diff options
Diffstat (limited to 'net/ipv4/fib_trie.c')
| -rw-r--r-- | net/ipv4/fib_trie.c | 561 |
1 files changed, 254 insertions, 307 deletions
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 200eb538fbb..5afeb5aa4c7 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -12,7 +12,7 @@ * * Hans Liss <hans.liss@its.uu.se> Uppsala Universitet * - * This work is based on the LPC-trie which is originally descibed in: + * This work is based on the LPC-trie which is originally described in: * * An experimental study of compression methods for dynamic tries * Stefan Nilsson and Matti Tikkanen. Algorithmica, 33(1):19-33, 2002. @@ -51,7 +51,6 @@ #define VERSION "0.409" #include <asm/uaccess.h> -#include <asm/system.h> #include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> @@ -72,6 +71,7 @@ #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> +#include <linux/export.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/protocol.h> @@ -95,7 +95,7 @@ typedef unsigned int t_key; #define IS_TNODE(n) (!(n->parent & T_LEAF)) #define IS_LEAF(n) (n->parent & T_LEAF) -struct node { +struct rt_trie_node { unsigned long parent; t_key key; }; @@ -109,9 +109,10 @@ struct leaf { struct leaf_info { struct hlist_node hlist; - struct rcu_head rcu; int plen; + u32 mask_plen; /* ntohl(inet_make_mask(plen)) */ struct list_head falh; + struct rcu_head rcu; }; struct tnode { @@ -123,10 +124,9 @@ struct tnode { unsigned int empty_children; /* KEYLENGTH bits needed */ union { struct rcu_head rcu; - struct work_struct work; struct tnode *tnode_free; }; - struct node *child[0]; + struct rt_trie_node __rcu *child[0]; }; #ifdef CONFIG_IP_FIB_TRIE_STATS @@ -151,16 +151,15 @@ struct trie_stat { }; struct trie { - struct node *trie; + struct rt_trie_node __rcu *trie; #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats stats; #endif }; -static void put_child(struct trie *t, struct tnode *tn, int i, struct node *n); -static void tnode_put_child_reorg(struct tnode *tn, int i, struct node *n, +static void tnode_put_child_reorg(struct tnode *tn, int i, struct rt_trie_node *n, int wasfull); -static struct node *resize(struct trie *t, struct tnode *tn); +static struct rt_trie_node *resize(struct trie *t, struct tnode *tn); static struct tnode *inflate(struct trie *t, struct tnode *tn); static struct tnode *halve(struct trie *t, struct tnode *tn); /* tnodes to free after resize(); protected by RTNL */ @@ -177,39 +176,58 @@ static const int sync_pages = 128; static struct kmem_cache *fn_alias_kmem __read_mostly; static struct kmem_cache *trie_leaf_kmem __read_mostly; -static inline struct tnode *node_parent(struct node *node) +/* + * caller must hold RTNL + */ +static inline struct tnode *node_parent(const struct rt_trie_node *node) { - return (struct tnode *)(node->parent & ~NODE_TYPE_MASK); + unsigned long parent; + + parent = rcu_dereference_index_check(node->parent, lockdep_rtnl_is_held()); + + return (struct tnode *)(parent & ~NODE_TYPE_MASK); } -static inline struct tnode *node_parent_rcu(struct node *node) +/* + * caller must hold RCU read lock or RTNL + */ +static inline struct tnode *node_parent_rcu(const struct rt_trie_node *node) { - struct tnode *ret = node_parent(node); + unsigned long parent; - return rcu_dereference_rtnl(ret); + parent = rcu_dereference_index_check(node->parent, rcu_read_lock_held() || + lockdep_rtnl_is_held()); + + return (struct tnode *)(parent & ~NODE_TYPE_MASK); } /* Same as rcu_assign_pointer * but that macro() assumes that value is a pointer. */ -static inline void node_set_parent(struct node *node, struct tnode *ptr) +static inline void node_set_parent(struct rt_trie_node *node, struct tnode *ptr) { smp_wmb(); node->parent = (unsigned long)ptr | NODE_TYPE(node); } -static inline struct node *tnode_get_child(struct tnode *tn, unsigned int i) +/* + * caller must hold RTNL + */ +static inline struct rt_trie_node *tnode_get_child(const struct tnode *tn, unsigned int i) { BUG_ON(i >= 1U << tn->bits); - return tn->child[i]; + return rtnl_dereference(tn->child[i]); } -static inline struct node *tnode_get_child_rcu(struct tnode *tn, unsigned int i) +/* + * caller must hold RCU read lock or RTNL + */ +static inline struct rt_trie_node *tnode_get_child_rcu(const struct tnode *tn, unsigned int i) { - struct node *ret = tnode_get_child(tn, i); + BUG_ON(i >= 1U << tn->bits); - return rcu_dereference_rtnl(ret); + return rcu_dereference_rtnl(tn->child[i]); } static inline int tnode_child_length(const struct tnode *tn) @@ -217,12 +235,12 @@ static inline int tnode_child_length(const struct tnode *tn) return 1 << tn->bits; } -static inline t_key mask_pfx(t_key k, unsigned short l) +static inline t_key mask_pfx(t_key k, unsigned int l) { return (l == 0) ? 0 : k >> (KEYLENGTH-l) << (KEYLENGTH-l); } -static inline t_key tkey_extract_bits(t_key a, int offset, int bits) +static inline t_key tkey_extract_bits(t_key a, unsigned int offset, unsigned int bits) { if (offset < KEYLENGTH) return ((t_key)(a << offset)) >> (KEYLENGTH - bits); @@ -347,17 +365,12 @@ static void __leaf_free_rcu(struct rcu_head *head) static inline void free_leaf(struct leaf *l) { - call_rcu_bh(&l->rcu, __leaf_free_rcu); -} - -static void __leaf_info_free_rcu(struct rcu_head *head) -{ - kfree(container_of(head, struct leaf_info, rcu)); + call_rcu(&l->rcu, __leaf_free_rcu); } static inline void free_leaf_info(struct leaf_info *leaf) { - call_rcu(&leaf->rcu, __leaf_info_free_rcu); + kfree_rcu(leaf, rcu); } static struct tnode *tnode_alloc(size_t size) @@ -365,27 +378,19 @@ static struct tnode *tnode_alloc(size_t size) if (size <= PAGE_SIZE) return kzalloc(size, GFP_KERNEL); else - return __vmalloc(size, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL); -} - -static void __tnode_vfree(struct work_struct *arg) -{ - struct tnode *tn = container_of(arg, struct tnode, work); - vfree(tn); + return vzalloc(size); } static void __tnode_free_rcu(struct rcu_head *head) { struct tnode *tn = container_of(head, struct tnode, rcu); size_t size = sizeof(struct tnode) + - (sizeof(struct node *) << tn->bits); + (sizeof(struct rt_trie_node *) << tn->bits); if (size <= PAGE_SIZE) kfree(tn); - else { - INIT_WORK(&tn->work, __tnode_vfree); - schedule_work(&tn->work); - } + else + vfree(tn); } static inline void tnode_free(struct tnode *tn) @@ -402,7 +407,7 @@ static void tnode_free_safe(struct tnode *tn) tn->tnode_free = tnode_free_head; tnode_free_head = tn; tnode_free_size += sizeof(struct tnode) + - (sizeof(struct node *) << tn->bits); + (sizeof(struct rt_trie_node *) << tn->bits); } static void tnode_free_flush(void) @@ -436,6 +441,7 @@ static struct leaf_info *leaf_info_new(int plen) struct leaf_info *li = kmalloc(sizeof(struct leaf_info), GFP_KERNEL); if (li) { li->plen = plen; + li->mask_plen = ntohl(inet_make_mask(plen)); INIT_LIST_HEAD(&li->falh); } return li; @@ -443,7 +449,7 @@ static struct leaf_info *leaf_info_new(int plen) static struct tnode *tnode_new(t_key key, int pos, int bits) { - size_t sz = sizeof(struct tnode) + (sizeof(struct node *) << bits); + size_t sz = sizeof(struct tnode) + (sizeof(struct rt_trie_node *) << bits); struct tnode *tn = tnode_alloc(sz); if (tn) { @@ -456,7 +462,7 @@ 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 node) << bits); + sizeof(struct rt_trie_node *) << bits); return tn; } @@ -465,7 +471,7 @@ static struct tnode *tnode_new(t_key key, int pos, int bits) * and no bits are skipped. See discussion in dyntree paper p. 6 */ -static inline int tnode_full(const struct tnode *tn, const struct node *n) +static inline int tnode_full(const struct tnode *tn, const struct rt_trie_node *n) { if (n == NULL || IS_LEAF(n)) return 0; @@ -473,8 +479,8 @@ static inline int tnode_full(const struct tnode *tn, const struct node *n) return ((struct tnode *) n)->pos == tn->pos + tn->bits; } -static inline void put_child(struct trie *t, struct tnode *tn, int i, - struct node *n) +static inline void put_child(struct tnode *tn, int i, + struct rt_trie_node *n) { tnode_put_child_reorg(tn, i, n, -1); } @@ -484,10 +490,10 @@ static inline void put_child(struct trie *t, struct tnode *tn, int i, * Update the value of full_children and empty_children. */ -static void tnode_put_child_reorg(struct tnode *tn, int i, struct node *n, +static void tnode_put_child_reorg(struct tnode *tn, int i, struct rt_trie_node *n, int wasfull) { - struct node *chi = tn->child[i]; + struct rt_trie_node *chi = rtnl_dereference(tn->child[i]); int isfull; BUG_ON(i >= 1<<tn->bits); @@ -515,7 +521,7 @@ static void tnode_put_child_reorg(struct tnode *tn, int i, struct node *n, } #define MAX_WORK 10 -static struct node *resize(struct trie *t, struct tnode *tn) +static struct rt_trie_node *resize(struct trie *t, struct tnode *tn) { int i; struct tnode *old_tn; @@ -605,7 +611,7 @@ static struct node *resize(struct trie *t, struct tnode *tn) /* Keep root node larger */ - if (!node_parent((struct node *)tn)) { + if (!node_parent((struct rt_trie_node *)tn)) { inflate_threshold_use = inflate_threshold_root; halve_threshold_use = halve_threshold_root; } else { @@ -635,7 +641,7 @@ static struct node *resize(struct trie *t, struct tnode *tn) /* Return if at least one inflate is run */ if (max_work != MAX_WORK) - return (struct node *) tn; + return (struct rt_trie_node *) tn; /* * Halve as long as the number of empty children in this @@ -663,9 +669,9 @@ static struct node *resize(struct trie *t, struct tnode *tn) if (tn->empty_children == tnode_child_length(tn) - 1) { one_child: for (i = 0; i < tnode_child_length(tn); i++) { - struct node *n; + struct rt_trie_node *n; - n = tn->child[i]; + n = rtnl_dereference(tn->child[i]); if (!n) continue; @@ -676,7 +682,21 @@ one_child: return n; } } - return (struct node *) tn; + return (struct rt_trie_node *) tn; +} + + +static void tnode_clean_free(struct tnode *tn) +{ + int i; + struct tnode *tofree; + + for (i = 0; i < tnode_child_length(tn); i++) { + tofree = (struct tnode *)rtnl_dereference(tn->child[i]); + if (tofree) + tnode_free(tofree); + } + tnode_free(tn); } static struct tnode *inflate(struct trie *t, struct tnode *tn) @@ -723,14 +743,14 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) goto nomem; } - put_child(t, tn, 2*i, (struct node *) left); - put_child(t, tn, 2*i+1, (struct node *) right); + put_child(tn, 2*i, (struct rt_trie_node *) left); + put_child(tn, 2*i+1, (struct rt_trie_node *) right); } } for (i = 0; i < olen; i++) { struct tnode *inode; - struct node *node = tnode_get_child(oldtnode, i); + struct rt_trie_node *node = tnode_get_child(oldtnode, i); struct tnode *left, *right; int size, j; @@ -742,12 +762,9 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) if (IS_LEAF(node) || ((struct tnode *) node)->pos > tn->pos + tn->bits - 1) { - if (tkey_extract_bits(node->key, - oldtnode->pos + oldtnode->bits, - 1) == 0) - put_child(t, tn, 2*i, node); - else - put_child(t, tn, 2*i+1, node); + put_child(tn, + tkey_extract_bits(node->key, oldtnode->pos, oldtnode->bits + 1), + node); continue; } @@ -755,8 +772,8 @@ static struct tnode *inflate(struct trie *t, struct tnode *tn) inode = (struct tnode *) node; if (inode->bits == 1) { - put_child(t, tn, 2*i, inode->child[0]); - put_child(t, tn, 2*i+1, 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; @@ -786,46 +803,36 @@ 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, inode->child[j]); - put_child(t, right, j, 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); } tnode_free_safe(oldtnode); return tn; nomem: - { - int size = tnode_child_length(tn); - int j; - - for (j = 0; j < size; j++) - if (tn->child[j]) - tnode_free((struct tnode *)tn->child[j]); - - tnode_free(tn); - - return ERR_PTR(-ENOMEM); - } + tnode_clean_free(tn); + return ERR_PTR(-ENOMEM); } static struct tnode *halve(struct trie *t, struct tnode *tn) { struct tnode *oldtnode = tn; - struct node *left, *right; + struct rt_trie_node *left, *right; int i; int olen = tnode_child_length(tn); @@ -856,7 +863,7 @@ static struct tnode *halve(struct trie *t, struct tnode *tn) if (!newn) goto nomem; - put_child(t, tn, i/2, (struct node *)newn); + put_child(tn, i/2, (struct rt_trie_node *)newn); } } @@ -871,37 +878,27 @@ 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; nomem: - { - int size = tnode_child_length(tn); - int j; - - for (j = 0; j < size; j++) - if (tn->child[j]) - tnode_free((struct tnode *)tn->child[j]); - - tnode_free(tn); - - return ERR_PTR(-ENOMEM); - } + tnode_clean_free(tn); + return ERR_PTR(-ENOMEM); } /* readside must use rcu_read_lock currently dump routines @@ -910,10 +907,9 @@ nomem: static struct leaf_info *find_leaf_info(struct leaf *l, int plen) { struct hlist_head *head = &l->list; - struct hlist_node *node; struct leaf_info *li; - hlist_for_each_entry_rcu(li, node, head, hlist) + hlist_for_each_entry_rcu(li, head, hlist) if (li->plen == plen) return li; @@ -933,12 +929,11 @@ static inline struct list_head *get_fa_head(struct leaf *l, int plen) static void insert_leaf_info(struct hlist_head *head, struct leaf_info *new) { struct leaf_info *li = NULL, *last = NULL; - struct hlist_node *node; if (hlist_empty(head)) { hlist_add_head_rcu(&new->hlist, head); } else { - hlist_for_each_entry(li, node, head, hlist) { + hlist_for_each_entry(li, head, hlist) { if (new->plen > li->plen) break; @@ -958,7 +953,7 @@ fib_find_node(struct trie *t, u32 key) { int pos; struct tnode *tn; - struct node *n; + struct rt_trie_node *n; pos = 0; n = rcu_dereference_rtnl(t->trie); @@ -993,17 +988,17 @@ static void trie_rebalance(struct trie *t, struct tnode *tn) key = tn->key; - while (tn != NULL && (tp = node_parent((struct node *)tn)) != NULL) { + while (tn != NULL && (tp = node_parent((struct rt_trie_node *)tn)) != NULL) { cindex = tkey_extract_bits(key, tp->pos, tp->bits); wasfull = tnode_full(tp, tnode_get_child(tp, cindex)); - tn = (struct tnode *) resize(t, (struct tnode *)tn); + tn = (struct tnode *)resize(t, tn); - tnode_put_child_reorg((struct tnode *)tp, cindex, - (struct node *)tn, wasfull); + tnode_put_child_reorg(tp, cindex, + (struct rt_trie_node *)tn, wasfull); - tp = node_parent((struct node *) tn); + tp = node_parent((struct rt_trie_node *) tn); if (!tp) - rcu_assign_pointer(t->trie, (struct node *)tn); + rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn); tnode_free_flush(); if (!tp) @@ -1013,9 +1008,9 @@ static void trie_rebalance(struct trie *t, struct tnode *tn) /* Handle last (top) tnode */ if (IS_TNODE(tn)) - tn = (struct tnode *)resize(t, (struct tnode *)tn); + tn = (struct tnode *)resize(t, tn); - rcu_assign_pointer(t->trie, (struct node *)tn); + rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn); tnode_free_flush(); } @@ -1025,7 +1020,7 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) { int pos, newpos; struct tnode *tp = NULL, *tn = NULL; - struct node *n; + struct rt_trie_node *n; struct leaf *l; int missbit; struct list_head *fa_head = NULL; @@ -1033,7 +1028,7 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) t_key cindex; pos = 0; - n = t->trie; + n = rtnl_dereference(t->trie); /* If we point to NULL, stop. Either the tree is empty and we should * just put a new leaf in if, or we have reached an empty child slot, @@ -1111,10 +1106,10 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) if (t->trie && n == NULL) { /* Case 2: n is NULL, and will just insert a new leaf */ - node_set_parent((struct node *)l, tp); + node_set_parent((struct rt_trie_node *)l, tp); cindex = tkey_extract_bits(key, tp->pos, tp->bits); - put_child(t, (struct tnode *)tp, cindex, (struct 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. */ /* @@ -1122,12 +1117,8 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) * first tnode need some special handling */ - if (tp) - pos = tp->pos+tp->bits; - else - pos = 0; - if (n) { + pos = tp ? tp->pos+tp->bits : 0; newpos = tkey_mismatch(key, pos, n->key); tn = tnode_new(n->key, newpos, 1); } else { @@ -1141,26 +1132,24 @@ static struct list_head *fib_insert_node(struct trie *t, u32 key, int plen) return NULL; } - node_set_parent((struct node *)tn, tp); + node_set_parent((struct rt_trie_node *)tn, tp); missbit = tkey_extract_bits(key, newpos, 1); - put_child(t, tn, missbit, (struct 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, (struct tnode *)tp, cindex, - (struct node *)tn); + put_child(tp, cindex, (struct rt_trie_node *)tn); } else { - rcu_assign_pointer(t->trie, (struct node *)tn); + rcu_assign_pointer(t->trie, (struct rt_trie_node *)tn); tp = tn; } } if (tp && tp->pos + tp->bits > 32) - pr_warning("fib_trie" - " tp=%p pos=%d, bits=%d, key=%0x plen=%d\n", - tp, tp->pos, tp->bits, key, plen); + pr_warn("fib_trie tp=%p pos=%d, bits=%d, key=%0x plen=%d\n", + tp, tp->pos, tp->bits, key, plen); /* Rebalance the trie */ @@ -1245,7 +1234,6 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) if (fa->fa_info->fib_priority != fi->fib_priority) break; if (fa->fa_type == cfg->fc_type && - fa->fa_scope == cfg->fc_scope && fa->fa_info == fi) { fa_match = fa; break; @@ -1271,7 +1259,6 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) new_fa->fa_tos = fa->fa_tos; new_fa->fa_info = fi; new_fa->fa_type = cfg->fc_type; - new_fa->fa_scope = cfg->fc_scope; state = fa->fa_state; new_fa->fa_state = state & ~FA_S_ACCESSED; @@ -1280,7 +1267,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) fib_release_info(fi_drop); if (state & FA_S_ACCESSED) - rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); + rt_cache_flush(cfg->fc_nlinfo.nl_net); rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, &cfg->fc_nlinfo, NLM_F_REPLACE); @@ -1308,7 +1295,6 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) new_fa->fa_info = fi; new_fa->fa_tos = tos; new_fa->fa_type = cfg->fc_type; - new_fa->fa_scope = cfg->fc_scope; new_fa->fa_state = 0; /* * Insert new entry to the list. @@ -1322,10 +1308,13 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) } } + if (!plen) + tb->tb_num_default++; + list_add_tail_rcu(&new_fa->fa_list, (fa ? &fa->fa_list : fa_head)); - rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); + rt_cache_flush(cfg->fc_nlinfo.nl_net); rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, &cfg->fc_nlinfo, 0); succeeded: @@ -1340,49 +1329,83 @@ err: } /* should be called with rcu_read_lock */ -static int check_leaf(struct trie *t, struct leaf *l, - t_key key, const struct flowi *flp, +static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l, + t_key key, const struct flowi4 *flp, struct fib_result *res, int fib_flags) { struct leaf_info *li; struct hlist_head *hhead = &l->list; - struct hlist_node *node; - hlist_for_each_entry_rcu(li, node, hhead, hlist) { - int err; - int plen = li->plen; - __be32 mask = inet_make_mask(plen); + hlist_for_each_entry_rcu(li, hhead, hlist) { + struct fib_alias *fa; - if (l->key != (key & ntohl(mask))) + if (l->key != (key & li->mask_plen)) continue; - err = fib_semantic_match(&li->falh, flp, res, plen, fib_flags); + list_for_each_entry_rcu(fa, &li->falh, fa_list) { + struct fib_info *fi = fa->fa_info; + int nhsel, err; + if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos) + continue; + if (fi->fib_dead) + continue; + if (fa->fa_info->fib_scope < flp->flowi4_scope) + continue; + fib_alias_accessed(fa); + err = fib_props[fa->fa_type].error; + if (err) { #ifdef CONFIG_IP_FIB_TRIE_STATS - if (err <= 0) - t->stats.semantic_match_passed++; - else - t->stats.semantic_match_miss++; + t->stats.semantic_match_passed++; +#endif + return err; + } + if (fi->fib_flags & RTNH_F_DEAD) + continue; + for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) { + const struct fib_nh *nh = &fi->fib_nh[nhsel]; + + if (nh->nh_flags & RTNH_F_DEAD) + continue; + if (flp->flowi4_oif && flp->flowi4_oif != nh->nh_oif) + continue; + +#ifdef CONFIG_IP_FIB_TRIE_STATS + t->stats.semantic_match_passed++; +#endif + res->prefixlen = li->plen; + res->nh_sel = nhsel; + res->type = fa->fa_type; + res->scope = fa->fa_info->fib_scope; + res->fi = fi; + res->table = tb; + res->fa_head = &li->falh; + if (!(fib_flags & FIB_LOOKUP_NOREF)) + atomic_inc(&fi->fib_clntref); + return 0; + } + } + +#ifdef CONFIG_IP_FIB_TRIE_STATS + t->stats.semantic_match_miss++; #endif - if (err <= 0) - return err; } return 1; } -int fib_table_lookup(struct fib_table *tb, const struct flowi *flp, +int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, struct fib_result *res, int fib_flags) { struct trie *t = (struct trie *) tb->tb_data; int ret; - struct node *n; + struct rt_trie_node *n; struct tnode *pn; - int pos, bits; - t_key key = ntohl(flp->fl4_dst); - int chopped_off; + unsigned int pos, bits; + t_key key = ntohl(flp->daddr); + unsigned int chopped_off; t_key cindex = 0; - int current_prefix_length = KEYLENGTH; + unsigned int current_prefix_length = KEYLENGTH; struct tnode *cn; t_key pref_mismatch; @@ -1398,7 +1421,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi *flp, /* Just a leaf? */ if (IS_LEAF(n)) { - ret = check_leaf(t, (struct leaf *)n, key, flp, res, fib_flags); + ret = check_leaf(tb, t, (struct leaf *)n, key, flp, res, fib_flags); goto found; } @@ -1423,7 +1446,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi *flp, } if (IS_LEAF(n)) { - ret = check_leaf(t, (struct leaf *)n, key, flp, res, fib_flags); + ret = check_leaf(tb, t, (struct leaf *)n, key, flp, res, fib_flags); if (ret > 0) goto backtrace; goto found; @@ -1507,7 +1530,8 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi *flp, * state.directly. */ if (pref_mismatch) { - int mp = KEYLENGTH - fls(pref_mismatch); + /* fls(x) = __fls(x) + 1 */ + int mp = KEYLENGTH - __fls(pref_mismatch) - 1; if (tkey_extract_bits(cn->key, mp, cn->pos - mp) != 0) goto backtrace; @@ -1541,7 +1565,7 @@ backtrace: if (chopped_off <= pn->bits) { cindex &= ~(1 << (chopped_off-1)); } else { - struct tnode *parent = node_parent_rcu((struct node *) pn); + struct tnode *parent = node_parent_rcu((struct rt_trie_node *) pn); if (!parent) goto failed; @@ -1562,22 +1586,23 @@ found: rcu_read_unlock(); return ret; } +EXPORT_SYMBOL_GPL(fib_table_lookup); /* * Remove the leaf and return parent. */ static void trie_leaf_remove(struct trie *t, struct leaf *l) { - struct tnode *tp = node_parent((struct node *) l); + struct tnode *tp = node_parent((struct rt_trie_node *) l); pr_debug("entering trie_leaf_remove(%p)\n", l); if (tp) { t_key cindex = tkey_extract_bits(l->key, tp->pos, tp->bits); - put_child(t, (struct tnode *)tp, cindex, NULL); + put_child(tp, cindex, NULL); trie_rebalance(t, tp); } else - rcu_assign_pointer(t->trie, NULL); + RCU_INIT_POINTER(t->trie, NULL); free_leaf(l); } @@ -1611,7 +1636,12 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) if (!l) return -ESRCH; - fa_head = get_fa_head(l, plen); + li = find_leaf_info(l, plen); + + if (!li) + return -ESRCH; + + fa_head = &li->falh; fa = fib_find_alias(fa_head, tos, 0); if (!fa) @@ -1629,7 +1659,9 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) if ((!cfg->fc_type || fa->fa_type == cfg->fc_type) && (cfg->fc_scope == RT_SCOPE_NOWHERE || - fa->fa_scope == cfg->fc_scope) && + fa->fa_info->fib_scope == cfg->fc_scope) && + (!cfg->fc_prefsrc || + fi->fib_prefsrc == cfg->fc_prefsrc) && (!cfg->fc_protocol || fi->fib_protocol == cfg->fc_protocol) && fib_nh_match(cfg, fi) == 0) { @@ -1645,11 +1677,11 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) rtmsg_fib(RTM_DELROUTE, htonl(key), fa, plen, tb->tb_id, &cfg->fc_nlinfo, 0); - l = fib_find_node(t, key); - li = find_leaf_info(l, plen); - list_del_rcu(&fa->fa_list); + if (!plen) + tb->tb_num_default--; + if (list_empty(fa_head)) { hlist_del_rcu(&li->hlist); free_leaf_info(li); @@ -1659,7 +1691,7 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) trie_leaf_remove(t, l); if (fa->fa_state & FA_S_ACCESSED) - rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); + rt_cache_flush(cfg->fc_nlinfo.nl_net); fib_release_info(fa->fa_info); alias_free_mem_rcu(fa); @@ -1688,10 +1720,10 @@ static int trie_flush_leaf(struct leaf *l) { int found = 0; struct hlist_head *lih = &l->list; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; struct leaf_info *li = NULL; - hlist_for_each_entry_safe(li, node, tmp, lih, hlist) { + hlist_for_each_entry_safe(li, tmp, lih, hlist) { found += trie_flush_list(&li->falh); if (list_empty(&li->falh)) { @@ -1706,7 +1738,7 @@ static int trie_flush_leaf(struct leaf *l) * Scan for the next right leaf starting at node p->child[idx] * Since we have back pointer, no recursion necessary. */ -static struct leaf *leaf_walk_rcu(struct tnode *p, struct node *c) +static struct leaf *leaf_walk_rcu(struct tnode *p, struct rt_trie_node *c) { do { t_key idx; @@ -1721,10 +1753,8 @@ static struct leaf *leaf_walk_rcu(struct tnode *p, struct node *c) if (!c) continue; - if (IS_LEAF(c)) { - prefetch(p->child[idx]); + if (IS_LEAF(c)) return (struct leaf *) c; - } /* Rescan start scanning in new node */ p = (struct tnode *) c; @@ -1732,7 +1762,7 @@ static struct leaf *leaf_walk_rcu(struct tnode *p, struct node *c) } /* Node empty, walk back up to parent */ - c = (struct node *) p; + c = (struct rt_trie_node *) p; } while ((p = node_parent_rcu(c)) != NULL); return NULL; /* Root of trie */ @@ -1753,7 +1783,7 @@ static struct leaf *trie_firstleaf(struct trie *t) static struct leaf *trie_nextleaf(struct leaf *l) { - struct node *c = (struct node *) l; + struct rt_trie_node *c = (struct rt_trie_node *) l; struct tnode *p = node_parent_rcu(c); if (!p) @@ -1802,80 +1832,6 @@ void fib_free_table(struct fib_table *tb) kfree(tb); } -void fib_table_select_default(struct fib_table *tb, - const struct flowi *flp, - struct fib_result *res) -{ - struct trie *t = (struct trie *) tb->tb_data; - int order, last_idx; - struct fib_info *fi = NULL; - struct fib_info *last_resort; - struct fib_alias *fa = NULL; - struct list_head *fa_head; - struct leaf *l; - - last_idx = -1; - last_resort = NULL; - order = -1; - - rcu_read_lock(); - - l = fib_find_node(t, 0); - if (!l) - goto out; - - fa_head = get_fa_head(l, 0); - if (!fa_head) - goto out; - - if (list_empty(fa_head)) - goto out; - - list_for_each_entry_rcu(fa, fa_head, fa_list) { - struct fib_info *next_fi = fa->fa_info; - - if (fa->fa_scope != res->scope || - fa->fa_type != RTN_UNICAST) - continue; - - if (next_fi->fib_priority > res->fi->fib_priority) - break; - if (!next_fi->fib_nh[0].nh_gw || - next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK) - continue; - - fib_alias_accessed(fa); - - if (fi == NULL) { - if (next_fi != res->fi) - break; - } else if (!fib_detect_death(fi, order, &last_resort, - &last_idx, tb->tb_default)) { - fib_result_assign(res, fi); - tb->tb_default = order; - goto out; - } - fi = next_fi; - order++; - } - if (order <= 0 || fi == NULL) { - tb->tb_default = -1; - goto out; - } - - if (!fib_detect_death(fi, order, &last_resort, &last_idx, - tb->tb_default)) { - fib_result_assign(res, fi); - tb->tb_default = order; - goto out; - } - if (last_idx >= 0) - fib_result_assign(res, last_resort); - tb->tb_default = last_idx; -out: - rcu_read_unlock(); -} - static int fn_trie_dump_fa(t_key key, int plen, struct list_head *fah, struct fib_table *tb, struct sk_buff *skb, struct netlink_callback *cb) @@ -1895,12 +1851,11 @@ static int fn_trie_dump_fa(t_key key, int plen, struct list_head *fah, continue; } - if (fib_dump_info(skb, NETLINK_CB(cb->skb).pid, + if (fib_dump_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWROUTE, tb->tb_id, fa->fa_type, - fa->fa_scope, xkey, plen, fa->fa_tos, @@ -1918,14 +1873,13 @@ static int fn_trie_dump_leaf(struct leaf *l, struct fib_table *tb, struct sk_buff *skb, struct netlink_callback *cb) { struct leaf_info *li; - struct hlist_node *node; int i, s_i; s_i = cb->args[4]; i = 0; /* rcu_read_lock is hold by caller */ - hlist_for_each_entry_rcu(li, node, &l->list, hlist) { + hlist_for_each_entry_rcu(li, &l->list, hlist) { if (i < s_i) { i++; continue; @@ -1990,7 +1944,7 @@ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, return skb->len; } -void __init fib_hash_init(void) +void __init fib_trie_init(void) { fn_alias_kmem = kmem_cache_create("ip_fib_alias", sizeof(struct fib_alias), @@ -2003,8 +1957,7 @@ void __init fib_hash_init(void) } -/* Fix more generic FIB names for init later */ -struct fib_table *fib_hash_table(u32 id) +struct fib_table *fib_trie_table(u32 id) { struct fib_table *tb; struct trie *t; @@ -2016,13 +1969,11 @@ struct fib_table *fib_hash_table(u32 id) tb->tb_id = id; tb->tb_default = -1; + tb->tb_num_default = 0; t = (struct trie *) tb->tb_data; memset(t, 0, sizeof(*t)); - if (id == RT_TABLE_LOCAL) - pr_info("IPv4 FIB: Using LC-trie version %s\n", VERSION); - return tb; } @@ -2036,7 +1987,7 @@ struct fib_trie_iter { unsigned int depth; }; -static struct node *fib_trie_get_next(struct fib_trie_iter *iter) +static struct rt_trie_node *fib_trie_get_next(struct fib_trie_iter *iter) { struct tnode *tn = iter->tnode; unsigned int cindex = iter->index; @@ -2050,7 +2001,7 @@ static struct node *fib_trie_get_next(struct fib_trie_iter *iter) iter->tnode, iter->index, iter->depth); rescan: while (cindex < (1<<tn->bits)) { - struct node *n = tnode_get_child_rcu(tn, cindex); + struct rt_trie_node *n = tnode_get_child_rcu(tn, cindex); if (n) { if (IS_LEAF(n)) { @@ -2069,7 +2020,7 @@ rescan: } /* Current node exhausted, pop back up */ - p = node_parent_rcu((struct node *)tn); + p = node_parent_rcu((struct rt_trie_node *)tn); if (p) { cindex = tkey_extract_bits(tn->key, p->pos, p->bits)+1; tn = p; @@ -2081,10 +2032,10 @@ rescan: return NULL; } -static struct node *fib_trie_get_first(struct fib_trie_iter *iter, +static struct rt_trie_node *fib_trie_get_first(struct fib_trie_iter *iter, struct trie *t) { - struct node *n; + struct rt_trie_node *n; if (!t) return NULL; @@ -2108,7 +2059,7 @@ static struct node *fib_trie_get_first(struct fib_trie_iter *iter, static void trie_collect_stats(struct trie *t, struct trie_stat *s) { - struct node *n; + struct rt_trie_node *n; struct fib_trie_iter iter; memset(s, 0, sizeof(*s)); @@ -2118,14 +2069,13 @@ static void trie_collect_stats(struct trie *t, struct trie_stat *s) if (IS_LEAF(n)) { struct leaf *l = (struct leaf *)n; struct leaf_info *li; - struct hlist_node *tmp; s->leaves++; s->totdepth += iter.depth; if (iter.depth > s->maxdepth) s->maxdepth = iter.depth; - hlist_for_each_entry_rcu(li, tmp, &l->list, hlist) + hlist_for_each_entry_rcu(li, &l->list, hlist) ++s->prefixes; } else { const struct tnode *tn = (const struct tnode *) n; @@ -2173,7 +2123,7 @@ static void trie_show_stats(struct seq_file *seq, struct trie_stat *stat) max--; pointers = 0; - for (i = 1; i <= max; i++) + for (i = 1; i < max; i++) if (stat->nodesizes[i] != 0) { seq_printf(seq, " %u: %u", i, stat->nodesizes[i]); pointers += (1<<i) * stat->nodesizes[i]; @@ -2181,7 +2131,7 @@ static void trie_show_stats(struct seq_file *seq, struct trie_stat *stat) seq_putc(seq, '\n'); seq_printf(seq, "\tPointers: %u\n", pointers); - bytes += sizeof(struct node *) * pointers; + bytes += sizeof(struct rt_trie_node *) * pointers; seq_printf(seq, "Null ptrs: %u\n", stat->nullpointers); seq_printf(seq, "Total size: %u kB\n", (bytes + 1023) / 1024); } @@ -2226,10 +2176,9 @@ static int fib_triestat_seq_show(struct seq_file *seq, void *v) for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; - struct hlist_node *node; struct fib_table *tb; - hlist_for_each_entry_rcu(tb, node, head, tb_hlist) { + hlist_for_each_entry_rcu(tb, head, tb_hlist) { struct trie *t = (struct trie *) tb->tb_data; struct trie_stat stat; @@ -2262,7 +2211,7 @@ static const struct file_operations fib_triestat_fops = { .release = single_release_net, }; -static struct node *fib_trie_get_idx(struct seq_file *seq, loff_t pos) +static struct rt_trie_node *fib_trie_get_idx(struct seq_file *seq, loff_t pos) { struct fib_trie_iter *iter = seq->private; struct net *net = seq_file_net(seq); @@ -2271,11 +2220,10 @@ static struct node *fib_trie_get_idx(struct seq_file *seq, loff_t pos) for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; - struct hlist_node *node; struct fib_table *tb; - hlist_for_each_entry_rcu(tb, node, head, tb_hlist) { - struct node *n; + hlist_for_each_entry_rcu(tb, head, tb_hlist) { + struct rt_trie_node *n; for (n = fib_trie_get_first(iter, (struct trie *) tb->tb_data); @@ -2304,7 +2252,7 @@ static void *fib_trie_seq_next(struct seq_file *seq, void *v, loff_t *pos) struct fib_table *tb = iter->tb; struct hlist_node *tb_node; unsigned int h; - struct node *n; + struct rt_trie_node *n; ++*pos; /* next node in same table */ @@ -2314,7 +2262,7 @@ static void *fib_trie_seq_next(struct seq_file *seq, void *v, loff_t *pos) /* walk rest of this hash chain */ h = tb->tb_id & (FIB_TABLE_HASHSZ - 1); - while ( (tb_node = rcu_dereference(tb->tb_hlist.next)) ) { + while ((tb_node = rcu_dereference(hlist_next_rcu(&tb->tb_hlist)))) { tb = hlist_entry(tb_node, struct fib_table, tb_hlist); n = fib_trie_get_first(iter, (struct trie *) tb->tb_data); if (n) @@ -2324,7 +2272,7 @@ static void *fib_trie_seq_next(struct seq_file *seq, void *v, loff_t *pos) /* new hash chain */ while (++h < FIB_TABLE_HASHSZ) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; - hlist_for_each_entry_rcu(tb, tb_node, head, tb_hlist) { + hlist_for_each_entry_rcu(tb, head, tb_hlist) { n = fib_trie_get_first(iter, (struct trie *) tb->tb_data); if (n) goto found; @@ -2390,7 +2338,7 @@ static inline const char *rtn_type(char *buf, size_t len, unsigned int t) static int fib_trie_seq_show(struct seq_file *seq, void *v) { const struct fib_trie_iter *iter = seq->private; - struct node *n = v; + struct rt_trie_node *n = v; if (!node_parent_rcu(n)) fib_table_print(seq, iter->tb); @@ -2407,13 +2355,12 @@ static int fib_trie_seq_show(struct seq_file *seq, void *v) } else { struct leaf *l = (struct leaf *) n; struct leaf_info *li; - struct hlist_node *node; __be32 val = htonl(l->key); seq_indent(seq, iter->depth); seq_printf(seq, " |-- %pI4\n", &val); - hlist_for_each_entry_rcu(li, node, &l->list, hlist) { + hlist_for_each_entry_rcu(li, &l->list, hlist) { struct fib_alias *fa; list_for_each_entry_rcu(fa, &li->falh, fa_list) { @@ -2422,7 +2369,7 @@ static int fib_trie_seq_show(struct seq_file *seq, void *v) seq_indent(seq, iter->depth+1); seq_printf(seq, " /%d %s %s", li->plen, rtn_scope(buf1, sizeof(buf1), - fa->fa_scope), + fa->fa_info->fib_scope), rtn_type(buf2, sizeof(buf2), fa->fa_type)); if (fa->fa_tos) @@ -2558,7 +2505,6 @@ static int fib_route_seq_show(struct seq_file *seq, void *v) { struct leaf *l = v; struct leaf_info *li; - struct hlist_node *node; if (v == SEQ_START_TOKEN) { seq_printf(seq, "%-127s\n", "Iface\tDestination\tGateway " @@ -2567,7 +2513,7 @@ static int fib_route_seq_show(struct seq_file *seq, void *v) return 0; } - hlist_for_each_entry_rcu(li, node, &l->list, hlist) { + hlist_for_each_entry_rcu(li, &l->list, hlist) { struct fib_alias *fa; __be32 mask, prefix; @@ -2577,16 +2523,17 @@ static int fib_route_seq_show(struct seq_file *seq, void *v) list_for_each_entry_rcu(fa, &li->falh, fa_list) { const struct fib_info *fi = fa->fa_info; unsigned int flags = fib_flag_trans(fa->fa_type, mask, fi); - int len; if (fa->fa_type == RTN_BROADCAST || fa->fa_type == RTN_MULTICAST) continue; + seq_setwidth(seq, 127); + if (fi) seq_printf(seq, "%s\t%08X\t%08X\t%04X\t%d\t%u\t" - "%d\t%08X\t%d\t%u\t%u%n", + "%d\t%08X\t%d\t%u\t%u", fi->fib_dev ? fi->fib_dev->name : "*", prefix, fi->fib_nh->nh_gw, flags, 0, 0, @@ -2595,15 +2542,15 @@ static int fib_route_seq_show(struct seq_file *seq, void *v) (fi->fib_advmss ? fi->fib_advmss + 40 : 0), fi->fib_window, - fi->fib_rtt >> 3, &len); + fi->fib_rtt >> 3); else seq_printf(seq, "*\t%08X\t%08X\t%04X\t%d\t%u\t" - "%d\t%08X\t%d\t%u\t%u%n", + "%d\t%08X\t%d\t%u\t%u", prefix, 0, flags, 0, 0, 0, - mask, 0, 0, 0, &len); + mask, 0, 0, 0); - seq_printf(seq, "%*s\n", 127 - len, ""); + seq_pad(seq, '\n'); } } @@ -2633,31 +2580,31 @@ static const struct file_operations fib_route_fops = { int __net_init fib_proc_init(struct net *net) { - if (!proc_net_fops_create(net, "fib_trie", S_IRUGO, &fib_trie_fops)) + if (!proc_create("fib_trie", S_IRUGO, net->proc_net, &fib_trie_fops)) goto out1; - if (!proc_net_fops_create(net, "fib_triestat", S_IRUGO, - &fib_triestat_fops)) + if (!proc_create("fib_triestat", S_IRUGO, net->proc_net, + &fib_triestat_fops)) goto out2; - if (!proc_net_fops_create(net, "route", S_IRUGO, &fib_route_fops)) + if (!proc_create("route", S_IRUGO, net->proc_net, &fib_route_fops)) goto out3; return 0; out3: - proc_net_remove(net, "fib_triestat"); + remove_proc_entry("fib_triestat", net->proc_net); out2: - proc_net_remove(net, "fib_trie"); + remove_proc_entry("fib_trie", net->proc_net); out1: return -ENOMEM; } void __net_exit fib_proc_exit(struct net *net) { - proc_net_remove(net, "fib_trie"); - proc_net_remove(net, "fib_triestat"); - proc_net_remove(net, "route"); + remove_proc_entry("fib_trie", net->proc_net); + remove_proc_entry("fib_triestat", net->proc_net); + remove_proc_entry("route", net->proc_net); } #endif /* CONFIG_PROC_FS */ |