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_error_report(sk); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index c35b469e851c..74c54b30600f 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -135,13 +135,16 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) /* This function calculates a "timeout" which is equivalent to the timeout of a * TCP connection after "boundary" unsuccessful, exponentially backed-off - * retransmissions with an initial RTO of TCP_RTO_MIN. + * retransmissions with an initial RTO of TCP_RTO_MIN or TCP_TIMEOUT_INIT if + * syn_set flag is set. */ static bool retransmits_timed_out(struct sock *sk, - unsigned int boundary) + unsigned int boundary, + bool syn_set) { unsigned int timeout, linear_backoff_thresh; unsigned int start_ts; + unsigned int rto_base = syn_set ? TCP_TIMEOUT_INIT : TCP_RTO_MIN; if (!inet_csk(sk)->icsk_retransmits) return false; @@ -151,12 +154,12 @@ static bool retransmits_timed_out(struct sock *sk, else start_ts = tcp_sk(sk)->retrans_stamp; - linear_backoff_thresh = ilog2(TCP_RTO_MAX/TCP_RTO_MIN); + linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base); if (boundary <= linear_backoff_thresh) - timeout = ((2 << boundary) - 1) * TCP_RTO_MIN; + timeout = ((2 << boundary) - 1) * rto_base; else - timeout = ((2 << linear_backoff_thresh) - 1) * TCP_RTO_MIN + + timeout = ((2 << linear_backoff_thresh) - 1) * rto_base + (boundary - linear_backoff_thresh) * TCP_RTO_MAX; return (tcp_time_stamp - start_ts) >= timeout; @@ -167,14 +170,15 @@ static int tcp_write_timeout(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); int retry_until; - bool do_reset; + bool do_reset, syn_set = 0; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) dst_negative_advice(sk); retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries; + syn_set = 1; } else { - if (retransmits_timed_out(sk, sysctl_tcp_retries1)) { + if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0)) { /* Black hole detection */ tcp_mtu_probing(icsk, sk); @@ -187,14 +191,14 @@ static int tcp_write_timeout(struct sock *sk) retry_until = tcp_orphan_retries(sk, alive); do_reset = alive || - !retransmits_timed_out(sk, retry_until); + !retransmits_timed_out(sk, retry_until, 0); if (tcp_out_of_resources(sk, do_reset)) return 1; } } - if (retransmits_timed_out(sk, retry_until)) { + if (retransmits_timed_out(sk, retry_until, syn_set)) { /* Has it gone just too far? */ tcp_write_err(sk); return 1; @@ -436,7 +440,7 @@ out_reset_timer: icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX); } inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, TCP_RTO_MAX); - if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1)) + if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1, 0)) __sk_dst_reset(sk); out:; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 32e0bef60d0a..fb23c2e63b52 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1260,6 +1260,49 @@ void udp_lib_unhash(struct sock *sk) } EXPORT_SYMBOL(udp_lib_unhash); +/* + * inet_rcv_saddr was changed, we must rehash secondary hash + */ +void udp_lib_rehash(struct sock *sk, u16 newhash) +{ + if (sk_hashed(sk)) { + struct udp_table *udptable = sk->sk_prot->h.udp_table; + struct udp_hslot *hslot, *hslot2, *nhslot2; + + hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); + nhslot2 = udp_hashslot2(udptable, newhash); + udp_sk(sk)->udp_portaddr_hash = newhash; + if (hslot2 != nhslot2) { + hslot = udp_hashslot(udptable, sock_net(sk), + udp_sk(sk)->udp_port_hash); + /* we must lock primary chain too */ + spin_lock_bh(&hslot->lock); + + spin_lock(&hslot2->lock); + hlist_nulls_del_init_rcu(&udp_sk(sk)->udp_portaddr_node); + hslot2->count--; + spin_unlock(&hslot2->lock); + + spin_lock(&nhslot2->lock); + hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node, + &nhslot2->head); + nhslot2->count++; + spin_unlock(&nhslot2->lock); + + spin_unlock_bh(&hslot->lock); + } + } +} +EXPORT_SYMBOL(udp_lib_rehash); + +static void udp_v4_rehash(struct sock *sk) +{ + u16 new_hash = udp4_portaddr_hash(sock_net(sk), + inet_sk(sk)->inet_rcv_saddr, + inet_sk(sk)->inet_num); + udp_lib_rehash(sk, new_hash); +} + static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int rc; @@ -1843,6 +1886,7 @@ struct proto udp_prot = { .backlog_rcv = __udp_queue_rcv_skb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, + .rehash = udp_v4_rehash, .get_port = udp_v4_get_port, .memory_allocated = &udp_memory_allocated, .sysctl_mem = sysctl_udp_mem, diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 869078d4eeb9..a580349f0b8a 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -61,7 +61,7 @@ static int xfrm4_get_saddr(struct net *net, static int xfrm4_get_tos(struct flowi *fl) { - return fl->fl4_tos; + return IPTOS_RT_MASK & fl->fl4_tos; /* Strip ECN bits */ } static int xfrm4_init_path(struct xfrm_dst *path, struct dst_entry *dst, diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index 1ef1366a0a03..47947624eccc 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -21,21 +21,25 @@ static int xfrm4_init_flags(struct xfrm_state *x) } static void -__xfrm4_init_tempsel(struct xfrm_state *x, struct flowi *fl, - struct xfrm_tmpl *tmpl, - xfrm_address_t *daddr, xfrm_address_t *saddr) +__xfrm4_init_tempsel(struct xfrm_selector *sel, struct flowi *fl) +{ + sel->daddr.a4 = fl->fl4_dst; + sel->saddr.a4 = fl->fl4_src; + sel->dport = xfrm_flowi_dport(fl); + sel->dport_mask = htons(0xffff); + sel->sport = xfrm_flowi_sport(fl); + sel->sport_mask = htons(0xffff); + sel->family = AF_INET; + sel->prefixlen_d = 32; + sel->prefixlen_s = 32; + sel->proto = fl->proto; + sel->ifindex = fl->oif; +} + +static void +xfrm4_init_temprop(struct xfrm_state *x, struct xfrm_tmpl *tmpl, + xfrm_address_t *daddr, xfrm_address_t *saddr) { - x->sel.daddr.a4 = fl->fl4_dst; - x->sel.saddr.a4 = fl->fl4_src; - x->sel.dport = xfrm_flowi_dport(fl); - x->sel.dport_mask = htons(0xffff); - x->sel.sport = xfrm_flowi_sport(fl); - x->sel.sport_mask = htons(0xffff); - x->sel.family = AF_INET; - x->sel.prefixlen_d = 32; - x->sel.prefixlen_s = 32; - x->sel.proto = fl->proto; - x->sel.ifindex = fl->oif; x->id = tmpl->id; if (x->id.daddr.a4 == 0) x->id.daddr.a4 = daddr->a4; @@ -70,6 +74,7 @@ static struct xfrm_state_afinfo xfrm4_state_afinfo = { .owner = THIS_MODULE, .init_flags = xfrm4_init_flags, .init_tempsel = __xfrm4_init_tempsel, + .init_temprop = xfrm4_init_temprop, .output = xfrm4_output, .extract_input = xfrm4_extract_input, .extract_output = xfrm4_extract_output, diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ab70a3fbcafa..324fac3b6c16 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4637,10 +4637,12 @@ int __init addrconf_init(void) if (err < 0) { printk(KERN_CRIT "IPv6 Addrconf:" " cannot initialize default policy table: %d.\n", err); - return err; + goto out; } - register_pernet_subsys(&addrconf_ops); + err = register_pernet_subsys(&addrconf_ops); + if (err < 0) + goto out_addrlabel; /* The addrconf netdev notifier requires that loopback_dev * has it's ipv6 private information allocated and setup @@ -4692,7 +4694,9 @@ errout: unregister_netdevice_notifier(&ipv6_dev_notf); errlo: unregister_pernet_subsys(&addrconf_ops); - +out_addrlabel: + ipv6_addr_label_cleanup(); +out: return err; } @@ -4703,6 +4707,7 @@ void addrconf_cleanup(void) unregister_netdevice_notifier(&ipv6_dev_notf); unregister_pernet_subsys(&addrconf_ops); + ipv6_addr_label_cleanup(); rtnl_lock(); diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index f0e774cea386..8175f802651b 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -393,6 +393,11 @@ int __init ipv6_addr_label_init(void) return register_pernet_subsys(&ipv6_addr_label_ops); } +void ipv6_addr_label_cleanup(void) +{ + unregister_pernet_subsys(&ipv6_addr_label_ops); +} + static const struct nla_policy ifal_policy[IFAL_MAX+1] = { [IFAL_ADDRESS] = { .len = sizeof(struct in6_addr), }, [IFAL_LABEL] = { .len = sizeof(u32), }, diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 7d929a22cbc2..ef371aa01ac5 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -105,9 +105,12 @@ ipv4_connected: if (ipv6_addr_any(&np->saddr)) ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); - if (ipv6_addr_any(&np->rcv_saddr)) + if (ipv6_addr_any(&np->rcv_saddr)) { ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &np->rcv_saddr); + if (sk->sk_prot->rehash) + sk->sk_prot->rehash(sk); + } goto out; } @@ -181,6 +184,8 @@ ipv4_connected: if (ipv6_addr_any(&np->rcv_saddr)) { ipv6_addr_copy(&np->rcv_saddr, &fl.fl6_src); inet->inet_rcv_saddr = LOOPBACK4_IPV6; + if (sk->sk_prot->rehash) + sk->sk_prot->rehash(sk); } ip6_dst_store(sk, dst, diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index d40b330c0ee6..980912ed7a38 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -639,7 +639,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) if (skb_has_frags(skb)) { int first_len = skb_pagelen(skb); - int truesizes = 0; + struct sk_buff *frag2; if (first_len - hlen > mtu || ((first_len - hlen) & 7) || @@ -651,18 +651,18 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) if (frag->len > mtu || ((frag->len & 7) && frag->next) || skb_headroom(frag) < hlen) - goto slow_path; + goto slow_path_clean; /* Partially cloned skb? */ if (skb_shared(frag)) - goto slow_path; + goto slow_path_clean; BUG_ON(frag->sk); if (skb->sk) { frag->sk = skb->sk; frag->destructor = sock_wfree; - truesizes += frag->truesize; } + skb->truesize -= frag->truesize; } err = 0; @@ -693,7 +693,6 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) first_len = skb_pagelen(skb); skb->data_len = first_len - skb_headlen(skb); - skb->truesize -= truesizes; skb->len = first_len; ipv6_hdr(skb)->payload_len = htons(first_len - sizeof(struct ipv6hdr)); @@ -756,6 +755,15 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) IPSTATS_MIB_FRAGFAILS); dst_release(&rt->dst); return err; + +slow_path_clean: + skb_walk_frags(skb, frag2) { + if (frag2 == frag) + break; + frag2->sk = NULL; + frag2->destructor = NULL; + skb->truesize += frag2->truesize; + } } slow_path: diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 13ef5bc05cf5..578f3c1a16db 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -113,14 +113,6 @@ static void nf_skb_free(struct sk_buff *skb) kfree_skb(NFCT_FRAG6_CB(skb)->orig); } -/* Memory Tracking Functions. */ -static void frag_kfree_skb(struct sk_buff *skb) -{ - atomic_sub(skb->truesize, &nf_init_frags.mem); - nf_skb_free(skb); - kfree_skb(skb); -} - /* Destruction primitives. */ static __inline__ void fq_put(struct nf_ct_frag6_queue *fq) @@ -282,66 +274,22 @@ static int nf_ct_frag6_queue(struct nf_ct_frag6_queue *fq, struct sk_buff *skb, } found: - /* We found where to put this one. Check for overlap with - * preceding fragment, and, if needed, align things so that - * any overlaps are eliminated. - */ - if (prev) { - int i = (NFCT_FRAG6_CB(prev)->offset + prev->len) - offset; - - if (i > 0) { - offset += i; - if (end <= offset) { - pr_debug("overlap\n"); - goto err; - } - if (!pskb_pull(skb, i)) { - pr_debug("Can't pull\n"); - goto err; - } - if (skb->ip_summed != CHECKSUM_UNNECESSARY) - skb->ip_summed = CHECKSUM_NONE; - } - } - - /* Look for overlap with succeeding segments. - * If we can merge fragments, do it. + /* RFC5722, Section 4: + * When reassembling an IPv6 datagram, if + * one or more its constituent fragments is determined to be an + * overlapping fragment, the entire datagram (and any constituent + * fragments, including those not yet received) MUST be silently + * discarded. */ - while (next && NFCT_FRAG6_CB(next)->offset < end) { - /* overlap is 'i' bytes */ - int i = end - NFCT_FRAG6_CB(next)->offset; - - if (i < next->len) { - /* Eat head of the next overlapped fragment - * and leave the loop. The next ones cannot overlap. - */ - pr_debug("Eat head of the overlapped parts.: %d", i); - if (!pskb_pull(next, i)) - goto err; - /* next fragment */ - NFCT_FRAG6_CB(next)->offset += i; - fq->q.meat -= i; - if (next->ip_summed != CHECKSUM_UNNECESSARY) - next->ip_summed = CHECKSUM_NONE; - break; - } else { - struct sk_buff *free_it = next; - - /* Old fragmnet is completely overridden with - * new one drop it. - */ - next = next->next; + /* Check for overlap with preceding fragment. */ + if (prev && + (NFCT_FRAG6_CB(prev)->offset + prev->len) - offset > 0) + goto discard_fq; - if (prev) - prev->next = next; - else - fq->q.fragments = next; - - fq->q.meat -= free_it->len; - frag_kfree_skb(free_it); - } - } + /* Look for overlap with succeeding segment. */ + if (next && NFCT_FRAG6_CB(next)->offset < end) + goto discard_fq; NFCT_FRAG6_CB(skb)->offset = offset; @@ -371,6 +319,8 @@ found: write_unlock(&nf_frags.lock); return 0; +discard_fq: + fq_kill(fq); err: return -1; } diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 545c4141b755..64cfef1b0a4c 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -149,13 +149,6 @@ int ip6_frag_match(struct inet_frag_queue *q, void *a) } EXPORT_SYMBOL(ip6_frag_match); -/* Memory Tracking Functions. */ -static void frag_kfree_skb(struct netns_frags *nf, struct sk_buff *skb) -{ - atomic_sub(skb->truesize, &nf->mem); - kfree_skb(skb); -} - void ip6_frag_init(struct inet_frag_queue *q, void *a) { struct frag_queue *fq = container_of(q, struct frag_queue, q); @@ -346,58 +339,22 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, } found: - /* We found where to put this one. Check for overlap with - * preceding fragment, and, if needed, align things so that - * any overlaps are eliminated. + /* RFC5722, Section 4: + * When reassembling an IPv6 datagram, if + * one or more its constituent fragments is determined to be an + * overlapping fragment, the entire datagram (and any constituent + * fragments, including those not yet received) MUST be silently + * discarded. */ - if (prev) { - int i = (FRAG6_CB(prev)->offset + prev->len) - offset; - if (i > 0) { - offset += i; - if (end <= offset) - goto err; - if (!pskb_pull(skb, i)) - goto err; - if (skb->ip_summed != CHECKSUM_UNNECESSARY) - skb->ip_summed = CHECKSUM_NONE; - } - } + /* Check for overlap with preceding fragment. */ + if (prev && + (FRAG6_CB(prev)->offset + prev->len) - offset > 0) + goto discard_fq; - /* Look for overlap with succeeding segments. - * If we can merge fragments, do it. - */ - while (next && FRAG6_CB(next)->offset < end) { - int i = end - FRAG6_CB(next)->offset; /* overlap is 'i' bytes */ - - if (i < next->len) { - /* Eat head of the next overlapped fragment - * and leave the loop. The next ones cannot overlap. - */ - if (!pskb_pull(next, i)) - goto err; - FRAG6_CB(next)->offset += i; /* next fragment */ - fq->q.meat -= i; - if (next->ip_summed != CHECKSUM_UNNECESSARY) - next->ip_summed = CHECKSUM_NONE; - break; - } else { - struct sk_buff *free_it = next; - - /* Old fragment is completely overridden with - * new one drop it. - */ - next = next->next; - - if (prev) - prev->next = next; - else - fq->q.fragments = next; - - fq->q.meat -= free_it->len; - frag_kfree_skb(fq->q.net, free_it); - } - } + /* Look for overlap with succeeding segment. */ + if (next && FRAG6_CB(next)->offset < end) + goto discard_fq; FRAG6_CB(skb)->offset = offset; @@ -436,6 +393,8 @@ found: write_unlock(&ip6_frags.lock); return -1; +discard_fq: + fq_kill(fq); err: IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d126365ac046..8323136bdc54 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -670,7 +670,7 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *dad if (net_ratelimit()) printk(KERN_WARNING - "Neighbour table overflow.\n"); + "ipv6: Neighbour table overflow.\n"); dst_free(&rt->dst); return NULL; } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 1dd1affdead2..5acb3560ff15 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -111,6 +111,15 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum) return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal, hash2_nulladdr); } +static void udp_v6_rehash(struct sock *sk) +{ + u16 new_hash = udp6_portaddr_hash(sock_net(sk), + &inet6_sk(sk)->rcv_saddr, + inet_sk(sk)->inet_num); + + udp_lib_rehash(sk, new_hash); +} + static inline int compute_score(struct sock *sk, struct net *net, unsigned short hnum, struct in6_addr *saddr, __be16 sport, @@ -1447,6 +1456,7 @@ struct proto udpv6_prot = { .backlog_rcv = udpv6_queue_rcv_skb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, + .rehash = udp_v6_rehash, .get_port = udp_v6_get_port, .memory_allocated = &udp_memory_allocated, .sysctl_mem = sysctl_udp_mem, diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index f417b77fa0e1..a67575d472a3 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -20,23 +20,27 @@ #include <net/addrconf.h> static void -__xfrm6_init_tempsel(struct xfrm_state *x, struct flowi *fl, - struct xfrm_tmpl *tmpl, - xfrm_address_t *daddr, xfrm_address_t *saddr) +__xfrm6_init_tempsel(struct xfrm_selector *sel, struct flowi *fl) { /* Initialize temporary selector matching only * to current session. */ - ipv6_addr_copy((struct in6_addr *)&x->sel.daddr, &fl->fl6_dst); - ipv6_addr_copy((struct in6_addr *)&x->sel.saddr, &fl->fl6_src); - x->sel.dport = xfrm_flowi_dport(fl); - x->sel.dport_mask = htons(0xffff); - x->sel.sport = xfrm_flowi_sport(fl); - x->sel.sport_mask = htons(0xffff); - x->sel.family = AF_INET6; - x->sel.prefixlen_d = 128; - x->sel.prefixlen_s = 128; - x->sel.proto = fl->proto; - x->sel.ifindex = fl->oif; + ipv6_addr_copy((struct in6_addr *)&sel->daddr, &fl->fl6_dst); + ipv6_addr_copy((struct in6_addr *)&sel->saddr, &fl->fl6_src); + sel->dport = xfrm_flowi_dport(fl); + sel->dport_mask = htons(0xffff); + sel->sport = xfrm_flowi_sport(fl); + sel->sport_mask = htons(0xffff); + sel->family = AF_INET6; + sel->prefixlen_d = 128; + sel->prefixlen_s = 128; + sel->proto = fl->proto; + sel->ifindex = fl->oif; +} + +static void +xfrm6_init_temprop(struct xfrm_state *x, struct xfrm_tmpl *tmpl, + xfrm_address_t *daddr, xfrm_address_t *saddr) +{ x->id = tmpl->id; if (ipv6_addr_any((struct in6_addr*)&x->id.daddr)) memcpy(&x->id.daddr, daddr, sizeof(x->sel.daddr)); @@ -168,6 +172,7 @@ static struct xfrm_state_afinfo xfrm6_state_afinfo = { .eth_proto = htons(ETH_P_IPV6), .owner = THIS_MODULE, .init_tempsel = __xfrm6_init_tempsel, + .init_temprop = xfrm6_init_temprop, .tmpl_sort = __xfrm6_tmpl_sort, .state_sort = __xfrm6_state_sort, .output = xfrm6_output, diff --git a/net/irda/irlan/irlan_common.c b/net/irda/irlan/irlan_common.c index a788f9e9427d..6130f9d9dbe1 100644 --- a/net/irda/irlan/irlan_common.c +++ b/net/irda/irlan/irlan_common.c @@ -1102,7 +1102,7 @@ int irlan_extract_param(__u8 *buf, char *name, char *value, __u16 *len) memcpy(&val_len, buf+n, 2); /* To avoid alignment problems */ le16_to_cpus(&val_len); n+=2; - if (val_len > 1016) { + if (val_len >= 1016) { IRDA_DEBUG(2, "%s(), parameter length to long\n", __func__ ); return -RSP_INVALID_COMMAND_FORMAT; } diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 023ba820236f..582612998211 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -1024,7 +1024,8 @@ static int llc_ui_setsockopt(struct socket *sock, int level, int optname, { struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); - int rc = -EINVAL, opt; + unsigned int opt; + int rc = -EINVAL; lock_sock(sk); if (unlikely(level != SOL_LLC || optlen != sizeof(int))) diff --git a/net/llc/llc_station.c b/net/llc/llc_station.c index e4dae0244d76..cf4aea3ba30f 100644 --- a/net/llc/llc_station.c +++ b/net/llc/llc_station.c @@ -689,7 +689,7 @@ static void llc_station_rcv(struct sk_buff *skb) int __init llc_station_init(void) { - u16 rc = -ENOBUFS; + int rc = -ENOBUFS; struct sk_buff *skb; struct llc_station_state_ev *ev; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index fa0f37e4afe4..28624282c5f3 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2199,9 +2199,6 @@ static void ieee80211_rx_cooked_monitor(struct ieee80211_rx_data *rx, struct net_device *prev_dev = NULL; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); - if (status->flag & RX_FLAG_INTERNAL_CMTR) - goto out_free_skb; - if (skb_headroom(skb) < sizeof(*rthdr) && pskb_expand_head(skb, sizeof(*rthdr), 0, GFP_ATOMIC)) goto out_free_skb; @@ -2260,7 +2257,6 @@ static void ieee80211_rx_cooked_monitor(struct ieee80211_rx_data *rx, } else goto out_free_skb; - status->flag |= RX_FLAG_INTERNAL_CMTR; return; out_free_skb: diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 4f8ddba48011..4c2f89df5cce 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -924,6 +924,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, ip_vs_out_stats(cp, skb); ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pp); + ip_vs_update_conntrack(skb, cp, 0); ip_vs_conn_put(cp); skb->ipvs_property = 1; diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 33b329bfc2d2..7e9af5b76d9e 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -410,7 +410,6 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, union nf_inet_addr to; __be16 port; struct ip_vs_conn *n_cp; - struct nf_conn *ct; #ifdef CONFIG_IP_VS_IPV6 /* This application helper doesn't work with IPv6 yet, @@ -497,11 +496,6 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, ip_vs_control_add(n_cp, cp); } - ct = (struct nf_conn *)skb->nfct; - if (ct && ct != &nf_conntrack_untracked) - ip_vs_expect_related(skb, ct, n_cp, - IPPROTO_TCP, &n_cp->dport, 1); - /* * Move tunnel to listen state */ diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 21e1a5e9b9d3..49df6bea6a2d 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -349,8 +349,8 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, } #endif -static void -ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp) +void +ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp, int outin) { struct nf_conn *ct = (struct nf_conn *)skb->nfct; struct nf_conntrack_tuple new_tuple; @@ -365,11 +365,17 @@ ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp) * real-server we will see RIP->DIP. */ new_tuple = ct->tuplehash[IP_CT_DIR_REPLY].tuple; - new_tuple.src.u3 = cp->daddr; + if (outin) + new_tuple.src.u3 = cp->daddr; + else + new_tuple.dst.u3 = cp->vaddr; /* * This will also take care of UDP and other protocols. */ - new_tuple.src.u.tcp.port = cp->dport; + if (outin) + new_tuple.src.u.tcp.port = cp->dport; + else + new_tuple.dst.u.tcp.port = cp->vport; nf_conntrack_alter_reply(ct, &new_tuple); } @@ -428,7 +434,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT"); - ip_vs_update_conntrack(skb, cp); + ip_vs_update_conntrack(skb, cp, 1); /* FIXME: when application helper enlarges the packet and the length is larger than the MTU of outgoing device, there will be still @@ -506,7 +512,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT"); - ip_vs_update_conntrack(skb, cp); + ip_vs_update_conntrack(skb, cp, 1); /* FIXME: when application helper enlarges the packet and the length is larger than the MTU of outgoing device, there will be still diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 1d9bdae06161..bd82450c193f 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -48,15 +48,17 @@ nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id, gfp_t gfp) { unsigned int off, len; struct nf_ct_ext_type *t; + size_t alloc_size; rcu_read_lock(); t = rcu_dereference(nf_ct_ext_types[id]); BUG_ON(t == NULL); off = ALIGN(sizeof(struct nf_ct_ext), t->align); len = off + t->len; + alloc_size = t->alloc_size; rcu_read_unlock(); - *ext = kzalloc(t->alloc_size, gfp); + *ext = kzalloc(alloc_size, gfp); if (!*ext) return NULL; diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 53d892210a04..f64de9544866 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1376,7 +1376,7 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, unsigned int msglen, origlen; const char *dptr, *end; s16 diff, tdiff = 0; - int ret; + int ret = NF_ACCEPT; typeof(nf_nat_sip_seq_adjust_hook) nf_nat_sip_seq_adjust; if (ctinfo != IP_CT_ESTABLISHED && diff --git a/net/netfilter/nf_tproxy_core.c b/net/netfilter/nf_tproxy_core.c index 5490fc37c92d..daab8c4a903c 100644 --- a/net/netfilter/nf_tproxy_core.c +++ b/net/netfilter/nf_tproxy_core.c @@ -70,7 +70,11 @@ nf_tproxy_destructor(struct sk_buff *skb) int nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk) { - if (inet_sk(sk)->transparent) { + bool transparent = (sk->sk_state == TCP_TIME_WAIT) ? + inet_twsk(sk)->tw_transparent : + inet_sk(sk)->transparent; + + if (transparent) { skb_orphan(skb); skb->sk = sk; skb->destructor = nf_tproxy_destructor; diff --git a/net/phonet/pep.c b/net/phonet/pep.c index b2a3ae6cad78..15003021f4f0 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -225,12 +225,13 @@ static void pipe_grant_credits(struct sock *sk) static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb) { struct pep_sock *pn = pep_sk(sk); - struct pnpipehdr *hdr = pnp_hdr(skb); + struct pnpipehdr *hdr; int wake = 0; if (!pskb_may_pull(skb, sizeof(*hdr) + 4)) return -EINVAL; + hdr = pnp_hdr(skb); if (hdr->data[0] != PN_PEP_TYPE_COMMON) { LIMIT_NETDEBUG(KERN_DEBUG"Phonet unknown PEP type: %u\n", (unsigned)hdr->data[0]); diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c index c397524c039c..c519939e8da9 100644 --- a/net/rds/tcp_connect.c +++ b/net/rds/tcp_connect.c @@ -43,7 +43,7 @@ void rds_tcp_state_change(struct sock *sk) struct rds_connection *conn; struct rds_tcp_connection *tc; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); conn = sk->sk_user_data; if (conn == NULL) { state_change = sk->sk_state_change; @@ -68,7 +68,7 @@ void rds_tcp_state_change(struct sock *sk) break; } out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); state_change(sk); } diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 975183fe6950..27844f231d10 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -114,7 +114,7 @@ void rds_tcp_listen_data_ready(struct sock *sk, int bytes) rdsdebug("listen data ready sk %p\n", sk); - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); ready = sk->sk_user_data; if (ready == NULL) { /* check for teardown race */ ready = sk->sk_data_ready; @@ -131,7 +131,7 @@ void rds_tcp_listen_data_ready(struct sock *sk, int bytes) queue_work(rds_wq, &rds_tcp_listen_work); out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); ready(sk, bytes); } diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c index 1aba6878fa5d..e43797404102 100644 --- a/net/rds/tcp_recv.c +++ b/net/rds/tcp_recv.c @@ -324,7 +324,7 @@ void rds_tcp_data_ready(struct sock *sk, int bytes) rdsdebug("data ready sk %p bytes %d\n", sk, bytes); - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); conn = sk->sk_user_data; if (conn == NULL) { /* check for teardown race */ ready = sk->sk_data_ready; @@ -338,7 +338,7 @@ void rds_tcp_data_ready(struct sock *sk, int bytes) if (rds_tcp_read_sock(conn, GFP_ATOMIC, KM_SOFTIRQ0) == -ENOMEM) queue_delayed_work(rds_wq, &conn->c_recv_w, 0); out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); ready(sk, bytes); } diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c index a28b895ff0d1..2f012a07d94d 100644 --- a/net/rds/tcp_send.c +++ b/net/rds/tcp_send.c @@ -224,7 +224,7 @@ void rds_tcp_write_space(struct sock *sk) struct rds_connection *conn; struct rds_tcp_connection *tc; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); conn = sk->sk_user_data; if (conn == NULL) { write_space = sk->sk_write_space; @@ -244,7 +244,7 @@ void rds_tcp_write_space(struct sock *sk) queue_delayed_work(rds_wq, &conn->c_send_w, 0); out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); /* * write_space is only called when data leaves tcp's send queue if diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 8e45e76a95f5..d952e7eac188 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -679,7 +679,7 @@ static int rose_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (addr_len == sizeof(struct sockaddr_rose) && addr->srose_ndigis > 1) return -EINVAL; - if (addr->srose_ndigis > ROSE_MAX_DIGIS) + if ((unsigned int) addr->srose_ndigis > ROSE_MAX_DIGIS) return -EINVAL; if ((dev = rose_dev_get(&addr->srose_addr)) == NULL) { @@ -739,7 +739,7 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le if (addr_len == sizeof(struct sockaddr_rose) && addr->srose_ndigis > 1) return -EINVAL; - if (addr->srose_ndigis > ROSE_MAX_DIGIS) + if ((unsigned int) addr->srose_ndigis > ROSE_MAX_DIGIS) return -EINVAL; /* Source + Destination digis should not exceed ROSE_MAX_DIGIS */ diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 340662789529..6318e1136b83 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -255,10 +255,6 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, error = -EINVAL; goto err_out; } - if (!list_empty(&flow->list)) { - error = -EEXIST; - goto err_out; - } } else { int i; unsigned long cl; diff --git a/net/sctp/output.c b/net/sctp/output.c index a646681f5acd..bcc4590ccaf2 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -92,7 +92,6 @@ struct sctp_packet *sctp_packet_config(struct sctp_packet *packet, SCTP_DEBUG_PRINTK("%s: packet:%p vtag:0x%x\n", __func__, packet, vtag); - sctp_packet_reset(packet); packet->vtag = vtag; if (ecn_capable && sctp_packet_empty(packet)) { diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 24b2cd555637..d344dc481ccc 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -1232,6 +1232,18 @@ out: return 0; } +static bool list_has_sctp_addr(const struct list_head *list, + union sctp_addr *ipaddr) +{ + struct sctp_transport *addr; + + list_for_each_entry(addr, list, transports) { + if (sctp_cmp_addr_exact(ipaddr, &addr->ipaddr)) + return true; + } + + return false; +} /* A restart is occurring, check to make sure no new addresses * are being added as we may be under a takeover attack. */ @@ -1240,10 +1252,10 @@ static int sctp_sf_check_restart_addrs(const struct sctp_association *new_asoc, struct sctp_chunk *init, sctp_cmd_seq_t *commands) { - struct sctp_transport *new_addr, *addr; - int found; + struct sctp_transport *new_addr; + int ret = 1; - /* Implementor's Guide - Sectin 5.2.2 + /* Implementor's Guide - Section 5.2.2 * ... * Before responding the endpoint MUST check to see if the * unexpected INIT adds new addresses to the association. If new @@ -1254,31 +1266,19 @@ static int sctp_sf_check_restart_addrs(const struct sctp_association *new_asoc, /* Search through all current addresses and make sure * we aren't adding any new ones. */ - new_addr = NULL; - found = 0; - list_for_each_entry(new_addr, &new_asoc->peer.transport_addr_list, - transports) { - found = 0; - list_for_each_entry(addr, &asoc->peer.transport_addr_list, - transports) { - if (sctp_cmp_addr_exact(&new_addr->ipaddr, - &addr->ipaddr)) { - found = 1; - break; - } - } - if (!found) + transports) { + if (!list_has_sctp_addr(&asoc->peer.transport_addr_list, + &new_addr->ipaddr)) { + sctp_sf_send_restart_abort(&new_addr->ipaddr, init, + commands); + ret = 0; break; - } - - /* If a new address was added, ABORT the sender. */ - if (!found && new_addr) { - sctp_sf_send_restart_abort(&new_addr->ipaddr, init, commands); + } } /* Return success if all addresses were found. */ - return found; + return ret; } /* Populate the verification/tie tags based on overlapping INIT diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 36cb66022a27..e9eaaf7d43c1 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -38,7 +38,7 @@ static const struct rpc_authops *auth_flavors[RPC_AUTH_MAXFLAVOR] = { static LIST_HEAD(cred_unused); static unsigned long number_cred_unused; -#define MAX_HASHTABLE_BITS (10) +#define MAX_HASHTABLE_BITS (14) static int param_set_hashtbl_sz(const char *val, const struct kernel_param *kp) { unsigned long num; diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index dcfc66bab2bb..12c485982814 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -745,17 +745,18 @@ gss_pipe_release(struct inode *inode) struct rpc_inode *rpci = RPC_I(inode); struct gss_upcall_msg *gss_msg; +restart: spin_lock(&inode->i_lock); - while (!list_empty(&rpci->in_downcall)) { + list_for_each_entry(gss_msg, &rpci->in_downcall, list) { - gss_msg = list_entry(rpci->in_downcall.next, - struct gss_upcall_msg, list); + if (!list_empty(&gss_msg->msg.list)) + continue; gss_msg->msg.errno = -EPIPE; atomic_inc(&gss_msg->count); __gss_unhash_msg(gss_msg); spin_unlock(&inode->i_lock); gss_release_msg(gss_msg); - spin_lock(&inode->i_lock); + goto restart; } spin_unlock(&inode->i_lock); diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 032644610524..778e5dfc5144 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -237,6 +237,7 @@ get_key(const void *p, const void *end, if (!supported_gss_krb5_enctype(alg)) { printk(KERN_WARNING "gss_kerberos_mech: unsupported " "encryption key algorithm %d\n", alg); + p = ERR_PTR(-EINVAL); goto out_err; } p = simple_get_netobj(p, end, &key); @@ -282,15 +283,19 @@ gss_import_v1_context(const void *p, const void *end, struct krb5_ctx *ctx) ctx->enctype = ENCTYPE_DES_CBC_RAW; ctx->gk5e = get_gss_krb5_enctype(ctx->enctype); - if (ctx->gk5e == NULL) + if (ctx->gk5e == NULL) { + p = ERR_PTR(-EINVAL); goto out_err; + } /* The downcall format was designed before we completely understood * the uses of the context fields; so it includes some stuff we * just give some minimal sanity-checking, and some we ignore * completely (like the next twenty bytes): */ - if (unlikely(p + 20 > end || p + 20 < p)) + if (unlikely(p + 20 > end || p + 20 < p)) { + p = ERR_PTR(-EFAULT); goto out_err; + } p += 20; p = simple_get_bytes(p, end, &tmp, sizeof(tmp)); if (IS_ERR(p)) @@ -619,6 +624,7 @@ gss_import_v2_context(const void *p, const void *end, struct krb5_ctx *ctx, if (ctx->seq_send64 != ctx->seq_send) { dprintk("%s: seq_send64 %lx, seq_send %x overflow?\n", __func__, (long unsigned)ctx->seq_send64, ctx->seq_send); + p = ERR_PTR(-EINVAL); goto out_err; } p = simple_get_bytes(p, end, &ctx->enctype, sizeof(ctx->enctype)); diff --git a/net/sunrpc/auth_gss/gss_spkm3_mech.c b/net/sunrpc/auth_gss/gss_spkm3_mech.c index dc3f1f5ed865..adade3d313f2 100644 --- a/net/sunrpc/auth_gss/gss_spkm3_mech.c +++ b/net/sunrpc/auth_gss/gss_spkm3_mech.c @@ -100,6 +100,7 @@ gss_import_sec_context_spkm3(const void *p, size_t len, if (version != 1) { dprintk("RPC: unknown spkm3 token format: " "obsolete nfs-utils?\n"); + p = ERR_PTR(-EINVAL); goto out_err_free_ctx; } @@ -135,8 +136,10 @@ gss_import_sec_context_spkm3(const void *p, size_t len, if (IS_ERR(p)) goto out_err_free_intg_alg; - if (p != end) + if (p != end) { + p = ERR_PTR(-EFAULT); goto out_err_free_intg_key; + } ctx_id->internal_ctx_id = ctx; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 2388d83b68ff..fa5549079d79 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -226,7 +226,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, stru goto out_no_principal; } - kref_init(&clnt->cl_kref); + atomic_set(&clnt->cl_count, 1); err = rpc_setup_pipedir(clnt, program->pipe_dir_name); if (err < 0) @@ -390,14 +390,14 @@ rpc_clone_client(struct rpc_clnt *clnt) if (new->cl_principal == NULL) goto out_no_principal; } - kref_init(&new->cl_kref); + atomic_set(&new->cl_count, 1); err = rpc_setup_pipedir(new, clnt->cl_program->pipe_dir_name); if (err != 0) goto out_no_path; if (new->cl_auth) atomic_inc(&new->cl_auth->au_count); xprt_get(clnt->cl_xprt); - kref_get(&clnt->cl_kref); + atomic_inc(&clnt->cl_count); rpc_register_client(new); rpciod_up(); return new; @@ -465,10 +465,8 @@ EXPORT_SYMBOL_GPL(rpc_shutdown_client); * Free an RPC client */ static void -rpc_free_client(struct kref *kref) +rpc_free_client(struct rpc_clnt *clnt) { - struct rpc_clnt *clnt = container_of(kref, struct rpc_clnt, cl_kref); - dprintk("RPC: destroying %s client for %s\n", clnt->cl_protname, clnt->cl_server); if (!IS_ERR(clnt->cl_path.dentry)) { @@ -495,12 +493,10 @@ out_free: * Free an RPC client */ static void -rpc_free_auth(struct kref *kref) +rpc_free_auth(struct rpc_clnt *clnt) { - struct rpc_clnt *clnt = container_of(kref, struct rpc_clnt, cl_kref); - if (clnt->cl_auth == NULL) { - rpc_free_client(kref); + rpc_free_client(clnt); return; } @@ -509,10 +505,11 @@ rpc_free_auth(struct kref *kref) * release remaining GSS contexts. This mechanism ensures * that it can do so safely. */ - kref_init(kref); + atomic_inc(&clnt->cl_count); rpcauth_release(clnt->cl_auth); clnt->cl_auth = NULL; - kref_put(kref, rpc_free_client); + if (atomic_dec_and_test(&clnt->cl_count)) + rpc_free_client(clnt); } /* @@ -525,7 +522,8 @@ rpc_release_client(struct rpc_clnt *clnt) if (list_empty(&clnt->cl_tasks)) wake_up(&destroy_wait); - kref_put(&clnt->cl_kref, rpc_free_auth); + if (atomic_dec_and_test(&clnt->cl_count)) + rpc_free_auth(clnt); } /** @@ -588,7 +586,7 @@ void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt) if (clnt != NULL) { rpc_task_release_client(task); task->tk_client = clnt; - kref_get(&clnt->cl_kref); + atomic_inc(&clnt->cl_count); if (clnt->cl_softrtry) task->tk_flags |= RPC_TASK_SOFT; /* Add to the client's list of all tasks */ @@ -931,7 +929,7 @@ call_reserveresult(struct rpc_task *task) task->tk_status = 0; if (status >= 0) { if (task->tk_rqstp) { - task->tk_action = call_allocate; + task->tk_action = call_refresh; return; } @@ -966,13 +964,54 @@ call_reserveresult(struct rpc_task *task) } /* - * 2. Allocate the buffer. For details, see sched.c:rpc_malloc. + * 2. Bind and/or refresh the credentials + */ +static void +call_refresh(struct rpc_task *task) +{ + dprint_status(task); + + task->tk_action = call_refreshresult; + task->tk_status = 0; + task->tk_client->cl_stats->rpcauthrefresh++; + rpcauth_refreshcred(task); +} + +/* + * 2a. Process the results of a credential refresh + */ +static void +call_refreshresult(struct rpc_task *task) +{ + int status = task->tk_status; + + dprint_status(task); + + task->tk_status = 0; + task->tk_action = call_allocate; + if (status >= 0 && rpcauth_uptodatecred(task)) + return; + switch (status) { + case -EACCES: + rpc_exit(task, -EACCES); + return; + case -ENOMEM: + rpc_exit(task, -ENOMEM); + return; + case -ETIMEDOUT: + rpc_delay(task, 3*HZ); + } + task->tk_action = call_refresh; +} + +/* + * 2b. Allocate the buffer. For details, see sched.c:rpc_malloc. * (Note: buffer memory is freed in xprt_release). */ static void call_allocate(struct rpc_task *task) { - unsigned int slack = task->tk_client->cl_auth->au_cslack; + unsigned int slack = task->tk_rqstp->rq_cred->cr_auth->au_cslack; struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = task->tk_xprt; struct rpc_procinfo *proc = task->tk_msg.rpc_proc; @@ -980,7 +1019,7 @@ call_allocate(struct rpc_task *task) dprint_status(task); task->tk_status = 0; - task->tk_action = call_refresh; + task->tk_action = call_bind; if (req->rq_buffer) return; @@ -1017,47 +1056,6 @@ call_allocate(struct rpc_task *task) rpc_exit(task, -ERESTARTSYS); } -/* - * 2a. Bind and/or refresh the credentials - */ -static void -call_refresh(struct rpc_task *task) -{ - dprint_status(task); - - task->tk_action = call_refreshresult; - task->tk_status = 0; - task->tk_client->cl_stats->rpcauthrefresh++; - rpcauth_refreshcred(task); -} - -/* - * 2b. Process the results of a credential refresh - */ -static void -call_refreshresult(struct rpc_task *task) -{ - int status = task->tk_status; - - dprint_status(task); - - task->tk_status = 0; - task->tk_action = call_bind; - if (status >= 0 && rpcauth_uptodatecred(task)) - return; - switch (status) { - case -EACCES: - rpc_exit(task, -EACCES); - return; - case -ENOMEM: - rpc_exit(task, -ENOMEM); - return; - case -ETIMEDOUT: - rpc_delay(task, 3*HZ); - } - task->tk_action = call_refresh; -} - static inline int rpc_task_need_encode(struct rpc_task *task) { diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 95ccbcf45d3e..8c8eef2b8f26 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -48,7 +48,7 @@ static void rpc_purge_list(struct rpc_inode *rpci, struct list_head *head, return; do { msg = list_entry(head->next, struct rpc_pipe_msg, list); - list_del(&msg->list); + list_del_init(&msg->list); msg->errno = err; destroy_msg(msg); } while (!list_empty(head)); @@ -208,7 +208,7 @@ rpc_pipe_release(struct inode *inode, struct file *filp) if (msg != NULL) { spin_lock(&inode->i_lock); msg->errno = -EAGAIN; - list_del(&msg->list); + list_del_init(&msg->list); spin_unlock(&inode->i_lock); rpci->ops->destroy_msg(msg); } @@ -268,7 +268,7 @@ rpc_pipe_read(struct file *filp, char __user *buf, size_t len, loff_t *offset) if (res < 0 || msg->len == msg->copied) { filp->private_data = NULL; spin_lock(&inode->i_lock); - list_del(&msg->list); + list_del_init(&msg->list); spin_unlock(&inode->i_lock); rpci->ops->destroy_msg(msg); } @@ -371,21 +371,23 @@ rpc_show_info(struct seq_file *m, void *v) static int rpc_info_open(struct inode *inode, struct file *file) { - struct rpc_clnt *clnt; + struct rpc_clnt *clnt = NULL; int ret = single_open(file, rpc_show_info, NULL); if (!ret) { struct seq_file *m = file->private_data; - mutex_lock(&inode->i_mutex); - clnt = RPC_I(inode)->private; - if (clnt) { - kref_get(&clnt->cl_kref); + + spin_lock(&file->f_path.dentry->d_lock); + if (!d_unhashed(file->f_path.dentry)) + clnt = RPC_I(inode)->private; + if (clnt != NULL && atomic_inc_not_zero(&clnt->cl_count)) { + spin_unlock(&file->f_path.dentry->d_lock); m->private = clnt; } else { + spin_unlock(&file->f_path.dentry->d_lock); single_release(inode, file); ret = -EINVAL; } - mutex_unlock(&inode->i_mutex); } return ret; } diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index b6309db56226..fe9306bf10cc 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -800,7 +800,7 @@ static void xs_udp_data_ready(struct sock *sk, int len) u32 _xid; __be32 *xp; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); dprintk("RPC: xs_udp_data_ready...\n"); if (!(xprt = xprt_from_sock(sk))) goto out; @@ -852,7 +852,7 @@ static void xs_udp_data_ready(struct sock *sk, int len) dropit: skb_free_datagram(sk, skb); out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); } static inline void xs_tcp_read_fraghdr(struct rpc_xprt *xprt, struct xdr_skb_reader *desc) @@ -1229,7 +1229,7 @@ static void xs_tcp_data_ready(struct sock *sk, int bytes) dprintk("RPC: xs_tcp_data_ready...\n"); - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); if (!(xprt = xprt_from_sock(sk))) goto out; if (xprt->shutdown) @@ -1248,7 +1248,7 @@ static void xs_tcp_data_ready(struct sock *sk, int bytes) read = tcp_read_sock(sk, &rd_desc, xs_tcp_data_recv); } while (read > 0); out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); } /* @@ -1301,7 +1301,7 @@ static void xs_tcp_state_change(struct sock *sk) { struct rpc_xprt *xprt; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); if (!(xprt = xprt_from_sock(sk))) goto out; dprintk("RPC: xs_tcp_state_change client %p...\n", xprt); @@ -1313,7 +1313,7 @@ static void xs_tcp_state_change(struct sock *sk) switch (sk->sk_state) { case TCP_ESTABLISHED: - spin_lock_bh(&xprt->transport_lock); + spin_lock(&xprt->transport_lock); if (!xprt_test_and_set_connected(xprt)) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); @@ -1327,7 +1327,7 @@ static void xs_tcp_state_change(struct sock *sk) xprt_wake_pending_tasks(xprt, -EAGAIN); } - spin_unlock_bh(&xprt->transport_lock); + spin_unlock(&xprt->transport_lock); break; case TCP_FIN_WAIT1: /* The client initiated a shutdown of the socket */ @@ -1365,7 +1365,7 @@ static void xs_tcp_state_change(struct sock *sk) xs_sock_mark_closed(xprt); } out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); } /** @@ -1376,7 +1376,7 @@ static void xs_error_report(struct sock *sk) { struct rpc_xprt *xprt; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); if (!(xprt = xprt_from_sock(sk))) goto out; dprintk("RPC: %s client %p...\n" @@ -1384,7 +1384,7 @@ static void xs_error_report(struct sock *sk) __func__, xprt, sk->sk_err); xprt_wake_pending_tasks(xprt, -EAGAIN); out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); } static void xs_write_space(struct sock *sk) @@ -1416,13 +1416,13 @@ static void xs_write_space(struct sock *sk) */ static void xs_udp_write_space(struct sock *sk) { - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); /* from net/core/sock.c:sock_def_write_space */ if (sock_writeable(sk)) xs_write_space(sk); - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); } /** @@ -1437,13 +1437,13 @@ static void xs_udp_write_space(struct sock *sk) */ static void xs_tcp_write_space(struct sock *sk) { - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); /* from net/core/stream.c:sk_stream_write_space */ if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) xs_write_space(sk); - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); } static void xs_udp_do_set_buffer_size(struct rpc_xprt *xprt) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 4414a18c63b4..0b39b2451ea5 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -692,6 +692,7 @@ static int unix_autobind(struct socket *sock) static u32 ordernum = 1; struct unix_address *addr; int err; + unsigned int retries = 0; mutex_lock(&u->readlock); @@ -717,9 +718,17 @@ retry: if (__unix_find_socket_byname(net, addr->name, addr->len, sock->type, addr->hash)) { spin_unlock(&unix_table_lock); - /* Sanity yield. It is unusual case, but yet... */ - if (!(ordernum&0xFF)) - yield(); + /* + * __unix_find_socket_byname() may take long time if many names + * are already in use. + */ + cond_resched(); + /* Give up if all names seems to be in use. */ + if (retries++ == 0xFFFFF) { + err = -ENOSPC; + kfree(addr); + goto out; + } goto retry; } addr->hash ^= sk->sk_type; diff --git a/net/wireless/wext-priv.c b/net/wireless/wext-priv.c index 3feb28e41c53..674d426a9d24 100644 --- a/net/wireless/wext-priv.c +++ b/net/wireless/wext-priv.c @@ -152,7 +152,7 @@ static int ioctl_private_iw_point(struct iw_point *iwp, unsigned int cmd, } else if (!iwp->pointer) return -EFAULT; - extra = kmalloc(extra_size, GFP_KERNEL); + extra = kzalloc(extra_size, GFP_KERNEL); if (!extra) return -ENOMEM; diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index a3cca0a94346..64f2ae1fdc15 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -101,7 +101,7 @@ resume: err = -EHOSTUNREACH; goto error_nolock; } - skb_dst_set_noref(skb, dst); + skb_dst_set(skb, dst_clone(dst)); x = dst->xfrm; } while (x && !(x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL)); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 2b3ed7ad4933..cbab6e1a8c9c 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1175,9 +1175,8 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, struct flowi *fl, tmpl->mode == XFRM_MODE_BEET) { remote = &tmpl->id.daddr; local = &tmpl->saddr; - family = tmpl->encap_family; - if (xfrm_addr_any(local, family)) { - error = xfrm_get_saddr(net, &tmp, remote, family); + if (xfrm_addr_any(local, tmpl->encap_family)) { + error = xfrm_get_saddr(net, &tmp, remote, tmpl->encap_family); if (error) goto fail; local = &tmp; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 5208b12fbfb4..eb96ce52f178 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -656,15 +656,23 @@ void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si) EXPORT_SYMBOL(xfrm_sad_getinfo); static int -xfrm_init_tempsel(struct xfrm_state *x, struct flowi *fl, - struct xfrm_tmpl *tmpl, - xfrm_address_t *daddr, xfrm_address_t *saddr, - unsigned short family) +xfrm_init_tempstate(struct xfrm_state *x, struct flowi *fl, + struct xfrm_tmpl *tmpl, + xfrm_address_t *daddr, xfrm_address_t *saddr, + unsigned short family) { struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); if (!afinfo) return -1; - afinfo->init_tempsel(x, fl, tmpl, daddr, saddr); + afinfo->init_tempsel(&x->sel, fl); + + if (family != tmpl->encap_family) { + xfrm_state_put_afinfo(afinfo); + afinfo = xfrm_state_get_afinfo(tmpl->encap_family); + if (!afinfo) + return -1; + } + afinfo->init_temprop(x, tmpl, daddr, saddr); xfrm_state_put_afinfo(afinfo); return 0; } @@ -790,37 +798,38 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, int error = 0; struct xfrm_state *best = NULL; u32 mark = pol->mark.v & pol->mark.m; + unsigned short encap_family = tmpl->encap_family; to_put = NULL; spin_lock_bh(&xfrm_state_lock); - h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, family); + h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family); hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) { - if (x->props.family == family && + if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && !(x->props.flags & XFRM_STATE_WILDRECV) && - xfrm_state_addr_check(x, daddr, saddr, family) && + xfrm_state_addr_check(x, daddr, saddr, encap_family) && tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) - xfrm_state_look_at(pol, x, fl, family, daddr, saddr, + xfrm_state_look_at(pol, x, fl, encap_family, daddr, saddr, &best, &acquire_in_progress, &error); } if (best) goto found; - h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, family); + h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, encap_family); hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h_wildcard, bydst) { - if (x->props.family == family && + if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && !(x->props.flags & XFRM_STATE_WILDRECV) && - xfrm_state_addr_check(x, daddr, saddr, family) && + xfrm_state_addr_check(x, daddr, saddr, encap_family) && tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) - xfrm_state_look_at(pol, x, fl, family, daddr, saddr, + xfrm_state_look_at(pol, x, fl, encap_family, daddr, saddr, &best, &acquire_in_progress, &error); } @@ -829,7 +838,7 @@ found: if (!x && !error && !acquire_in_progress) { if (tmpl->id.spi && (x0 = __xfrm_state_lookup(net, mark, daddr, tmpl->id.spi, - tmpl->id.proto, family)) != NULL) { + tmpl->id.proto, encap_family)) != NULL) { to_put = x0; error = -EEXIST; goto out; @@ -839,9 +848,9 @@ found: error = -ENOMEM; goto out; } - /* Initialize temporary selector matching only + /* Initialize temporary state matching only * to current session. */ - xfrm_init_tempsel(x, fl, tmpl, daddr, saddr, family); + xfrm_init_tempstate(x, fl, tmpl, daddr, saddr, family); memcpy(&x->mark, &pol->mark, sizeof(x->mark)); error = security_xfrm_state_alloc_acquire(x, pol->security, fl->secid); @@ -856,10 +865,10 @@ found: x->km.state = XFRM_STATE_ACQ; list_add(&x->km.all, &net->xfrm.state_all); hlist_add_head(&x->bydst, net->xfrm.state_bydst+h); - h = xfrm_src_hash(net, daddr, saddr, family); + h = xfrm_src_hash(net, daddr, saddr, encap_family); hlist_add_head(&x->bysrc, net->xfrm.state_bysrc+h); if (x->id.spi) { - h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, family); + h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, encap_family); hlist_add_head(&x->byspi, net->xfrm.state_byspi+h); } x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; |