diff options
author | Ingo Molnar <mingo@elte.hu> | 2010-09-15 10:27:31 +0200 |
---|---|---|
committer | Ingo Molnar <mingo@elte.hu> | 2010-09-15 10:27:31 +0200 |
commit | 3aabae7d9dfaed60effe93662f02c19bafc18537 (patch) | |
tree | af94cdd69add07601d9f3f5988dfc1dc255e3886 /net | |
parent | 79e406d7b00ab2b261ae32a59f266fd3b7af6f29 (diff) | |
parent | 57c072c7113f54f9512624d6c665db6184448782 (diff) |
Merge branch 'tip/perf/core' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into perf/core
Diffstat (limited to 'net')
36 files changed, 293 insertions, 244 deletions
diff --git a/net/9p/client.c b/net/9p/client.c index dc6f2f26d02..9eb72505308 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/ax25/ax25_ds_timer.c b/net/ax25/ax25_ds_timer.c index 2ce79df0068..c7d81436213 100644 --- a/net/ax25/ax25_ds_timer.c +++ b/net/ax25/ax25_ds_timer.c @@ -112,8 +112,8 @@ void ax25_ds_heartbeat_expiry(ax25_cb *ax25) if (sk) { sock_hold(sk); ax25_destroy_socket(ax25); - sock_put(sk); bh_unlock_sock(sk); + sock_put(sk); } else ax25_destroy_socket(ax25); return; diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 2c911c0759c..137f23259a9 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -162,8 +162,8 @@ static inline struct nf_bridge_info *nf_bridge_unshare(struct sk_buff *skb) if (tmp) { memcpy(tmp, nf_bridge, sizeof(struct nf_bridge_info)); atomic_set(&tmp->use, 1); - nf_bridge_put(nf_bridge); } + nf_bridge_put(nf_bridge); nf_bridge = tmp; } return nf_bridge; @@ -761,9 +761,11 @@ static int br_nf_dev_queue_xmit(struct sk_buff *skb) { if (skb->nfct != NULL && skb->protocol == htons(ETH_P_IP) && skb->len + nf_bridge_mtu_reduction(skb) > skb->dev->mtu && - !skb_is_gso(skb)) + !skb_is_gso(skb)) { + /* BUG: Should really parse the IP options here. */ + memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); return ip_fragment(skb, br_dev_queue_push_xmit); - else + } else return br_dev_queue_push_xmit(skb); } #else diff --git a/net/caif/cfrfml.c b/net/caif/cfrfml.c index eb1602022ac..9a699242d10 100644 --- a/net/caif/cfrfml.c +++ b/net/caif/cfrfml.c @@ -7,7 +7,7 @@ #include <linux/stddef.h> #include <linux/spinlock.h> #include <linux/slab.h> -#include <linux/unaligned/le_byteshift.h> +#include <asm/unaligned.h> #include <net/caif/caif_layer.h> #include <net/caif/cfsrvl.h> #include <net/caif/cfpkt.h> diff --git a/net/core/dev.c b/net/core/dev.c index 2308cce4804..561ee3a8652 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2062,16 +2062,16 @@ 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); diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 9fbe7f7429b..6743146e4d6 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -232,7 +232,7 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, est->last_packets = bstats->packets; est->avpps = rate_est->pps<<10; - spin_lock(&est_tree_lock); + spin_lock_bh(&est_tree_lock); if (!elist[idx].timer.function) { INIT_LIST_HEAD(&elist[idx].list); setup_timer(&elist[idx].timer, est_timer, idx); @@ -243,7 +243,7 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, list_add_rcu(&est->list, &elist[idx].list); gen_add_node(est); - spin_unlock(&est_tree_lock); + spin_unlock_bh(&est_tree_lock); return 0; } @@ -270,7 +270,7 @@ void gen_kill_estimator(struct gnet_stats_basic_packed *bstats, { struct gen_estimator *e; - spin_lock(&est_tree_lock); + spin_lock_bh(&est_tree_lock); while ((e = gen_find_node(bstats, rate_est))) { rb_erase(&e->node, &est_root); @@ -281,7 +281,7 @@ void gen_kill_estimator(struct gnet_stats_basic_packed *bstats, list_del_rcu(&e->list); call_rcu(&e->e_rcu, __gen_kill_estimator); } - spin_unlock(&est_tree_lock); + spin_unlock_bh(&est_tree_lock); } EXPORT_SYMBOL(gen_kill_estimator); @@ -320,9 +320,9 @@ bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats, ASSERT_RTNL(); - spin_lock(&est_tree_lock); + spin_lock_bh(&est_tree_lock); res = gen_find_node(bstats, rate_est) != NULL; - spin_unlock(&est_tree_lock); + spin_unlock_bh(&est_tree_lock); return res; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 12e61e351d0..56ba3c4e476 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2574,6 +2574,10 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features) __copy_skb_header(nskb, skb); nskb->mac_len = skb->mac_len; + /* nskb and skb might have different headroom */ + if (nskb->ip_summed == CHECKSUM_PARTIAL) + nskb->csum_start += skb_headroom(nskb) - headroom; + skb_reset_mac_header(nskb); skb_set_network_header(nskb, skb->mac_len); nskb->transport_header = (nskb->network_header + @@ -2704,7 +2708,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) return -E2BIG; headroom = skb_headroom(p); - nskb = netdev_alloc_skb(p->dev, headroom + skb_gro_offset(p)); + nskb = alloc_skb(headroom + skb_gro_offset(p), GFP_ATOMIC); if (unlikely(!nskb)) return -ENOMEM; diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 7c3a7d19124..571f8950ed0 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -46,7 +46,7 @@ config IP_ADVANCED_ROUTER rp_filter on use: echo 1 > /proc/sys/net/ipv4/conf/<device>/rp_filter - and + or echo 1 > /proc/sys/net/ipv4/conf/all/rp_filter Note that some distributions enable it in startup scripts. diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index f0550941df7..721a8a37b45 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 a4396891835..7d02a9f999f 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 79d057a939b..4a8e370862b 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/route.c b/net/ipv4/route.c index 3f56b6e6c6a..6298f75d5e9 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -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 176e11aaea7..3fb1428e526 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -451,7 +451,8 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) mask |= POLLOUT | POLLWRNORM; } - } + } else + mask |= POLLOUT | POLLWRNORM; if (tp->urg_data & TCP_URG_VALID) mask |= POLLPRI; @@ -2011,11 +2012,8 @@ adjudge_to_death: } } if (sk->sk_state != TCP_CLOSE) { - int orphan_count = percpu_counter_read_positive( - sk->sk_prot->orphan_count); - sk_mem_reclaim(sk); - if (tcp_too_many_orphans(sk, orphan_count)) { + if (tcp_too_many_orphans(sk, 0)) { if (net_ratelimit()) printk(KERN_INFO "TCP: too many of orphaned " "sockets\n"); @@ -3212,7 +3210,7 @@ void __init tcp_init(void) { struct sk_buff *skb = NULL; unsigned long nr_pages, limit; - int order, i, max_share; + int i, max_share, cnt; unsigned long jiffy = jiffies; BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb)); @@ -3261,22 +3259,12 @@ void __init tcp_init(void) INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain); } - /* Try to be a bit smarter and adjust defaults depending - * on available memory. - */ - for (order = 0; ((1 << order) << PAGE_SHIFT) < - (tcp_hashinfo.bhash_size * sizeof(struct inet_bind_hashbucket)); - order++) - ; - if (order >= 4) { - tcp_death_row.sysctl_max_tw_buckets = 180000; - sysctl_tcp_max_orphans = 4096 << (order - 4); - sysctl_max_syn_backlog = 1024; - } else if (order < 3) { - tcp_death_row.sysctl_max_tw_buckets >>= (3 - order); - sysctl_tcp_max_orphans >>= (3 - order); - sysctl_max_syn_backlog = 128; - } + + cnt = tcp_hashinfo.ehash_mask + 1; + + tcp_death_row.sysctl_max_tw_buckets = cnt / 2; + sysctl_tcp_max_orphans = cnt / 2; + sysctl_max_syn_backlog = max(128, cnt / 256); /* Set the pressure threshold to be a fraction of global memory that * is up to 1/2 at 256 MB, decreasing toward zero with the amount of diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 0ec9bd0ae94..850c737e08e 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -196,10 +196,10 @@ void tcp_get_allowed_congestion_control(char *buf, size_t maxlen) int tcp_set_allowed_congestion_control(char *val) { struct tcp_congestion_ops *ca; - char *clone, *name; + char *saved_clone, *clone, *name; int ret = 0; - clone = kstrdup(val, GFP_USER); + saved_clone = clone = kstrdup(val, GFP_USER); if (!clone) return -ENOMEM; @@ -226,6 +226,7 @@ int tcp_set_allowed_congestion_control(char *val) } out: spin_unlock(&tcp_cong_list_lock); + kfree(saved_clone); return ret; } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 808bb920c9f..c35b469e851 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -66,18 +66,18 @@ static void tcp_write_err(struct sock *sk) static int tcp_out_of_resources(struct sock *sk, int do_reset) { struct tcp_sock *tp = tcp_sk(sk); - int orphans = percpu_counter_read_positive(&tcp_orphan_count); + int shift = 0; /* If peer does not open window for long time, or did not transmit * anything for long time, penalize it. */ if ((s32)(tcp_time_stamp - tp->lsndtime) > 2*TCP_RTO_MAX || !do_reset) - orphans <<= 1; + shift++; /* If some dubious ICMP arrived, penalize even more. */ if (sk->sk_err_soft) - orphans <<= 1; + shift++; - if (tcp_too_many_orphans(sk, orphans)) { + if (tcp_too_many_orphans(sk, shift)) { if (net_ratelimit()) printk(KERN_INFO "Out of socket memory\n"); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 32e0bef60d0..fb23c2e63b5 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/ipv6/datagram.c b/net/ipv6/datagram.c index 7d929a22cbc..ef371aa01ac 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/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 13ef5bc05cf..578f3c1a16d 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 545c4141b75..64cfef1b0a4 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/udp.c b/net/ipv6/udp.c index 1dd1affdead..5acb3560ff1 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/irda/af_irda.c b/net/irda/af_irda.c index 79986a674f6..fd55b5135de 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -824,8 +824,8 @@ static int irda_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) err = irda_open_tsap(self, addr->sir_lsap_sel, addr->sir_name); if (err < 0) { - kfree(self->ias_obj->name); - kfree(self->ias_obj); + irias_delete_object(self->ias_obj); + self->ias_obj = NULL; goto out; } diff --git a/net/irda/irlan/irlan_common.c b/net/irda/irlan/irlan_common.c index a788f9e9427..6130f9d9dbe 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/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 58c6c4cda73..1ae697681bc 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -132,7 +132,7 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, printk("\n"); } - if (data_len < ETH_HLEN) + if (!pskb_may_pull(skb, sizeof(ETH_HLEN))) goto error; secpath_reset(skb); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 798a91b100c..ded5c3843e0 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -732,6 +732,12 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) rtnl_unlock(); + /* + * Now all work items will be gone, but the + * timer might still be armed, so delete it + */ + del_timer_sync(&local->work_timer); + cancel_work_sync(&local->reconfig_filter); ieee80211_clear_tx_pending(local); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 4f8ddba4801..4c2f89df5cc 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 f228a17ec64..7e9af5b76d9 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -45,6 +45,7 @@ #include <linux/netfilter.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_expect.h> +#include <net/netfilter/nf_nat.h> #include <net/netfilter/nf_nat_helper.h> #include <linux/gfp.h> #include <net/protocol.h> @@ -359,7 +360,7 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, buf_len = strlen(buf); ct = nf_ct_get(skb, &ctinfo); - if (ct && !nf_ct_is_untracked(ct)) { + if (ct && !nf_ct_is_untracked(ct) && nfct_nat(ct)) { /* If mangling fails this function will return 0 * which will cause the packet to be dropped. * Mangling can only fail under memory pressure, @@ -409,7 +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, @@ -496,11 +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 21e1a5e9b9d..49df6bea6a2 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/netlink/af_netlink.c b/net/netlink/af_netlink.c index 980fe4ad001..cd96ed3ccee 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2102,6 +2102,26 @@ static void __net_exit netlink_net_exit(struct net *net) #endif } +static void __init netlink_add_usersock_entry(void) +{ + unsigned long *listeners; + int groups = 32; + + listeners = kzalloc(NLGRPSZ(groups) + sizeof(struct listeners_rcu_head), + GFP_KERNEL); + if (!listeners) + panic("netlink_add_usersock_entry: Cannot allocate listneres\n"); + + netlink_table_grab(); + + nl_table[NETLINK_USERSOCK].groups = groups; + nl_table[NETLINK_USERSOCK].listeners = listeners; + nl_table[NETLINK_USERSOCK].module = THIS_MODULE; + nl_table[NETLINK_USERSOCK].registered = 1; + + netlink_table_ungrab(); +} + static struct pernet_operations __net_initdata netlink_net_ops = { .init = netlink_net_init, .exit = netlink_net_exit, @@ -2150,6 +2170,8 @@ static int __init netlink_proto_init(void) hash->rehash_time = jiffies; } + netlink_add_usersock_entry(); + sock_register(&netlink_family_ops); register_pernet_subsys(&netlink_net_ops); /* The netlink device handler may be needed early. */ diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 537a48732e9..7ebf7439b47 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -350,22 +350,19 @@ tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_police *police = a->priv; - struct tc_police opt; - - opt.index = police->tcf_index; - opt.action = police->tcf_action; - opt.mtu = police->tcfp_mtu; - opt.burst = police->tcfp_burst; - opt.refcnt = police->tcf_refcnt - ref; - opt.bindcnt = police->tcf_bindcnt - bind; + struct tc_police opt = { + .index = police->tcf_index, + .action = police->tcf_action, + .mtu = police->tcfp_mtu, + .burst = police->tcfp_burst, + .refcnt = police->tcf_refcnt - ref, + .bindcnt = police->tcf_bindcnt - bind, + }; + if (police->tcfp_R_tab) opt.rate = police->tcfp_R_tab->rate; - else - memset(&opt.rate, 0, sizeof(opt.rate)); if (police->tcfp_P_tab) opt.peakrate = police->tcfp_P_tab->rate; - else - memset(&opt.peakrate, 0, sizeof(opt.peakrate)); NLA_PUT(skb, TCA_POLICE_TBF, sizeof(opt), &opt); if (police->tcfp_result) NLA_PUT_U32(skb, TCA_POLICE_RESULT, police->tcfp_result); diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index abd904be428..47496098d35 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -761,8 +761,8 @@ init_vf(struct hfsc_class *cl, unsigned int len) if (f != cl->cl_f) { cl->cl_f = f; cftree_update(cl); - update_cfmin(cl->cl_parent); } + update_cfmin(cl->cl_parent); } } diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 24b2cd55563..d344dc481cc 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/unix/af_unix.c b/net/unix/af_unix.c index 4414a18c63b..0b39b2451ea 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/core.c b/net/wireless/core.c index 541e2fff5e9..d6d046b9f6f 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -475,12 +475,10 @@ int wiphy_register(struct wiphy *wiphy) mutex_lock(&cfg80211_mutex); res = device_add(&rdev->wiphy.dev); - if (res) - goto out_unlock; - - res = rfkill_register(rdev->rfkill); - if (res) - goto out_rm_dev; + if (res) { + mutex_unlock(&cfg80211_mutex); + return res; + } /* set up regulatory info */ wiphy_update_regulatory(wiphy, NL80211_REGDOM_SET_BY_CORE); @@ -509,13 +507,18 @@ int wiphy_register(struct wiphy *wiphy) cfg80211_debugfs_rdev_add(rdev); mutex_unlock(&cfg80211_mutex); + /* + * due to a locking dependency this has to be outside of the + * cfg80211_mutex lock + */ + res = rfkill_register(rdev->rfkill); + if (res) + goto out_rm_dev; + return 0; out_rm_dev: device_del(&rdev->wiphy.dev); - -out_unlock: - mutex_unlock(&cfg80211_mutex); return res; } EXPORT_SYMBOL(wiphy_register); diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index bb5e0a5ecfa..7e5c3a45f81 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -1420,6 +1420,9 @@ int cfg80211_wext_giwessid(struct net_device *dev, { struct wireless_dev *wdev = dev->ieee80211_ptr; + data->flags = 0; + data->length = 0; + switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: return cfg80211_ibss_wext_giwessid(dev, info, data, ssid); diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index 0ef17bc42ba..8f5116f5af1 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -782,6 +782,22 @@ static int ioctl_standard_iw_point(struct iw_point *iwp, unsigned int cmd, } } + if (IW_IS_GET(cmd) && !(descr->flags & IW_DESCR_FLAG_NOMAX)) { + /* + * If this is a GET, but not NOMAX, it means that the extra + * data is not bounded by userspace, but by max_tokens. Thus + * set the length to max_tokens. This matches the extra data + * allocation. + * The driver should fill it with the number of tokens it + * provided, and it may check iwp->length rather than having + * knowledge of max_tokens. If the driver doesn't change the + * iwp->length, this ioctl just copies back max_token tokens + * filled with zeroes. Hopefully the driver isn't claiming + * them to be valid data. + */ + iwp->length = descr->max_tokens; + } + err = handler(dev, info, (union iwreq_data *) iwp, extra); iwp->length += essid_compat; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index b14ed4b1f27..8bae6b22c84 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1801,7 +1801,7 @@ static int xfrm_add_sa_expire(struct sk_buff *skb, struct nlmsghdr *nlh, struct xfrm_user_expire *ue = nlmsg_data(nlh); struct xfrm_usersa_info *p = &ue->state; struct xfrm_mark m; - u32 mark = xfrm_mark_get(attrs, &m);; + u32 mark = xfrm_mark_get(attrs, &m); x = xfrm_state_lookup(net, mark, &p->id.daddr, p->id.spi, p->id.proto, p->family); |