* 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>
#include <linux/netlink.h>
#include <linux/init.h>
#include <linux/list.h>
+#include <linux/slab.h>
#include <net/net_namespace.h>
#include <net/ip.h>
#include <net/protocol.h>
unsigned char bits; /* 2log(KEYLENGTH) bits needed */
unsigned int full_children; /* KEYLENGTH bits needed */
unsigned int empty_children; /* KEYLENGTH bits needed */
- struct rcu_head rcu;
+ 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);
-static void tnode_free(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;
return rcu_dereference(ret);
}
+/* 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)
{
- rcu_assign_pointer(node->parent,
- (unsigned long)ptr | NODE_TYPE(node));
+ smp_wmb();
+ node->parent = (unsigned long)ptr | NODE_TYPE(node);
}
static inline struct node *tnode_get_child(struct tnode *tn, unsigned int i)
{
struct node *ret = tnode_get_child(tn, i);
- return rcu_dereference(ret);
+ return rcu_dereference_check(ret,
+ rcu_read_lock_held() ||
+ lockdep_rtnl_is_held());
}
static inline int tnode_child_length(const struct tnode *tn)
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)
{
kmem_cache_free(trie_leaf_kmem, l);
}
+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));
static struct tnode *tnode_alloc(size_t size)
{
- struct page *pages;
-
if (size <= PAGE_SIZE)
return kzalloc(size, GFP_KERNEL);
+ else
+ return __vmalloc(size, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL);
+}
- pages = alloc_pages(GFP_KERNEL|__GFP_ZERO, get_order(size));
- if (!pages)
- return NULL;
-
- return page_address(pages);
+static void __tnode_vfree(struct work_struct *arg)
+{
+ struct tnode *tn = container_of(arg, struct tnode, work);
+ vfree(tn);
}
static void __tnode_free_rcu(struct rcu_head *head)
if (size <= PAGE_SIZE)
kfree(tn);
- else
- free_pages((unsigned long)tn, get_order(size));
+ else {
+ INIT_WORK(&tn->work, __tnode_vfree);
+ schedule_work(&tn->work);
+ }
}
static inline void tnode_free(struct tnode *tn)
{
- if (IS_LEAF(tn)) {
- struct leaf *l = (struct leaf *) tn;
- call_rcu_bh(&l->rcu, __leaf_free_rcu);
- } else
+ if (IS_LEAF(tn))
+ free_leaf((struct leaf *) tn);
+ else
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);
BUG_ON(i >= 1<<tn->bits);
-
/* update emptyChildren */
if (n == NULL && chi != NULL)
tn->empty_children++;
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:
{
struct node *n;
pos = 0;
- n = rcu_dereference(t->trie);
+ n = rcu_dereference_check(t->trie,
+ rcu_read_lock_held() ||
+ lockdep_rtnl_is_held());
while (n != NULL && NODE_TYPE(n) == T_TNODE) {
tn = (struct tnode *) n;
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 */
li = leaf_info_new(plen);
if (!li) {
- tnode_free((struct tnode *) l);
+ free_leaf(l);
return NULL;
}
if (!tn) {
free_leaf_info(li);
- tnode_free((struct tnode *) l);
+ free_leaf(l);
return NULL;
}
/* 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;
* and we need to allocate a new one of those as well.
*/
- if (fa && fa->fa_info->fib_priority == fi->fib_priority) {
- struct fib_alias *fa_orig;
+ if (fa && fa->fa_tos == tos &&
+ fa->fa_info->fib_priority == fi->fib_priority) {
+ struct fib_alias *fa_first, *fa_match;
err = -EEXIST;
if (cfg->fc_nlflags & NLM_F_EXCL)
goto out;
+ /* We have 2 goals:
+ * 1. Find exact match for type, scope, fib_info to avoid
+ * duplicate routes
+ * 2. Find next 'fa' (or head), NLM_F_APPEND inserts before it
+ */
+ fa_match = NULL;
+ fa_first = fa;
+ fa = list_entry(fa->fa_list.prev, struct fib_alias, fa_list);
+ list_for_each_entry_continue(fa, fa_head, fa_list) {
+ if (fa->fa_tos != tos)
+ break;
+ 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;
+ }
+ }
+
if (cfg->fc_nlflags & NLM_F_REPLACE) {
struct fib_info *fi_drop;
u8 state;
- if (fi->fib_treeref > 1)
+ fa = fa_first;
+ if (fa_match) {
+ if (fa == fa_match)
+ err = 0;
goto out;
-
+ }
err = -ENOBUFS;
new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL);
if (new_fa == NULL)
new_fa->fa_type = cfg->fc_type;
new_fa->fa_scope = cfg->fc_scope;
state = fa->fa_state;
- new_fa->fa_state &= ~FA_S_ACCESSED;
+ new_fa->fa_state = state & ~FA_S_ACCESSED;
list_replace_rcu(&fa->fa_list, &new_fa->fa_list);
alias_free_mem_rcu(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);
* uses the same scope, type, and nexthop
* information.
*/
- fa_orig = fa;
- list_for_each_entry(fa, fa_orig->fa_list.prev, fa_list) {
- if (fa->fa_tos != tos)
- break;
- 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)
- goto out;
- }
+ if (fa_match)
+ goto out;
if (!(cfg->fc_nlflags & NLM_F_APPEND))
- fa = fa_orig;
+ fa = fa_first;
}
err = -ENOENT;
if (!(cfg->fc_nlflags & NLM_F_CREATE))
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:
return 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,
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;
return ret;
}
-/* only called from updater side */
-static int trie_leaf_remove(struct trie *t, t_key key)
+/*
+ * Remove the leaf and return parent.
+ */
+static void trie_leaf_remove(struct trie *t, struct leaf *l)
{
- t_key cindex;
- struct tnode *tp = NULL;
- struct node *n = t->trie;
- struct leaf *l;
+ struct tnode *tp = node_parent((struct node *) l);
- pr_debug("entering trie_leaf_remove(%p)\n", n);
-
- /* Note that in the case skipped bits, those bits are *not* checked!
- * When we finish this, we will have NULL or a T_LEAF, and the
- * T_LEAF may or may not match our key.
- */
-
- while (n != NULL && IS_TNODE(n)) {
- struct tnode *tn = (struct tnode *) n;
- check_tnode(tn);
- n = tnode_get_child(tn, tkey_extract_bits(key,
- tn->pos, tn->bits));
-
- BUG_ON(n && node_parent(n) != tn);
- }
- l = (struct leaf *) n;
-
- if (!n || !tkey_equals(l->key, key))
- return 0;
-
- /*
- * Key found.
- * Remove the leaf and rebalance the tree
- */
- tp = node_parent(n);
- tnode_free((struct tnode *) n);
+ pr_debug("entering trie_leaf_remove(%p)\n", l);
if (tp) {
- cindex = tkey_extract_bits(key, tp->pos, tp->bits);
+ 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);
- return 1;
+ free_leaf(l);
}
/*
* 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;
pr_debug("Deleting %08x/%d tos=%d t=%p\n", key, plen, tos, t);
fa_to_delete = NULL;
- fa_head = fa->fa_list.prev;
-
- list_for_each_entry(fa, fa_head, fa_list) {
+ fa = list_entry(fa->fa_list.prev, struct fib_alias, fa_list);
+ list_for_each_entry_continue(fa, fa_head, fa_list) {
struct fib_info *fi = fa->fa_info;
if (fa->fa_tos != tos)
}
if (hlist_empty(&l->list))
- trie_leaf_remove(t, key);
+ 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);
return 0;
}
-static int trie_flush_list(struct trie *t, struct list_head *head)
+static int trie_flush_list(struct list_head *head)
{
struct fib_alias *fa, *fa_node;
int found = 0;
return found;
}
-static int trie_flush_leaf(struct trie *t, struct leaf *l)
+static int trie_flush_leaf(struct leaf *l)
{
int found = 0;
struct hlist_head *lih = &l->list;
struct leaf_info *li = NULL;
hlist_for_each_entry_safe(li, node, tmp, lih, hlist) {
- found += trie_flush_list(t, &li->falh);
+ found += trie_flush_list(&li->falh);
if (list_empty(&li->falh)) {
hlist_del_rcu(&li->hlist);
return found;
}
-/* rcu_read_lock needs to be hold by caller from readside */
-
-static struct leaf *nextleaf(struct trie *t, struct leaf *thisleaf)
+/*
+ * 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)
{
- struct node *c = (struct node *) thisleaf;
- struct tnode *p;
- int idx;
- struct node *trie = rcu_dereference(t->trie);
-
- if (c == NULL) {
- if (trie == NULL)
- return NULL;
-
- if (IS_LEAF(trie)) /* trie w. just a leaf */
- return (struct leaf *) trie;
-
- p = (struct tnode *)trie; /* Start */
- } else
- p = node_parent_rcu(c);
-
- while (p) {
- int pos, last;
+ do {
+ t_key idx;
- /* Find the next child of the parent */
if (c)
- pos = 1 + tkey_extract_bits(c->key, p->pos, p->bits);
+ idx = tkey_extract_bits(c->key, p->pos, p->bits) + 1;
else
- pos = 0;
-
- last = 1 << p->bits;
- for (idx = pos; idx < last ; idx++) {
- c = rcu_dereference(p->child[idx]);
+ idx = 0;
+ while (idx < 1u << p->bits) {
+ c = tnode_get_child_rcu(p, idx++);
if (!c)
continue;
- /* Decend if tnode */
- while (IS_TNODE(c)) {
- p = (struct tnode *) c;
- idx = 0;
-
- /* Rightmost non-NULL branch */
- if (p && IS_TNODE(p))
- while (!(c = rcu_dereference(p->child[idx]))
- && idx < (1<<p->bits)) idx++;
-
- /* Done with this tnode? */
- if (idx >= (1 << p->bits) || !c)
- goto up;
+ if (IS_LEAF(c)) {
+ prefetch(p->child[idx]);
+ return (struct leaf *) c;
}
- return (struct leaf *) c;
+
+ /* Rescan start scanning in new node */
+ p = (struct tnode *) c;
+ idx = 0;
}
-up:
- /* No more children go up one step */
+
+ /* Node empty, walk back up to parent */
c = (struct node *) p;
- p = node_parent_rcu(c);
- }
- return NULL; /* Ready. Root of trie */
+ } while ( (p = node_parent_rcu(c)) != NULL);
+
+ return NULL; /* Root of trie */
+}
+
+static struct leaf *trie_firstleaf(struct trie *t)
+{
+ struct tnode *n = (struct tnode *) rcu_dereference(t->trie);
+
+ if (!n)
+ return NULL;
+
+ if (IS_LEAF(n)) /* trie is just a leaf */
+ return (struct leaf *) n;
+
+ return leaf_walk_rcu(n, NULL);
+}
+
+static struct leaf *trie_nextleaf(struct leaf *l)
+{
+ struct node *c = (struct node *) l;
+ struct tnode *p = node_parent_rcu(c);
+
+ if (!p)
+ return NULL; /* trie with just one leaf */
+
+ return leaf_walk_rcu(p, c);
+}
+
+static struct leaf *trie_leafindex(struct trie *t, int index)
+{
+ struct leaf *l = trie_firstleaf(t);
+
+ while (l && index-- > 0)
+ l = trie_nextleaf(l);
+
+ return l;
}
+
/*
* 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 *ll = NULL, *l = NULL;
- int found = 0, h;
+ struct leaf *l, *ll = NULL;
+ int found = 0;
- for (h = 0; (l = nextleaf(t, l)) != NULL; h++) {
- found += trie_flush_leaf(t, l);
+ for (l = trie_firstleaf(t); l; l = trie_nextleaf(l)) {
+ found += trie_flush_leaf(l);
if (ll && hlist_empty(&ll->list))
- trie_leaf_remove(t, ll->key);
+ trie_leaf_remove(t, ll);
ll = l;
}
if (ll && hlist_empty(&ll->list))
- trie_leaf_remove(t, ll->key);
+ trie_leaf_remove(t, ll);
pr_debug("trie_flush found=%d\n", found);
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;
{
int i, s_i;
struct fib_alias *fa;
-
__be32 xkey = htonl(key);
- s_i = cb->args[4];
+ s_i = cb->args[5];
i = 0;
/* rcu_read_lock is hold by caller */
i++;
continue;
}
- BUG_ON(!fa->fa_info);
if (fib_dump_info(skb, NETLINK_CB(cb->skb).pid,
cb->nlh->nlmsg_seq,
xkey,
plen,
fa->fa_tos,
- fa->fa_info, 0) < 0) {
- cb->args[4] = i;
+ fa->fa_info, NLM_F_MULTI) < 0) {
+ cb->args[5] = i;
return -1;
}
i++;
}
- cb->args[4] = i;
+ cb->args[5] = i;
return skb->len;
}
-static int fn_trie_dump_plen(struct trie *t, int plen, struct fib_table *tb,
- struct sk_buff *skb, struct netlink_callback *cb)
+static int fn_trie_dump_leaf(struct leaf *l, struct fib_table *tb,
+ struct sk_buff *skb, struct netlink_callback *cb)
{
- int h, s_h;
- struct list_head *fa_head;
- struct leaf *l = NULL;
+ struct leaf_info *li;
+ struct hlist_node *node;
+ int i, s_i;
- s_h = cb->args[3];
+ s_i = cb->args[4];
+ i = 0;
- for (h = 0; (l = nextleaf(t, l)) != NULL; h++) {
- if (h < s_h)
+ /* rcu_read_lock is hold by caller */
+ hlist_for_each_entry_rcu(li, node, &l->list, hlist) {
+ if (i < s_i) {
+ i++;
continue;
- if (h > s_h)
- memset(&cb->args[4], 0,
- sizeof(cb->args) - 4*sizeof(cb->args[0]));
-
- fa_head = get_fa_head(l, plen);
+ }
- if (!fa_head)
- continue;
+ if (i > s_i)
+ cb->args[5] = 0;
- if (list_empty(fa_head))
+ if (list_empty(&li->falh))
continue;
- if (fn_trie_dump_fa(l->key, plen, fa_head, tb, skb, cb) < 0) {
- cb->args[3] = h;
+ if (fn_trie_dump_fa(l->key, li->plen, &li->falh, tb, skb, cb) < 0) {
+ cb->args[4] = i;
return -1;
}
+ i++;
}
- cb->args[3] = h;
+
+ cb->args[4] = i;
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)
{
- int m, s_m;
+ struct leaf *l;
struct trie *t = (struct trie *) tb->tb_data;
-
- s_m = cb->args[2];
+ t_key key = cb->args[2];
+ int count = cb->args[3];
rcu_read_lock();
- for (m = 0; m <= 32; m++) {
- if (m < s_m)
- continue;
- if (m > s_m)
- memset(&cb->args[3], 0,
- sizeof(cb->args) - 3*sizeof(cb->args[0]));
+ /* Dump starting at last key.
+ * Note: 0.0.0.0/0 (ie default) is first key.
+ */
+ if (count == 0)
+ l = trie_firstleaf(t);
+ else {
+ /* Normally, continue from last key, but if that is missing
+ * fallback to using slow rescan
+ */
+ l = fib_find_node(t, key);
+ if (!l)
+ l = trie_leafindex(t, count);
+ }
- if (fn_trie_dump_plen(t, 32-m, tb, skb, cb) < 0) {
- cb->args[2] = m;
- goto out;
+ while (l) {
+ cb->args[2] = l->key;
+ if (fn_trie_dump_leaf(l, tb, skb, cb) < 0) {
+ cb->args[3] = count;
+ rcu_read_unlock();
+ return -1;
}
+
+ ++count;
+ l = trie_nextleaf(l);
+ memset(&cb->args[4], 0,
+ sizeof(cb->args) - 4*sizeof(cb->args[0]));
}
+ cb->args[3] = count;
rcu_read_unlock();
- cb->args[2] = m;
+
return skb->len;
-out:
- rcu_read_unlock();
- return -1;
}
void __init fib_hash_init(void)
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));
/* Depth first Trie walk iterator */
struct fib_trie_iter {
struct seq_net_private p;
- struct trie *trie_local, *trie_main;
+ struct fib_table *tb;
struct tnode *tnode;
- struct trie *trie;
unsigned index;
unsigned depth;
};
static struct node *fib_trie_get_first(struct fib_trie_iter *iter,
struct trie *t)
{
- struct node *n ;
+ struct node *n;
if (!t)
return NULL;
n = rcu_dereference(t->trie);
-
- if (!iter)
+ if (!n)
return NULL;
- if (n) {
- if (IS_TNODE(n)) {
- iter->tnode = (struct tnode *) n;
- iter->trie = t;
- iter->index = 0;
- iter->depth = 1;
- } else {
- iter->tnode = NULL;
- iter->trie = t;
- iter->index = 0;
- iter->depth = 0;
- }
- return n;
+ if (IS_TNODE(n)) {
+ iter->tnode = (struct tnode *) n;
+ iter->index = 0;
+ iter->depth = 1;
+ } else {
+ iter->tnode = NULL;
+ iter->index = 0;
+ iter->depth = 0;
}
- return NULL;
+
+ return n;
}
static void trie_collect_stats(struct trie *t, struct trie_stat *s)
memset(s, 0, sizeof(*s));
rcu_read_lock();
- for (n = fib_trie_get_first(&iter, t); n;
- n = fib_trie_get_next(&iter)) {
+ for (n = fib_trie_get_first(&iter, t); n; n = fib_trie_get_next(&iter)) {
if (IS_LEAF(n)) {
struct leaf *l = (struct leaf *)n;
struct leaf_info *li;
}
#endif /* CONFIG_IP_FIB_TRIE_STATS */
-static void fib_trie_show(struct seq_file *seq, const char *name,
- struct trie *trie)
+static void fib_table_print(struct seq_file *seq, struct fib_table *tb)
{
- struct trie_stat stat;
-
- trie_collect_stats(trie, &stat);
- seq_printf(seq, "%s:\n", name);
- trie_show_stats(seq, &stat);
-#ifdef CONFIG_IP_FIB_TRIE_STATS
- trie_show_usage(seq, &trie->stats);
-#endif
+ if (tb->tb_id == RT_TABLE_LOCAL)
+ seq_puts(seq, "Local:\n");
+ else if (tb->tb_id == RT_TABLE_MAIN)
+ seq_puts(seq, "Main:\n");
+ else
+ seq_printf(seq, "Id %d:\n", tb->tb_id);
}
+
static int fib_triestat_seq_show(struct seq_file *seq, void *v)
{
struct net *net = (struct net *)seq->private;
- struct fib_table *tb;
+ unsigned int h;
seq_printf(seq,
"Basic info: size of leaf:"
" %Zd bytes, size of tnode: %Zd bytes.\n",
sizeof(struct leaf), sizeof(struct tnode));
- tb = fib_get_table(net, RT_TABLE_LOCAL);
- if (tb)
- fib_trie_show(seq, "Local", (struct trie *) tb->tb_data);
+ 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;
- tb = fib_get_table(net, RT_TABLE_MAIN);
- if (tb)
- fib_trie_show(seq, "Main", (struct trie *) tb->tb_data);
+ hlist_for_each_entry_rcu(tb, node, head, tb_hlist) {
+ struct trie *t = (struct trie *) tb->tb_data;
+ struct trie_stat stat;
- return 0;
-}
+ if (!t)
+ continue;
-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;
+ fib_table_print(seq, tb);
+
+ trie_collect_stats(t, &stat);
+ trie_show_stats(seq, &stat);
+#ifdef CONFIG_IP_FIB_TRIE_STATS
+ trie_show_usage(seq, &t->stats);
+#endif
+ }
}
+
return 0;
}
-static int fib_triestat_seq_release(struct inode *ino, struct file *f)
+static int fib_triestat_seq_open(struct inode *inode, struct file *file)
{
- 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 fib_trie_iter *iter,
- loff_t pos)
+static struct 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);
loff_t idx = 0;
- struct node *n;
+ unsigned int h;
- for (n = fib_trie_get_first(iter, iter->trie_local);
- n; ++idx, n = fib_trie_get_next(iter)) {
- if (pos == idx)
- return n;
- }
+ 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;
- for (n = fib_trie_get_first(iter, iter->trie_main);
- n; ++idx, n = fib_trie_get_next(iter)) {
- if (pos == idx)
- return n;
+ hlist_for_each_entry_rcu(tb, node, head, tb_hlist) {
+ struct node *n;
+
+ for (n = fib_trie_get_first(iter,
+ (struct trie *) tb->tb_data);
+ n; n = fib_trie_get_next(iter))
+ if (pos == idx++) {
+ iter->tb = tb;
+ return n;
+ }
+ }
}
+
return NULL;
}
static void *fib_trie_seq_start(struct seq_file *seq, loff_t *pos)
__acquires(RCU)
{
- struct fib_trie_iter *iter = seq->private;
- struct fib_table *tb;
-
- if (!iter->trie_local) {
- tb = fib_get_table(iter->p.net, RT_TABLE_LOCAL);
- if (tb)
- iter->trie_local = (struct trie *) tb->tb_data;
- }
- if (!iter->trie_main) {
- tb = fib_get_table(iter->p.net, RT_TABLE_MAIN);
- if (tb)
- iter->trie_main = (struct trie *) tb->tb_data;
- }
rcu_read_lock();
- if (*pos == 0)
- return SEQ_START_TOKEN;
- return fib_trie_get_idx(iter, *pos - 1);
+ return fib_trie_get_idx(seq, *pos);
}
static void *fib_trie_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct fib_trie_iter *iter = seq->private;
- void *l = v;
+ struct net *net = seq_file_net(seq);
+ struct fib_table *tb = iter->tb;
+ struct hlist_node *tb_node;
+ unsigned int h;
+ struct node *n;
++*pos;
- if (v == SEQ_START_TOKEN)
- return fib_trie_get_idx(iter, 0);
-
- v = fib_trie_get_next(iter);
- BUG_ON(v == l);
- if (v)
- return v;
+ /* next node in same table */
+ n = fib_trie_get_next(iter);
+ if (n)
+ return n;
- /* continue scan in next trie */
- if (iter->trie == iter->trie_local)
- return fib_trie_get_first(iter, iter->trie_main);
+ /* walk rest of this hash chain */
+ h = tb->tb_id & (FIB_TABLE_HASHSZ - 1);
+ while ( (tb_node = rcu_dereference(tb->tb_hlist.next)) ) {
+ tb = hlist_entry(tb_node, struct fib_table, tb_hlist);
+ n = fib_trie_get_first(iter, (struct trie *) tb->tb_data);
+ if (n)
+ goto found;
+ }
+ /* 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) {
+ n = fib_trie_get_first(iter, (struct trie *) tb->tb_data);
+ if (n)
+ goto found;
+ }
+ }
return NULL;
+
+found:
+ iter->tb = tb;
+ return n;
}
static void fib_trie_seq_stop(struct seq_file *seq, void *v)
}
}
-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",
const struct fib_trie_iter *iter = seq->private;
struct node *n = v;
- if (v == SEQ_START_TOKEN)
- return 0;
-
- if (!node_parent_rcu(n)) {
- if (iter->trie == iter->trie_local)
- seq_puts(seq, "<local>:\n");
- else
- seq_puts(seq, "<main>:\n");
- }
+ if (!node_parent_rcu(n))
+ fib_table_print(seq, iter->tb);
if (IS_TNODE(n)) {
struct tnode *tn = (struct tnode *) n;
__be32 prf = htonl(mask_pfx(tn->key, tn->pos));
seq_indent(seq, iter->depth-1);
- seq_printf(seq, " +-- %d.%d.%d.%d/%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 {
struct leaf *l = (struct leaf *) n;
- int i;
+ struct leaf_info *li;
+ struct hlist_node *node;
__be32 val = htonl(l->key);
seq_indent(seq, iter->depth);
- seq_printf(seq, " |-- %d.%d.%d.%d\n", NIPQUAD(val));
- for (i = 32; i >= 0; i--) {
- struct leaf_info *li = find_leaf_info(l, i);
-
- if (li) {
- struct fib_alias *fa;
-
- list_for_each_entry_rcu(fa, &li->falh, fa_list) {
- char buf1[32], buf2[32];
-
- seq_indent(seq, iter->depth+1);
- seq_printf(seq, " /%d %s %s", i,
- rtn_scope(buf1, sizeof(buf1),
- fa->fa_scope),
- rtn_type(buf2, sizeof(buf2),
- fa->fa_type));
- if (fa->fa_tos)
- seq_printf(seq, "tos =%d\n",
- fa->fa_tos);
- seq_putc(seq, '\n');
- }
+ seq_printf(seq, " |-- %pI4\n", &val);
+
+ hlist_for_each_entry_rcu(li, node, &l->list, hlist) {
+ struct fib_alias *fa;
+
+ list_for_each_entry_rcu(fa, &li->falh, fa_list) {
+ char buf1[32], buf2[32];
+
+ seq_indent(seq, iter->depth+1);
+ seq_printf(seq, " /%d %s %s", li->plen,
+ rtn_scope(buf1, sizeof(buf1),
+ fa->fa_scope),
+ rtn_type(buf2, sizeof(buf2),
+ fa->fa_type));
+ if (fa->fa_tos)
+ seq_printf(seq, " tos=%d", fa->fa_tos);
+ seq_putc(seq, '\n');
}
}
}
.release = seq_release_net,
};
+struct fib_route_iter {
+ struct seq_net_private p;
+ struct trie *main_trie;
+ loff_t pos;
+ t_key key;
+};
+
+static struct leaf *fib_route_get_idx(struct fib_route_iter *iter, loff_t pos)
+{
+ struct leaf *l = NULL;
+ struct trie *t = iter->main_trie;
+
+ /* use cache location of last found key */
+ if (iter->pos > 0 && pos >= iter->pos && (l = fib_find_node(t, iter->key)))
+ pos -= iter->pos;
+ else {
+ iter->pos = 0;
+ l = trie_firstleaf(t);
+ }
+
+ while (l && pos-- > 0) {
+ iter->pos++;
+ l = trie_nextleaf(l);
+ }
+
+ if (l)
+ iter->key = pos; /* remember it */
+ else
+ iter->pos = 0; /* forget it */
+
+ return l;
+}
+
+static void *fib_route_seq_start(struct seq_file *seq, loff_t *pos)
+ __acquires(RCU)
+{
+ struct fib_route_iter *iter = seq->private;
+ struct fib_table *tb;
+
+ rcu_read_lock();
+ tb = fib_get_table(seq_file_net(seq), RT_TABLE_MAIN);
+ if (!tb)
+ return NULL;
+
+ iter->main_trie = (struct trie *) tb->tb_data;
+ if (*pos == 0)
+ return SEQ_START_TOKEN;
+ else
+ return fib_route_get_idx(iter, *pos - 1);
+}
+
+static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+ struct fib_route_iter *iter = seq->private;
+ struct leaf *l = v;
+
+ ++*pos;
+ if (v == SEQ_START_TOKEN) {
+ iter->pos = 0;
+ l = trie_firstleaf(iter->main_trie);
+ } else {
+ iter->pos++;
+ l = trie_nextleaf(l);
+ }
+
+ if (l)
+ iter->key = l->key;
+ else
+ iter->pos = 0;
+ return l;
+}
+
+static void fib_route_seq_stop(struct seq_file *seq, void *v)
+ __releases(RCU)
+{
+ rcu_read_unlock();
+}
+
static unsigned fib_flag_trans(int type, __be32 mask, const struct fib_info *fi)
{
static unsigned type2flags[RTN_MAX + 1] = {
*/
static int fib_route_seq_show(struct seq_file *seq, void *v)
{
- const struct fib_trie_iter *iter = seq->private;
struct leaf *l = v;
- int i;
- char bf[128];
+ struct leaf_info *li;
+ struct hlist_node *node;
if (v == SEQ_START_TOKEN) {
seq_printf(seq, "%-127s\n", "Iface\tDestination\tGateway "
return 0;
}
- if (iter->trie == iter->trie_local)
- return 0;
-
- if (IS_TNODE(l))
- return 0;
-
- for (i = 32; i >= 0; i--) {
- struct leaf_info *li = find_leaf_info(l, i);
+ hlist_for_each_entry_rcu(li, node, &l->list, hlist) {
struct fib_alias *fa;
__be32 mask, prefix;
- if (!li)
- continue;
-
mask = inet_make_mask(li->plen);
prefix = htonl(l->key);
list_for_each_entry_rcu(fa, &li->falh, fa_list) {
const struct fib_info *fi = fa->fa_info;
unsigned flags = fib_flag_trans(fa->fa_type, mask, fi);
+ int len;
if (fa->fa_type == RTN_BROADCAST
|| fa->fa_type == RTN_MULTICAST)
continue;
if (fi)
- snprintf(bf, sizeof(bf),
- "%s\t%08X\t%08X\t%04X\t%d\t%u\t%d\t%08X\t%d\t%u\t%u",
+ 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",
fi->fib_dev ? fi->fib_dev->name : "*",
prefix,
fi->fib_nh->nh_gw, flags, 0, 0,
(fi->fib_advmss ?
fi->fib_advmss + 40 : 0),
fi->fib_window,
- fi->fib_rtt >> 3);
+ fi->fib_rtt >> 3, &len);
else
- snprintf(bf, sizeof(bf),
- "*\t%08X\t%08X\t%04X\t%d\t%u\t%d\t%08X\t%d\t%u\t%u",
+ seq_printf(seq,
+ "*\t%08X\t%08X\t%04X\t%d\t%u\t"
+ "%d\t%08X\t%d\t%u\t%u%n",
prefix, 0, flags, 0, 0, 0,
- mask, 0, 0, 0);
+ mask, 0, 0, 0, &len);
- seq_printf(seq, "%-127s\n", bf);
+ seq_printf(seq, "%*s\n", 127 - len, "");
}
}
}
static const struct seq_operations fib_route_seq_ops = {
- .start = fib_trie_seq_start,
- .next = fib_trie_seq_next,
- .stop = fib_trie_seq_stop,
+ .start = fib_route_seq_start,
+ .next = fib_route_seq_next,
+ .stop = fib_route_seq_stop,
.show = fib_route_seq_show,
};
static int fib_route_seq_open(struct inode *inode, struct file *file)
{
return seq_open_net(inode, file, &fib_route_seq_ops,
- sizeof(struct fib_trie_iter));
+ sizeof(struct fib_route_iter));
}
static const struct file_operations fib_route_fops = {
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff