--- zzzz-none-000/linux-3.10.107/net/ipv6/ip6_fib.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/net/ipv6/ip6_fib.c 2021-02-04 17:41:59.000000000 +0000 @@ -9,14 +9,12 @@ * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. - */ - -/* - * Changes: - * Yuji SEKIYA @USAGI: Support default route on router node; - * remove ip6_null_entry from the top of - * routing table. - * Ville Nuorvala: Fixed routing subtrees. + * + * Changes: + * Yuji SEKIYA @USAGI: Support default route on router node; + * remove ip6_null_entry from the top of + * routing table. + * Ville Nuorvala: Fixed routing subtrees. */ #define pr_fmt(fmt) "IPv6: " fmt @@ -34,6 +32,7 @@ #include #include #include +#include #include #include @@ -46,24 +45,13 @@ #define RT6_TRACE(x...) do { ; } while (0) #endif -static struct kmem_cache * fib6_node_kmem __read_mostly; +static struct kmem_cache *fib6_node_kmem __read_mostly; -enum fib_walk_state_t -{ -#ifdef CONFIG_IPV6_SUBTREES - FWS_S, -#endif - FWS_L, - FWS_R, - FWS_C, - FWS_U -}; - -struct fib6_cleaner_t -{ - struct fib6_walker_t w; +struct fib6_cleaner { + struct fib6_walker w; struct net *net; int (*func)(struct rt6_info *, void *arg); + int sernum; void *arg; }; @@ -75,12 +63,11 @@ #define FWS_INIT FWS_L #endif -static void fib6_prune_clones(struct net *net, struct fib6_node *fn, - struct rt6_info *rt); +static void fib6_prune_clones(struct net *net, struct fib6_node *fn); static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn); static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_node *fn); -static int fib6_walk(struct fib6_walker_t *w); -static int fib6_walk_continue(struct fib6_walker_t *w); +static int fib6_walk(struct fib6_walker *w); +static int fib6_walk_continue(struct fib6_walker *w); /* * A routing update causes an increase of the serial number on the @@ -89,34 +76,41 @@ * result of redirects, path MTU changes, etc. */ -static __u32 rt_sernum; - static void fib6_gc_timer_cb(unsigned long arg); static LIST_HEAD(fib6_walkers); #define FOR_WALKERS(w) list_for_each_entry(w, &fib6_walkers, lh) -static inline void fib6_walker_link(struct fib6_walker_t *w) +static void fib6_walker_link(struct fib6_walker *w) { write_lock_bh(&fib6_walker_lock); list_add(&w->lh, &fib6_walkers); write_unlock_bh(&fib6_walker_lock); } -static inline void fib6_walker_unlink(struct fib6_walker_t *w) +static void fib6_walker_unlink(struct fib6_walker *w) { write_lock_bh(&fib6_walker_lock); list_del(&w->lh); write_unlock_bh(&fib6_walker_lock); } -static __inline__ u32 fib6_new_sernum(void) + +static int fib6_new_sernum(struct net *net) { - u32 n = ++rt_sernum; - if ((__s32)n <= 0) - rt_sernum = n = 1; - return n; + int new, old; + + do { + old = atomic_read(&net->ipv6.fib6_sernum); + new = old < INT_MAX ? old + 1 : 1; + } while (atomic_cmpxchg(&net->ipv6.fib6_sernum, + old, new) != old); + return new; } +enum { + FIB6_NO_SERNUM_CHANGE = 0, +}; + /* * Auxiliary address test functions for the radix tree. * @@ -133,21 +127,21 @@ # define BITOP_BE32_SWIZZLE 0 #endif -static __inline__ __be32 addr_bit_set(const void *token, int fn_bit) +static __be32 addr_bit_set(const void *token, int fn_bit) { const __be32 *addr = token; /* * Here, - * 1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f) + * 1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f) * is optimized version of * htonl(1 << ((~fn_bit)&0x1F)) * See include/asm-generic/bitops/le.h. */ return (__force __be32)(1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)) & - addr[fn_bit >> 5]; + net_hdr_word(&addr[fn_bit >> 5]); } -static __inline__ struct fib6_node * node_alloc(void) +static struct fib6_node *node_alloc(void) { struct fib6_node *fn; @@ -156,15 +150,45 @@ return fn; } -static __inline__ void node_free(struct fib6_node * fn) +static void node_free(struct fib6_node *fn) { kmem_cache_free(fib6_node_kmem, fn); } -static __inline__ void rt6_release(struct rt6_info *rt) +static void rt6_rcu_free(struct rt6_info *rt) { - if (atomic_dec_and_test(&rt->rt6i_ref)) - dst_free(&rt->dst); + call_rcu(&rt->dst.rcu_head, dst_rcu_free); +} + +static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) +{ + int cpu; + + if (!non_pcpu_rt->rt6i_pcpu) + return; + + for_each_possible_cpu(cpu) { + struct rt6_info **ppcpu_rt; + struct rt6_info *pcpu_rt; + + ppcpu_rt = per_cpu_ptr(non_pcpu_rt->rt6i_pcpu, cpu); + pcpu_rt = *ppcpu_rt; + if (pcpu_rt) { + rt6_rcu_free(pcpu_rt); + *ppcpu_rt = NULL; + } + } + + free_percpu(non_pcpu_rt->rt6i_pcpu); + non_pcpu_rt->rt6i_pcpu = NULL; +} + +static void rt6_release(struct rt6_info *rt) +{ + if (atomic_dec_and_test(&rt->rt6i_ref)) { + rt6_free_pcpu(rt); + rt6_rcu_free(rt); + } } static void fib6_link_table(struct net *net, struct fib6_table *tb) @@ -241,6 +265,7 @@ return NULL; } +EXPORT_SYMBOL_GPL(fib6_get_table); static void __net_init fib6_tables_init(struct net *net) { @@ -262,7 +287,17 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, int flags, pol_lookup_t lookup) { - return (struct dst_entry *) lookup(net, net->ipv6.fib6_main_tbl, fl6, flags); + struct rt6_info *rt; + + rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, flags); + if (rt->rt6i_flags & RTF_REJECT && + rt->dst.error == -EAGAIN) { + ip6_rt_put(rt); + rt = net->ipv6.ip6_null_entry; + dst_hold(&rt->dst); + } + + return &rt->dst; } static void __net_init fib6_tables_init(struct net *net) @@ -272,7 +307,7 @@ #endif -static int fib6_dump_node(struct fib6_walker_t *w) +static int fib6_dump_node(struct fib6_walker *w) { int res; struct rt6_info *rt; @@ -284,7 +319,6 @@ w->leaf = rt; return 1; } - WARN_ON(res == 0); } w->leaf = NULL; return 0; @@ -292,7 +326,7 @@ static void fib6_dump_end(struct netlink_callback *cb) { - struct fib6_walker_t *w = (void*)cb->args[2]; + struct fib6_walker *w = (void *)cb->args[2]; if (w) { if (cb->args[4]) { @@ -302,7 +336,7 @@ cb->args[2] = 0; kfree(w); } - cb->done = (void*)cb->args[3]; + cb->done = (void *)cb->args[3]; cb->args[1] = 3; } @@ -315,7 +349,7 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, struct netlink_callback *cb) { - struct fib6_walker_t *w; + struct fib6_walker *w; int res; w = (void *)cb->args[2]; @@ -360,7 +394,7 @@ unsigned int h, s_h; unsigned int e = 0, s_e; struct rt6_rtnl_dump_arg arg; - struct fib6_walker_t *w; + struct fib6_walker *w; struct fib6_table *tb; struct hlist_head *head; int res = 0; @@ -425,17 +459,16 @@ * node. */ -static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr, - int addrlen, int plen, +static struct fib6_node *fib6_add_1(struct fib6_node *root, + struct in6_addr *addr, int plen, int offset, int allow_create, - int replace_required) + int replace_required, int sernum) { struct fib6_node *fn, *in, *ln; struct fib6_node *pn = NULL; struct rt6key *key; int bit; __be32 dir = 0; - __u32 sernum = fib6_new_sernum(); RT6_TRACE("fib6_add_1\n"); @@ -485,7 +518,7 @@ fn->fn_sernum = sernum; dir = addr_bit_set(addr, fn->fn_bit); pn = fn; - fn = dir ? fn->right: fn->left; + fn = dir ? fn->right : fn->left; } while (fn); if (!allow_create) { @@ -543,7 +576,7 @@ but if it is >= plen, the value is ignored in any case. */ - bit = __ipv6_addr_diff(addr, &key->addr, addrlen); + bit = __ipv6_addr_diff(addr, &key->addr, sizeof(*addr)); /* * (intermediate)[in] @@ -632,12 +665,44 @@ return ln; } -static inline bool rt6_qualify_for_ecmp(struct rt6_info *rt) +static bool rt6_qualify_for_ecmp(struct rt6_info *rt) { return (rt->rt6i_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) == RTF_GATEWAY; } +static void fib6_copy_metrics(u32 *mp, const struct mx6_config *mxc) +{ + int i; + + for (i = 0; i < RTAX_MAX; i++) { + if (test_bit(i, mxc->mx_valid)) + mp[i] = mxc->mx[i]; + } +} + +static int fib6_commit_metrics(struct dst_entry *dst, struct mx6_config *mxc) +{ + if (!mxc->mx) + return 0; + + if (dst->flags & DST_HOST) { + u32 *mp = dst_metrics_write_ptr(dst); + + if (unlikely(!mp)) + return -ENOMEM; + + fib6_copy_metrics(mp, mxc); + } else { + dst_init_metrics(dst, mxc->mx, false); + + /* We've stolen mx now. */ + mxc->mx = NULL; + } + + return 0; +} + static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, struct net *net) { @@ -666,16 +731,18 @@ */ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, - struct nl_info *info) + struct nl_info *info, struct mx6_config *mxc) { struct rt6_info *iter = NULL; struct rt6_info **ins; + struct rt6_info **fallback_ins = NULL; int replace = (info->nlh && (info->nlh->nlmsg_flags & NLM_F_REPLACE)); int add = (!info->nlh || (info->nlh->nlmsg_flags & NLM_F_CREATE)); int found = 0; bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); + int err; ins = &fn->leaf; @@ -692,8 +759,13 @@ (info->nlh->nlmsg_flags & NLM_F_EXCL)) return -EEXIST; if (replace) { - found++; - break; + if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) { + found++; + break; + } + if (rt_can_ecmp) + fallback_ins = fallback_ins ?: ins; + goto next_iter; } if (iter->dst.dev == rt->dst.dev && @@ -708,6 +780,7 @@ rt6_clean_expires(iter); else rt6_set_expires(iter, rt->dst.expires); + iter->rt6i_pmtu = rt->rt6i_pmtu; return -EEXIST; } /* If we have the same destination and the same metric, @@ -729,9 +802,17 @@ if (iter->rt6i_metric > rt->rt6i_metric) break; +next_iter: ins = &iter->dst.rt6_next; } + if (fallback_ins && !found) { + /* No ECMP-able route found, replace first non-ECMP one */ + ins = fallback_ins; + iter = *ins; + found++; + } + /* Reset round-robin state, if necessary */ if (ins == &fn->leaf) fn->rr_ptr = NULL; @@ -774,11 +855,15 @@ pr_warn("NLM_F_CREATE should be set when creating new route\n"); add: + err = fib6_commit_metrics(&rt->dst, mxc); + if (err) + return err; + rt->dst.rt6_next = iter; *ins = rt; rt->rt6i_node = fn; atomic_inc(&rt->rt6i_ref); - inet6_rt_notify(RTM_NEWROUTE, rt, info); + inet6_rt_notify(RTM_NEWROUTE, rt, info, 0); info->nl_net->ipv6.rt6_stats->fib_rt_entries++; if (!(fn->fn_flags & RTN_RTINFO)) { @@ -787,29 +872,57 @@ } } else { + int nsiblings; + if (!found) { if (add) goto add; pr_warn("NLM_F_REPLACE set, but no existing node found!\n"); return -ENOENT; } + + err = fib6_commit_metrics(&rt->dst, mxc); + if (err) + return err; + *ins = rt; rt->rt6i_node = fn; rt->dst.rt6_next = iter->dst.rt6_next; atomic_inc(&rt->rt6i_ref); - inet6_rt_notify(RTM_NEWROUTE, rt, info); + inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE); if (!(fn->fn_flags & RTN_RTINFO)) { info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; } + nsiblings = iter->rt6i_nsiblings; fib6_purge_rt(iter, fn, info->nl_net); rt6_release(iter); + + if (nsiblings) { + /* Replacing an ECMP route, remove all siblings */ + ins = &rt->dst.rt6_next; + iter = *ins; + while (iter) { + if (iter->rt6i_metric > rt->rt6i_metric) + break; + if (rt6_qualify_for_ecmp(iter)) { + *ins = iter->dst.rt6_next; + fib6_purge_rt(iter, fn, info->nl_net); + rt6_release(iter); + nsiblings--; + } else { + ins = &iter->dst.rt6_next; + } + iter = *ins; + } + WARN_ON(nsiblings != 0); + } } return 0; } -static __inline__ void fib6_start_gc(struct net *net, struct rt6_info *rt) +static void fib6_start_gc(struct net *net, struct rt6_info *rt) { if (!timer_pending(&net->ipv6.ip6_fib_timer) && (rt->rt6i_flags & (RTF_EXPIRES | RTF_CACHE))) @@ -830,12 +943,18 @@ * with source addr info in sub-trees */ -int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) +int fib6_add(struct fib6_node *root, struct rt6_info *rt, + struct nl_info *info, struct mx6_config *mxc) { struct fib6_node *fn, *pn = NULL; int err = -ENOMEM; int allow_create = 1; int replace_required = 0; + int sernum = fib6_new_sernum(info->nl_net); + + if (WARN_ON_ONCE((rt->dst.flags & DST_NOCACHE) && + !atomic_read(&rt->dst.__refcnt))) + return -EINVAL; if (info->nlh) { if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) @@ -846,9 +965,9 @@ if (!allow_create && !replace_required) pr_warn("RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n"); - fn = fib6_add_1(root, &rt->rt6i_dst.addr, sizeof(struct in6_addr), - rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst), - allow_create, replace_required); + fn = fib6_add_1(root, &rt->rt6i_dst.addr, rt->rt6i_dst.plen, + offsetof(struct rt6_info, rt6i_dst), allow_create, + replace_required, sernum); if (IS_ERR(fn)) { err = PTR_ERR(fn); fn = NULL; @@ -882,14 +1001,14 @@ sfn->leaf = info->nl_net->ipv6.ip6_null_entry; atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref); sfn->fn_flags = RTN_ROOT; - sfn->fn_sernum = fib6_new_sernum(); + sfn->fn_sernum = sernum; /* Now add the first leaf node to new subtree */ sn = fib6_add_1(sfn, &rt->rt6i_src.addr, - sizeof(struct in6_addr), rt->rt6i_src.plen, + rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), - allow_create, replace_required); + allow_create, replace_required, sernum); if (IS_ERR(sn)) { /* If it is failed, discard just allocated @@ -906,9 +1025,9 @@ fn->subtree = sfn; } else { sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr, - sizeof(struct in6_addr), rt->rt6i_src.plen, + rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), - allow_create, replace_required); + allow_create, replace_required, sernum); if (IS_ERR(sn)) { err = PTR_ERR(sn); @@ -924,11 +1043,12 @@ } #endif - err = fib6_add_rt2node(fn, rt, info); + err = fib6_add_rt2node(fn, rt, info, mxc); if (!err) { fib6_start_gc(info->nl_net, rt); if (!(rt->rt6i_flags & RTF_CACHE)) - fib6_prune_clones(info->nl_net, pn, rt); + fib6_prune_clones(info->nl_net, pn); + rt->dst.flags &= ~DST_NOCACHE; } out: @@ -953,7 +1073,8 @@ atomic_inc(&pn->leaf->rt6i_ref); } #endif - dst_free(&rt->dst); + if (!(rt->dst.flags & DST_NOCACHE)) + dst_free(&rt->dst); } return err; @@ -964,7 +1085,8 @@ st_failure: if (fn && !(fn->fn_flags & (RTN_RTINFO|RTN_ROOT))) fib6_repair_tree(info->nl_net, fn); - dst_free(&rt->dst); + if (!(rt->dst.flags & DST_NOCACHE)) + dst_free(&rt->dst); return err; #endif } @@ -979,8 +1101,8 @@ const struct in6_addr *addr; /* search key */ }; -static struct fib6_node * fib6_lookup_1(struct fib6_node *root, - struct lookup_args *args) +static struct fib6_node *fib6_lookup_1(struct fib6_node *root, + struct lookup_args *args) { struct fib6_node *fn; __be32 dir; @@ -1042,8 +1164,8 @@ return NULL; } -struct fib6_node * fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr, - const struct in6_addr *saddr) +struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr, + const struct in6_addr *saddr) { struct fib6_node *fn; struct lookup_args args[] = { @@ -1075,9 +1197,9 @@ */ -static struct fib6_node * fib6_locate_1(struct fib6_node *root, - const struct in6_addr *addr, - int plen, int offset) +static struct fib6_node *fib6_locate_1(struct fib6_node *root, + const struct in6_addr *addr, + int plen, int offset) { struct fib6_node *fn; @@ -1105,9 +1227,9 @@ return NULL; } -struct fib6_node * fib6_locate(struct fib6_node *root, - const struct in6_addr *daddr, int dst_len, - const struct in6_addr *saddr, int src_len) +struct fib6_node *fib6_locate(struct fib6_node *root, + const struct in6_addr *daddr, int dst_len, + const struct in6_addr *saddr, int src_len) { struct fib6_node *fn; @@ -1162,7 +1284,7 @@ int children; int nstate; struct fib6_node *child, *pn; - struct fib6_walker_t *w; + struct fib6_walker *w; int iter = 0; for (;;) { @@ -1171,12 +1293,14 @@ WARN_ON(fn->fn_flags & RTN_RTINFO); WARN_ON(fn->fn_flags & RTN_TL_ROOT); - WARN_ON(fn->leaf != NULL); + WARN_ON(fn->leaf); children = 0; child = NULL; - if (fn->right) child = fn->right, children |= 1; - if (fn->left) child = fn->left, children |= 2; + if (fn->right) + child = fn->right, children |= 1; + if (fn->left) + child = fn->left, children |= 2; if (children == 3 || FIB6_SUBTREE(fn) #ifdef CONFIG_IPV6_SUBTREES @@ -1204,8 +1328,10 @@ } else { WARN_ON(fn->fn_flags & RTN_ROOT); #endif - if (pn->right == fn) pn->right = child; - else if (pn->left == fn) pn->left = child; + if (pn->right == fn) + pn->right = child; + else if (pn->left == fn) + pn->left = child; #if RT6_DEBUG >= 2 else WARN_ON(1); @@ -1237,10 +1363,10 @@ w->node = child; if (children&2) { RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state); - w->state = w->state>=FWS_R ? FWS_U : FWS_INIT; + w->state = w->state >= FWS_R ? FWS_U : FWS_INIT; } else { RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state); - w->state = w->state>=FWS_C ? FWS_U : FWS_INIT; + w->state = w->state >= FWS_C ? FWS_U : FWS_INIT; } } } @@ -1260,7 +1386,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, struct nl_info *info) { - struct fib6_walker_t *w; + struct fib6_walker *w; struct rt6_info *rt = *rtp; struct net *net = info->nl_net; @@ -1310,7 +1436,7 @@ fib6_purge_rt(rt, fn, net); - inet6_rt_notify(RTM_DELROUTE, rt, info); + inet6_rt_notify(RTM_DELROUTE, rt, info, 0); rt6_release(rt); } @@ -1321,8 +1447,8 @@ struct rt6_info **rtp; #if RT6_DEBUG >= 2 - if (rt->dst.obsolete>0) { - WARN_ON(fn != NULL); + if (rt->dst.obsolete > 0) { + WARN_ON(fn); return -ENOENT; } #endif @@ -1341,7 +1467,7 @@ pn = pn->parent; } #endif - fib6_prune_clones(info->nl_net, pn, rt); + fib6_prune_clones(info->nl_net, pn); } /* @@ -1381,7 +1507,7 @@ * <0 -> walk is terminated by an error. */ -static int fib6_walk_continue(struct fib6_walker_t *w) +static int fib6_walk_continue(struct fib6_walker *w) { struct fib6_node *fn, *pn; @@ -1465,7 +1591,7 @@ } } -static int fib6_walk(struct fib6_walker_t *w) +static int fib6_walk(struct fib6_walker *w) { int res; @@ -1479,15 +1605,25 @@ return res; } -static int fib6_clean_node(struct fib6_walker_t *w) +static int fib6_clean_node(struct fib6_walker *w) { int res; struct rt6_info *rt; - struct fib6_cleaner_t *c = container_of(w, struct fib6_cleaner_t, w); + struct fib6_cleaner *c = container_of(w, struct fib6_cleaner, w); struct nl_info info = { .nl_net = c->net, }; + if (c->sernum != FIB6_NO_SERNUM_CHANGE && + w->node->fn_sernum != c->sernum) + w->node->fn_sernum = c->sernum; + + if (!c->func) { + WARN_ON_ONCE(c->sernum == FIB6_NO_SERNUM_CHANGE); + w->leaf = NULL; + return 0; + } + for (rt = w->leaf; rt; rt = rt->dst.rt6_next) { res = c->func(rt, c->arg); if (res < 0) { @@ -1521,9 +1657,9 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root, int (*func)(struct rt6_info *, void *arg), - int prune, void *arg) + bool prune, int sernum, void *arg) { - struct fib6_cleaner_t c; + struct fib6_cleaner c; c.w.root = root; c.w.func = fib6_clean_node; @@ -1531,33 +1667,16 @@ c.w.count = 0; c.w.skip = 0; c.func = func; + c.sernum = sernum; c.arg = arg; c.net = net; fib6_walk(&c.w); } -void fib6_clean_all_ro(struct net *net, int (*func)(struct rt6_info *, void *arg), - int prune, void *arg) -{ - struct fib6_table *table; - struct hlist_head *head; - unsigned int h; - - rcu_read_lock(); - for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { - head = &net->ipv6.fib_table_hash[h]; - hlist_for_each_entry_rcu(table, head, tb6_hlist) { - read_lock_bh(&table->tb6_lock); - fib6_clean_tree(net, &table->tb6_root, - func, prune, arg); - read_unlock_bh(&table->tb6_lock); - } - } - rcu_read_unlock(); -} -void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg), - int prune, void *arg) +static void __fib6_clean_all(struct net *net, + int (*func)(struct rt6_info *, void *), + int sernum, void *arg) { struct fib6_table *table; struct hlist_head *head; @@ -1569,13 +1688,19 @@ hlist_for_each_entry_rcu(table, head, tb6_hlist) { write_lock_bh(&table->tb6_lock); fib6_clean_tree(net, &table->tb6_root, - func, prune, arg); + func, false, sernum, arg); write_unlock_bh(&table->tb6_lock); } } rcu_read_unlock(); } +void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *), + void *arg) +{ + __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg); +} + static int fib6_prune_clone(struct rt6_info *rt, void *arg) { if (rt->rt6i_flags & RTF_CACHE) { @@ -1586,10 +1711,17 @@ return 0; } -static void fib6_prune_clones(struct net *net, struct fib6_node *fn, - struct rt6_info *rt) +static void fib6_prune_clones(struct net *net, struct fib6_node *fn) { - fib6_clean_tree(net, fn, fib6_prune_clone, 1, rt); + fib6_clean_tree(net, fn, fib6_prune_clone, true, + FIB6_NO_SERNUM_CHANGE, NULL); +} + +static void fib6_flush_trees(struct net *net) +{ + int new_sernum = fib6_new_sernum(net); + + __fib6_clean_all(net, NULL, new_sernum, NULL); } /* @@ -1663,7 +1795,7 @@ gc_args.more = icmp6_dst_gc(); - fib6_clean_all(net, fib6_age, 0, NULL); + fib6_clean_all(net, fib6_age, NULL); now = jiffies; net->ipv6.ip6_rt_last_gc = now; @@ -1734,7 +1866,7 @@ kfree(net->ipv6.rt6_stats); out_timer: return -ENOMEM; - } +} static void fib6_net_exit(struct net *net) { @@ -1775,6 +1907,8 @@ NULL); if (ret) goto out_unregister_subsys; + + __fib6_flush_trees = fib6_flush_trees; out: return ret; @@ -1790,3 +1924,189 @@ unregister_pernet_subsys(&fib6_net_ops); kmem_cache_destroy(fib6_node_kmem); } + +#ifdef CONFIG_PROC_FS + +struct ipv6_route_iter { + struct seq_net_private p; + struct fib6_walker w; + loff_t skip; + struct fib6_table *tbl; + int sernum; +}; + +static int ipv6_route_seq_show(struct seq_file *seq, void *v) +{ + struct rt6_info *rt = v; + struct ipv6_route_iter *iter = seq->private; + + seq_printf(seq, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen); + +#ifdef CONFIG_IPV6_SUBTREES + seq_printf(seq, "%pi6 %02x ", &rt->rt6i_src.addr, rt->rt6i_src.plen); +#else + seq_puts(seq, "00000000000000000000000000000000 00 "); +#endif + if (rt->rt6i_flags & RTF_GATEWAY) + seq_printf(seq, "%pi6", &rt->rt6i_gateway); + else + seq_puts(seq, "00000000000000000000000000000000"); + + seq_printf(seq, " %08x %08x %08x %08x %8s\n", + rt->rt6i_metric, atomic_read(&rt->dst.__refcnt), + rt->dst.__use, rt->rt6i_flags, + rt->dst.dev ? rt->dst.dev->name : ""); + iter->w.leaf = NULL; + return 0; +} + +static int ipv6_route_yield(struct fib6_walker *w) +{ + struct ipv6_route_iter *iter = w->args; + + if (!iter->skip) + return 1; + + do { + iter->w.leaf = iter->w.leaf->dst.rt6_next; + iter->skip--; + if (!iter->skip && iter->w.leaf) + return 1; + } while (iter->w.leaf); + + return 0; +} + +static void ipv6_route_seq_setup_walk(struct ipv6_route_iter *iter) +{ + memset(&iter->w, 0, sizeof(iter->w)); + iter->w.func = ipv6_route_yield; + iter->w.root = &iter->tbl->tb6_root; + iter->w.state = FWS_INIT; + iter->w.node = iter->w.root; + iter->w.args = iter; + iter->sernum = iter->w.root->fn_sernum; + INIT_LIST_HEAD(&iter->w.lh); + fib6_walker_link(&iter->w); +} + +static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl, + struct net *net) +{ + unsigned int h; + struct hlist_node *node; + + if (tbl) { + h = (tbl->tb6_id & (FIB6_TABLE_HASHSZ - 1)) + 1; + node = rcu_dereference_bh(hlist_next_rcu(&tbl->tb6_hlist)); + } else { + h = 0; + node = NULL; + } + + while (!node && h < FIB6_TABLE_HASHSZ) { + node = rcu_dereference_bh( + hlist_first_rcu(&net->ipv6.fib_table_hash[h++])); + } + return hlist_entry_safe(node, struct fib6_table, tb6_hlist); +} + +static void ipv6_route_check_sernum(struct ipv6_route_iter *iter) +{ + if (iter->sernum != iter->w.root->fn_sernum) { + iter->sernum = iter->w.root->fn_sernum; + iter->w.state = FWS_INIT; + iter->w.node = iter->w.root; + WARN_ON(iter->w.skip); + iter->w.skip = iter->w.count; + } +} + +static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + int r; + struct rt6_info *n; + struct net *net = seq_file_net(seq); + struct ipv6_route_iter *iter = seq->private; + + if (!v) + goto iter_table; + + n = ((struct rt6_info *)v)->dst.rt6_next; + if (n) { + ++*pos; + return n; + } + +iter_table: + ipv6_route_check_sernum(iter); + read_lock(&iter->tbl->tb6_lock); + r = fib6_walk_continue(&iter->w); + read_unlock(&iter->tbl->tb6_lock); + if (r > 0) { + if (v) + ++*pos; + return iter->w.leaf; + } else if (r < 0) { + fib6_walker_unlink(&iter->w); + return NULL; + } + fib6_walker_unlink(&iter->w); + + iter->tbl = ipv6_route_seq_next_table(iter->tbl, net); + if (!iter->tbl) + return NULL; + + ipv6_route_seq_setup_walk(iter); + goto iter_table; +} + +static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(RCU_BH) +{ + struct net *net = seq_file_net(seq); + struct ipv6_route_iter *iter = seq->private; + + rcu_read_lock_bh(); + iter->tbl = ipv6_route_seq_next_table(NULL, net); + iter->skip = *pos; + + if (iter->tbl) { + ipv6_route_seq_setup_walk(iter); + return ipv6_route_seq_next(seq, NULL, pos); + } else { + return NULL; + } +} + +static bool ipv6_route_iter_active(struct ipv6_route_iter *iter) +{ + struct fib6_walker *w = &iter->w; + return w->node && !(w->state == FWS_U && w->node == w->root); +} + +static void ipv6_route_seq_stop(struct seq_file *seq, void *v) + __releases(RCU_BH) +{ + struct ipv6_route_iter *iter = seq->private; + + if (ipv6_route_iter_active(iter)) + fib6_walker_unlink(&iter->w); + + rcu_read_unlock_bh(); +} + +static const struct seq_operations ipv6_route_seq_ops = { + .start = ipv6_route_seq_start, + .next = ipv6_route_seq_next, + .stop = ipv6_route_seq_stop, + .show = ipv6_route_seq_show +}; + +int ipv6_route_open(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &ipv6_route_seq_ops, + sizeof(struct ipv6_route_iter)); +} + +#endif /* CONFIG_PROC_FS */