* IP-address lookup using LC-tries. Stefan Nilsson and Gunnar Karlsson
* IEEE Journal on Selected Areas in Communications, 17(6):1083-1092, June 1999
*
- * Version: $Id: fib_trie.c,v 1.3 2005/06/08 14:20:01 robert Exp $
- *
*
* Code from fib_hash has been reused which includes the following header:
*
* Patrick McHardy <kaber@trash.net>
*/
-#define VERSION "0.408"
+#define VERSION "0.409"
#include <asm/uaccess.h>
#include <asm/system.h>
union {
struct rcu_head rcu;
struct work_struct work;
+ struct tnode *tnode_free;
};
struct node *child[0];
};
static struct 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 */
+static struct tnode *tnode_free_head;
+static size_t tnode_free_size;
+
+/*
+ * synchronize_rcu after call_rcu for that many pages; it should be especially
+ * useful before resizing the root node with PREEMPT_NONE configs; the value was
+ * obtained experimentally, aiming to avoid visible slowdown.
+ */
+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 const int halve_threshold = 25;
static const int inflate_threshold = 50;
-static const int halve_threshold_root = 8;
-static const int inflate_threshold_root = 15;
-
+static const int halve_threshold_root = 15;
+static const int inflate_threshold_root = 30;
static void __alias_free_mem(struct rcu_head *head)
{
call_rcu(&tn->rcu, __tnode_free_rcu);
}
+static void tnode_free_safe(struct tnode *tn)
+{
+ BUG_ON(IS_LEAF(tn));
+ tn->tnode_free = tnode_free_head;
+ tnode_free_head = tn;
+ tnode_free_size += sizeof(struct tnode) +
+ (sizeof(struct node *) << tn->bits);
+}
+
+static void tnode_free_flush(void)
+{
+ struct tnode *tn;
+
+ while ((tn = tnode_free_head)) {
+ tnode_free_head = tn->tnode_free;
+ tn->tnode_free = NULL;
+ tnode_free(tn);
+ }
+
+ if (tnode_free_size >= PAGE_SIZE * sync_pages) {
+ tnode_free_size = 0;
+ synchronize_rcu();
+ }
+}
+
static struct leaf *leaf_new(void)
{
struct leaf *l = kmem_cache_alloc(trie_leaf_kmem, GFP_KERNEL);
rcu_assign_pointer(tn->child[i], n);
}
+#define MAX_WORK 10
static struct node *resize(struct trie *t, struct tnode *tn)
{
int i;
- int err = 0;
struct tnode *old_tn;
int inflate_threshold_use;
int halve_threshold_use;
- int max_resize;
+ int max_work;
if (!tn)
return NULL;
/* No children */
if (tn->empty_children == tnode_child_length(tn)) {
- tnode_free(tn);
+ tnode_free_safe(tn);
return NULL;
}
/* One child */
if (tn->empty_children == tnode_child_length(tn) - 1)
- for (i = 0; i < tnode_child_length(tn); i++) {
- struct node *n;
-
- n = tn->child[i];
- if (!n)
- continue;
-
- /* compress one level */
- node_set_parent(n, NULL);
- tnode_free(tn);
- return n;
- }
+ goto one_child;
/*
* Double as long as the resulting node has a number of
* nonempty nodes that are above the threshold.
/* Keep root node larger */
- if (!tn->parent)
+ if (!node_parent((struct node*) tn)) {
inflate_threshold_use = inflate_threshold_root;
- else
+ halve_threshold_use = halve_threshold_root;
+ }
+ else {
inflate_threshold_use = inflate_threshold;
+ halve_threshold_use = halve_threshold;
+ }
- err = 0;
- max_resize = 10;
- while ((tn->full_children > 0 && max_resize-- &&
+ max_work = MAX_WORK;
+ while ((tn->full_children > 0 && max_work-- &&
50 * (tn->full_children + tnode_child_length(tn)
- tn->empty_children)
>= inflate_threshold_use * tnode_child_length(tn))) {
}
}
- if (max_resize < 0) {
- if (!tn->parent)
- pr_warning("Fix inflate_threshold_root."
- " Now=%d size=%d bits\n",
- inflate_threshold_root, tn->bits);
- else
- pr_warning("Fix inflate_threshold."
- " Now=%d size=%d bits\n",
- inflate_threshold, tn->bits);
- }
-
check_tnode(tn);
+ /* Return if at least one inflate is run */
+ if( max_work != MAX_WORK)
+ return (struct node *) tn;
+
/*
* Halve as long as the number of empty children in this
* node is above threshold.
*/
-
- /* Keep root node larger */
-
- if (!tn->parent)
- halve_threshold_use = halve_threshold_root;
- else
- halve_threshold_use = halve_threshold;
-
- err = 0;
- max_resize = 10;
- while (tn->bits > 1 && max_resize-- &&
+ max_work = MAX_WORK;
+ while (tn->bits > 1 && max_work-- &&
100 * (tnode_child_length(tn) - tn->empty_children) <
halve_threshold_use * tnode_child_length(tn)) {
}
}
- if (max_resize < 0) {
- if (!tn->parent)
- pr_warning("Fix halve_threshold_root."
- " Now=%d size=%d bits\n",
- halve_threshold_root, tn->bits);
- else
- pr_warning("Fix halve_threshold."
- " Now=%d size=%d bits\n",
- halve_threshold, tn->bits);
- }
/* Only one child remains */
- if (tn->empty_children == tnode_child_length(tn) - 1)
+ if (tn->empty_children == tnode_child_length(tn) - 1) {
+one_child:
for (i = 0; i < tnode_child_length(tn); i++) {
struct node *n;
/* compress one level */
node_set_parent(n, NULL);
- tnode_free(tn);
+ tnode_free_safe(tn);
return n;
}
-
+ }
return (struct node *) tn;
}
put_child(t, tn, 2*i, inode->child[0]);
put_child(t, tn, 2*i+1, inode->child[1]);
- tnode_free(inode);
+ tnode_free_safe(inode);
continue;
}
put_child(t, tn, 2*i, resize(t, left));
put_child(t, tn, 2*i+1, resize(t, right));
- tnode_free(inode);
+ tnode_free_safe(inode);
}
- tnode_free(oldtnode);
+ tnode_free_safe(oldtnode);
return tn;
nomem:
{
put_child(t, newBinNode, 1, right);
put_child(t, tn, i/2, resize(t, newBinNode));
}
- tnode_free(oldtnode);
+ tnode_free_safe(oldtnode);
return tn;
nomem:
{
return NULL;
}
-static struct node *trie_rebalance(struct trie *t, struct tnode *tn)
+static void trie_rebalance(struct trie *t, struct tnode *tn)
{
int wasfull;
- t_key cindex, key = tn->key;
+ t_key cindex, key;
struct tnode *tp;
+ key = tn->key;
+
while (tn != NULL && (tp = node_parent((struct node *)tn)) != NULL) {
cindex = tkey_extract_bits(key, tp->pos, tp->bits);
wasfull = tnode_full(tp, tnode_get_child(tp, cindex));
tp = node_parent((struct node *) tn);
if (!tp)
+ rcu_assign_pointer(t->trie, (struct node *)tn);
+
+ tnode_free_flush();
+ if (!tp)
break;
tn = tp;
}
if (IS_TNODE(tn))
tn = (struct tnode *)resize(t, (struct tnode *)tn);
- return (struct node *)tn;
+ rcu_assign_pointer(t->trie, (struct node *)tn);
+ tnode_free_flush();
+
+ return;
}
/* only used from updater-side */
/* Rebalance the trie */
- rcu_assign_pointer(t->trie, trie_rebalance(t, tp));
+ trie_rebalance(t, tp);
done:
return fa_head;
}
/*
* Caller must hold RTNL.
*/
-static int fn_trie_insert(struct fib_table *tb, struct fib_config *cfg)
+int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
{
struct trie *t = (struct trie *) tb->tb_data;
struct fib_alias *fa, *new_fa;
fib_release_info(fi_drop);
if (state & FA_S_ACCESSED)
- rt_cache_flush(-1);
+ rt_cache_flush(cfg->fc_nlinfo.nl_net, -1);
rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen,
tb->tb_id, &cfg->fc_nlinfo, NLM_F_REPLACE);
list_add_tail_rcu(&new_fa->fa_list,
(fa ? &fa->fa_list : fa_head));
- rt_cache_flush(-1);
+ rt_cache_flush(cfg->fc_nlinfo.nl_net, -1);
rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id,
&cfg->fc_nlinfo, 0);
succeeded:
if (l->key != (key & ntohl(mask)))
continue;
- err = fib_semantic_match(&li->falh, flp, res,
- htonl(l->key), mask, plen);
+ err = fib_semantic_match(&li->falh, flp, res, plen);
#ifdef CONFIG_IP_FIB_TRIE_STATS
if (err <= 0)
t->stats.semantic_match_miss++;
#endif
if (err <= 0)
- return plen;
+ return err;
}
- return -1;
+ return 1;
}
-static int fn_trie_lookup(struct fib_table *tb, const struct flowi *flp,
- struct fib_result *res)
+int fib_table_lookup(struct fib_table *tb, const struct flowi *flp,
+ struct fib_result *res)
{
struct trie *t = (struct trie *) tb->tb_data;
- int plen, ret = 0;
+ int ret;
struct node *n;
struct tnode *pn;
int pos, bits;
/* Just a leaf? */
if (IS_LEAF(n)) {
- plen = check_leaf(t, (struct leaf *)n, key, flp, res);
- if (plen < 0)
- goto failed;
- ret = 0;
+ ret = check_leaf(t, (struct leaf *)n, key, flp, res);
goto found;
}
cindex = tkey_extract_bits(mask_pfx(key, current_prefix_length),
pos, bits);
- n = tnode_get_child(pn, cindex);
+ n = tnode_get_child_rcu(pn, cindex);
if (n == NULL) {
#ifdef CONFIG_IP_FIB_TRIE_STATS
}
if (IS_LEAF(n)) {
- plen = check_leaf(t, (struct leaf *)n, key, flp, res);
- if (plen < 0)
+ ret = check_leaf(t, (struct leaf *)n, key, flp, res);
+ if (ret > 0)
goto backtrace;
-
- ret = 0;
goto found;
}
if (chopped_off <= pn->bits) {
cindex &= ~(1 << (chopped_off-1));
} else {
- struct tnode *parent = node_parent((struct node *) pn);
+ struct tnode *parent = node_parent_rcu((struct node *) pn);
if (!parent)
goto failed;
if (tp) {
t_key cindex = tkey_extract_bits(l->key, tp->pos, tp->bits);
put_child(t, (struct tnode *)tp, cindex, NULL);
- rcu_assign_pointer(t->trie, trie_rebalance(t, tp));
+ trie_rebalance(t, tp);
} else
rcu_assign_pointer(t->trie, NULL);
/*
* Caller must hold RTNL.
*/
-static int fn_trie_delete(struct fib_table *tb, struct fib_config *cfg)
+int fib_table_delete(struct fib_table *tb, struct fib_config *cfg)
{
struct trie *t = (struct trie *) tb->tb_data;
u32 key, mask;
trie_leaf_remove(t, l);
if (fa->fa_state & FA_S_ACCESSED)
- rt_cache_flush(-1);
+ rt_cache_flush(cfg->fc_nlinfo.nl_net, -1);
fib_release_info(fa->fa_info);
alias_free_mem_rcu(fa);
static struct leaf *trie_nextleaf(struct leaf *l)
{
struct node *c = (struct node *) l;
- struct tnode *p = node_parent(c);
+ struct tnode *p = node_parent_rcu(c);
if (!p)
return NULL; /* trie with just one leaf */
/*
* Caller must hold RTNL.
*/
-static int fn_trie_flush(struct fib_table *tb)
+int fib_table_flush(struct fib_table *tb)
{
struct trie *t = (struct trie *) tb->tb_data;
struct leaf *l, *ll = NULL;
return found;
}
-static void fn_trie_select_default(struct fib_table *tb,
- const struct flowi *flp,
- struct fib_result *res)
+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;
return skb->len;
}
-static int fn_trie_dump(struct fib_table *tb, struct sk_buff *skb,
- struct netlink_callback *cb)
+int fib_table_dump(struct fib_table *tb, struct sk_buff *skb,
+ struct netlink_callback *cb)
{
struct leaf *l;
struct trie *t = (struct trie *) tb->tb_data;
tb->tb_id = id;
tb->tb_default = -1;
- tb->tb_lookup = fn_trie_lookup;
- tb->tb_insert = fn_trie_insert;
- tb->tb_delete = fn_trie_delete;
- tb->tb_flush = fn_trie_flush;
- tb->tb_select_default = fn_trie_select_default;
- tb->tb_dump = fn_trie_dump;
t = (struct trie *) tb->tb_data;
memset(t, 0, sizeof(*t));
static int fib_triestat_seq_open(struct inode *inode, struct file *file)
{
- int err;
- struct net *net;
-
- net = get_proc_net(inode);
- if (net == NULL)
- return -ENXIO;
- err = single_open(file, fib_triestat_seq_show, net);
- if (err < 0) {
- put_net(net);
- return err;
- }
- return 0;
-}
-
-static int fib_triestat_seq_release(struct inode *ino, struct file *f)
-{
- struct seq_file *seq = f->private_data;
- put_net(seq->private);
- return single_release(ino, f);
+ return single_open_net(inode, file, fib_triestat_seq_show);
}
static const struct file_operations fib_triestat_fops = {
.open = fib_triestat_seq_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = fib_triestat_seq_release,
+ .release = single_release_net,
};
static struct node *fib_trie_get_idx(struct seq_file *seq, loff_t pos)
}
}
-static const char *rtn_type_names[__RTN_MAX] = {
+static const char *const rtn_type_names[__RTN_MAX] = {
[RTN_UNSPEC] = "UNSPEC",
[RTN_UNICAST] = "UNICAST",
[RTN_LOCAL] = "LOCAL",
__be32 prf = htonl(mask_pfx(tn->key, tn->pos));
seq_indent(seq, iter->depth-1);
- seq_printf(seq, " +-- " NIPQUAD_FMT "/%d %d %d %d\n",
- NIPQUAD(prf), tn->pos, tn->bits, tn->full_children,
+ seq_printf(seq, " +-- %pI4/%d %d %d %d\n",
+ &prf, tn->pos, tn->bits, tn->full_children,
tn->empty_children);
} else {
__be32 val = htonl(l->key);
seq_indent(seq, iter->depth);
- seq_printf(seq, " |-- " NIPQUAD_FMT "\n", NIPQUAD(val));
+ seq_printf(seq, " |-- %pI4\n", &val);
hlist_for_each_entry_rcu(li, node, &l->list, hlist) {
struct fib_alias *fa;