diff options
Diffstat (limited to 'net/ipv4')
-rw-r--r-- | net/ipv4/Makefile | 2 | ||||
-rw-r--r-- | net/ipv4/arp.c | 2 | ||||
-rw-r--r-- | net/ipv4/fib_frontend.c | 1 | ||||
-rw-r--r-- | net/ipv4/fib_semantics.c | 42 | ||||
-rw-r--r-- | net/ipv4/fib_trie.c | 53 | ||||
-rw-r--r-- | net/ipv4/ip_fragment.c | 4 | ||||
-rw-r--r-- | net/ipv4/ip_input.c | 7 | ||||
-rw-r--r-- | net/ipv4/route.c | 229 | ||||
-rw-r--r-- | net/ipv4/sysctl_net_ipv4.c | 15 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 9 | ||||
-rw-r--r-- | net/ipv4/tcp_cong.c | 3 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 27 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 22 | ||||
-rw-r--r-- | net/ipv4/tcp_minisocks.c | 2 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 33 | ||||
-rw-r--r-- | net/ipv4/xfrm4_input.c | 4 | ||||
-rw-r--r-- | net/ipv4/xfrm4_policy.c | 1 |
17 files changed, 281 insertions, 175 deletions
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index ae2ccf2..15ca63e 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -49,7 +49,7 @@ obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o -obj-$(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) += tcp_memcontrol.o +obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index a0124eb..77e87af 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -827,7 +827,7 @@ static int arp_process(struct sk_buff *skb) } if (arp->ar_op == htons(ARPOP_REQUEST) && - ip_route_input(skb, tip, sip, 0, dev) == 0) { + ip_route_input_noref(skb, tip, sip, 0, dev) == 0) { rt = skb_rtable(skb); addr_type = rt->rt_type; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 8732cc7..c43ae3f 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1046,6 +1046,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo if (event == NETDEV_UNREGISTER) { fib_disable_ip(dev, 2, -1); + rt_flush_dev(dev); return NOTIFY_DONE; } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index e55171f..da80dc1 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -140,6 +140,21 @@ const struct fib_prop fib_props[RTN_MAX + 1] = { }, }; +static void rt_fibinfo_free(struct rtable __rcu **rtp) +{ + struct rtable *rt = rcu_dereference_protected(*rtp, 1); + + if (!rt) + return; + + /* Not even needed : RCU_INIT_POINTER(*rtp, NULL); + * because we waited an RCU grace period before calling + * free_fib_info_rcu() + */ + + dst_free(&rt->dst); +} + static void free_nh_exceptions(struct fib_nh *nh) { struct fnhe_hash_bucket *hash = nh->nh_exceptions; @@ -153,6 +168,9 @@ static void free_nh_exceptions(struct fib_nh *nh) struct fib_nh_exception *next; next = rcu_dereference_protected(fnhe->fnhe_next, 1); + + rt_fibinfo_free(&fnhe->fnhe_rth); + kfree(fnhe); fnhe = next; @@ -161,6 +179,23 @@ static void free_nh_exceptions(struct fib_nh *nh) kfree(hash); } +static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp) +{ + int cpu; + + if (!rtp) + return; + + for_each_possible_cpu(cpu) { + struct rtable *rt; + + rt = rcu_dereference_protected(*per_cpu_ptr(rtp, cpu), 1); + if (rt) + dst_free(&rt->dst); + } + free_percpu(rtp); +} + /* Release a nexthop info record */ static void free_fib_info_rcu(struct rcu_head *head) { @@ -171,10 +206,8 @@ static void free_fib_info_rcu(struct rcu_head *head) dev_put(nexthop_nh->nh_dev); if (nexthop_nh->nh_exceptions) free_nh_exceptions(nexthop_nh); - if (nexthop_nh->nh_rth_output) - dst_release(&nexthop_nh->nh_rth_output->dst); - if (nexthop_nh->nh_rth_input) - dst_release(&nexthop_nh->nh_rth_input->dst); + rt_fibinfo_free_cpus(nexthop_nh->nh_pcpu_rth_output); + rt_fibinfo_free(&nexthop_nh->nh_rth_input); } endfor_nexthops(fi); release_net(fi->fib_net); @@ -804,6 +837,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) fi->fib_nhs = nhs; change_nexthops(fi) { nexthop_nh->nh_parent = fi; + nexthop_nh->nh_pcpu_rth_output = alloc_percpu(struct rtable __rcu *); } endfor_nexthops(fi) if (cfg->fc_mx) { diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 18cbc15..f0cdb30 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -159,7 +159,6 @@ struct trie { #endif }; -static void put_child(struct trie *t, struct tnode *tn, int i, struct rt_trie_node *n); static void tnode_put_child_reorg(struct tnode *tn, int i, struct rt_trie_node *n, int wasfull); static struct rt_trie_node *resize(struct trie *t, struct tnode *tn); @@ -473,7 +472,7 @@ static struct tnode *tnode_new(t_key key, int pos, int bits) } pr_debug("AT %p s=%zu %zu\n", tn, sizeof(struct tnode), - sizeof(struct rt_trie_node) << bits); + sizeof(struct rt_trie_node *) << bits); return tn; } @@ -490,7 +489,7 @@ static inline int tnode_full(const struct tnode *tn, const struct rt_trie_node * return ((struct tnode *) n)->pos == tn->pos + tn->bits; } -static inline void put_child(struct trie *t, struct tnode *tn, int i, +static inline void put_child(struct tnode *tn, int i, struct rt_trie_node *n) { tnode_put_child_reorg(tn, i, n, -1); @@ -754,8 +753,8 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) goto nomem; } - put_child(t, tn, 2*i, (struct rt_trie_node *) left); - put_child(t, tn, 2*i+1, (struct rt_trie_node *) right); + put_child(tn, 2*i, (struct rt_trie_node *) left); + put_child(tn, 2*i+1, (struct rt_trie_node *) right); } } @@ -776,9 +775,9 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) if (tkey_extract_bits(node->key, oldtnode->pos + oldtnode->bits, 1) == 0) - put_child(t, tn, 2*i, node); + put_child(tn, 2*i, node); else - put_child(t, tn, 2*i+1, node); + put_child(tn, 2*i+1, node); continue; } @@ -786,8 +785,8 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) inode = (struct tnode *) node; if (inode->bits == 1) { - put_child(t, tn, 2*i, rtnl_dereference(inode->child[0])); - put_child(t, tn, 2*i+1, rtnl_dereference(inode->child[1])); + put_child(tn, 2*i, rtnl_dereference(inode->child[0])); + put_child(tn, 2*i+1, rtnl_dereference(inode->child[1])); tnode_free_safe(inode); continue; @@ -817,22 +816,22 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) */ left = (struct tnode *) tnode_get_child(tn, 2*i); - put_child(t, tn, 2*i, NULL); + put_child(tn, 2*i, NULL); BUG_ON(!left); right = (struct tnode *) tnode_get_child(tn, 2*i+1); - put_child(t, tn, 2*i+1, NULL); + put_child(tn, 2*i+1, NULL); BUG_ON(!right); size = tnode_child_length(left); for (j = 0; j < size; j++) { - put_child(t, left, j, rtnl_dereference(inode->child[j])); - put_child(t, right, j, rtnl_dereference(inode->child[j + size])); + put_child(left, j, rtnl_dereference(inode->child[j])); + put_child(right, j, rtnl_dereference(inode->child[j + size])); } - put_child(t, tn, 2*i, resize(t, left)); - put_child(t, tn, 2*i+1, resize(t, right)); + put_child(tn, 2*i, resize(t, left)); + put_child(tn, 2*i+1, resize(t, right)); tnode_free_safe(inode); } @@ -877,7 +876,7 @@ static struct tnode *halve(struct trie *t, struct tnode *tn) if (!newn) goto nomem; - put_child(t, tn, i/2, (struct rt_trie_node *)newn); + put_child(tn, i/2, (struct rt_trie_node *)newn); } } @@ -892,21 +891,21 @@ static struct tnode *halve(struct trie *t, struct tnode *tn) if (left == NULL) { if (right == NULL) /* Both are empty */ continue; - put_child(t, tn, i/2, right); + put_child(tn, i/2, right); continue; } if (right == NULL) { - put_child(t, tn, i/2, left); + put_child(tn, i/2, left); continue; } /* Two nonempty children */ newBinNode = (struct tnode *) tnode_get_child(tn, i/2); - put_child(t, tn, i/2, NULL); - put_child(t, newBinNode, 0, left); - put_child(t, newBinNode, 1, right); - put_child(t, tn, i/2, resize(t, newBinNode)); + put_child(tn, i/2, NULL); + put_child(newBinNode, 0, left); + put_child(newBinNode, 1, right); + put_child(tn, i/2, resize(t, newBinNode)); } tnode_free_safe(oldtnode); return tn; @@ -1125,7 +1124,7 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) node_set_parent((struct rt_trie_node *)l, tp); cindex = tkey_extract_bits(key, tp->pos, tp->bits); - put_child(t, tp, cindex, (struct rt_trie_node *)l); + put_child(tp, cindex, (struct rt_trie_node *)l); } else { /* Case 3: n is a LEAF or a TNODE and the key doesn't match. */ /* @@ -1155,12 +1154,12 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) node_set_parent((struct rt_trie_node *)tn, tp); missbit = tkey_extract_bits(key, newpos, 1); - put_child(t, tn, missbit, (struct rt_trie_node *)l); - put_child(t, tn, 1-missbit, n); + put_child(tn, missbit, (struct rt_trie_node *)l); + put_child(tn, 1-missbit, n); if (tp) { cindex = tkey_extract_bits(key, tp->pos, tp->bits); - put_child(t, tp, cindex, (struct rt_trie_node *)tn); + put_child(tp, cindex, (struct rt_trie_node *)tn); } else { rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn); tp = tn; @@ -1619,7 +1618,7 @@ static void trie_leaf_remove(struct trie *t, struct leaf *l) if (tp) { t_key cindex = tkey_extract_bits(l->key, tp->pos, tp->bits); - put_child(t, tp, cindex, NULL); + put_child(tp, cindex, NULL); trie_rebalance(t, tp); } else RCU_INIT_POINTER(t->trie, NULL); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 7ad88e5..8d07c97 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -258,8 +258,8 @@ static void ip_expire(unsigned long arg) /* skb dst is stale, drop it, and perform route lookup again */ skb_dst_drop(head); iph = ip_hdr(head); - err = ip_route_input(head, iph->daddr, iph->saddr, - iph->tos, head->dev); + err = ip_route_input_noref(head, iph->daddr, iph->saddr, + iph->tos, head->dev); if (err) goto out_rcu_unlock; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 93134b0..f1395a6 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -314,6 +314,7 @@ drop: } int sysctl_ip_early_demux __read_mostly = 1; +EXPORT_SYMBOL(sysctl_ip_early_demux); static int ip_rcv_finish(struct sk_buff *skb) { @@ -324,14 +325,12 @@ static int ip_rcv_finish(struct sk_buff *skb) const struct net_protocol *ipprot; int protocol = iph->protocol; - rcu_read_lock(); ipprot = rcu_dereference(inet_protos[protocol]); if (ipprot && ipprot->early_demux) { ipprot->early_demux(skb); /* must reload iph, skb->head might have changed */ iph = ip_hdr(skb); } - rcu_read_unlock(); } /* @@ -339,8 +338,8 @@ static int ip_rcv_finish(struct sk_buff *skb) * how the packet travels inside Linux networking. */ if (!skb_dst(skb)) { - int err = ip_route_input(skb, iph->daddr, iph->saddr, - iph->tos, skb->dev); + int err = ip_route_input_noref(skb, iph->daddr, iph->saddr, + iph->tos, skb->dev); if (unlikely(err)) { if (err == -EXDEV) NET_INC_STATS_BH(dev_net(skb->dev), diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 3f7bb71..e4ba974 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -70,7 +70,6 @@ #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> -#include <linux/bootmem.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> @@ -80,7 +79,6 @@ #include <linux/netdevice.h> #include <linux/proc_fs.h> #include <linux/init.h> -#include <linux/workqueue.h> #include <linux/skbuff.h> #include <linux/inetdevice.h> #include <linux/igmp.h> @@ -88,11 +86,9 @@ #include <linux/mroute.h> #include <linux/netfilter_ipv4.h> #include <linux/random.h> -#include <linux/jhash.h> #include <linux/rcupdate.h> #include <linux/times.h> #include <linux/slab.h> -#include <linux/prefetch.h> #include <net/dst.h> #include <net/net_namespace.h> #include <net/protocol.h> @@ -147,6 +143,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu); static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); +static void ipv4_dst_destroy(struct dst_entry *dst); static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, int how) @@ -170,6 +167,7 @@ static struct dst_ops ipv4_dst_ops = { .default_advmss = ipv4_default_advmss, .mtu = ipv4_mtu, .cow_metrics = ipv4_cow_metrics, + .destroy = ipv4_dst_destroy, .ifdown = ipv4_dst_ifdown, .negative_advice = ipv4_negative_advice, .link_failure = ipv4_link_failure, @@ -587,11 +585,17 @@ static void ip_rt_build_flow_key(struct flowi4 *fl4, const struct sock *sk, build_sk_flow_key(fl4, sk); } -static DEFINE_SEQLOCK(fnhe_seqlock); +static inline void rt_free(struct rtable *rt) +{ + call_rcu(&rt->dst.rcu_head, dst_rcu_free); +} + +static DEFINE_SPINLOCK(fnhe_lock); static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash) { struct fib_nh_exception *fnhe, *oldest; + struct rtable *orig; oldest = rcu_dereference(hash->chain); for (fnhe = rcu_dereference(oldest->fnhe_next); fnhe; @@ -599,6 +603,11 @@ static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash) if (time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp)) oldest = fnhe; } + orig = rcu_dereference(oldest->fnhe_rth); + if (orig) { + RCU_INIT_POINTER(oldest->fnhe_rth, NULL); + rt_free(orig); + } return oldest; } @@ -620,7 +629,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, int depth; u32 hval = fnhe_hashfun(daddr); - write_seqlock_bh(&fnhe_seqlock); + spin_lock_bh(&fnhe_lock); hash = nh->nh_exceptions; if (!hash) { @@ -667,7 +676,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, fnhe->fnhe_stamp = jiffies; out_unlock: - write_sequnlock_bh(&fnhe_seqlock); + spin_unlock_bh(&fnhe_lock); return; } @@ -1164,61 +1173,118 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr) return NULL; } -static void rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, +static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, __be32 daddr) { - __be32 fnhe_daddr, gw; - unsigned long expires; - unsigned int seq; - u32 pmtu; - -restart: - seq = read_seqbegin(&fnhe_seqlock); - fnhe_daddr = fnhe->fnhe_daddr; - gw = fnhe->fnhe_gw; - pmtu = fnhe->fnhe_pmtu; - expires = fnhe->fnhe_expires; - if (read_seqretry(&fnhe_seqlock, seq)) - goto restart; - - if (daddr != fnhe_daddr) - return; + bool ret = false; + + spin_lock_bh(&fnhe_lock); - if (pmtu) { - unsigned long diff = expires - jiffies; + if (daddr == fnhe->fnhe_daddr) { + struct rtable *orig; - if (time_before(jiffies, expires)) { - rt->rt_pmtu = pmtu; - dst_set_expires(&rt->dst, diff); + if (fnhe->fnhe_pmtu) { + unsigned long expires = fnhe->fnhe_expires; + unsigned long diff = expires - jiffies; + + if (time_before(jiffies, expires)) { + rt->rt_pmtu = fnhe->fnhe_pmtu; + dst_set_expires(&rt->dst, diff); + } } + if (fnhe->fnhe_gw) { + rt->rt_flags |= RTCF_REDIRECTED; + rt->rt_gateway = fnhe->fnhe_gw; + } + + orig = rcu_dereference(fnhe->fnhe_rth); + rcu_assign_pointer(fnhe->fnhe_rth, rt); + if (orig) + rt_free(orig); + + fnhe->fnhe_stamp = jiffies; + ret = true; + } else { + /* Routes we intend to cache in nexthop exception have + * the DST_NOCACHE bit clear. However, if we are + * unsuccessful at storing this route into the cache + * we really need to set it. + */ + rt->dst.flags |= DST_NOCACHE; } - if (gw) { - rt->rt_flags |= RTCF_REDIRECTED; - rt->rt_gateway = gw; - } - fnhe->fnhe_stamp = jiffies; -} + spin_unlock_bh(&fnhe_lock); -static inline void rt_release_rcu(struct rcu_head *head) -{ - struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head); - dst_release(dst); + return ret; } -static void rt_cache_route(struct fib_nh *nh, struct rtable *rt) +static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt) { - struct rtable *orig, *prev, **p = &nh->nh_rth_output; - - if (rt_is_input_route(rt)) - p = &nh->nh_rth_input; + struct rtable *orig, *prev, **p; + bool ret = true; + if (rt_is_input_route(rt)) { + p = (struct rtable **)&nh->nh_rth_input; + } else { + if (!nh->nh_pcpu_rth_output) + goto nocache; + p = (struct rtable **)__this_cpu_ptr(nh->nh_pcpu_rth_output); + } orig = *p; prev = cmpxchg(p, orig, rt); if (prev == orig) { - dst_clone(&rt->dst); if (orig) - call_rcu_bh(&orig->dst.rcu_head, rt_release_rcu); + rt_free(orig); + } else { + /* Routes we intend to cache in the FIB nexthop have + * the DST_NOCACHE bit clear. However, if we are + * unsuccessful at storing this route into the cache + * we really need to set it. + */ +nocache: + rt->dst.flags |= DST_NOCACHE; + ret = false; + } + + return ret; +} + +static DEFINE_SPINLOCK(rt_uncached_lock); +static LIST_HEAD(rt_uncached_list); + +static void rt_add_uncached_list(struct rtable *rt) +{ + spin_lock_bh(&rt_uncached_lock); + list_add_tail(&rt->rt_uncached, &rt_uncached_list); + spin_unlock_bh(&rt_uncached_lock); +} + +static void ipv4_dst_destroy(struct dst_entry *dst) +{ + struct rtable *rt = (struct rtable *) dst; + + if (dst->flags & DST_NOCACHE) { + spin_lock_bh(&rt_uncached_lock); + list_del(&rt->rt_uncached); + spin_unlock_bh(&rt_uncached_lock); + } +} + +void rt_flush_dev(struct net_device *dev) +{ + if (!list_empty(&rt_uncached_list)) { + struct net *net = dev_net(dev); + struct rtable *rt; + + spin_lock_bh(&rt_uncached_lock); + list_for_each_entry(rt, &rt_uncached_list, rt_uncached) { + if (rt->dst.dev != dev) + continue; + rt->dst.dev = net->loopback_dev; + dev_hold(rt->dst.dev); + dev_put(dev); + } + spin_unlock_bh(&rt_uncached_lock); } } @@ -1234,20 +1300,24 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, struct fib_nh_exception *fnhe, struct fib_info *fi, u16 type, u32 itag) { + bool cached = false; + if (fi) { struct fib_nh *nh = &FIB_RES_NH(*res); if (nh->nh_gw && nh->nh_scope == RT_SCOPE_LINK) rt->rt_gateway = nh->nh_gw; - if (unlikely(fnhe)) - rt_bind_exception(rt, fnhe, daddr); dst_init_metrics(&rt->dst, fi->fib_metrics, true); #ifdef CONFIG_IP_ROUTE_CLASSID rt->dst.tclassid = nh->nh_tclassid; #endif - if (!(rt->dst.flags & DST_HOST)) - rt_cache_route(nh, rt); + if (unlikely(fnhe)) + cached = rt_bind_exception(rt, fnhe, daddr); + else if (!(rt->dst.flags & DST_NOCACHE)) + cached = rt_cache_route(nh, rt); } + if (unlikely(!cached)) + rt_add_uncached_list(rt); #ifdef CONFIG_IP_ROUTE_CLASSID #ifdef CONFIG_IP_MULTIPLE_TABLES @@ -1261,7 +1331,7 @@ static struct rtable *rt_dst_alloc(struct net_device *dev, bool nopolicy, bool noxfrm, bool will_cache) { return dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK, - (will_cache ? 0 : DST_HOST) | DST_NOCACHE | + (will_cache ? 0 : (DST_HOST | DST_NOCACHE)) | (nopolicy ? DST_NOPOLICY : 0) | (noxfrm ? DST_NOXFRM : 0)); } @@ -1314,6 +1384,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth->rt_iif = 0; rth->rt_pmtu = 0; rth->rt_gateway = 0; + INIT_LIST_HEAD(&rth->rt_uncached); if (our) { rth->dst.input= ip_local_deliver; rth->rt_flags |= RTCF_LOCAL; @@ -1366,8 +1437,7 @@ static void ip_handle_martian_source(struct net_device *dev, static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, struct in_device *in_dev, - __be32 daddr, __be32 saddr, u32 tos, - struct rtable **result) + __be32 daddr, __be32 saddr, u32 tos) { struct rtable *rth; int err; @@ -1416,9 +1486,9 @@ static int __mkroute_input(struct sk_buff *skb, do_cache = false; if (res->fi) { if (!itag) { - rth = FIB_RES_NH(*res).nh_rth_input; + rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); if (rt_cache_valid(rth)) { - dst_hold(&rth->dst); + skb_dst_set_noref(skb, &rth->dst); goto out; } do_cache = true; @@ -1440,13 +1510,14 @@ static int __mkroute_input(struct sk_buff *skb, rth->rt_iif = 0; rth->rt_pmtu = 0; rth->rt_gateway = 0; + INIT_LIST_HEAD(&rth->rt_uncached); rth->dst.input = ip_forward; rth->dst.output = ip_output; rt_set_nexthop(rth, daddr, res, NULL, res->fi, res->type, itag); + skb_dst_set(skb, &rth->dst); out: - *result = rth; err = 0; cleanup: return err; @@ -1458,21 +1529,13 @@ static int ip_mkroute_input(struct sk_buff *skb, struct in_device *in_dev, __be32 daddr, __be32 saddr, u32 tos) { - struct rtable *rth = NULL; - int err; - #ifdef CONFIG_IP_ROUTE_MULTIPATH if (res->fi && res->fi->fib_nhs > 1) fib_select_multipath(res); #endif /* create a routing cache entry */ - err = __mkroute_input(skb, res, in_dev, daddr, saddr, tos, &rth); - if (err) - return err; - - skb_dst_set(skb, &rth->dst); - return 0; + return __mkroute_input(skb, res, in_dev, daddr, saddr, tos); } /* @@ -1586,10 +1649,11 @@ local_input: do_cache = false; if (res.fi) { if (!itag) { - rth = FIB_RES_NH(res).nh_rth_input; + rth = rcu_dereference(FIB_RES_NH(res).nh_rth_input); if (rt_cache_valid(rth)) { - dst_hold(&rth->dst); - goto set_and_out; + skb_dst_set_noref(skb, &rth->dst); + err = 0; + goto out; } do_cache = true; } @@ -1613,6 +1677,7 @@ local_input: rth->rt_iif = 0; rth->rt_pmtu = 0; rth->rt_gateway = 0; + INIT_LIST_HEAD(&rth->rt_uncached); if (res.type == RTN_UNREACHABLE) { rth->dst.input= ip_error; rth->dst.error= -err; @@ -1620,7 +1685,6 @@ local_input: } if (do_cache) rt_cache_route(&FIB_RES_NH(res), rth); -set_and_out: skb_dst_set(skb, &rth->dst); err = 0; goto out; @@ -1658,8 +1722,8 @@ martian_source_keep_err: goto out; } -int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, - u8 tos, struct net_device *dev) +int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, + u8 tos, struct net_device *dev) { int res; @@ -1702,7 +1766,7 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, rcu_read_unlock(); return res; } -EXPORT_SYMBOL(ip_route_input); +EXPORT_SYMBOL(ip_route_input_noref); /* called with rcu_read_lock() */ static struct rtable *__mkroute_output(const struct fib_result *res, @@ -1752,19 +1816,23 @@ static struct rtable *__mkroute_output(const struct fib_result *res, fnhe = NULL; if (fi) { + struct rtable __rcu **prth; + fnhe = find_exception(&FIB_RES_NH(*res), fl4->daddr); - if (!fnhe) { - rth = FIB_RES_NH(*res).nh_rth_output; - if (rt_cache_valid(rth)) { - dst_hold(&rth->dst); - return rth; - } + if (fnhe) + prth = &fnhe->fnhe_rth; + else + prth = __this_cpu_ptr(FIB_RES_NH(*res).nh_pcpu_rth_output); + rth = rcu_dereference(*prth); + if (rt_cache_valid(rth)) { + dst_hold(&rth->dst); + return rth; } } rth = rt_dst_alloc(dev_out, IN_DEV_CONF_GET(in_dev, NOPOLICY), IN_DEV_CONF_GET(in_dev, NOXFRM), - fi && !fnhe); + fi); if (!rth) return ERR_PTR(-ENOBUFS); @@ -1777,6 +1845,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res, rth->rt_iif = orig_oif ? : 0; rth->rt_pmtu = 0; rth->rt_gateway = 0; + INIT_LIST_HEAD(&rth->rt_uncached); RT_CACHE_STAT_INC(out_slow_tot); @@ -2056,6 +2125,8 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_type = ort->rt_type; rt->rt_gateway = ort->rt_gateway; + INIT_LIST_HEAD(&rt->rt_uncached); + dst_free(new); } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 5840c32..1b5ce96 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -184,7 +184,7 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write, int ret; unsigned long vec[3]; struct net *net = current->nsproxy->net_ns; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM struct mem_cgroup *memcg; #endif @@ -203,7 +203,7 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write, if (ret) return ret; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM rcu_read_lock(); memcg = mem_cgroup_from_task(current); @@ -784,13 +784,6 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec }, { - .procname = "rt_cache_rebuild_count", - .data = &init_net.ipv4.sysctl_rt_cache_rebuild_count, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { .procname = "ping_group_range", .data = &init_net.ipv4.sysctl_ping_group_range, .maxlen = sizeof(init_net.ipv4.sysctl_ping_group_range), @@ -829,8 +822,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) table[5].data = &net->ipv4.sysctl_icmp_ratemask; table[6].data = - &net->ipv4.sysctl_rt_cache_rebuild_count; - table[7].data = &net->ipv4.sysctl_ping_group_range; } @@ -842,8 +833,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) net->ipv4.sysctl_ping_group_range[0] = 1; net->ipv4.sysctl_ping_group_range[1] = 0; - net->ipv4.sysctl_rt_cache_rebuild_count = 4; - tcp_init_mem(net); net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 581ecf0..2109ff4 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -811,7 +811,9 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, old_size_goal + mss_now > xmit_size_goal)) { xmit_size_goal = old_size_goal; } else { - tp->xmit_size_goal_segs = xmit_size_goal / mss_now; + tp->xmit_size_goal_segs = + min_t(u16, xmit_size_goal / mss_now, + sk->sk_gso_max_segs); xmit_size_goal = tp->xmit_size_goal_segs * mss_now; } } @@ -2681,7 +2683,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level, /* Cap the max timeout in ms TCP will retry/retrans * before giving up and aborting (ETIMEDOUT) a connection. */ - icsk->icsk_user_timeout = msecs_to_jiffies(val); + if (val < 0) + err = -EINVAL; + else + icsk->icsk_user_timeout = msecs_to_jiffies(val); break; default: err = -ENOPROTOOPT; diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 4d4db16..1432cdb 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -291,7 +291,8 @@ bool tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight) left = tp->snd_cwnd - in_flight; if (sk_can_gso(sk) && left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd && - left * tp->mss_cache < sk->sk_gso_max_size) + left * tp->mss_cache < sk->sk_gso_max_size && + left < sk->sk_gso_max_segs) return true; return left <= tcp_max_tso_deferred_mss(tp); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3e07a64..2fd2bc9 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4351,19 +4351,20 @@ static void tcp_ofo_queue(struct sock *sk) static bool tcp_prune_ofo_queue(struct sock *sk); static int tcp_prune_queue(struct sock *sk); -static int tcp_try_rmem_schedule(struct sock *sk, unsigned int size) +static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb, + unsigned int size) { if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || - !sk_rmem_schedule(sk, size)) { + !sk_rmem_schedule(sk, skb, size)) { if (tcp_prune_queue(sk) < 0) return -1; - if (!sk_rmem_schedule(sk, size)) { + if (!sk_rmem_schedule(sk, skb, size)) { if (!tcp_prune_ofo_queue(sk)) return -1; - if (!sk_rmem_schedule(sk, size)) + if (!sk_rmem_schedule(sk, skb, size)) return -1; } } @@ -4418,7 +4419,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) TCP_ECN_check_ce(tp, skb); - if (unlikely(tcp_try_rmem_schedule(sk, skb->truesize))) { + if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFODROP); __kfree_skb(skb); return; @@ -4552,17 +4553,17 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size) { - struct sk_buff *skb; + struct sk_buff *skb = NULL; struct tcphdr *th; bool fragstolen; - if (tcp_try_rmem_schedule(sk, size + sizeof(*th))) - goto err; - skb = alloc_skb(size + sizeof(*th), sk->sk_allocation); if (!skb) goto err; + if (tcp_try_rmem_schedule(sk, skb, size + sizeof(*th))) + goto err_free; + th = (struct tcphdr *)skb_put(skb, sizeof(*th)); skb_reset_transport_header(skb); memset(th, 0, sizeof(*th)); @@ -4633,7 +4634,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) if (eaten <= 0) { queue_and_out: if (eaten < 0 && - tcp_try_rmem_schedule(sk, skb->truesize)) + tcp_try_rmem_schedule(sk, skb, skb->truesize)) goto drop; eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen); @@ -5475,7 +5476,9 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, if (tp->copied_seq == tp->rcv_nxt && len - tcp_header_len <= tp->ucopy.len) { #ifdef CONFIG_NET_DMA - if (tcp_dma_try_early_copy(sk, skb, tcp_header_len)) { + if (tp->ucopy.task == current && + sock_owned_by_user(sk) && + tcp_dma_try_early_copy(sk, skb, tcp_header_len)) { copied_early = 1; eaten = 1; } @@ -5602,7 +5605,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) tcp_set_state(sk, TCP_ESTABLISHED); if (skb != NULL) { - sk->sk_rx_dst = dst_clone(skb_dst(skb)); + inet_sk_rx_dst_set(sk, skb); security_inet_conn_established(sk, skb); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index b6b07c9..42b2a6a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1617,21 +1617,19 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) #endif if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ + struct dst_entry *dst = sk->sk_rx_dst; + sock_rps_save_rxhash(sk, skb); - if (sk->sk_rx_dst) { - struct dst_entry *dst = sk->sk_rx_dst; - if (dst->ops->check(dst, 0) == NULL) { + if (dst) { + if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || + dst->ops->check(dst, 0) == NULL) { dst_release(dst); sk->sk_rx_dst = NULL; } } - if (unlikely(sk->sk_rx_dst == NULL)) { - struct inet_sock *icsk = inet_sk(sk); - struct rtable *rt = skb_rtable(skb); + if (unlikely(sk->sk_rx_dst == NULL)) + inet_sk_rx_dst_set(sk, skb); - sk->sk_rx_dst = dst_clone(&rt->dst); - icsk->rx_dst_ifindex = inet_iif(skb); - } if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) { rsk = sk; goto reset; @@ -1709,11 +1707,11 @@ void tcp_v4_early_demux(struct sk_buff *skb) skb->destructor = sock_edemux; if (sk->sk_state != TCP_TIME_WAIT) { struct dst_entry *dst = sk->sk_rx_dst; - struct inet_sock *icsk = inet_sk(sk); + if (dst) dst = dst_check(dst, 0); if (dst && - icsk->rx_dst_ifindex == skb->skb_iif) + inet_sk(sk)->rx_dst_ifindex == skb->skb_iif) skb_dst_set_noref(skb, dst); } } @@ -2635,7 +2633,7 @@ struct proto tcp_prot = { .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM .init_cgroup = tcp_init_cgroup, .destroy_cgroup = tcp_destroy_cgroup, .proto_cgroup = tcp_proto_cgroup, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 5912ac3..232a90c 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -387,7 +387,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, struct tcp_sock *oldtp = tcp_sk(sk); struct tcp_cookie_values *oldcvp = oldtp->cookie_values; - newsk->sk_rx_dst = dst_clone(skb_dst(skb)); + inet_sk_rx_dst_set(newsk, skb); /* TCP Cookie Transactions require space for the cookie pair, * as it differs for each connection. There is no need to diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 33cd065..a7b3ec9 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1522,21 +1522,21 @@ static void tcp_cwnd_validate(struct sock *sk) * when we would be allowed to send the split-due-to-Nagle skb fully. */ static unsigned int tcp_mss_split_point(const struct sock *sk, const struct sk_buff *skb, - unsigned int mss_now, unsigned int cwnd) + unsigned int mss_now, unsigned int max_segs) { const struct tcp_sock *tp = tcp_sk(sk); - u32 needed, window, cwnd_len; + u32 needed, window, max_len; window = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; - cwnd_len = mss_now * cwnd; + max_len = mss_now * max_segs; - if (likely(cwnd_len <= window && skb != tcp_write_queue_tail(sk))) - return cwnd_len; + if (likely(max_len <= window && skb != tcp_write_queue_tail(sk))) + return max_len; needed = min(skb->len, window); - if (cwnd_len <= needed) - return cwnd_len; + if (max_len <= needed) + return max_len; return needed - needed % mss_now; } @@ -1765,7 +1765,8 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) limit = min(send_win, cong_win); /* If a full-sized TSO skb can be sent, do it. */ - if (limit >= sk->sk_gso_max_size) + if (limit >= min_t(unsigned int, sk->sk_gso_max_size, + sk->sk_gso_max_segs * tp->mss_cache)) goto send_now; /* Middle in queue won't get any more data, full sendable already? */ @@ -1999,7 +2000,9 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, limit = mss_now; if (tso_segs > 1 && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, - cwnd_quota); + min_t(unsigned int, + cwnd_quota, + sk->sk_gso_max_segs)); if (skb->len > limit && unlikely(tso_fragment(sk, skb, limit, mss_now, gfp))) @@ -2045,7 +2048,8 @@ void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, if (unlikely(sk->sk_state == TCP_CLOSE)) return; - if (tcp_write_xmit(sk, cur_mss, nonagle, 0, GFP_ATOMIC)) + if (tcp_write_xmit(sk, cur_mss, nonagle, 0, + sk_gfp_atomic(sk, GFP_ATOMIC))) tcp_check_probe_timer(sk); } @@ -2666,7 +2670,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, if (cvp != NULL && cvp->s_data_constant && cvp->s_data_desired) s_data_desired = cvp->s_data_desired; - skb = alloc_skb(MAX_TCP_HEADER + 15 + s_data_desired, GFP_ATOMIC); + skb = alloc_skb(MAX_TCP_HEADER + 15 + s_data_desired, + sk_gfp_atomic(sk, GFP_ATOMIC)); if (unlikely(!skb)) { dst_release(dst); return NULL; @@ -3064,7 +3069,7 @@ void tcp_send_ack(struct sock *sk) * tcp_transmit_skb() will set the ownership to this * sock. */ - buff = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC); + buff = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC)); if (buff == NULL) { inet_csk_schedule_ack(sk); inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN; @@ -3079,7 +3084,7 @@ void tcp_send_ack(struct sock *sk) /* Send it off, this clears delayed acks for us. */ TCP_SKB_CB(buff)->when = tcp_time_stamp; - tcp_transmit_skb(sk, buff, 0, GFP_ATOMIC); + tcp_transmit_skb(sk, buff, 0, sk_gfp_atomic(sk, GFP_ATOMIC)); } /* This routine sends a packet with an out of date sequence @@ -3099,7 +3104,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent) struct sk_buff *skb; /* We don't queue it, tcp_transmit_skb() sets ownership. */ - skb = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC); + skb = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC)); if (skb == NULL) return -1; diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 58d23a5..06814b6 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -27,8 +27,8 @@ static inline int xfrm4_rcv_encap_finish(struct sk_buff *skb) if (skb_dst(skb) == NULL) { const struct iphdr *iph = ip_hdr(skb); - if (ip_route_input(skb, iph->daddr, iph->saddr, - iph->tos, skb->dev)) + if (ip_route_input_noref(skb, iph->daddr, iph->saddr, + iph->tos, skb->dev)) goto drop; } return dst_input(skb); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index c628184..681ea2f 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -92,6 +92,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt.rt_type = rt->rt_type; xdst->u.rt.rt_gateway = rt->rt_gateway; xdst->u.rt.rt_pmtu = rt->rt_pmtu; + INIT_LIST_HEAD(&xdst->u.rt.rt_uncached); return 0; } |