From cbbd42eb61241fcd721f3b02bcb612894e2f02e6 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Sat, 22 Oct 2011 21:58:20 +0000 Subject: ipv4: fix ipsec forward performance regression [ Upstream commit b73233960a59ee66e09d642f13d0592b13651e94 ] There is bug in commit 5e2b61f(ipv4: Remove flowi from struct rtable). It makes xfrm4_fill_dst() modify wrong data structure. Signed-off-by: Zheng Yan Reported-by: Kim Phillips Acked-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/xfrm4_policy.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 981e43e..581fe0a 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -79,13 +79,13 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, struct rtable *rt = (struct rtable *)xdst->route; const struct flowi4 *fl4 = &fl->u.ip4; - rt->rt_key_dst = fl4->daddr; - rt->rt_key_src = fl4->saddr; - rt->rt_key_tos = fl4->flowi4_tos; - rt->rt_route_iif = fl4->flowi4_iif; - rt->rt_iif = fl4->flowi4_iif; - rt->rt_oif = fl4->flowi4_oif; - rt->rt_mark = fl4->flowi4_mark; + xdst->u.rt.rt_key_dst = fl4->daddr; + xdst->u.rt.rt_key_src = fl4->saddr; + xdst->u.rt.rt_key_tos = fl4->flowi4_tos; + xdst->u.rt.rt_route_iif = fl4->flowi4_iif; + xdst->u.rt.rt_iif = fl4->flowi4_iif; + xdst->u.rt.rt_oif = fl4->flowi4_oif; + xdst->u.rt.rt_mark = fl4->flowi4_mark; xdst->u.dst.dev = dev; dev_hold(dev); -- cgit v1.1 From 37c88f5fe7f287a945949e6f4570700c210ebe0f Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Thu, 29 Sep 2011 17:10:10 +0000 Subject: tcp: properly handle md5sig_pool references [ Upstream commit 260fcbeb1ae9e768a44c9925338fbacb0d7e5ba9 ] tcp_v4_clear_md5_list() assumes that multiple tcp md5sig peers only hold one reference to md5sig_pool. but tcp_v4_md5_do_add() increases use count of md5sig_pool for each peer. This patch makes tcp_v4_md5_do_add() only increases use count for the first tcp md5sig peer. Signed-off-by: Zheng Yan Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_ipv4.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index b3e6956..69790aa 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -909,18 +909,21 @@ int tcp_v4_md5_do_add(struct sock *sk, __be32 addr, } sk_nocaps_add(sk, NETIF_F_GSO_MASK); } - if (tcp_alloc_md5sig_pool(sk) == NULL) { + + md5sig = tp->md5sig_info; + if (md5sig->entries4 == 0 && + tcp_alloc_md5sig_pool(sk) == NULL) { kfree(newkey); return -ENOMEM; } - md5sig = tp->md5sig_info; if (md5sig->alloced4 == md5sig->entries4) { keys = kmalloc((sizeof(*keys) * (md5sig->entries4 + 1)), GFP_ATOMIC); if (!keys) { kfree(newkey); - tcp_free_md5sig_pool(); + if (md5sig->entries4 == 0) + tcp_free_md5sig_pool(); return -ENOMEM; } @@ -964,6 +967,7 @@ int tcp_v4_md5_do_del(struct sock *sk, __be32 addr) kfree(tp->md5sig_info->keys4); tp->md5sig_info->keys4 = NULL; tp->md5sig_info->alloced4 = 0; + tcp_free_md5sig_pool(); } else if (tp->md5sig_info->entries4 != i) { /* Need to do some manipulation */ memmove(&tp->md5sig_info->keys4[i], @@ -971,7 +975,6 @@ int tcp_v4_md5_do_del(struct sock *sk, __be32 addr) (tp->md5sig_info->entries4 - i) * sizeof(struct tcp4_md5sig_key)); } - tcp_free_md5sig_pool(); return 0; } } -- cgit v1.1 From b00654416d4baccf2269ec888e55d6df069cd36f Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Sun, 2 Oct 2011 04:21:50 +0000 Subject: tcp: properly update lost_cnt_hint during shifting [ Upstream commit 1e5289e121372a3494402b1b131b41bfe1cf9b7f ] lost_skb_hint is used by tcp_mark_head_lost() to mark the first unhandled skb. lost_cnt_hint is the number of packets or sacked packets before the lost_skb_hint; When shifting a skb that is before the lost_skb_hint, if tcp_is_fack() is ture, the skb has already been counted in the lost_cnt_hint; if tcp_is_fack() is false, tcp_sacktag_one() will increase the lost_cnt_hint. So tcp_shifted_skb() does not need to adjust the lost_cnt_hint by itself. When shifting a skb that is equal to lost_skb_hint, the shifted packets will not be counted by tcp_mark_head_lost(). So tcp_shifted_skb() should adjust the lost_cnt_hint even tcp_is_fack(tp) is true. Signed-off-by: Zheng Yan Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_input.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b6771f9..c68040f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1380,9 +1380,7 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, BUG_ON(!pcount); - /* Tweak before seqno plays */ - if (!tcp_is_fack(tp) && tcp_is_sack(tp) && tp->lost_skb_hint && - !before(TCP_SKB_CB(tp->lost_skb_hint)->seq, TCP_SKB_CB(skb)->seq)) + if (skb == tp->lost_skb_hint) tp->lost_cnt_hint += pcount; TCP_SKB_CB(prev)->end_seq += shifted; -- cgit v1.1 From 919130981e72465867038ac1dec823dbd7a87eb5 Mon Sep 17 00:00:00 2001 From: Ted Feng Date: Thu, 8 Dec 2011 00:46:21 +0000 Subject: ipip, sit: copy parms.name after register_netdevice commit 72b36015ba43a3cca5303f5534d2c3e1899eae29 upstream. Same fix as 731abb9cb2 for ipip and sit tunnel. Commit 1c5cae815d removed an explicit call to dev_alloc_name in ipip_tunnel_locate and ipip6_tunnel_locate, because register_netdevice will now create a valid name, however the tunnel keeps a copy of the name in the private parms structure. Fix this by copying the name back after register_netdevice has successfully returned. This shows up if you do a simple tunnel add, followed by a tunnel show: $ sudo ip tunnel add mode ipip remote 10.2.20.211 $ ip tunnel tunl0: ip/ip remote any local any ttl inherit nopmtudisc tunl%d: ip/ip remote 10.2.20.211 local any ttl inherit $ sudo ip tunnel add mode sit remote 10.2.20.212 $ ip tunnel sit0: ipv6/ip remote any local any ttl 64 nopmtudisc 6rd-prefix 2002::/16 sit%d: ioctl 89f8 failed: No such device sit%d: ipv6/ip remote 10.2.20.212 local any ttl inherit Signed-off-by: Ted Feng Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/ipip.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 378b20b..6f06f7f 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -285,6 +285,8 @@ static struct ip_tunnel * ipip_tunnel_locate(struct net *net, if (register_netdevice(dev) < 0) goto failed_free; + strcpy(nt->parms.name, dev->name); + dev_hold(dev); ipip_tunnel_link(ipn, nt); return nt; @@ -759,7 +761,6 @@ static int ipip_tunnel_init(struct net_device *dev) struct ip_tunnel *tunnel = netdev_priv(dev); tunnel->dev = dev; - strcpy(tunnel->parms.name, dev->name); memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4); memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); @@ -825,6 +826,7 @@ static void ipip_destroy_tunnels(struct ipip_net *ipn, struct list_head *head) static int __net_init ipip_init_net(struct net *net) { struct ipip_net *ipn = net_generic(net, ipip_net_id); + struct ip_tunnel *t; int err; ipn->tunnels[0] = ipn->tunnels_wc; @@ -848,6 +850,9 @@ static int __net_init ipip_init_net(struct net *net) if ((err = register_netdev(ipn->fb_tunnel_dev))) goto err_reg_dev; + t = netdev_priv(ipn->fb_tunnel_dev); + + strcpy(t->parms.name, ipn->fb_tunnel_dev->name); return 0; err_reg_dev: -- cgit v1.1 From 9ec14c04ec6be93ff397adf250bc91ee77742bfb Mon Sep 17 00:00:00 2001 From: Gerlando Falauto Date: Mon, 19 Dec 2011 22:58:04 +0000 Subject: net: have ipconfig not wait if no dev is available [ Upstream commit cd7816d14953c8af910af5bb92f488b0b277e29d ] previous commit 3fb72f1e6e6165c5f495e8dc11c5bbd14c73385c makes IP-Config wait for carrier on at least one network device. Before waiting (predefined value 120s), check that at least one device was successfully brought up. Otherwise (e.g. buggy bootloader which does not set the MAC address) there is no point in waiting for carrier. Cc: Micha Nelissen Cc: Holger Brunck Signed-off-by: Gerlando Falauto Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/ipconfig.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index ab7e554..7fbcaba 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -252,6 +252,10 @@ static int __init ic_open_devs(void) } } + /* no point in waiting if we could not bring up at least one device */ + if (!ic_first_dev) + goto have_carrier; + /* wait for a carrier on at least one device */ start = jiffies; while (jiffies - start < msecs_to_jiffies(CONF_CARRIER_TIMEOUT)) { -- cgit v1.1 From 6c3efb1526c3fcdab3e5bbc9c77710b306493507 Mon Sep 17 00:00:00 2001 From: Weiping Pan Date: Thu, 1 Dec 2011 15:47:06 +0000 Subject: ipv4: flush route cache after change accept_local [ Upstream commit d01ff0a049f749e0bf10a35bb23edd012718c8c2 ] After reset ipv4_devconf->data[IPV4_DEVCONF_ACCEPT_LOCAL] to 0, we should flush route cache, or it will continue receive packets with local source address, which should be dropped. Signed-off-by: Weiping Pan Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/devinet.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 4155abc..7d7fb20 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1490,7 +1490,9 @@ static int devinet_conf_proc(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + int old_value = *(int *)ctl->data; int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + int new_value = *(int *)ctl->data; if (write) { struct ipv4_devconf *cnf = ctl->extra1; @@ -1501,6 +1503,9 @@ static int devinet_conf_proc(ctl_table *ctl, int write, if (cnf == net->ipv4.devconf_dflt) devinet_copy_dflt_conf(net, i); + if (i == IPV4_DEVCONF_ACCEPT_LOCAL - 1) + if ((new_value == 0) && (old_value != 0)) + rt_cache_flush(net, 0); } return ret; -- cgit v1.1 From ad5dd5dc45d80c397dfe314934e91d0ead793928 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 21 Dec 2011 15:47:16 -0500 Subject: ipv4: reintroduce route cache garbage collector [ Upstream commit 9f28a2fc0bd77511f649c0a788c7bf9a5fd04edb ] Commit 2c8cec5c10b (ipv4: Cache learned PMTU information in inetpeer) removed IP route cache garbage collector a bit too soon, as this gc was responsible for expired routes cleanup, releasing their neighbour reference. As pointed out by Robert Gladewitz, recent kernels can fill and exhaust their neighbour cache. Reintroduce the garbage collection, since we'll have to wait our neighbour lookups become refcount-less to not depend on this stuff. Reported-by: Robert Gladewitz Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/route.c | 106 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 106 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 75ef66f..b01f569 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -132,6 +132,9 @@ static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; static int rt_chain_length_max __read_mostly = 20; +static struct delayed_work expires_work; +static unsigned long expires_ljiffies; + /* * Interface to generic destination cache. */ @@ -821,6 +824,97 @@ static int has_noalias(const struct rtable *head, const struct rtable *rth) return ONE; } +static void rt_check_expire(void) +{ + static unsigned int rover; + unsigned int i = rover, goal; + struct rtable *rth; + struct rtable __rcu **rthp; + unsigned long samples = 0; + unsigned long sum = 0, sum2 = 0; + unsigned long delta; + u64 mult; + + delta = jiffies - expires_ljiffies; + expires_ljiffies = jiffies; + mult = ((u64)delta) << rt_hash_log; + if (ip_rt_gc_timeout > 1) + do_div(mult, ip_rt_gc_timeout); + goal = (unsigned int)mult; + if (goal > rt_hash_mask) + goal = rt_hash_mask + 1; + for (; goal > 0; goal--) { + unsigned long tmo = ip_rt_gc_timeout; + unsigned long length; + + i = (i + 1) & rt_hash_mask; + rthp = &rt_hash_table[i].chain; + + if (need_resched()) + cond_resched(); + + samples++; + + if (rcu_dereference_raw(*rthp) == NULL) + continue; + length = 0; + spin_lock_bh(rt_hash_lock_addr(i)); + while ((rth = rcu_dereference_protected(*rthp, + lockdep_is_held(rt_hash_lock_addr(i)))) != NULL) { + prefetch(rth->dst.rt_next); + if (rt_is_expired(rth)) { + *rthp = rth->dst.rt_next; + rt_free(rth); + continue; + } + if (rth->dst.expires) { + /* Entry is expired even if it is in use */ + if (time_before_eq(jiffies, rth->dst.expires)) { +nofree: + tmo >>= 1; + rthp = &rth->dst.rt_next; + /* + * We only count entries on + * a chain with equal hash inputs once + * so that entries for different QOS + * levels, and other non-hash input + * attributes don't unfairly skew + * the length computation + */ + length += has_noalias(rt_hash_table[i].chain, rth); + continue; + } + } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout)) + goto nofree; + + /* Cleanup aged off entries. */ + *rthp = rth->dst.rt_next; + rt_free(rth); + } + spin_unlock_bh(rt_hash_lock_addr(i)); + sum += length; + sum2 += length*length; + } + if (samples) { + unsigned long avg = sum / samples; + unsigned long sd = int_sqrt(sum2 / samples - avg*avg); + rt_chain_length_max = max_t(unsigned long, + ip_rt_gc_elasticity, + (avg + 4*sd) >> FRACT_BITS); + } + rover = i; +} + +/* + * rt_worker_func() is run in process context. + * we call rt_check_expire() to scan part of the hash table + */ +static void rt_worker_func(struct work_struct *work) +{ + rt_check_expire(); + schedule_delayed_work(&expires_work, ip_rt_gc_interval); +} + /* * Perturbation of rt_genid by a small quantity [1..256] * Using 8 bits of shuffling ensure we can call rt_cache_invalidate() @@ -3088,6 +3182,13 @@ static ctl_table ipv4_route_table[] = { .proc_handler = proc_dointvec_jiffies, }, { + .procname = "gc_interval", + .data = &ip_rt_gc_interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { .procname = "redirect_load", .data = &ip_rt_redirect_load, .maxlen = sizeof(int), @@ -3297,6 +3398,11 @@ int __init ip_rt_init(void) devinet_init(); ip_fib_init(); + INIT_DELAYED_WORK_DEFERRABLE(&expires_work, rt_worker_func); + expires_ljiffies = jiffies; + schedule_delayed_work(&expires_work, + net_random() % ip_rt_gc_interval + ip_rt_gc_interval); + if (ip_rt_proc_init()) printk(KERN_ERR "Unable to create route proc files\n"); #ifdef CONFIG_XFRM -- cgit v1.1 From 732e81a7579eb0adb26aeadb209e919ee984d01e Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Thu, 22 Dec 2011 17:03:29 +1100 Subject: ipv4: using prefetch requires including prefetch.h [ Upstream commit b9eda06f80b0db61a73bd87c6b0eb67d8aca55ad ] Signed-off-by: Stephen Rothwell Acked-by: Eric Dumazet Acked-by: David Miller Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- net/ipv4/route.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/ipv4') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index b01f569..4845bfe 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -91,6 +91,7 @@ #include #include #include +#include #include #include #include -- cgit v1.1 From 49ffa26eca87d3518ed88d3e6feebf1b80837a15 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Mon, 9 Jan 2012 14:06:46 -0800 Subject: igmp: Avoid zero delay when receiving odd mixture of IGMP queries commit a8c1f65c79cbbb2f7da782d4c9d15639a9b94b27 upstream. Commit 5b7c84066733c5dfb0e4016d939757b38de189e4 ('ipv4: correct IGMP behavior on v3 query during v2-compatibility mode') added yet another case for query parsing, which can result in max_delay = 0. Substitute a value of 1, as in the usual v3 case. Reported-by: Simon McVittie References: http://bugs.debian.org/654876 Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- net/ipv4/igmp.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index d577199..e0d42db 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -875,6 +875,8 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, * to be intended in a v3 query. */ max_delay = IGMPV3_MRC(ih3->code)*(HZ/IGMP_TIMER_SCALE); + if (!max_delay) + max_delay = 1; /* can't mod w/ 0 */ } else { /* v3 */ if (!pskb_may_pull(skb, sizeof(struct igmpv3_query))) return; -- cgit v1.1 From d253520a7b2c2223fb4f704f06d10f2c547bdeef Mon Sep 17 00:00:00 2001 From: Nick Bowler Date: Tue, 8 Nov 2011 12:12:44 +0000 Subject: ah: Correctly pass error codes in ahash output callback. commit 069294e813ed5f27f82613b027609bcda5f1b914 upstream. The AH4/6 ahash output callbacks pass nexthdr to xfrm_output_resume instead of the error code. This appears to be a copy+paste error from the input case, where nexthdr is expected. This causes the driver to continuously add AH headers to the datagram until either an allocation fails and the packet is dropped or the ahash driver hits a synchronous fallback and the resulting monstrosity is transmitted. Correct this issue by simply passing the error code unadulterated. Signed-off-by: Nick Bowler Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/ah4.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index c1f4154..33ca186 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -136,8 +136,6 @@ static void ah_output_done(struct crypto_async_request *base, int err) memcpy(top_iph+1, iph+1, top_iph->ihl*4 - sizeof(struct iphdr)); } - err = ah->nexthdr; - kfree(AH_SKB_CB(skb)->tmp); xfrm_output_resume(skb, err); } -- cgit v1.1 From c0ab420c6822529fa5aba05668e1e983b065460f Mon Sep 17 00:00:00 2001 From: Nick Bowler Date: Tue, 8 Nov 2011 12:12:45 +0000 Subject: ah: Read nexthdr value before overwriting it in ahash input callback. commit b7ea81a58adc123a4e980cb0eff9eb5c144b5dc7 upstream. The AH4/6 ahash input callbacks read out the nexthdr field from the AH header *after* they overwrite that header. This is obviously not going to end well. Fix it up. Signed-off-by: Nick Bowler Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/ah4.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 33ca186..c7056b2 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -262,12 +262,12 @@ static void ah_input_done(struct crypto_async_request *base, int err) if (err) goto out; + err = ah->nexthdr; + skb->network_header += ah_hlen; memcpy(skb_network_header(skb), work_iph, ihl); __skb_pull(skb, ah_hlen + ihl); skb_set_transport_header(skb, -ihl); - - err = ah->nexthdr; out: kfree(AH_SKB_CB(skb)->tmp); xfrm_input_resume(skb, err); -- cgit v1.1 From ffee9a18f29a0645c2d117083e025f557c738018 Mon Sep 17 00:00:00 2001 From: Nick Bowler Date: Thu, 10 Nov 2011 09:01:27 +0000 Subject: ah: Don't return NET_XMIT_DROP on input. commit 4b90a603a1b21d63cf743cc833680cb195a729f6 upstream. When the ahash driver returns -EBUSY, AH4/6 input functions return NET_XMIT_DROP, presumably copied from the output code path. But returning transmit codes on input doesn't make a lot of sense. Since NET_XMIT_DROP is a positive int, this gets interpreted as the next header type (i.e., success). As that can only end badly, remove the check. Signed-off-by: Nick Bowler Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/ah4.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index c7056b2..36d1440 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -369,8 +369,6 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) if (err == -EINPROGRESS) goto out; - if (err == -EBUSY) - err = NET_XMIT_DROP; goto out_free; } -- cgit v1.1 From 8b4bb350e120fe0b32a0b1b8d227e65af03e3993 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Sat, 28 Jan 2012 17:29:46 +0000 Subject: tcp: fix tcp_trim_head() to adjust segment count with skb MSS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 5b35e1e6e9ca651e6b291c96d1106043c9af314a ] This commit fixes tcp_trim_head() to recalculate the number of segments in the skb with the skb's existing MSS, so trimming the head causes the skb segment count to be monotonically non-increasing - it should stay the same or go down, but not increase. Previously tcp_trim_head() used the current MSS of the connection. But if there was a decrease in MSS between original transmission and ACK (e.g. due to PMTUD), this could cause tcp_trim_head() to counter-intuitively increase the segment count when trimming bytes off the head of an skb. This violated assumptions in tcp_tso_acked() that tcp_trim_head() only decreases the packet count, so that packets_acked in tcp_tso_acked() could underflow, leading tcp_clean_rtx_queue() to pass u32 pkts_acked values as large as 0xffffffff to ca_ops->pkts_acked(). As an aside, if tcp_trim_head() had really wanted the skb to reflect the current MSS, it should have called tcp_set_skb_tso_segs() unconditionally, since a decrease in MSS would mean that a single-packet skb should now be sliced into multiple segments. Signed-off-by: Neal Cardwell Acked-by: Nandita Dukkipati Acked-by: Ilpo Järvinen Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_output.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 882e0b0..faf257b 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1134,11 +1134,9 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) sk_mem_uncharge(sk, len); sock_set_flag(sk, SOCK_QUEUE_SHRUNK); - /* Any change of skb->len requires recalculation of tso - * factor and mss. - */ + /* Any change of skb->len requires recalculation of tso factor. */ if (tcp_skb_pcount(skb) > 1) - tcp_set_skb_tso_segs(sk, skb, tcp_current_mss(sk)); + tcp_set_skb_tso_segs(sk, skb, tcp_skb_mss(skb)); return 0; } -- cgit v1.1 From 81ecd154d0b07bd5dab6e4f09336cb068b70bcb9 Mon Sep 17 00:00:00 2001 From: shawnlu Date: Fri, 20 Jan 2012 12:22:04 +0000 Subject: tcp: md5: using remote adress for md5 lookup in rst packet [ Upstream commit 8a622e71f58ec9f092fc99eacae0e6cf14f6e742 ] md5 key is added in socket through remote address. remote address should be used in finding md5 key when sending out reset packet. Signed-off-by: shawnlu Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_ipv4.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 69790aa..53b0125 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -630,7 +630,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) arg.iov[0].iov_len = sizeof(rep.th); #ifdef CONFIG_TCP_MD5SIG - key = sk ? tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->daddr) : NULL; + key = sk ? tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->saddr) : NULL; if (key) { rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | -- cgit v1.1 From 8a533666d1591cf4ea596c6bd710e2fe682cb56a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 9 Feb 2012 16:13:19 -0500 Subject: net: fix NULL dereferences in check_peer_redir() [ Upstream commit d3aaeb38c40e5a6c08dd31a1b64da65c4352be36, along with dependent backports of commits: 69cce1d1404968f78b177a0314f5822d5afdbbfb 9de79c127cccecb11ae6a21ab1499e87aa222880 218fa90f072e4aeff9003d57e390857f4f35513e 580da35a31f91a594f3090b7a2c39b85cb051a12 f7e57044eeb1841847c24aa06766c8290c202583 e049f28883126c689cf95859480d9ee4ab23b7fa ] Gergely Kalman reported crashes in check_peer_redir(). It appears commit f39925dbde778 (ipv4: Cache learned redirect information in inetpeer.) added a race, leading to possible NULL ptr dereference. Since we can now change dst neighbour, we should make sure a reader can safely use a neighbour. Add RCU protection to dst neighbour, and make sure check_peer_redir() can be called safely by different cpus in parallel. As neighbours are already freed after one RCU grace period, this patch should not add typical RCU penalty (cache cold effects) Many thanks to Gergely for providing a pretty report pointing to the bug. Reported-by: Gergely Kalman Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/arp.c | 28 +++++++++++++++++----------- net/ipv4/ip_gre.c | 2 +- net/ipv4/ip_output.c | 22 ++++++++++++++++++---- net/ipv4/route.c | 31 +++++++++++++++++++------------ 4 files changed, 55 insertions(+), 28 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 1b74d3b..1d5675e 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -518,26 +518,32 @@ EXPORT_SYMBOL(arp_find); /* END OF OBSOLETE FUNCTIONS */ +struct neighbour *__arp_bind_neighbour(struct dst_entry *dst, __be32 nexthop) +{ + struct net_device *dev = dst->dev; + + if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) + nexthop = 0; + return __neigh_lookup_errno( +#if defined(CONFIG_ATM_CLIP) || defined(CONFIG_ATM_CLIP_MODULE) + dev->type == ARPHRD_ATM ? + clip_tbl_hook : +#endif + &arp_tbl, &nexthop, dev); +} + int arp_bind_neighbour(struct dst_entry *dst) { struct net_device *dev = dst->dev; - struct neighbour *n = dst->neighbour; + struct neighbour *n = dst_get_neighbour(dst); if (dev == NULL) return -EINVAL; if (n == NULL) { - __be32 nexthop = ((struct rtable *)dst)->rt_gateway; - if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) - nexthop = 0; - n = __neigh_lookup_errno( -#if defined(CONFIG_ATM_CLIP) || defined(CONFIG_ATM_CLIP_MODULE) - dev->type == ARPHRD_ATM ? - clip_tbl_hook : -#endif - &arp_tbl, &nexthop, dev); + n = __arp_bind_neighbour(dst, ((struct rtable *)dst)->rt_gateway); if (IS_ERR(n)) return PTR_ERR(n); - dst->neighbour = n; + dst_set_neighbour(dst, n); } return 0; } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 8871067..d7bb94c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -731,9 +731,9 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev } #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) else if (skb->protocol == htons(ETH_P_IPV6)) { + struct neighbour *neigh = dst_get_neighbour(skb_dst(skb)); const struct in6_addr *addr6; int addr_type; - struct neighbour *neigh = skb_dst(skb)->neighbour; if (neigh == NULL) goto tx_error; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 0c99db4..51a3eec 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -182,6 +182,8 @@ static inline int ip_finish_output2(struct sk_buff *skb) struct rtable *rt = (struct rtable *)dst; struct net_device *dev = dst->dev; unsigned int hh_len = LL_RESERVED_SPACE(dev); + struct neighbour *neigh; + int res; if (rt->rt_type == RTN_MULTICAST) { IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUTMCAST, skb->len); @@ -203,10 +205,22 @@ static inline int ip_finish_output2(struct sk_buff *skb) skb = skb2; } - if (dst->hh) - return neigh_hh_output(dst->hh, skb); - else if (dst->neighbour) - return dst->neighbour->output(skb); + rcu_read_lock(); + if (dst->hh) { + int res = neigh_hh_output(dst->hh, skb); + + rcu_read_unlock(); + return res; + } else { + neigh = dst_get_neighbour(dst); + if (neigh) { + res = neigh->output(skb); + + rcu_read_unlock(); + return res; + } + rcu_read_unlock(); + } if (net_ratelimit()) printk(KERN_DEBUG "ip_finish_output2: No header cache and no neighbour!\n"); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 4845bfe..65ff2e5 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -416,7 +416,13 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v) "HHUptod\tSpecDst"); else { struct rtable *r = v; - int len; + struct neighbour *n; + int len, HHUptod; + + rcu_read_lock(); + n = dst_get_neighbour(&r->dst); + HHUptod = (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0; + rcu_read_unlock(); seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t" "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n", @@ -431,8 +437,7 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v) dst_metric(&r->dst, RTAX_RTTVAR)), r->rt_key_tos, r->dst.hh ? atomic_read(&r->dst.hh->hh_refcnt) : -1, - r->dst.hh ? (r->dst.hh->hh_output == - dev_queue_xmit) : 0, + HHUptod, r->rt_spec_dst, &len); seq_printf(seq, "%*s\n", 127 - len, ""); @@ -1688,23 +1693,25 @@ static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer) { struct rtable *rt = (struct rtable *) dst; __be32 orig_gw = rt->rt_gateway; + struct neighbour *n, *old_n; dst_confirm(&rt->dst); - neigh_release(rt->dst.neighbour); - rt->dst.neighbour = NULL; - rt->rt_gateway = peer->redirect_learned.a4; - if (arp_bind_neighbour(&rt->dst) || - !(rt->dst.neighbour->nud_state & NUD_VALID)) { - if (rt->dst.neighbour) - neigh_event_send(rt->dst.neighbour, NULL); + n = __arp_bind_neighbour(&rt->dst, rt->rt_gateway); + if (IS_ERR(n)) + return PTR_ERR(n); + old_n = xchg(&rt->dst._neighbour, n); + if (old_n) + neigh_release(old_n); + if (!n || !(n->nud_state & NUD_VALID)) { + if (n) + neigh_event_send(n, NULL); rt->rt_gateway = orig_gw; return -EAGAIN; } else { rt->rt_flags |= RTCF_REDIRECTED; - call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, - rt->dst.neighbour); + call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); } return 0; } -- cgit v1.1 From c4f2403478002bdb0a46a62f87909aeda8058d8b Mon Sep 17 00:00:00 2001 From: Li Wei Date: Tue, 8 Nov 2011 21:39:28 +0000 Subject: ipv4: fix for ip_options_rcv_srr() daddr update. [ Upstream commit b12f62efb8ec0b9523bdb6c2d412c07193086de9 ] When opt->srr_is_hit is set skb_rtable(skb) has been updated for 'nexthop' and iph->daddr should always equals to skb_rtable->rt_dst holds, We need update iph->daddr either. Signed-off-by: Li Wei Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/ip_options.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/ipv4') diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index ec93335..05d20cc 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -640,6 +640,7 @@ int ip_options_rcv_srr(struct sk_buff *skb) } if (srrptr <= srrspace) { opt->srr_is_hit = 1; + iph->daddr = nexthop; opt->is_changed = 1; } return 0; -- cgit v1.1 From 5805d4729059f578c8283ccc44021342fbe8c93d Mon Sep 17 00:00:00 2001 From: Li Wei Date: Tue, 22 Nov 2011 23:33:10 +0000 Subject: ipv4: Save nexthop address of LSRR/SSRR option to IPCB. [ Upstream commit ac8a48106be49c422575ddc7531b776f8eb49610 ] We can not update iph->daddr in ip_options_rcv_srr(), It is too early. When some exception ocurred later (eg. in ip_forward() when goto sr_failed) we need the ip header be identical to the original one as ICMP need it. Add a field 'nexthop' in struct ip_options to save nexthop of LSRR or SSRR option. Signed-off-by: Li Wei Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/ip_forward.c | 2 +- net/ipv4/ip_options.c | 5 +++-- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 3b34d1c..29a07b6 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -84,7 +84,7 @@ int ip_forward(struct sk_buff *skb) rt = skb_rtable(skb); - if (opt->is_strictroute && ip_hdr(skb)->daddr != rt->rt_gateway) + if (opt->is_strictroute && opt->nexthop != rt->rt_gateway) goto sr_failed; if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) && diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 05d20cc..1e60f76 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -568,12 +568,13 @@ void ip_forward_options(struct sk_buff *skb) ) { if (srrptr + 3 > srrspace) break; - if (memcmp(&ip_hdr(skb)->daddr, &optptr[srrptr-1], 4) == 0) + if (memcmp(&opt->nexthop, &optptr[srrptr-1], 4) == 0) break; } if (srrptr + 3 <= srrspace) { opt->is_changed = 1; ip_rt_get_source(&optptr[srrptr-1], skb, rt); + ip_hdr(skb)->daddr = opt->nexthop; optptr[2] = srrptr+4; } else if (net_ratelimit()) printk(KERN_CRIT "ip_forward(): Argh! Destination lost!\n"); @@ -640,7 +641,7 @@ int ip_options_rcv_srr(struct sk_buff *skb) } if (srrptr <= srrspace) { opt->srr_is_hit = 1; - iph->daddr = nexthop; + opt->nexthop = nexthop; opt->is_changed = 1; } return 0; -- cgit v1.1 From ab2fd30a38e23f0b6f2e331889b31f4f6fb2378a Mon Sep 17 00:00:00 2001 From: Li Wei Date: Thu, 9 Feb 2012 21:15:25 +0000 Subject: ipv4: Fix wrong order of ip_rt_get_source() and update iph->daddr. [ Upstream commit 5dc7883f2a7c25f8df40d7479687153558cd531b ] This patch fix a bug which introduced by commit ac8a4810 (ipv4: Save nexthop address of LSRR/SSRR option to IPCB.).In that patch, we saved the nexthop of SRR in ip_option->nexthop and update iph->daddr until we get to ip_forward_options(), but we need to update it before ip_rt_get_source(), otherwise we may get a wrong src. Signed-off-by: Li Wei Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/ip_options.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 1e60f76..42dd1a9 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -573,8 +573,8 @@ void ip_forward_options(struct sk_buff *skb) } if (srrptr + 3 <= srrspace) { opt->is_changed = 1; - ip_rt_get_source(&optptr[srrptr-1], skb, rt); ip_hdr(skb)->daddr = opt->nexthop; + ip_rt_get_source(&optptr[srrptr-1], skb, rt); optptr[2] = srrptr+4; } else if (net_ratelimit()) printk(KERN_CRIT "ip_forward(): Argh! Destination lost!\n"); -- cgit v1.1 From 1831cd9e1fb43c2e700e795827cb9531e679b0ef Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Fri, 10 Feb 2012 04:07:11 +0000 Subject: net: Don't proxy arp respond if iif == rt->dst.dev if private VLAN is disabled [ Upstream commit 70620c46ac2b45c24b0f22002fdf5ddd1f7daf81 ] Commit 653241 (net: RFC3069, private VLAN proxy arp support) changed the behavior of arp proxy to send arp replies back out on the interface the request came in even if the private VLAN feature is disabled. Previously we checked rt->dst.dev != skb->dev for in scenarios, when proxy arp is enabled on for the netdevice and also when individual proxy neighbour entries have been added. This patch adds the check back for the pneigh_lookup() scenario. Signed-off-by: Thomas Graf Acked-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/arp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 1d5675e..d8f852d 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -906,7 +906,8 @@ static int arp_process(struct sk_buff *skb) if (addr_type == RTN_UNICAST && (arp_fwd_proxy(in_dev, dev, rt) || arp_fwd_pvlan(in_dev, dev, rt, sip, tip) || - pneigh_lookup(&arp_tbl, net, &tip, dev, 0))) { + (rt->dst.dev != dev && + pneigh_lookup(&arp_tbl, net, &tip, dev, 0)))) { n = neigh_event_ns(&arp_tbl, sha, &sip, dev); if (n) neigh_release(n); -- cgit v1.1 From 39b73fb4fedd23980b720d0272e5e26510cd6940 Mon Sep 17 00:00:00 2001 From: Shawn Lu Date: Sat, 4 Feb 2012 12:38:09 +0000 Subject: tcp_v4_send_reset: binding oif to iif in no sock case [ Upstream commit e2446eaab5585555a38ea0df4e01ff313dbb4ac9 ] Binding RST packet outgoing interface to incoming interface for tcp v4 when there is no socket associate with it. when sk is not NULL, using sk->sk_bound_dev_if instead. (suggested by Eric Dumazet). This has few benefits: 1. tcp_v6_send_reset already did that. 2. This helps tcp connect with SO_BINDTODEVICE set. When connection is lost, we still able to sending out RST using same interface. 3. we are sending reply, it is most likely to be succeed if iif is used Signed-off-by: Shawn Lu Acked-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_ipv4.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 53b0125..04c6592 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -650,6 +650,11 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) arg.iov[0].iov_len, IPPROTO_TCP, 0); arg.csumoffset = offsetof(struct tcphdr, check) / 2; arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0; + /* When socket is gone, all binding information is lost. + * routing might fail in this case. using iif for oif to + * make sure we can deliver it + */ + arg.bound_dev_if = sk ? sk->sk_bound_dev_if : inet_iif(skb); net = dev_net(skb_dst(skb)->dev); ip_send_reply(net->ipv4.tcp_sock, skb, ip_hdr(skb)->saddr, -- cgit v1.1 From 382e8f84cb3db5295aa2f142a11e42eac6544ab4 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Sun, 12 Feb 2012 18:37:09 +0000 Subject: tcp: allow tcp_sacktag_one() to tag ranges not aligned with skbs [ Upstream commit cc9a672ee522d4805495b98680f4a3db5d0a0af9 ] This commit allows callers of tcp_sacktag_one() to pass in sequence ranges that do not align with skb boundaries, as tcp_shifted_skb() needs to do in an upcoming fix in this patch series. In fact, now tcp_sacktag_one() does not need to depend on an input skb at all, which makes its semantics and dependencies more clear. Signed-off-by: Neal Cardwell Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_input.c | 36 ++++++++++++++++++++++-------------- 1 file changed, 22 insertions(+), 14 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c68040f..af41044 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1289,25 +1289,26 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, return in_sack; } -static u8 tcp_sacktag_one(struct sk_buff *skb, struct sock *sk, - struct tcp_sacktag_state *state, +/* Mark the given newly-SACKed range as such, adjusting counters and hints. */ +static u8 tcp_sacktag_one(struct sock *sk, + struct tcp_sacktag_state *state, u8 sacked, + u32 start_seq, u32 end_seq, int dup_sack, int pcount) { struct tcp_sock *tp = tcp_sk(sk); - u8 sacked = TCP_SKB_CB(skb)->sacked; int fack_count = state->fack_count; /* Account D-SACK for retransmitted packet. */ if (dup_sack && (sacked & TCPCB_RETRANS)) { if (tp->undo_marker && tp->undo_retrans && - after(TCP_SKB_CB(skb)->end_seq, tp->undo_marker)) + after(end_seq, tp->undo_marker)) tp->undo_retrans--; if (sacked & TCPCB_SACKED_ACKED) state->reord = min(fack_count, state->reord); } /* Nothing to do; acked frame is about to be dropped (was ACKed). */ - if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una)) + if (!after(end_seq, tp->snd_una)) return sacked; if (!(sacked & TCPCB_SACKED_ACKED)) { @@ -1326,13 +1327,13 @@ static u8 tcp_sacktag_one(struct sk_buff *skb, struct sock *sk, /* New sack for not retransmitted frame, * which was in hole. It is reordering. */ - if (before(TCP_SKB_CB(skb)->seq, + if (before(start_seq, tcp_highest_sack_seq(tp))) state->reord = min(fack_count, state->reord); /* SACK enhanced F-RTO (RFC4138; Appendix B) */ - if (!after(TCP_SKB_CB(skb)->end_seq, tp->frto_highmark)) + if (!after(end_seq, tp->frto_highmark)) state->flag |= FLAG_ONLY_ORIG_SACKED; } @@ -1350,8 +1351,7 @@ static u8 tcp_sacktag_one(struct sk_buff *skb, struct sock *sk, /* Lost marker hint past SACKed? Tweak RFC3517 cnt */ if (!tcp_is_fack(tp) && (tp->lost_skb_hint != NULL) && - before(TCP_SKB_CB(skb)->seq, - TCP_SKB_CB(tp->lost_skb_hint)->seq)) + before(start_seq, TCP_SKB_CB(tp->lost_skb_hint)->seq)) tp->lost_cnt_hint += pcount; if (fack_count > tp->fackets_out) @@ -1407,7 +1407,11 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, } /* We discard results */ - tcp_sacktag_one(skb, sk, state, dup_sack, pcount); + tcp_sacktag_one(sk, state, + TCP_SKB_CB(skb)->sacked, + TCP_SKB_CB(skb)->seq, + TCP_SKB_CB(skb)->end_seq, + dup_sack, pcount); /* Difference in this won't matter, both ACKed by the same cumul. ACK */ TCP_SKB_CB(prev)->sacked |= (TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS); @@ -1646,10 +1650,14 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, break; if (in_sack) { - TCP_SKB_CB(skb)->sacked = tcp_sacktag_one(skb, sk, - state, - dup_sack, - tcp_skb_pcount(skb)); + TCP_SKB_CB(skb)->sacked = + tcp_sacktag_one(sk, + state, + TCP_SKB_CB(skb)->sacked, + TCP_SKB_CB(skb)->seq, + TCP_SKB_CB(skb)->end_seq, + dup_sack, + tcp_skb_pcount(skb)); if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp))) -- cgit v1.1 From dd31c1ce7ef7b363215081fde02f13bf3e50b5a1 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Sun, 12 Feb 2012 18:37:10 +0000 Subject: tcp: fix range tcp_shifted_skb() passes to tcp_sacktag_one() [ Upstream commit daef52bab1fd26e24e8e9578f8fb33ba1d0cb412 ] Fix the newly-SACKed range to be the range of newly-shifted bytes. Previously - since 832d11c5cd076abc0aa1eaf7be96c81d1a59ce41 - tcp_shifted_skb() incorrectly called tcp_sacktag_one() with the start and end sequence numbers of the skb it passes in set to the range just beyond the range that is newly-SACKed. This commit also removes a special-case adjustment to lost_cnt_hint in tcp_shifted_skb() since the pre-existing adjustment of lost_cnt_hint in tcp_sacktag_one() now properly handles this things now that the correct start sequence number is passed in. Signed-off-by: Neal Cardwell Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_input.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index af41044..78689e5 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1370,6 +1370,9 @@ static u8 tcp_sacktag_one(struct sock *sk, return sacked; } +/* Shift newly-SACKed bytes from this skb to the immediately previous + * already-SACKed sk_buff. Mark the newly-SACKed bytes as such. + */ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, struct tcp_sacktag_state *state, unsigned int pcount, int shifted, int mss, @@ -1377,12 +1380,11 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *prev = tcp_write_queue_prev(sk, skb); + u32 start_seq = TCP_SKB_CB(skb)->seq; /* start of newly-SACKed */ + u32 end_seq = start_seq + shifted; /* end of newly-SACKed */ BUG_ON(!pcount); - if (skb == tp->lost_skb_hint) - tp->lost_cnt_hint += pcount; - TCP_SKB_CB(prev)->end_seq += shifted; TCP_SKB_CB(skb)->seq += shifted; @@ -1406,12 +1408,11 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, skb_shinfo(skb)->gso_type = 0; } - /* We discard results */ - tcp_sacktag_one(sk, state, - TCP_SKB_CB(skb)->sacked, - TCP_SKB_CB(skb)->seq, - TCP_SKB_CB(skb)->end_seq, - dup_sack, pcount); + /* Adjust counters and hints for the newly sacked sequence range but + * discard the return value since prev is already marked. + */ + tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, + start_seq, end_seq, dup_sack, pcount); /* Difference in this won't matter, both ACKed by the same cumul. ACK */ TCP_SKB_CB(prev)->sacked |= (TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS); -- cgit v1.1 From 623f1904ef55789082259573bb6248df5fea3d92 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Mon, 13 Feb 2012 20:22:08 +0000 Subject: tcp: fix tcp_shifted_skb() adjustment of lost_cnt_hint for FACK [ Upstream commit 0af2a0d0576205dda778d25c6c344fc6508fc81d ] This commit ensures that lost_cnt_hint is correctly updated in tcp_shifted_skb() for FACK TCP senders. The lost_cnt_hint adjustment in tcp_sacktag_one() only applies to non-FACK senders, so FACK senders need their own adjustment. This applies the spirit of 1e5289e121372a3494402b1b131b41bfe1cf9b7f - except now that the sequence range passed into tcp_sacktag_one() is correct we need only have a special case adjustment for FACK. Signed-off-by: Neal Cardwell Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_input.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 78689e5..ee08f11f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1385,6 +1385,10 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, BUG_ON(!pcount); + /* Adjust hint for FACK. Non-FACK is handled in tcp_sacktag_one(). */ + if (tcp_is_fack(tp) && (skb == tp->lost_skb_hint)) + tp->lost_cnt_hint += pcount; + TCP_SKB_CB(prev)->end_seq += shifted; TCP_SKB_CB(skb)->seq += shifted; -- cgit v1.1 From bebee22bcbf0026f92141990972bd5863ef9b69c Mon Sep 17 00:00:00 2001 From: Flavio Leitner Date: Mon, 24 Oct 2011 02:56:38 -0400 Subject: route: fix ICMP redirect validation [ Upstream commit 7cc9150ebe8ec06cafea9f1c10d92ddacf88d8ae ] The commit f39925dbde7788cfb96419c0f092b086aa325c0f (ipv4: Cache learned redirect information in inetpeer.) removed some ICMP packet validations which are required by RFC 1122, section 3.2.2.2: ... A Redirect message SHOULD be silently discarded if the new gateway address it specifies is not on the same connected (sub-) net through which the Redirect arrived [INTRO:2, Appendix A], or if the source of the Redirect is not the current first-hop gateway for the specified destination (see Section 3.3.1). Signed-off-by: Flavio Leitner Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/route.c | 36 +++++++++++++++++++++++++++++++----- 1 file changed, 31 insertions(+), 5 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 65ff2e5..f881be2 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1373,7 +1373,12 @@ static void rt_del(unsigned hash, struct rtable *rt) void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, __be32 saddr, struct net_device *dev) { + int s, i; struct in_device *in_dev = __in_dev_get_rcu(dev); + struct rtable *rt; + __be32 skeys[2] = { saddr, 0 }; + int ikeys[2] = { dev->ifindex, 0 }; + struct flowi4 fl4; struct inet_peer *peer; struct net *net; @@ -1396,13 +1401,34 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, goto reject_redirect; } - peer = inet_getpeer_v4(daddr, 1); - if (peer) { - peer->redirect_learned.a4 = new_gw; + memset(&fl4, 0, sizeof(fl4)); + fl4.daddr = daddr; + for (s = 0; s < 2; s++) { + for (i = 0; i < 2; i++) { + fl4.flowi4_oif = ikeys[i]; + fl4.saddr = skeys[s]; + rt = __ip_route_output_key(net, &fl4); + if (IS_ERR(rt)) + continue; - inet_putpeer(peer); + if (rt->dst.error || rt->dst.dev != dev || + rt->rt_gateway != old_gw) { + ip_rt_put(rt); + continue; + } - atomic_inc(&__rt_peer_genid); + if (!rt->peer) + rt_bind_peer(rt, rt->rt_dst, 1); + + peer = rt->peer; + if (peer) { + peer->redirect_learned.a4 = new_gw; + atomic_inc(&__rt_peer_genid); + } + + ip_rt_put(rt); + return; + } } return; -- cgit v1.1 From 42ab5316ddcaa0de23e88e8a3d363c767b9ab0b3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 18 Nov 2011 15:24:32 -0500 Subject: ipv4: fix redirect handling [ Upstream commit 9cc20b268a5a14f5e57b8ad405a83513ab0d78dc ] commit f39925dbde77 (ipv4: Cache learned redirect information in inetpeer.) introduced a regression in ICMP redirect handling. It assumed ipv4_dst_check() would be called because all possible routes were attached to the inetpeer we modify in ip_rt_redirect(), but thats not true. commit 7cc9150ebe (route: fix ICMP redirect validation) tried to fix this but solution was not complete. (It fixed only one route) So we must lookup existing routes (including different TOS values) and call check_peer_redir() on them. Reported-by: Ivan Zahariev Signed-off-by: Eric Dumazet CC: Flavio Leitner Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/route.c | 109 +++++++++++++++++++++++++++++-------------------------- 1 file changed, 58 insertions(+), 51 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index f881be2..6b95f74 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1369,16 +1369,41 @@ static void rt_del(unsigned hash, struct rtable *rt) spin_unlock_bh(rt_hash_lock_addr(hash)); } +static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer) +{ + struct rtable *rt = (struct rtable *) dst; + __be32 orig_gw = rt->rt_gateway; + struct neighbour *n, *old_n; + + dst_confirm(&rt->dst); + + rt->rt_gateway = peer->redirect_learned.a4; + n = __arp_bind_neighbour(&rt->dst, rt->rt_gateway); + if (IS_ERR(n)) + return PTR_ERR(n); + old_n = xchg(&rt->dst._neighbour, n); + if (old_n) + neigh_release(old_n); + if (!n || !(n->nud_state & NUD_VALID)) { + if (n) + neigh_event_send(n, NULL); + rt->rt_gateway = orig_gw; + return -EAGAIN; + } else { + rt->rt_flags |= RTCF_REDIRECTED; + call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); + } + return 0; +} + /* called in rcu_read_lock() section */ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, __be32 saddr, struct net_device *dev) { int s, i; struct in_device *in_dev = __in_dev_get_rcu(dev); - struct rtable *rt; __be32 skeys[2] = { saddr, 0 }; int ikeys[2] = { dev->ifindex, 0 }; - struct flowi4 fl4; struct inet_peer *peer; struct net *net; @@ -1401,33 +1426,42 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, goto reject_redirect; } - memset(&fl4, 0, sizeof(fl4)); - fl4.daddr = daddr; for (s = 0; s < 2; s++) { for (i = 0; i < 2; i++) { - fl4.flowi4_oif = ikeys[i]; - fl4.saddr = skeys[s]; - rt = __ip_route_output_key(net, &fl4); - if (IS_ERR(rt)) - continue; - - if (rt->dst.error || rt->dst.dev != dev || - rt->rt_gateway != old_gw) { - ip_rt_put(rt); - continue; - } + unsigned int hash; + struct rtable __rcu **rthp; + struct rtable *rt; + + hash = rt_hash(daddr, skeys[s], ikeys[i], rt_genid(net)); + + rthp = &rt_hash_table[hash].chain; + + while ((rt = rcu_dereference(*rthp)) != NULL) { + rthp = &rt->dst.rt_next; + + if (rt->rt_key_dst != daddr || + rt->rt_key_src != skeys[s] || + rt->rt_oif != ikeys[i] || + rt_is_input_route(rt) || + rt_is_expired(rt) || + !net_eq(dev_net(rt->dst.dev), net) || + rt->dst.error || + rt->dst.dev != dev || + rt->rt_gateway != old_gw) + continue; - if (!rt->peer) - rt_bind_peer(rt, rt->rt_dst, 1); + if (!rt->peer) + rt_bind_peer(rt, rt->rt_dst, 1); - peer = rt->peer; - if (peer) { - peer->redirect_learned.a4 = new_gw; - atomic_inc(&__rt_peer_genid); + peer = rt->peer; + if (peer) { + if (peer->redirect_learned.a4 != new_gw) { + peer->redirect_learned.a4 = new_gw; + atomic_inc(&__rt_peer_genid); + } + check_peer_redir(&rt->dst, peer); + } } - - ip_rt_put(rt); - return; } } return; @@ -1715,33 +1749,6 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu) } } -static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer) -{ - struct rtable *rt = (struct rtable *) dst; - __be32 orig_gw = rt->rt_gateway; - struct neighbour *n, *old_n; - - dst_confirm(&rt->dst); - - rt->rt_gateway = peer->redirect_learned.a4; - n = __arp_bind_neighbour(&rt->dst, rt->rt_gateway); - if (IS_ERR(n)) - return PTR_ERR(n); - old_n = xchg(&rt->dst._neighbour, n); - if (old_n) - neigh_release(old_n); - if (!n || !(n->nud_state & NUD_VALID)) { - if (n) - neigh_event_send(n, NULL); - rt->rt_gateway = orig_gw; - return -EAGAIN; - } else { - rt->rt_flags |= RTCF_REDIRECTED; - call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); - } - return 0; -} - static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) { struct rtable *rt = (struct rtable *) dst; -- cgit v1.1 From e38b849e2fc481c5a6924f6872468104969e5d3c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 23 Feb 2012 10:55:02 +0000 Subject: ipsec: be careful of non existing mac headers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit 03606895cd98c0a628b17324fd7b5ff15db7e3cd ] Niccolo Belli reported ipsec crashes in case we handle a frame without mac header (atm in his case) Before copying mac header, better make sure it is present. Bugzilla reference: https://bugzilla.kernel.org/show_bug.cgi?id=42809 Reported-by: Niccolò Belli Tested-by: Niccolò Belli Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/xfrm4_mode_beet.c | 5 +---- net/ipv4/xfrm4_mode_tunnel.c | 6 ++---- 2 files changed, 3 insertions(+), 8 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c index 6341818..e3db3f9 100644 --- a/net/ipv4/xfrm4_mode_beet.c +++ b/net/ipv4/xfrm4_mode_beet.c @@ -110,10 +110,7 @@ static int xfrm4_beet_input(struct xfrm_state *x, struct sk_buff *skb) skb_push(skb, sizeof(*iph)); skb_reset_network_header(skb); - - memmove(skb->data - skb->mac_len, skb_mac_header(skb), - skb->mac_len); - skb_set_mac_header(skb, -skb->mac_len); + skb_mac_header_rebuild(skb); xfrm4_beet_make_header(skb); diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 534972e..ed4bf11 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -66,7 +66,6 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) { - const unsigned char *old_mac; int err = -EINVAL; if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP) @@ -84,10 +83,9 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) if (!(x->props.flags & XFRM_STATE_NOECN)) ipip_ecn_decapsulate(skb); - old_mac = skb_mac_header(skb); - skb_set_mac_header(skb, -skb->mac_len); - memmove(skb_mac_header(skb), old_mac, skb->mac_len); skb_reset_network_header(skb); + skb_mac_header_rebuild(skb); + err = 0; out: -- cgit v1.1 From 85526d578a0c7b6723c1a429b39870ce3bfec11c Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Sun, 26 Feb 2012 10:06:19 +0000 Subject: tcp: fix false reordering signal in tcp_shifted_skb [ Upstream commit 4c90d3b30334833450ccbb02f452d4972a3c3c3f ] When tcp_shifted_skb() shifts bytes from the skb that is currently pointed to by 'highest_sack' then the increment of TCP_SKB_CB(skb)->seq implicitly advances tcp_highest_sack_seq(). This implicit advancement, combined with the recent fix to pass the correct SACKed range into tcp_sacktag_one(), caused tcp_sacktag_one() to think that the newly SACKed range was before the tcp_highest_sack_seq(), leading to a call to tcp_update_reordering() with a degree of reordering matching the size of the newly SACKed range (typically just 1 packet, which is a NOP, but potentially larger). This commit fixes this by simply calling tcp_sacktag_one() before the TCP_SKB_CB(skb)->seq advancement that can advance our notion of the highest SACKed sequence. Correspondingly, we can simplify the code a little now that tcp_shifted_skb() should update the lost_cnt_hint in all cases where skb == tp->lost_skb_hint. Signed-off-by: Neal Cardwell Acked-by: Yuchung Cheng Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_input.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index ee08f11f..8eb1302 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1385,8 +1385,16 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, BUG_ON(!pcount); - /* Adjust hint for FACK. Non-FACK is handled in tcp_sacktag_one(). */ - if (tcp_is_fack(tp) && (skb == tp->lost_skb_hint)) + /* Adjust counters and hints for the newly sacked sequence + * range but discard the return value since prev is already + * marked. We must tag the range first because the seq + * advancement below implicitly advances + * tcp_highest_sack_seq() when skb is highest_sack. + */ + tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, + start_seq, end_seq, dup_sack, pcount); + + if (skb == tp->lost_skb_hint) tp->lost_cnt_hint += pcount; TCP_SKB_CB(prev)->end_seq += shifted; @@ -1412,12 +1420,6 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, skb_shinfo(skb)->gso_type = 0; } - /* Adjust counters and hints for the newly sacked sequence range but - * discard the return value since prev is already marked. - */ - tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, - start_seq, end_seq, dup_sack, pcount); - /* Difference in this won't matter, both ACKed by the same cumul. ACK */ TCP_SKB_CB(prev)->sacked |= (TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS); -- cgit v1.1 From 6046dc7d1b061d0f8e820757716de7df5079aa35 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Fri, 2 Mar 2012 21:36:51 +0000 Subject: tcp: don't fragment SACKed skbs in tcp_mark_head_lost() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [ Upstream commit c0638c247f559e1a16ee79e54df14bca2cb679ea ] In tcp_mark_head_lost() we should not attempt to fragment a SACKed skb to mark the first portion as lost. This is for two primary reasons: (1) tcp_shifted_skb() coalesces adjacent regions of SACKed skbs. When doing this, it preserves the sum of their packet counts in order to reflect the real-world dynamics on the wire. But given that skbs can have remainders that do not align to MSS boundaries, this packet count preservation means that for SACKed skbs there is not necessarily a direct linear relationship between tcp_skb_pcount(skb) and skb->len. Thus tcp_mark_head_lost()'s previous attempts to fragment off and mark as lost a prefix of length (packets - oldcnt)*mss from SACKed skbs were leading to occasional failures of the WARN_ON(len > skb->len) in tcp_fragment() (which used to be a BUG_ON(); see the recent "crash in tcp_fragment" thread on netdev). (2) there is no real point in fragmenting off part of a SACKed skb and calling tcp_skb_mark_lost() on it, since tcp_skb_mark_lost() is a NOP for SACKed skbs. Signed-off-by: Neal Cardwell Acked-by: Ilpo Järvinen Acked-by: Yuchung Cheng Acked-by: Nandita Dukkipati Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_input.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 8eb1302..ab9dcfb 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2549,6 +2549,7 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) if (cnt > packets) { if ((tcp_is_sack(tp) && !tcp_is_fack(tp)) || + (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) || (oldcnt >= packets)) break; -- cgit v1.1 From 619b6e476fdf85f17d80df72f647f2fb85535339 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Mon, 5 Mar 2012 19:35:04 +0000 Subject: tcp: fix tcp_shift_skb_data() to not shift SACKed data below snd_una [ Upstream commit 4648dc97af9d496218a05353b0e442b3dfa6aaab ] This commit fixes tcp_shift_skb_data() so that it does not shift SACKed data below snd_una. This fixes an issue whose symptoms exactly match reports showing tp->sacked_out going negative since 3.3.0-rc4 (see "WARNING: at net/ipv4/tcp_input.c:3418" thread on netdev). Since 2008 (832d11c5cd076abc0aa1eaf7be96c81d1a59ce41) tcp_shift_skb_data() had been shifting SACKed ranges that were below snd_una. It checked that the *end* of the skb it was about to shift from was above snd_una, but did not check that the end of the actual shifted range was above snd_una; this commit adds that check. Shifting SACKed ranges below snd_una is problematic because for such ranges tcp_sacktag_one() short-circuits: it does not declare anything as SACKed and does not increase sacked_out. Before the fixes in commits cc9a672ee522d4805495b98680f4a3db5d0a0af9 and daef52bab1fd26e24e8e9578f8fb33ba1d0cb412, shifting SACKed ranges below snd_una happened to work because tcp_shifted_skb() was always (incorrectly) passing in to tcp_sacktag_one() an skb whose end_seq tcp_shift_skb_data() had already guaranteed was beyond snd_una. Hence tcp_sacktag_one() never short-circuited and always increased tp->sacked_out in this case. After those two fixes, my testing has verified that shifting SACKed ranges below snd_una could cause tp->sacked_out to go negative with the following sequence of events: (1) tcp_shift_skb_data() sees an skb whose end_seq is beyond snd_una, then shifts a prefix of that skb that is below snd_una (2) tcp_shifted_skb() increments the packet count of the already-SACKed prev sk_buff (3) tcp_sacktag_one() sees the end of the new SACKed range is below snd_una, so it short-circuits and doesn't increase tp->sacked_out (5) tcp_clean_rtx_queue() sees the SACKed skb has been ACKed, decrements tp->sacked_out by this "inflated" pcount that was missing a matching increase in tp->sacked_out, and hence tp->sacked_out underflows to a u32 like 0xFFFFFFFF, which casted to s32 is negative. (6) this leads to the warnings seen in the recent "WARNING: at net/ipv4/tcp_input.c:3418" thread on the netdev list; e.g.: tcp_input.c:3418 WARN_ON((int)tp->sacked_out < 0); More generally, I think this bug can be tickled in some cases where two or more ACKs from the receiver are lost and then a DSACK arrives that is immediately above an existing SACKed skb in the write queue. This fix changes tcp_shift_skb_data() to abort this sequence at step (1) in the scenario above by noticing that the bytes are below snd_una and not shifting them. Signed-off-by: Neal Cardwell Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_input.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index ab9dcfb..72b1857 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1567,6 +1567,10 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, } } + /* tcp_sacktag_one() won't SACK-tag ranges below snd_una */ + if (!after(TCP_SKB_CB(skb)->seq + len, tp->snd_una)) + goto fallback; + if (!skb_shift(prev, skb, len)) goto fallback; if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss, dup_sack)) -- cgit v1.1 From 137a954db947096bd9378ff5a6a77336231f4a90 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 10 Mar 2012 09:20:21 +0000 Subject: tcp: fix syncookie regression [ Upstream commit dfd25ffffc132c00070eed64200e8950da5d7e9d ] commit ea4fc0d619 (ipv4: Don't use rt->rt_{src,dst} in ip_queue_xmit()) added a serious regression on synflood handling. Simon Kirby discovered a successful connection was delayed by 20 seconds before being responsive. In my tests, I discovered that xmit frames were lost, and needed ~4 retransmits and a socket dst rebuild before being really sent. In case of syncookie initiated connection, we use a different path to initialize the socket dst, and inet->cork.fl.u.ip4 is left cleared. As ip_queue_xmit() now depends on inet flow being setup, fix this by copying the temp flowi4 we use in cookie_v4_check(). Reported-by: Simon Kirby Bisected-by: Simon Kirby Signed-off-by: Eric Dumazet Tested-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/syncookies.c | 30 ++++++++++++++++-------------- net/ipv4/tcp_ipv4.c | 10 +++++++--- 2 files changed, 23 insertions(+), 17 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 4382629..895f215 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -277,6 +277,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, struct rtable *rt; __u8 rcv_wscale; bool ecn_ok = false; + struct flowi4 fl4; if (!sysctl_tcp_syncookies || !th->ack || th->rst) goto out; @@ -344,20 +345,16 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, * hasn't changed since we received the original syn, but I see * no easy way to do this. */ - { - struct flowi4 fl4; - - flowi4_init_output(&fl4, 0, sk->sk_mark, RT_CONN_FLAGS(sk), - RT_SCOPE_UNIVERSE, IPPROTO_TCP, - inet_sk_flowi_flags(sk), - (opt && opt->srr) ? opt->faddr : ireq->rmt_addr, - ireq->loc_addr, th->source, th->dest); - security_req_classify_flow(req, flowi4_to_flowi(&fl4)); - rt = ip_route_output_key(sock_net(sk), &fl4); - if (IS_ERR(rt)) { - reqsk_free(req); - goto out; - } + flowi4_init_output(&fl4, 0, sk->sk_mark, RT_CONN_FLAGS(sk), + RT_SCOPE_UNIVERSE, IPPROTO_TCP, + inet_sk_flowi_flags(sk), + (opt && opt->srr) ? opt->faddr : ireq->rmt_addr, + ireq->loc_addr, th->source, th->dest); + security_req_classify_flow(req, flowi4_to_flowi(&fl4)); + rt = ip_route_output_key(sock_net(sk), &fl4); + if (IS_ERR(rt)) { + reqsk_free(req); + goto out; } /* Try to redo what tcp_v4_send_synack did. */ @@ -371,5 +368,10 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, ireq->rcv_wscale = rcv_wscale; ret = get_cookie_sock(sk, skb, req, &rt->dst); + /* ip_queue_xmit() depends on our flow being setup + * Normal sockets get it right from inet_csk_route_child_sock() + */ + if (ret) + inet_sk(ret)->cork.fl.u.ip4 = fl4; out: return ret; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 04c6592..53a5af6 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1454,9 +1454,13 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; newinet->inet_id = newtp->write_seq ^ jiffies; - if (!dst && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL) - goto put_and_exit; - + if (!dst) { + dst = inet_csk_route_child_sock(sk, newsk, req); + if (!dst) + goto put_and_exit; + } else { + /* syncookie case : see end of cookie_v4_check() */ + } sk_setup_caps(newsk, dst); tcp_mtup_init(newsk); -- cgit v1.1