From bafa6d9d89072c1a18853afe9ee5de05c491c13a Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Fri, 7 Sep 2012 00:45:29 +0000 Subject: ipv4/route: arg delay is useless in rt_cache_flush() Since route cache deletion (89aef8921bfbac22f), delay is no more used. Remove it. Signed-off-by: Nicolas Dichtel Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/arp.c | 2 +- net/ipv4/devinet.c | 6 +++--- net/ipv4/fib_frontend.c | 20 ++++++++++---------- net/ipv4/fib_rules.c | 2 +- net/ipv4/fib_trie.c | 6 +++--- net/ipv4/route.c | 19 +++---------------- 6 files changed, 21 insertions(+), 34 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 77e87aff419a..47800459e4cb 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1225,7 +1225,7 @@ static int arp_netdev_event(struct notifier_block *this, unsigned long event, switch (event) { case NETDEV_CHANGEADDR: neigh_changeaddr(&arp_tbl, dev); - rt_cache_flush(dev_net(dev), 0); + rt_cache_flush(dev_net(dev)); break; default: break; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 44bf82e3aef7..9b55b6f5a585 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1503,7 +1503,7 @@ static int devinet_conf_proc(ctl_table *ctl, int write, if (i == IPV4_DEVCONF_ACCEPT_LOCAL - 1 || i == IPV4_DEVCONF_ROUTE_LOCALNET - 1) if ((new_value == 0) && (old_value != 0)) - rt_cache_flush(net, 0); + rt_cache_flush(net); } return ret; @@ -1537,7 +1537,7 @@ static int devinet_sysctl_forward(ctl_table *ctl, int write, dev_disable_lro(idev->dev); } rtnl_unlock(); - rt_cache_flush(net, 0); + rt_cache_flush(net); } } @@ -1554,7 +1554,7 @@ static int ipv4_doint_and_flush(ctl_table *ctl, int write, struct net *net = ctl->extra2; if (write && *valp != val) - rt_cache_flush(net, 0); + rt_cache_flush(net); return ret; } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index c43ae3fba792..8e2b475da9fa 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -148,7 +148,7 @@ static void fib_flush(struct net *net) } if (flushed) - rt_cache_flush(net, -1); + rt_cache_flush(net); } /* @@ -999,11 +999,11 @@ static void nl_fib_lookup_exit(struct net *net) net->ipv4.fibnl = NULL; } -static void fib_disable_ip(struct net_device *dev, int force, int delay) +static void fib_disable_ip(struct net_device *dev, int force) { if (fib_sync_down_dev(dev, force)) fib_flush(dev_net(dev)); - rt_cache_flush(dev_net(dev), delay); + rt_cache_flush(dev_net(dev)); arp_ifdown(dev); } @@ -1020,7 +1020,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, fib_sync_up(dev); #endif atomic_inc(&net->ipv4.dev_addr_genid); - rt_cache_flush(dev_net(dev), -1); + rt_cache_flush(dev_net(dev)); break; case NETDEV_DOWN: fib_del_ifaddr(ifa, NULL); @@ -1029,9 +1029,9 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, /* Last address was deleted from this interface. * Disable IP. */ - fib_disable_ip(dev, 1, 0); + fib_disable_ip(dev, 1); } else { - rt_cache_flush(dev_net(dev), -1); + rt_cache_flush(dev_net(dev)); } break; } @@ -1045,7 +1045,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo struct net *net = dev_net(dev); if (event == NETDEV_UNREGISTER) { - fib_disable_ip(dev, 2, -1); + fib_disable_ip(dev, 2); rt_flush_dev(dev); return NOTIFY_DONE; } @@ -1062,14 +1062,14 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo fib_sync_up(dev); #endif atomic_inc(&net->ipv4.dev_addr_genid); - rt_cache_flush(dev_net(dev), -1); + rt_cache_flush(dev_net(dev)); break; case NETDEV_DOWN: - fib_disable_ip(dev, 0, 0); + fib_disable_ip(dev, 0); break; case NETDEV_CHANGEMTU: case NETDEV_CHANGE: - rt_cache_flush(dev_net(dev), 0); + rt_cache_flush(dev_net(dev)); break; case NETDEV_UNREGISTER_BATCH: break; diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index a83d74e498d2..274309d3aded 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -259,7 +259,7 @@ static size_t fib4_rule_nlmsg_payload(struct fib_rule *rule) static void fib4_rule_flush_cache(struct fib_rules_ops *ops) { - rt_cache_flush(ops->fro_net, -1); + rt_cache_flush(ops->fro_net); } static const struct fib_rules_ops __net_initdata fib4_rules_ops_template = { diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 57bd978483e1..d1b93595b4a7 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1286,7 +1286,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) fib_release_info(fi_drop); if (state & FA_S_ACCESSED) - rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); + rt_cache_flush(cfg->fc_nlinfo.nl_net); rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, &cfg->fc_nlinfo, NLM_F_REPLACE); @@ -1333,7 +1333,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) list_add_tail_rcu(&new_fa->fa_list, (fa ? &fa->fa_list : fa_head)); - rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); + rt_cache_flush(cfg->fc_nlinfo.nl_net); rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, &cfg->fc_nlinfo, 0); succeeded: @@ -1708,7 +1708,7 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) trie_leaf_remove(t, l); if (fa->fa_state & FA_S_ACCESSED) - rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); + rt_cache_flush(cfg->fc_nlinfo.nl_net); fib_release_info(fa->fa_info); alias_free_mem_rcu(fa); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 82cf2a722b23..f6436d3b207a 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -461,11 +461,7 @@ static void rt_cache_invalidate(struct net *net) atomic_add(shuffle + 1U, &net->ipv4.rt_genid); } -/* - * delay < 0 : invalidate cache (fast : entries will be deleted later) - * delay >= 0 : invalidate & flush cache (can be long) - */ -void rt_cache_flush(struct net *net, int delay) +void rt_cache_flush(struct net *net) { rt_cache_invalidate(net); } @@ -2345,7 +2341,7 @@ int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb) void ip_rt_multicast_event(struct in_device *in_dev) { - rt_cache_flush(dev_net(in_dev->dev), 0); + rt_cache_flush(dev_net(in_dev->dev)); } #ifdef CONFIG_SYSCTL @@ -2354,16 +2350,7 @@ static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write, size_t *lenp, loff_t *ppos) { if (write) { - int flush_delay; - ctl_table ctl; - struct net *net; - - memcpy(&ctl, __ctl, sizeof(ctl)); - ctl.data = &flush_delay; - proc_dointvec(&ctl, write, buffer, lenp, ppos); - - net = (struct net *)__ctl->extra1; - rt_cache_flush(net, flush_delay); + rt_cache_flush((struct net *)__ctl->extra1); return 0; } -- cgit v1.2.2 From 2885da72966fcb89f48d554339d347fb02b5ea78 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 7 Sep 2012 22:27:11 +0200 Subject: net: rt_cache_flush() cleanup We dont use jhash anymore since route cache removal, so we can get rid of get_random_bytes() calls for rt_genid changes. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/route.c | 19 ++----------------- 1 file changed, 2 insertions(+), 17 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index f6436d3b207a..be27cfa96e88 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -447,23 +447,9 @@ static inline bool rt_is_expired(const struct rtable *rth) return rth->rt_genid != rt_genid(dev_net(rth->dst.dev)); } -/* - * Perturbation of rt_genid by a small quantity [1..256] - * Using 8 bits of shuffling ensure we can call rt_cache_invalidate() - * many times (2^24) without giving recent rt_genid. - * Jenkins hash is strong enough that litle changes of rt_genid are OK. - */ -static void rt_cache_invalidate(struct net *net) -{ - unsigned char shuffle; - - get_random_bytes(&shuffle, sizeof(shuffle)); - atomic_add(shuffle + 1U, &net->ipv4.rt_genid); -} - void rt_cache_flush(struct net *net) { - rt_cache_invalidate(net); + atomic_inc(&net->ipv4.rt_genid); } static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, @@ -2520,8 +2506,7 @@ static __net_initdata struct pernet_operations sysctl_route_ops = { static __net_init int rt_genid_init(struct net *net) { - get_random_bytes(&net->ipv4.rt_genid, - sizeof(net->ipv4.rt_genid)); + atomic_set(&net->ipv4.rt_genid, 0); get_random_bytes(&net->ipv4.dev_addr_genid, sizeof(net->ipv4.dev_addr_genid)); return 0; -- cgit v1.2.2 From b42664f898c976247f7f609b8bb9c94d7475ca10 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Mon, 10 Sep 2012 22:09:44 +0000 Subject: netns: move net->ipv4.rt_genid to net->rt_genid This commit prepares the use of rt_genid by both IPv4 and IPv6. Initialization is left in IPv4 part. Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- net/ipv4/route.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index be27cfa96e88..fd9af60397b5 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -202,11 +202,6 @@ EXPORT_SYMBOL(ip_tos2prio); static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat); #define RT_CACHE_STAT_INC(field) __this_cpu_inc(rt_cache_stat.field) -static inline int rt_genid(struct net *net) -{ - return atomic_read(&net->ipv4.rt_genid); -} - #ifdef CONFIG_PROC_FS static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos) { @@ -449,7 +444,7 @@ static inline bool rt_is_expired(const struct rtable *rth) void rt_cache_flush(struct net *net) { - atomic_inc(&net->ipv4.rt_genid); + rt_genid_bump(net); } static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, @@ -2506,7 +2501,7 @@ static __net_initdata struct pernet_operations sysctl_route_ops = { static __net_init int rt_genid_init(struct net *net) { - atomic_set(&net->ipv4.rt_genid, 0); + atomic_set(&net->rt_genid, 0); get_random_bytes(&net->ipv4.dev_addr_genid, sizeof(net->ipv4.dev_addr_genid)); return 0; -- cgit v1.2.2 From 1d57f19539c074105791da6384a8ad674bba8037 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 17 Sep 2012 12:51:39 +0000 Subject: tcp: fix regression in urgent data handling Stephan Springl found that commit 1402d366019fed "tcp: introduce tcp_try_coalesce" introduced a regression for rlogin It turns out problem comes from TCP urgent data handling and a change in behavior in input path. rlogin sends two one-byte packets with URG ptr set, and when next data frame is coalesced, we lack sk_data_ready() calls to wakeup consumer. Signed-off-by: Eric Dumazet Reported-by: Stephan Springl Cc: Alexander Duyck Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 6e38c6c23caa..d377f4854cb8 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4661,7 +4661,7 @@ queue_and_out: if (eaten > 0) kfree_skb_partial(skb, fragstolen); - else if (!sock_flag(sk, SOCK_DEAD)) + if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk, 0); return; } @@ -5556,8 +5556,7 @@ no_ack: #endif if (eaten) kfree_skb_partial(skb, fragstolen); - else - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk, 0); return 0; } } -- cgit v1.2.2 From 15c041759bfcd9ab0a4e43f1c16e2644977d0467 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michal=20Kube=C4=8Dek?= Date: Fri, 14 Sep 2012 04:59:52 +0000 Subject: tcp: flush DMA queue before sk_wait_data if rcv_wnd is zero If recv() syscall is called for a TCP socket so that - IOAT DMA is used - MSG_WAITALL flag is used - requested length is bigger than sk_rcvbuf - enough data has already arrived to bring rcv_wnd to zero then when tcp_recvmsg() gets to calling sk_wait_data(), receive window can be still zero while sk_async_wait_queue exhausts enough space to keep it zero. As this queue isn't cleaned until the tcp_service_net_dma() call, sk_wait_data() cannot receive any data and blocks forever. If zero receive window and non-empty sk_async_wait_queue is detected before calling sk_wait_data(), process the queue first. Signed-off-by: Michal Kubecek Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2109ff4a1daf..bf9a8ab29459 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1762,8 +1762,14 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, } #ifdef CONFIG_NET_DMA - if (tp->ucopy.dma_chan) - dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); + if (tp->ucopy.dma_chan) { + if (tp->rcv_wnd == 0 && + !skb_queue_empty(&sk->sk_async_wait_queue)) { + tcp_service_net_dma(sk, true); + tcp_cleanup_rbuf(sk, copied); + } else + dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); + } #endif if (copied >= target) { /* Do not sleep, just process backlog. */ -- cgit v1.2.2 From bc26ccd8fc756749de95606d28314efd0ce5aec3 Mon Sep 17 00:00:00 2001 From: Andrey Vagin Date: Wed, 19 Sep 2012 09:40:00 +0000 Subject: tcp: restore rcv_wscale in a repair mode (v2) rcv_wscale is a symetric parameter with snd_wscale. Both this parameters are set on a connection handshake. Without this value a remote window size can not be interpreted correctly, because a value from a packet should be shifted on rcv_wscale. And one more thing is that wscale_ok should be set too. This patch doesn't break a backward compatibility. If someone uses it in a old scheme, a rcv window will be restored with the same bug (rcv_wscale = 0). v2: Save backward compatibility on big-endian system. Before the first two bytes were snd_wscale and the second two bytes were rcv_wscale. Now snd_wscale is opt_val & 0xFFFF and rcv_wscale >> 16. This approach is independent on byte ordering. Cc: David S. Miller Cc: Alexey Kuznetsov Cc: James Morris Cc: Hideaki YOSHIFUJI Cc: Patrick McHardy CC: Pavel Emelyanov Signed-off-by: Andrew Vagin Acked-by: Pavel Emelyanov Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index bf9a8ab29459..5f6419341821 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2331,10 +2331,17 @@ static int tcp_repair_options_est(struct tcp_sock *tp, tp->rx_opt.mss_clamp = opt.opt_val; break; case TCPOPT_WINDOW: - if (opt.opt_val > 14) - return -EFBIG; + { + u16 snd_wscale = opt.opt_val & 0xFFFF; + u16 rcv_wscale = opt.opt_val >> 16; + + if (snd_wscale > 14 || rcv_wscale > 14) + return -EFBIG; - tp->rx_opt.snd_wscale = opt.opt_val; + tp->rx_opt.snd_wscale = snd_wscale; + tp->rx_opt.rcv_wscale = rcv_wscale; + tp->rx_opt.wscale_ok = 1; + } break; case TCPOPT_SACK_PERM: if (opt.opt_val != 0) -- cgit v1.2.2 From bf5b30b8a4416de04f1ac1196281ddb318669464 Mon Sep 17 00:00:00 2001 From: Zhao Hongjiang Date: Thu, 20 Sep 2012 22:37:25 +0000 Subject: net: change return values from -EACCES to -EPERM Change return value from -EACCES to -EPERM when the permission check fails. Signed-off-by: Zhao Hongjiang Signed-off-by: David S. Miller --- net/ipv4/devinet.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 9b55b6f5a585..e12fad773852 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -725,7 +725,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) break; case SIOCSIFFLAGS: - ret = -EACCES; + ret = -EPERM; if (!capable(CAP_NET_ADMIN)) goto out; break; @@ -733,7 +733,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) case SIOCSIFBRDADDR: /* Set the broadcast address */ case SIOCSIFDSTADDR: /* Set the destination address */ case SIOCSIFNETMASK: /* Set the netmask for the interface */ - ret = -EACCES; + ret = -EPERM; if (!capable(CAP_NET_ADMIN)) goto out; ret = -EINVAL; -- cgit v1.2.2 From ab43ed8b7490cb387782423ecf74aeee7237e591 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 22 Sep 2012 00:08:29 +0000 Subject: ipv4: raw: fix icmp_filter() icmp_filter() should not modify its input, or else its caller would need to recompute ip_hdr() if skb->head is reallocated. Use skb_header_pointer() instead of pskb_may_pull() and change the prototype to make clear both sk and skb are const. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/raw.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index ff0f071969ea..d23c6571ba1c 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -131,18 +131,20 @@ found: * 0 - deliver * 1 - block */ -static __inline__ int icmp_filter(struct sock *sk, struct sk_buff *skb) +static int icmp_filter(const struct sock *sk, const struct sk_buff *skb) { - int type; + struct icmphdr _hdr; + const struct icmphdr *hdr; - if (!pskb_may_pull(skb, sizeof(struct icmphdr))) + hdr = skb_header_pointer(skb, skb_transport_offset(skb), + sizeof(_hdr), &_hdr); + if (!hdr) return 1; - type = icmp_hdr(skb)->type; - if (type < 32) { + if (hdr->type < 32) { __u32 data = raw_sk(sk)->filter.data; - return ((1 << type) & data) != 0; + return ((1U << hdr->type) & data) != 0; } /* Do not block unknown ICMP types */ -- cgit v1.2.2 From bc9259a8bae9e814fc1f775a1b3effa13e6ad330 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 27 Sep 2012 04:11:00 +0000 Subject: inetpeer: fix token initialization When jiffies wraps around (for example, 5 minutes after the boot, see INITIAL_JIFFIES) and peer has just been created, now - peer->rate_last can be < XRLIM_BURST_FACTOR * timeout, so token is not set to the maximum value, thus some icmp packets can be unexpectedly dropped. Fix this case by initializing last_rate to 60 seconds in the past. Signed-off-by: Nicolas Dichtel Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/inetpeer.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index e1e0a4e8fd34..c7527f6b9ad9 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -510,7 +510,10 @@ relookup: secure_ipv6_id(daddr->addr.a6)); p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; p->rate_tokens = 0; - p->rate_last = 0; + /* 60*HZ is arbitrary, but chosen enough high so that the first + * calculation of tokens is at its maximum. + */ + p->rate_last = jiffies - 60*HZ; INIT_LIST_HEAD(&p->gc_list); /* Link the node. */ -- cgit v1.2.2