[IPV4]: Increase number of possible routing tables to 2^32 Increase the number of possible routing tables to 2^32 by replacing the fixed sized array of pointers by a hash table and replacing iterations over all possible table IDs by hash table walking.
Signed-off-by: Patrick McHardy <[EMAIL PROTECTED]> --- commit 148d1ca7c199005b5a92f8154a7caf3f78529672 tree ee025abdbab6fe6a4eac916791b8a06f0622d71e parent a9fe50e925cdc0471b88bcf6f3cc18278b63c984 author Patrick McHardy <[EMAIL PROTECTED]> Thu, 10 Aug 2006 20:52:30 +0200 committer Patrick McHardy <[EMAIL PROTECTED]> Thu, 10 Aug 2006 20:52:30 +0200 include/net/ip_fib.h | 25 ++---------- net/ipv4/fib_frontend.c | 102 +++++++++++++++++++++++++++++++---------------- net/ipv4/fib_hash.c | 26 ++++++------ net/ipv4/fib_rules.c | 4 +- net/ipv4/fib_trie.c | 26 ++++++------ 5 files changed, 101 insertions(+), 82 deletions(-) diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 0dcbf16..8e9ba56 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -150,6 +150,7 @@ #define FIB_RES_NETMASK(res) (0) #endif /* CONFIG_IP_ROUTE_MULTIPATH_WRANDOM */ struct fib_table { + struct hlist_node tb_hlist; u32 tb_id; unsigned tb_stamp; int (*tb_lookup)(struct fib_table *tb, const struct flowi *flp, struct fib_result *res); @@ -200,29 +201,13 @@ static inline void fib_select_default(co } #else /* CONFIG_IP_MULTIPLE_TABLES */ -#define ip_fib_local_table (fib_tables[RT_TABLE_LOCAL]) -#define ip_fib_main_table (fib_tables[RT_TABLE_MAIN]) +#define ip_fib_local_table fib_get_table(RT_TABLE_LOCAL) +#define ip_fib_main_table fib_get_table(RT_TABLE_MAIN) -extern struct fib_table * fib_tables[RT_TABLE_MAX+1]; extern int fib_lookup(struct flowi *flp, struct fib_result *res); -extern struct fib_table *__fib_new_table(u32 id); - -static inline struct fib_table *fib_get_table(u32 id) -{ - if (id == 0) - id = RT_TABLE_MAIN; - - return fib_tables[id]; -} - -static inline struct fib_table *fib_new_table(u32 id) -{ - if (id == 0) - id = RT_TABLE_MAIN; - - return fib_tables[id] ? : __fib_new_table(id); -} +extern struct fib_table *fib_new_table(u32 id); +extern struct fib_table *fib_get_table(u32 id); extern void fib_select_default(const struct flowi *flp, struct fib_result *res); #endif /* CONFIG_IP_MULTIPLE_TABLES */ diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 2696ede..ad4c14f 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -37,6 +37,7 @@ #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/init.h> +#include <linux/list.h> #include <net/ip.h> #include <net/protocol.h> @@ -51,48 +52,67 @@ #define FFprint(a...) printk(KERN_DEBUG #ifndef CONFIG_IP_MULTIPLE_TABLES -#define RT_TABLE_MIN RT_TABLE_MAIN - struct fib_table *ip_fib_local_table; struct fib_table *ip_fib_main_table; -#else +#define FIB_TABLE_HASHSZ 1 +static struct hlist_head fib_table_hash[FIB_TABLE_HASHSZ]; -#define RT_TABLE_MIN 1 +#else -struct fib_table *fib_tables[RT_TABLE_MAX+1]; +#define FIB_TABLE_HASHSZ 256 +static struct hlist_head fib_table_hash[FIB_TABLE_HASHSZ]; -struct fib_table *__fib_new_table(u32 id) +struct fib_table *fib_new_table(u32 id) { struct fib_table *tb; + unsigned int h; + if (id == 0) + id = RT_TABLE_MAIN; + tb = fib_get_table(id); + if (tb) + return tb; tb = fib_hash_init(id); if (!tb) return NULL; - fib_tables[id] = tb; + h = id & (FIB_TABLE_HASHSZ - 1); + hlist_add_head_rcu(&tb->tb_hlist, &fib_table_hash[h]); return tb; } +struct fib_table *fib_get_table(u32 id) +{ + struct fib_table *tb; + struct hlist_node *node; + unsigned int h; + if (id == 0) + id = RT_TABLE_MAIN; + h = id & (FIB_TABLE_HASHSZ - 1); + rcu_read_lock(); + hlist_for_each_entry_rcu(tb, node, &fib_table_hash[h], tb_hlist) { + if (tb->tb_id == id) { + rcu_read_unlock(); + return tb; + } + } + rcu_read_unlock(); + return NULL; +} #endif /* CONFIG_IP_MULTIPLE_TABLES */ - static void fib_flush(void) { int flushed = 0; -#ifdef CONFIG_IP_MULTIPLE_TABLES struct fib_table *tb; - u32 id; + struct hlist_node *node; + unsigned int h; - for (id = RT_TABLE_MAX; id>0; id--) { - if ((tb = fib_get_table(id))==NULL) - continue; - flushed += tb->tb_flush(tb); + for (h = 0; h < FIB_TABLE_HASHSZ; h++) { + hlist_for_each_entry(tb, node, &fib_table_hash[h], tb_hlist) + flushed += tb->tb_flush(tb); } -#else /* CONFIG_IP_MULTIPLE_TABLES */ - flushed += ip_fib_main_table->tb_flush(ip_fib_main_table); - flushed += ip_fib_local_table->tb_flush(ip_fib_local_table); -#endif /* CONFIG_IP_MULTIPLE_TABLES */ if (flushed) rt_cache_flush(-1); @@ -334,29 +354,37 @@ int inet_rtm_newroute(struct sk_buff *sk int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) { - u32 t; - u32 s_t; + unsigned int h, s_h; + unsigned int e = 0, s_e; struct fib_table *tb; + struct hlist_node *node; + int dumped = 0; if (NLMSG_PAYLOAD(cb->nlh, 0) >= sizeof(struct rtmsg) && ((struct rtmsg*)NLMSG_DATA(cb->nlh))->rtm_flags&RTM_F_CLONED) return ip_rt_dump(skb, cb); - s_t = cb->args[0]; - if (s_t == 0) - s_t = cb->args[0] = RT_TABLE_MIN; - - for (t=s_t; t<=RT_TABLE_MAX; t++) { - if (t < s_t) continue; - if (t > s_t) - memset(&cb->args[1], 0, sizeof(cb->args)-sizeof(cb->args[0])); - if ((tb = fib_get_table(t))==NULL) - continue; - if (tb->tb_dump(tb, skb, cb) < 0) - break; + s_h = cb->args[0]; + s_e = cb->args[1]; + + for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) { + e = 0; + hlist_for_each_entry(tb, node, &fib_table_hash[h], tb_hlist) { + if (e < s_e) + goto next; + if (dumped) + memset(&cb->args[2], 0, sizeof(cb->args) - + 2 * sizeof(cb->args[0])); + if (tb->tb_dump(tb, skb, cb) < 0) + goto out; + dumped = 1; +next: + e++; + } } - - cb->args[0] = t; +out: + cb->args[1] = e; + cb->args[0] = h; return skb->len; } @@ -654,9 +682,15 @@ static struct notifier_block fib_netdev_ void __init ip_fib_init(void) { + unsigned int i; + + for (i = 0; i < FIB_TABLE_HASHSZ; i++) + INIT_HLIST_HEAD(&fib_table_hash[i]); #ifndef CONFIG_IP_MULTIPLE_TABLES ip_fib_local_table = fib_hash_init(RT_TABLE_LOCAL); + hlist_add_head_rcu(&ip_fib_local_table->tb_hlist, &fib_table_hash[0]); ip_fib_main_table = fib_hash_init(RT_TABLE_MAIN); + hlist_add_head_rcu(&ip_fib_main_table->tb_hlist, &fib_table_hash[0]); #else fib4_rules_init(); #endif diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c index f8d5c80..b5bee1a 100644 --- a/net/ipv4/fib_hash.c +++ b/net/ipv4/fib_hash.c @@ -684,7 +684,7 @@ fn_hash_dump_bucket(struct sk_buff *skb, struct fib_node *f; int i, s_i; - s_i = cb->args[3]; + s_i = cb->args[4]; i = 0; hlist_for_each_entry(f, node, head, fn_hash) { struct fib_alias *fa; @@ -704,14 +704,14 @@ fn_hash_dump_bucket(struct sk_buff *skb, fa->fa_tos, fa->fa_info, NLM_F_MULTI) < 0) { - cb->args[3] = i; + cb->args[4] = i; return -1; } next: i++; } } - cb->args[3] = i; + cb->args[4] = i; return skb->len; } @@ -722,21 +722,21 @@ fn_hash_dump_zone(struct sk_buff *skb, s { int h, s_h; - s_h = cb->args[2]; + s_h = cb->args[3]; for (h=0; h < fz->fz_divisor; h++) { if (h < s_h) continue; if (h > s_h) - memset(&cb->args[3], 0, - sizeof(cb->args) - 3*sizeof(cb->args[0])); + memset(&cb->args[4], 0, + sizeof(cb->args) - 4*sizeof(cb->args[0])); if (fz->fz_hash == NULL || hlist_empty(&fz->fz_hash[h])) continue; if (fn_hash_dump_bucket(skb, cb, tb, fz, &fz->fz_hash[h])<0) { - cb->args[2] = h; + cb->args[3] = h; return -1; } } - cb->args[2] = h; + cb->args[3] = h; return skb->len; } @@ -746,21 +746,21 @@ static int fn_hash_dump(struct fib_table struct fn_zone *fz; struct fn_hash *table = (struct fn_hash*)tb->tb_data; - s_m = cb->args[1]; + s_m = cb->args[2]; read_lock(&fib_hash_lock); for (fz = table->fn_zone_list, m=0; fz; fz = fz->fz_next, m++) { if (m < s_m) continue; if (m > s_m) - memset(&cb->args[2], 0, - sizeof(cb->args) - 2*sizeof(cb->args[0])); + memset(&cb->args[3], 0, + sizeof(cb->args) - 3*sizeof(cb->args[0])); if (fn_hash_dump_zone(skb, cb, tb, fz) < 0) { - cb->args[1] = m; + cb->args[2] = m; read_unlock(&fib_hash_lock); return -1; } } read_unlock(&fib_hash_lock); - cb->args[1] = m; + cb->args[2] = m; return skb->len; } diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 0330b9c..ce185ac 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -172,8 +172,8 @@ static struct fib_table *fib_empty_table u32 id; for (id = 1; id <= RT_TABLE_MAX; id++) - if (fib_tables[id] == NULL) - return __fib_new_table(id); + if (fib_get_table(id) == NULL) + return fib_new_table(id); return NULL; } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index b98f211..3e7b0d4 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1848,7 +1848,7 @@ static int fn_trie_dump_fa(t_key key, in u32 xkey = htonl(key); - s_i = cb->args[3]; + s_i = cb->args[4]; i = 0; /* rcu_read_lock is hold by caller */ @@ -1870,12 +1870,12 @@ static int fn_trie_dump_fa(t_key key, in plen, fa->fa_tos, fa->fa_info, 0) < 0) { - cb->args[3] = i; + cb->args[4] = i; return -1; } i++; } - cb->args[3] = i; + cb->args[4] = i; return skb->len; } @@ -1886,14 +1886,14 @@ static int fn_trie_dump_plen(struct trie struct list_head *fa_head; struct leaf *l = NULL; - s_h = cb->args[2]; + s_h = cb->args[3]; for (h = 0; (l = nextleaf(t, l)) != NULL; h++) { if (h < s_h) continue; if (h > s_h) - memset(&cb->args[3], 0, - sizeof(cb->args) - 3*sizeof(cb->args[0])); + memset(&cb->args[4], 0, + sizeof(cb->args) - 4*sizeof(cb->args[0])); fa_head = get_fa_head(l, plen); @@ -1904,11 +1904,11 @@ static int fn_trie_dump_plen(struct trie continue; if (fn_trie_dump_fa(l->key, plen, fa_head, tb, skb, cb)<0) { - cb->args[2] = h; + cb->args[3] = h; return -1; } } - cb->args[2] = h; + cb->args[3] = h; return skb->len; } @@ -1917,23 +1917,23 @@ static int fn_trie_dump(struct fib_table int m, s_m; struct trie *t = (struct trie *) tb->tb_data; - s_m = cb->args[1]; + s_m = cb->args[2]; rcu_read_lock(); for (m = 0; m <= 32; m++) { if (m < s_m) continue; if (m > s_m) - memset(&cb->args[2], 0, - sizeof(cb->args) - 2*sizeof(cb->args[0])); + memset(&cb->args[3], 0, + sizeof(cb->args) - 3*sizeof(cb->args[0])); if (fn_trie_dump_plen(t, 32-m, tb, skb, cb)<0) { - cb->args[1] = m; + cb->args[2] = m; goto out; } } rcu_read_unlock(); - cb->args[1] = m; + cb->args[2] = m; return skb->len; out: rcu_read_unlock(); - To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html