From e1ef4bf23b1ced0bf78a1c98289f746486e5c912 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Fri, 4 Aug 2006 03:39:22 -0700 Subject: [IPV4]: Use Protocol Independant Policy Routing Rules Framework Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- net/ipv4/fib_frontend.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4/fib_frontend.c') diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index ba2a70745a6..fe4a53d4d10 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -656,7 +656,7 @@ void __init ip_fib_init(void) ip_fib_local_table = fib_hash_init(RT_TABLE_LOCAL); ip_fib_main_table = fib_hash_init(RT_TABLE_MAIN); #else - fib_rules_init(); + fib4_rules_init(); #endif register_netdevice_notifier(&fib_netdev_notifier); -- cgit v1.2.3-70-g09d2 From 1823730fbc89fadde72a7bb3b7bdf03cc7b8835c Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Fri, 4 Aug 2006 23:04:54 -0700 Subject: [IPv4]: Move interface address bits to linux/if_addr.h Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/if_addr.h | 53 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/rtnetlink.h | 56 ----------------------------------------------- net/core/rtnetlink.c | 1 + net/decnet/dn_dev.c | 1 + net/ipv4/devinet.c | 1 + net/ipv4/fib_frontend.c | 1 + net/ipv6/addrconf.c | 1 + net/ipv6/ndisc.c | 1 + 8 files changed, 59 insertions(+), 56 deletions(-) create mode 100644 include/linux/if_addr.h (limited to 'net/ipv4/fib_frontend.c') diff --git a/include/linux/if_addr.h b/include/linux/if_addr.h new file mode 100644 index 00000000000..e1590454db5 --- /dev/null +++ b/include/linux/if_addr.h @@ -0,0 +1,53 @@ +#ifndef __LINUX_IF_ADDR_H +#define __LINUX_IF_ADDR_H + +#include + +struct ifaddrmsg +{ + __u8 ifa_family; + __u8 ifa_prefixlen; /* The prefix length */ + __u8 ifa_flags; /* Flags */ + __u8 ifa_scope; /* Address scope */ + __u32 ifa_index; /* Link index */ +}; + +/* + * Important comment: + * IFA_ADDRESS is prefix address, rather than local interface address. + * It makes no difference for normally configured broadcast interfaces, + * but for point-to-point IFA_ADDRESS is DESTINATION address, + * local address is supplied in IFA_LOCAL attribute. + */ +enum +{ + IFA_UNSPEC, + IFA_ADDRESS, + IFA_LOCAL, + IFA_LABEL, + IFA_BROADCAST, + IFA_ANYCAST, + IFA_CACHEINFO, + IFA_MULTICAST, + __IFA_MAX, +}; + +#define IFA_MAX (__IFA_MAX - 1) + +/* ifa_flags */ +#define IFA_F_SECONDARY 0x01 +#define IFA_F_TEMPORARY IFA_F_SECONDARY + +#define IFA_F_DEPRECATED 0x20 +#define IFA_F_TENTATIVE 0x40 +#define IFA_F_PERMANENT 0x80 + +struct ifa_cacheinfo +{ + __u32 ifa_prefered; + __u32 ifa_valid; + __u32 cstamp; /* created timestamp, hundredths of seconds */ + __u32 tstamp; /* updated timestamp, hundredths of seconds */ +}; + +#endif diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index bf353538ae9..890c4d4038b 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -384,62 +384,6 @@ struct rta_session }; -/********************************************************* - * Interface address. - ****/ - -struct ifaddrmsg -{ - unsigned char ifa_family; - unsigned char ifa_prefixlen; /* The prefix length */ - unsigned char ifa_flags; /* Flags */ - unsigned char ifa_scope; /* See above */ - int ifa_index; /* Link index */ -}; - -enum -{ - IFA_UNSPEC, - IFA_ADDRESS, - IFA_LOCAL, - IFA_LABEL, - IFA_BROADCAST, - IFA_ANYCAST, - IFA_CACHEINFO, - IFA_MULTICAST, - __IFA_MAX -}; - -#define IFA_MAX (__IFA_MAX - 1) - -/* ifa_flags */ - -#define IFA_F_SECONDARY 0x01 -#define IFA_F_TEMPORARY IFA_F_SECONDARY - -#define IFA_F_DEPRECATED 0x20 -#define IFA_F_TENTATIVE 0x40 -#define IFA_F_PERMANENT 0x80 - -struct ifa_cacheinfo -{ - __u32 ifa_prefered; - __u32 ifa_valid; - __u32 cstamp; /* created timestamp, hundredths of seconds */ - __u32 tstamp; /* updated timestamp, hundredths of seconds */ -}; - - -#define IFA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifaddrmsg)))) -#define IFA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifaddrmsg)) - -/* - Important comment: - IFA_ADDRESS is prefix address, rather than local interface address. - It makes no difference for normally configured broadcast interfaces, - but for point-to-point IFA_ADDRESS is DESTINATION address, - local address is supplied in IFA_LOCAL attribute. - */ /************************************************************** * Neighbour discovery. diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index aa7cff2257b..35712031e2c 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -35,6 +35,7 @@ #include #include #include +#include #include #include diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 476455fbdb0..632c5a90b58 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include #include diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 80bf5b2ea2e..398e7b9ca66 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include #include diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index fe4a53d4d10..a83f1aa8034 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include #include diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ed766eebc02..c2a4db843e5 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -48,6 +48,7 @@ #include #include #include +#include #include #include #include diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 67cfc3813c3..5743e8bffef 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -62,6 +62,7 @@ #include #endif +#include #include #include #include -- cgit v1.2.3-70-g09d2 From 2dfe55b47e3d66ded5a84caf71e0da5710edf48b Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 10 Aug 2006 23:08:33 -0700 Subject: [NET]: Use u32 for routing table IDs Use u32 for routing table IDs in net/ipv4 and net/decnet in preparation of support for a larger number of routing tables. net/ipv6 already uses u32 everywhere and needs no further changes. No functional changes are made by this patch. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/net/dn_fib.h | 4 ++-- include/net/ip_fib.h | 14 +++++++------- net/decnet/dn_fib.c | 6 +++--- net/decnet/dn_table.c | 10 +++++----- net/ipv4/fib_frontend.c | 8 ++++---- net/ipv4/fib_hash.c | 4 ++-- net/ipv4/fib_lookup.h | 4 ++-- net/ipv4/fib_rules.c | 2 +- net/ipv4/fib_semantics.c | 4 ++-- net/ipv4/fib_trie.c | 6 +++--- 10 files changed, 31 insertions(+), 31 deletions(-) (limited to 'net/ipv4/fib_frontend.c') diff --git a/include/net/dn_fib.h b/include/net/dn_fib.h index 32bc8ce5c5c..cd9c3782f83 100644 --- a/include/net/dn_fib.h +++ b/include/net/dn_fib.h @@ -94,7 +94,7 @@ struct dn_fib_node { struct dn_fib_table { - int n; + u32 n; int (*insert)(struct dn_fib_table *t, struct rtmsg *r, struct dn_kern_rta *rta, struct nlmsghdr *n, @@ -137,7 +137,7 @@ extern int dn_fib_sync_up(struct net_device *dev); /* * dn_tables.c */ -extern struct dn_fib_table *dn_fib_get_table(int n, int creat); +extern struct dn_fib_table *dn_fib_get_table(u32 n, int creat); extern struct dn_fib_table *dn_fib_empty_table(void); extern void dn_fib_table_init(void); extern void dn_fib_table_cleanup(void); diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index adf73586bc0..0dcbf166eb9 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -150,7 +150,7 @@ struct fib_result_nl { #endif /* CONFIG_IP_ROUTE_MULTIPATH_WRANDOM */ struct fib_table { - unsigned char tb_id; + u32 tb_id; unsigned tb_stamp; int (*tb_lookup)(struct fib_table *tb, const struct flowi *flp, struct fib_result *res); int (*tb_insert)(struct fib_table *table, struct rtmsg *r, @@ -173,14 +173,14 @@ struct fib_table { extern struct fib_table *ip_fib_local_table; extern struct fib_table *ip_fib_main_table; -static inline struct fib_table *fib_get_table(int id) +static inline struct fib_table *fib_get_table(u32 id) { if (id != RT_TABLE_LOCAL) return ip_fib_main_table; return ip_fib_local_table; } -static inline struct fib_table *fib_new_table(int id) +static inline struct fib_table *fib_new_table(u32 id) { return fib_get_table(id); } @@ -205,9 +205,9 @@ static inline void fib_select_default(const struct flowi *flp, struct fib_result 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(int id); +extern struct fib_table *__fib_new_table(u32 id); -static inline struct fib_table *fib_get_table(int id) +static inline struct fib_table *fib_get_table(u32 id) { if (id == 0) id = RT_TABLE_MAIN; @@ -215,7 +215,7 @@ static inline struct fib_table *fib_get_table(int id) return fib_tables[id]; } -static inline struct fib_table *fib_new_table(int id) +static inline struct fib_table *fib_new_table(u32 id) { if (id == 0) id = RT_TABLE_MAIN; @@ -248,7 +248,7 @@ extern int fib_convert_rtentry(int cmd, struct nlmsghdr *nl, struct rtmsg *rtm, extern u32 __fib_res_prefsrc(struct fib_result *res); /* Exported by fib_hash.c */ -extern struct fib_table *fib_hash_init(int id); +extern struct fib_table *fib_hash_init(u32 id); #ifdef CONFIG_IP_MULTIPLE_TABLES extern int fib4_rules_dump(struct sk_buff *skb, struct netlink_callback *cb); diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index ed5fb5c3eab..7b3bf5c3d72 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -534,8 +534,8 @@ int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) int dn_fib_dump(struct sk_buff *skb, struct netlink_callback *cb) { - int t; - int s_t; + u32 t; + u32 s_t; struct dn_fib_table *tb; if (NLMSG_PAYLOAD(cb->nlh, 0) >= sizeof(struct rtmsg) && @@ -765,7 +765,7 @@ void dn_fib_flush(void) { int flushed = 0; struct dn_fib_table *tb; - int id; + u32 id; for(id = RT_TABLE_MAX; id > 0; id--) { if ((tb = dn_fib_get_table(id, 0)) == NULL) diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index 2e01b67398c..1601ee5406a 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -264,7 +264,7 @@ static int dn_fib_nh_match(struct rtmsg *r, struct nlmsghdr *nlh, struct dn_kern } static int dn_fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, - u8 tb_id, u8 type, u8 scope, void *dst, int dst_len, + u32 tb_id, u8 type, u8 scope, void *dst, int dst_len, struct dn_fib_info *fi, unsigned int flags) { struct rtmsg *rtm; @@ -327,7 +327,7 @@ rtattr_failure: } -static void dn_rtmsg_fib(int event, struct dn_fib_node *f, int z, int tb_id, +static void dn_rtmsg_fib(int event, struct dn_fib_node *f, int z, u32 tb_id, struct nlmsghdr *nlh, struct netlink_skb_parms *req) { struct sk_buff *skb; @@ -740,7 +740,7 @@ out: } -struct dn_fib_table *dn_fib_get_table(int n, int create) +struct dn_fib_table *dn_fib_get_table(u32 n, int create) { struct dn_fib_table *t; @@ -777,7 +777,7 @@ struct dn_fib_table *dn_fib_get_table(int n, int create) return t; } -static void dn_fib_del_tree(int n) +static void dn_fib_del_tree(u32 n) { struct dn_fib_table *t; @@ -791,7 +791,7 @@ static void dn_fib_del_tree(int n) struct dn_fib_table *dn_fib_empty_table(void) { - int id; + u32 id; for(id = RT_TABLE_MIN; id <= RT_TABLE_MAX; id++) if (dn_fib_tables[id] == NULL) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index a83f1aa8034..06f4b23f6f5 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -62,7 +62,7 @@ struct fib_table *ip_fib_main_table; struct fib_table *fib_tables[RT_TABLE_MAX+1]; -struct fib_table *__fib_new_table(int id) +struct fib_table *__fib_new_table(u32 id) { struct fib_table *tb; @@ -82,7 +82,7 @@ static void fib_flush(void) int flushed = 0; #ifdef CONFIG_IP_MULTIPLE_TABLES struct fib_table *tb; - int id; + u32 id; for (id = RT_TABLE_MAX; id>0; id--) { if ((tb = fib_get_table(id))==NULL) @@ -333,8 +333,8 @@ int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) { - int t; - int s_t; + u32 t; + u32 s_t; struct fib_table *tb; if (NLMSG_PAYLOAD(cb->nlh, 0) >= sizeof(struct rtmsg) && diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c index 72c633b357c..f8d5c8024cc 100644 --- a/net/ipv4/fib_hash.c +++ b/net/ipv4/fib_hash.c @@ -765,9 +765,9 @@ static int fn_hash_dump(struct fib_table *tb, struct sk_buff *skb, struct netlin } #ifdef CONFIG_IP_MULTIPLE_TABLES -struct fib_table * fib_hash_init(int id) +struct fib_table * fib_hash_init(u32 id) #else -struct fib_table * __init fib_hash_init(int id) +struct fib_table * __init fib_hash_init(u32 id) #endif { struct fib_table *tb; diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index ef6609ea0eb..ddd52496b45 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -30,11 +30,11 @@ extern struct fib_info *fib_create_info(const struct rtmsg *r, extern int fib_nh_match(struct rtmsg *r, struct nlmsghdr *, struct kern_rta *rta, struct fib_info *fi); extern int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, - u8 tb_id, u8 type, u8 scope, void *dst, + u32 tb_id, u8 type, u8 scope, void *dst, int dst_len, u8 tos, struct fib_info *fi, unsigned int); extern void rtmsg_fib(int event, u32 key, struct fib_alias *fa, - int z, int tb_id, + int z, u32 tb_id, struct nlmsghdr *n, struct netlink_skb_parms *req); extern struct fib_alias *fib_find_alias(struct list_head *fah, u8 tos, u32 prio); diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index d242e5291fc..58fb91b00fd 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -169,7 +169,7 @@ static int fib4_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) static struct fib_table *fib_empty_table(void) { - int id; + u32 id; for (id = 1; id <= RT_TABLE_MAX; id++) if (fib_tables[id] == NULL) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 38bca473c7e..c7a112b5a18 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -273,7 +273,7 @@ int ip_fib_check_default(u32 gw, struct net_device *dev) } void rtmsg_fib(int event, u32 key, struct fib_alias *fa, - int z, int tb_id, + int z, u32 tb_id, struct nlmsghdr *n, struct netlink_skb_parms *req) { struct sk_buff *skb; @@ -939,7 +939,7 @@ u32 __fib_res_prefsrc(struct fib_result *res) int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, - u8 tb_id, u8 type, u8 scope, void *dst, int dst_len, u8 tos, + u32 tb_id, u8 type, u8 scope, void *dst, int dst_len, u8 tos, struct fib_info *fi, unsigned int flags) { struct rtmsg *rtm; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 01801c0f885..4a27b2d573a 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1148,7 +1148,7 @@ fn_trie_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, key = ntohl(key); - pr_debug("Insert table=%d %08x/%d\n", tb->tb_id, key, plen); + pr_debug("Insert table=%u %08x/%d\n", tb->tb_id, key, plen); mask = ntohl(inet_make_mask(plen)); @@ -1943,9 +1943,9 @@ out: /* Fix more generic FIB names for init later */ #ifdef CONFIG_IP_MULTIPLE_TABLES -struct fib_table * fib_hash_init(int id) +struct fib_table * fib_hash_init(u32 id) #else -struct fib_table * __init fib_hash_init(int id) +struct fib_table * __init fib_hash_init(u32 id) #endif { struct fib_table *tb; -- cgit v1.2.3-70-g09d2 From 9e762a4a89b302cb3b26a1f9bb33eff459eaeca9 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 10 Aug 2006 23:09:48 -0700 Subject: [NET]: Introduce RTA_TABLE/FRA_TABLE attributes Introduce RTA_TABLE route attribute and FRA_TABLE routing rule attribute to hold 32 bit routing table IDs. Usespace compatibility is provided by continuing to accept and send the rtm_table field, but because of its limited size it can only carry the low 8 bits of the table ID. This implies that if larger IDs are used, _all_ userspace programs using them need to use RTA_TABLE. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/fib_rules.h | 4 ++++ include/linux/rtnetlink.h | 8 ++++++++ include/net/fib_rules.h | 7 +++++++ net/core/fib_rules.c | 5 +++-- net/decnet/dn_fib.c | 7 ++++--- net/decnet/dn_route.c | 1 + net/decnet/dn_table.c | 1 + net/ipv4/fib_frontend.c | 7 ++++--- net/ipv4/fib_rules.c | 1 + net/ipv4/fib_semantics.c | 1 + net/ipv4/route.c | 1 + net/ipv6/fib6_rules.c | 1 + net/ipv6/route.c | 13 +++++++++---- 13 files changed, 45 insertions(+), 12 deletions(-) (limited to 'net/ipv4/fib_frontend.c') diff --git a/include/linux/fib_rules.h b/include/linux/fib_rules.h index 5e503f0ca6e..19a82b6c1c1 100644 --- a/include/linux/fib_rules.h +++ b/include/linux/fib_rules.h @@ -36,6 +36,10 @@ enum FRA_UNUSED5, FRA_FWMARK, /* netfilter mark (IPv4) */ FRA_FLOW, /* flow/class id */ + FRA_UNUSED6, + FRA_UNUSED7, + FRA_UNUSED8, + FRA_TABLE, /* Extended table id */ __FRA_MAX }; diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 0aaffa2ae66..ea422a539a0 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -264,6 +264,7 @@ enum rtattr_type_t RTA_CACHEINFO, RTA_SESSION, RTA_MP_ALGO, + RTA_TABLE, __RTA_MAX }; @@ -717,6 +718,13 @@ extern void __rtnl_unlock(void); } \ } while(0) +static inline u32 rtm_get_table(struct rtattr **rta, u8 table) +{ + return RTA_GET_U32(rta[RTA_TABLE-1]); +rtattr_failure: + return table; +} + #endif /* __KERNEL__ */ diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 61375d9e53f..8e2f473d3e8 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -74,6 +74,13 @@ static inline void fib_rule_put(struct fib_rule *rule) call_rcu(&rule->rcu, fib_rule_put_rcu); } +static inline u32 frh_get_table(struct fib_rule_hdr *frh, struct nlattr **nla) +{ + if (nla[FRA_TABLE]) + return nla_get_u32(nla[FRA_TABLE]); + return frh->table; +} + extern int fib_rules_register(struct fib_rules_ops *); extern int fib_rules_unregister(struct fib_rules_ops *); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 6cdad24038e..873b04d5df8 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -187,7 +187,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) rule->action = frh->action; rule->flags = frh->flags; - rule->table = frh->table; + rule->table = frh_get_table(frh, tb); if (!rule->pref && ops->default_pref) rule->pref = ops->default_pref(); @@ -245,7 +245,7 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (frh->action && (frh->action != rule->action)) continue; - if (frh->table && (frh->table != rule->table)) + if (frh->table && (frh_get_table(frh, tb) != rule->table)) continue; if (tb[FRA_PRIORITY] && @@ -291,6 +291,7 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, frh = nlmsg_data(nlh); frh->table = rule->table; + NLA_PUT_U32(skb, FRA_TABLE, rule->table); frh->res1 = 0; frh->res2 = 0; frh->action = rule->action; diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index 7b3bf5c3d72..fb596373daa 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -491,7 +491,8 @@ static int dn_fib_check_attr(struct rtmsg *r, struct rtattr **rta) if (attr) { if (RTA_PAYLOAD(attr) < 4 && RTA_PAYLOAD(attr) != 2) return -EINVAL; - if (i != RTA_MULTIPATH && i != RTA_METRICS) + if (i != RTA_MULTIPATH && i != RTA_METRICS && + i != RTA_TABLE) rta[i-1] = (struct rtattr *)RTA_DATA(attr); } } @@ -508,7 +509,7 @@ int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if (dn_fib_check_attr(r, rta)) return -EINVAL; - tb = dn_fib_get_table(r->rtm_table, 0); + tb = dn_fib_get_table(rtm_get_table(rta, r->rtm_table), 0); if (tb) return tb->delete(tb, r, (struct dn_kern_rta *)rta, nlh, &NETLINK_CB(skb)); @@ -524,7 +525,7 @@ int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if (dn_fib_check_attr(r, rta)) return -EINVAL; - tb = dn_fib_get_table(r->rtm_table, 1); + tb = dn_fib_get_table(rtm_get_table(rta, r->rtm_table), 1); if (tb) return tb->insert(tb, r, (struct dn_kern_rta *)rta, nlh, &NETLINK_CB(skb)); diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 5e6f4616ca1..4c963213fba 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1486,6 +1486,7 @@ static int dn_rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, r->rtm_src_len = 0; r->rtm_tos = 0; r->rtm_table = RT_TABLE_MAIN; + RTA_PUT_U32(skb, RTA_TABLE, RT_TABLE_MAIN); r->rtm_type = rt->rt_type; r->rtm_flags = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED; r->rtm_scope = RT_SCOPE_UNIVERSE; diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index 1601ee5406a..eca7c1e10c8 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -278,6 +278,7 @@ static int dn_fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, rtm->rtm_src_len = 0; rtm->rtm_tos = 0; rtm->rtm_table = tb_id; + RTA_PUT_U32(skb, RTA_TABLE, tb_id); rtm->rtm_flags = fi->fib_flags; rtm->rtm_scope = scope; rtm->rtm_type = type; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 06f4b23f6f5..2696ede52de 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -294,7 +294,8 @@ static int inet_check_attr(struct rtmsg *r, struct rtattr **rta) if (attr) { if (RTA_PAYLOAD(attr) < 4) return -EINVAL; - if (i != RTA_MULTIPATH && i != RTA_METRICS) + if (i != RTA_MULTIPATH && i != RTA_METRICS && + i != RTA_TABLE) *rta = (struct rtattr*)RTA_DATA(attr); } } @@ -310,7 +311,7 @@ int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (inet_check_attr(r, rta)) return -EINVAL; - tb = fib_get_table(r->rtm_table); + tb = fib_get_table(rtm_get_table(rta, r->rtm_table)); if (tb) return tb->tb_delete(tb, r, (struct kern_rta*)rta, nlh, &NETLINK_CB(skb)); return -ESRCH; @@ -325,7 +326,7 @@ int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (inet_check_attr(r, rta)) return -EINVAL; - tb = fib_new_table(r->rtm_table); + tb = fib_new_table(rtm_get_table(rta, r->rtm_table)); if (tb) return tb->tb_insert(tb, r, (struct kern_rta*)rta, nlh, &NETLINK_CB(skb)); return -ENOBUFS; diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 58fb91b00fd..0330b9cc4b5 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -184,6 +184,7 @@ static struct nla_policy fib4_rule_policy[FRA_MAX+1] __read_mostly = { [FRA_DST] = { .type = NLA_U32 }, [FRA_FWMARK] = { .type = NLA_U32 }, [FRA_FLOW] = { .type = NLA_U32 }, + [FRA_TABLE] = { .type = NLA_U32 }, }; static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index c7a112b5a18..ab753df20a3 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -953,6 +953,7 @@ fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, rtm->rtm_src_len = 0; rtm->rtm_tos = tos; rtm->rtm_table = tb_id; + RTA_PUT_U32(skb, RTA_TABLE, tb_id); rtm->rtm_type = type; rtm->rtm_flags = fi->fib_flags; rtm->rtm_scope = scope; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index b873cbcdd0b..12128b82c9d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2652,6 +2652,7 @@ static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event, r->rtm_src_len = 0; r->rtm_tos = rt->fl.fl4_tos; r->rtm_table = RT_TABLE_MAIN; + RTA_PUT_U32(skb, RTA_TABLE, RT_TABLE_MAIN); r->rtm_type = rt->rt_type; r->rtm_scope = RT_SCOPE_UNIVERSE; r->rtm_protocol = RTPROT_UNSPEC; diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 22a2fdb0983..2c4fbc855e6 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -129,6 +129,7 @@ static struct nla_policy fib6_rule_policy[RTA_MAX+1] __read_mostly = { [FRA_PRIORITY] = { .type = NLA_U32 }, [FRA_SRC] = { .minlen = sizeof(struct in6_addr) }, [FRA_DST] = { .minlen = sizeof(struct in6_addr) }, + [FRA_TABLE] = { .type = NLA_U32 }, }; static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e08d84063c1..843c5509fce 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1859,7 +1859,8 @@ int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (inet6_rtm_to_rtmsg(r, arg, &rtmsg)) return -EINVAL; - return ip6_route_del(&rtmsg, nlh, arg, &NETLINK_CB(skb), r->rtm_table); + return ip6_route_del(&rtmsg, nlh, arg, &NETLINK_CB(skb), + rtm_get_table(arg, r->rtm_table)); } int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) @@ -1869,7 +1870,8 @@ int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (inet6_rtm_to_rtmsg(r, arg, &rtmsg)) return -EINVAL; - return ip6_route_add(&rtmsg, nlh, arg, &NETLINK_CB(skb), r->rtm_table); + return ip6_route_add(&rtmsg, nlh, arg, &NETLINK_CB(skb), + rtm_get_table(arg, r->rtm_table)); } struct rt6_rtnl_dump_arg @@ -1887,6 +1889,7 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, struct nlmsghdr *nlh; unsigned char *b = skb->tail; struct rta_cacheinfo ci; + u32 table; if (prefix) { /* user wants prefix routes only */ if (!(rt->rt6i_flags & RTF_PREFIX_RT)) { @@ -1902,9 +1905,11 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, rtm->rtm_src_len = rt->rt6i_src.plen; rtm->rtm_tos = 0; if (rt->rt6i_table) - rtm->rtm_table = rt->rt6i_table->tb6_id; + table = rt->rt6i_table->tb6_id; else - rtm->rtm_table = RT6_TABLE_UNSPEC; + table = RT6_TABLE_UNSPEC; + rtm->rtm_table = table; + RTA_PUT_U32(skb, RTA_TABLE, table); if (rt->rt6i_flags&RTF_REJECT) rtm->rtm_type = RTN_UNREACHABLE; else if (rt->rt6i_dev && (rt->rt6i_dev->flags&IFF_LOOPBACK)) -- cgit v1.2.3-70-g09d2 From 1af5a8c4a11cfed0c9a7f30fcfb689981750599c Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 10 Aug 2006 23:10:46 -0700 Subject: [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 Signed-off-by: David S. Miller --- 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(-) (limited to 'net/ipv4/fib_frontend.c') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 0dcbf166eb9..8e9ba563d34 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -150,6 +150,7 @@ struct fib_result_nl { #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(const struct flowi *flp, struct fib_result } #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 2696ede52de..ad4c14f968a 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include @@ -51,48 +52,67 @@ #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 *skb, struct nlmsghdr* nlh, void *arg) 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_notifier = { 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 f8d5c8024cc..b5bee1a71e5 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 netlink_callback *cb, 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, struct netlink_callback *cb, 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, struct netlink_callback *cb, { 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 *tb, struct sk_buff *skb, struct netlin 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 0330b9cc4b5..ce185ac6f26 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -172,8 +172,8 @@ static struct fib_table *fib_empty_table(void) 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 4a27b2d573a..2a580eb2579 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, int plen, struct list_head *fah, struct fi 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, int plen, struct list_head *fah, struct fi 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 *t, int plen, struct fib_table *tb, str 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 *t, int plen, struct fib_table *tb, str 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 *tb, struct sk_buff *skb, struct netlin 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(); -- cgit v1.2.3-70-g09d2 From 4e902c57417c4c285b98ba2722468d1c3ed83d1b Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Thu, 17 Aug 2006 18:14:52 -0700 Subject: [IPv4]: FIB configuration using struct fib_config Introduces struct fib_config replacing the ugly struct kern_rta prone to ordering issues. Avoids creating faked netlink messages for auto generated routes or requests via ioctl. A new interface net/nexthop.h is added to help navigate through nexthop configuration arrays. A new struct nl_info will be used to carry the necessary netlink information to be used for notifications later on. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/net/ip_fib.h | 55 +++---- include/net/netlink.h | 10 ++ include/net/nexthop.h | 33 ++++ net/ipv4/fib_frontend.c | 364 +++++++++++++++++++++++++++++++++++--------- net/ipv4/fib_hash.c | 94 ++++++------ net/ipv4/fib_lookup.h | 11 +- net/ipv4/fib_semantics.c | 385 ++++++++++++++--------------------------------- net/ipv4/fib_trie.c | 76 ++++------ 8 files changed, 560 insertions(+), 468 deletions(-) create mode 100644 include/net/nexthop.h (limited to 'net/ipv4/fib_frontend.c') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 8e9ba563d34..42ed96fab3f 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -20,25 +20,32 @@ #include #include -/* WARNING: The ordering of these elements must match ordering - * of RTA_* rtnetlink attribute numbers. - */ -struct kern_rta { - void *rta_dst; - void *rta_src; - int *rta_iif; - int *rta_oif; - void *rta_gw; - u32 *rta_priority; - void *rta_prefsrc; - struct rtattr *rta_mx; - struct rtattr *rta_mp; - unsigned char *rta_protoinfo; - u32 *rta_flow; - struct rta_cacheinfo *rta_ci; - struct rta_session *rta_sess; - u32 *rta_mp_alg; -}; +struct fib_config { + u8 fc_family; + u8 fc_dst_len; + u8 fc_src_len; + u8 fc_tos; + u8 fc_protocol; + u8 fc_scope; + u8 fc_type; + /* 1 byte unused */ + u32 fc_table; + u32 fc_dst; + u32 fc_src; + u32 fc_gw; + int fc_oif; + u32 fc_flags; + u32 fc_priority; + u32 fc_prefsrc; + struct nlattr *fc_mx; + struct rtnexthop *fc_mp; + int fc_mx_len; + int fc_mp_len; + u32 fc_flow; + u32 fc_mp_alg; + u32 fc_nlflags; + struct nl_info fc_nlinfo; + }; struct fib_info; @@ -154,12 +161,8 @@ struct fib_table { u32 tb_id; unsigned tb_stamp; int (*tb_lookup)(struct fib_table *tb, const struct flowi *flp, struct fib_result *res); - int (*tb_insert)(struct fib_table *table, struct rtmsg *r, - struct kern_rta *rta, struct nlmsghdr *n, - struct netlink_skb_parms *req); - int (*tb_delete)(struct fib_table *table, struct rtmsg *r, - struct kern_rta *rta, struct nlmsghdr *n, - struct netlink_skb_parms *req); + int (*tb_insert)(struct fib_table *, struct fib_config *); + int (*tb_delete)(struct fib_table *, struct fib_config *); int (*tb_dump)(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb); int (*tb_flush)(struct fib_table *table); @@ -228,8 +231,6 @@ struct rtentry; extern int ip_fib_check_default(u32 gw, struct net_device *dev); extern int fib_sync_down(u32 local, struct net_device *dev, int force); extern int fib_sync_up(struct net_device *dev); -extern int fib_convert_rtentry(int cmd, struct nlmsghdr *nl, struct rtmsg *rtm, - struct kern_rta *rta, struct rtentry *r); extern u32 __fib_res_prefsrc(struct fib_result *res); /* Exported by fib_hash.c */ diff --git a/include/net/netlink.h b/include/net/netlink.h index bf593eb59e1..47044da167c 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -192,6 +192,16 @@ struct nla_policy { u16 minlen; }; +/** + * struct nl_info - netlink source information + * @nlh: Netlink message header of original request + * @pid: Netlink PID of requesting application + */ +struct nl_info { + struct nlmsghdr *nlh; + u32 pid; +}; + extern void netlink_run_queue(struct sock *sk, unsigned int *qlen, int (*cb)(struct sk_buff *, struct nlmsghdr *, int *)); diff --git a/include/net/nexthop.h b/include/net/nexthop.h new file mode 100644 index 00000000000..3334dbfa5aa --- /dev/null +++ b/include/net/nexthop.h @@ -0,0 +1,33 @@ +#ifndef __NET_NEXTHOP_H +#define __NET_NEXTHOP_H + +#include +#include + +static inline int rtnh_ok(const struct rtnexthop *rtnh, int remaining) +{ + return remaining >= sizeof(*rtnh) && + rtnh->rtnh_len >= sizeof(*rtnh) && + rtnh->rtnh_len <= remaining; +} + +static inline struct rtnexthop *rtnh_next(const struct rtnexthop *rtnh, + int *remaining) +{ + int totlen = NLA_ALIGN(rtnh->rtnh_len); + + *remaining -= totlen; + return (struct rtnexthop *) ((char *) rtnh + totlen); +} + +static inline struct nlattr *rtnh_attrs(const struct rtnexthop *rtnh) +{ + return (struct nlattr *) ((char *) rtnh + NLA_ALIGN(sizeof(*rtnh))); +} + +static inline int rtnh_attrlen(const struct rtnexthop *rtnh) +{ + return rtnh->rtnh_len - NLA_ALIGN(sizeof(*rtnh)); +} + +#endif diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index ad4c14f968a..acc18bdf2de 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -253,42 +253,190 @@ e_inval: #ifndef CONFIG_IP_NOSIOCRT +static inline u32 sk_extract_addr(struct sockaddr *addr) +{ + return ((struct sockaddr_in *) addr)->sin_addr.s_addr; +} + +static int put_rtax(struct nlattr *mx, int len, int type, u32 value) +{ + struct nlattr *nla; + + nla = (struct nlattr *) ((char *) mx + len); + nla->nla_type = type; + nla->nla_len = nla_attr_size(4); + *(u32 *) nla_data(nla) = value; + + return len + nla_total_size(4); +} + +static int rtentry_to_fib_config(int cmd, struct rtentry *rt, + struct fib_config *cfg) +{ + u32 addr; + int plen; + + memset(cfg, 0, sizeof(*cfg)); + + if (rt->rt_dst.sa_family != AF_INET) + return -EAFNOSUPPORT; + + /* + * Check mask for validity: + * a) it must be contiguous. + * b) destination must have all host bits clear. + * c) if application forgot to set correct family (AF_INET), + * reject request unless it is absolutely clear i.e. + * both family and mask are zero. + */ + plen = 32; + addr = sk_extract_addr(&rt->rt_dst); + if (!(rt->rt_flags & RTF_HOST)) { + u32 mask = sk_extract_addr(&rt->rt_genmask); + + if (rt->rt_genmask.sa_family != AF_INET) { + if (mask || rt->rt_genmask.sa_family) + return -EAFNOSUPPORT; + } + + if (bad_mask(mask, addr)) + return -EINVAL; + + plen = inet_mask_len(mask); + } + + cfg->fc_dst_len = plen; + cfg->fc_dst = addr; + + if (cmd != SIOCDELRT) { + cfg->fc_nlflags = NLM_F_CREATE; + cfg->fc_protocol = RTPROT_BOOT; + } + + if (rt->rt_metric) + cfg->fc_priority = rt->rt_metric - 1; + + if (rt->rt_flags & RTF_REJECT) { + cfg->fc_scope = RT_SCOPE_HOST; + cfg->fc_type = RTN_UNREACHABLE; + return 0; + } + + cfg->fc_scope = RT_SCOPE_NOWHERE; + cfg->fc_type = RTN_UNICAST; + + if (rt->rt_dev) { + char *colon; + struct net_device *dev; + char devname[IFNAMSIZ]; + + if (copy_from_user(devname, rt->rt_dev, IFNAMSIZ-1)) + return -EFAULT; + + devname[IFNAMSIZ-1] = 0; + colon = strchr(devname, ':'); + if (colon) + *colon = 0; + dev = __dev_get_by_name(devname); + if (!dev) + return -ENODEV; + cfg->fc_oif = dev->ifindex; + if (colon) { + struct in_ifaddr *ifa; + struct in_device *in_dev = __in_dev_get_rtnl(dev); + if (!in_dev) + return -ENODEV; + *colon = ':'; + for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) + if (strcmp(ifa->ifa_label, devname) == 0) + break; + if (ifa == NULL) + return -ENODEV; + cfg->fc_prefsrc = ifa->ifa_local; + } + } + + addr = sk_extract_addr(&rt->rt_gateway); + if (rt->rt_gateway.sa_family == AF_INET && addr) { + cfg->fc_gw = addr; + if (rt->rt_flags & RTF_GATEWAY && + inet_addr_type(addr) == RTN_UNICAST) + cfg->fc_scope = RT_SCOPE_UNIVERSE; + } + + if (cmd == SIOCDELRT) + return 0; + + if (rt->rt_flags & RTF_GATEWAY && !cfg->fc_gw) + return -EINVAL; + + if (cfg->fc_scope == RT_SCOPE_NOWHERE) + cfg->fc_scope = RT_SCOPE_LINK; + + if (rt->rt_flags & (RTF_MTU | RTF_WINDOW | RTF_IRTT)) { + struct nlattr *mx; + int len = 0; + + mx = kzalloc(3 * nla_total_size(4), GFP_KERNEL); + if (mx == NULL) + return -ENOMEM; + + if (rt->rt_flags & RTF_MTU) + len = put_rtax(mx, len, RTAX_ADVMSS, rt->rt_mtu - 40); + + if (rt->rt_flags & RTF_WINDOW) + len = put_rtax(mx, len, RTAX_WINDOW, rt->rt_window); + + if (rt->rt_flags & RTF_IRTT) + len = put_rtax(mx, len, RTAX_RTT, rt->rt_irtt << 3); + + cfg->fc_mx = mx; + cfg->fc_mx_len = len; + } + + return 0; +} + /* * Handle IP routing ioctl calls. These are used to manipulate the routing tables */ int ip_rt_ioctl(unsigned int cmd, void __user *arg) { + struct fib_config cfg; + struct rtentry rt; int err; - struct kern_rta rta; - struct rtentry r; - struct { - struct nlmsghdr nlh; - struct rtmsg rtm; - } req; switch (cmd) { case SIOCADDRT: /* Add a route */ case SIOCDELRT: /* Delete a route */ if (!capable(CAP_NET_ADMIN)) return -EPERM; - if (copy_from_user(&r, arg, sizeof(struct rtentry))) + + if (copy_from_user(&rt, arg, sizeof(rt))) return -EFAULT; + rtnl_lock(); - err = fib_convert_rtentry(cmd, &req.nlh, &req.rtm, &rta, &r); + err = rtentry_to_fib_config(cmd, &rt, &cfg); if (err == 0) { + struct fib_table *tb; + if (cmd == SIOCDELRT) { - struct fib_table *tb = fib_get_table(req.rtm.rtm_table); - err = -ESRCH; + tb = fib_get_table(cfg.fc_table); if (tb) - err = tb->tb_delete(tb, &req.rtm, &rta, &req.nlh, NULL); + err = tb->tb_delete(tb, &cfg); + else + err = -ESRCH; } else { - struct fib_table *tb = fib_new_table(req.rtm.rtm_table); - err = -ENOBUFS; + tb = fib_new_table(cfg.fc_table); if (tb) - err = tb->tb_insert(tb, &req.rtm, &rta, &req.nlh, NULL); + err = tb->tb_insert(tb, &cfg); + else + err = -ENOBUFS; } - kfree(rta.rta_mx); + + /* allocated by rtentry_to_fib_config() */ + kfree(cfg.fc_mx); } rtnl_unlock(); return err; @@ -305,51 +453,134 @@ int ip_rt_ioctl(unsigned int cmd, void *arg) #endif -static int inet_check_attr(struct rtmsg *r, struct rtattr **rta) +static struct nla_policy rtm_ipv4_policy[RTA_MAX+1] __read_mostly = { + [RTA_DST] = { .type = NLA_U32 }, + [RTA_SRC] = { .type = NLA_U32 }, + [RTA_IIF] = { .type = NLA_U32 }, + [RTA_OIF] = { .type = NLA_U32 }, + [RTA_GATEWAY] = { .type = NLA_U32 }, + [RTA_PRIORITY] = { .type = NLA_U32 }, + [RTA_PREFSRC] = { .type = NLA_U32 }, + [RTA_METRICS] = { .type = NLA_NESTED }, + [RTA_MULTIPATH] = { .minlen = sizeof(struct rtnexthop) }, + [RTA_PROTOINFO] = { .type = NLA_U32 }, + [RTA_FLOW] = { .type = NLA_U32 }, + [RTA_MP_ALGO] = { .type = NLA_U32 }, +}; + +static int rtm_to_fib_config(struct sk_buff *skb, struct nlmsghdr *nlh, + struct fib_config *cfg) { - int i; - - for (i=1; i<=RTA_MAX; i++, rta++) { - struct rtattr *attr = *rta; - if (attr) { - if (RTA_PAYLOAD(attr) < 4) - return -EINVAL; - if (i != RTA_MULTIPATH && i != RTA_METRICS && - i != RTA_TABLE) - *rta = (struct rtattr*)RTA_DATA(attr); + struct nlattr *attr; + int err, remaining; + struct rtmsg *rtm; + + err = nlmsg_validate(nlh, sizeof(*rtm), RTA_MAX, rtm_ipv4_policy); + if (err < 0) + goto errout; + + memset(cfg, 0, sizeof(*cfg)); + + rtm = nlmsg_data(nlh); + cfg->fc_family = rtm->rtm_family; + cfg->fc_dst_len = rtm->rtm_dst_len; + cfg->fc_src_len = rtm->rtm_src_len; + cfg->fc_tos = rtm->rtm_tos; + cfg->fc_table = rtm->rtm_table; + cfg->fc_protocol = rtm->rtm_protocol; + cfg->fc_scope = rtm->rtm_scope; + cfg->fc_type = rtm->rtm_type; + cfg->fc_flags = rtm->rtm_flags; + cfg->fc_nlflags = nlh->nlmsg_flags; + + cfg->fc_nlinfo.pid = NETLINK_CB(skb).pid; + cfg->fc_nlinfo.nlh = nlh; + + nlmsg_for_each_attr(attr, nlh, sizeof(struct rtmsg), remaining) { + switch (attr->nla_type) { + case RTA_DST: + cfg->fc_dst = nla_get_u32(attr); + break; + case RTA_SRC: + cfg->fc_src = nla_get_u32(attr); + break; + case RTA_OIF: + cfg->fc_oif = nla_get_u32(attr); + break; + case RTA_GATEWAY: + cfg->fc_gw = nla_get_u32(attr); + break; + case RTA_PRIORITY: + cfg->fc_priority = nla_get_u32(attr); + break; + case RTA_PREFSRC: + cfg->fc_prefsrc = nla_get_u32(attr); + break; + case RTA_METRICS: + cfg->fc_mx = nla_data(attr); + cfg->fc_mx_len = nla_len(attr); + break; + case RTA_MULTIPATH: + cfg->fc_mp = nla_data(attr); + cfg->fc_mp_len = nla_len(attr); + break; + case RTA_FLOW: + cfg->fc_flow = nla_get_u32(attr); + break; + case RTA_MP_ALGO: + cfg->fc_mp_alg = nla_get_u32(attr); + break; + case RTA_TABLE: + cfg->fc_table = nla_get_u32(attr); + break; } } + return 0; +errout: + return err; } int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { - struct fib_table * tb; - struct rtattr **rta = arg; - struct rtmsg *r = NLMSG_DATA(nlh); + struct fib_config cfg; + struct fib_table *tb; + int err; - if (inet_check_attr(r, rta)) - return -EINVAL; + err = rtm_to_fib_config(skb, nlh, &cfg); + if (err < 0) + goto errout; - tb = fib_get_table(rtm_get_table(rta, r->rtm_table)); - if (tb) - return tb->tb_delete(tb, r, (struct kern_rta*)rta, nlh, &NETLINK_CB(skb)); - return -ESRCH; + tb = fib_get_table(cfg.fc_table); + if (tb == NULL) { + err = -ESRCH; + goto errout; + } + + err = tb->tb_delete(tb, &cfg); +errout: + return err; } int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { - struct fib_table * tb; - struct rtattr **rta = arg; - struct rtmsg *r = NLMSG_DATA(nlh); + struct fib_config cfg; + struct fib_table *tb; + int err; - if (inet_check_attr(r, rta)) - return -EINVAL; + err = rtm_to_fib_config(skb, nlh, &cfg); + if (err < 0) + goto errout; - tb = fib_new_table(rtm_get_table(rta, r->rtm_table)); - if (tb) - return tb->tb_insert(tb, r, (struct kern_rta*)rta, nlh, &NETLINK_CB(skb)); - return -ENOBUFS; + tb = fib_new_table(cfg.fc_table); + if (tb == NULL) { + err = -ENOBUFS; + goto errout; + } + + err = tb->tb_insert(tb, &cfg); +errout: + return err; } int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) @@ -396,17 +627,19 @@ out: only when netlink is already locked. */ -static void fib_magic(int cmd, int type, u32 dst, int dst_len, struct in_ifaddr *ifa) +static void fib_magic(int cmd, int type, u32 dst, int dst_len, + struct in_ifaddr *ifa) { - struct fib_table * tb; - struct { - struct nlmsghdr nlh; - struct rtmsg rtm; - } req; - struct kern_rta rta; - - memset(&req.rtm, 0, sizeof(req.rtm)); - memset(&rta, 0, sizeof(rta)); + struct fib_table *tb; + struct fib_config cfg = { + .fc_protocol = RTPROT_KERNEL, + .fc_type = type, + .fc_dst = dst, + .fc_dst_len = dst_len, + .fc_prefsrc = ifa->ifa_local, + .fc_oif = ifa->ifa_dev->dev->ifindex, + .fc_nlflags = NLM_F_CREATE | NLM_F_APPEND, + }; if (type == RTN_UNICAST) tb = fib_new_table(RT_TABLE_MAIN); @@ -416,26 +649,17 @@ static void fib_magic(int cmd, int type, u32 dst, int dst_len, struct in_ifaddr if (tb == NULL) return; - req.nlh.nlmsg_len = sizeof(req); - req.nlh.nlmsg_type = cmd; - req.nlh.nlmsg_flags = NLM_F_REQUEST|NLM_F_CREATE|NLM_F_APPEND; - req.nlh.nlmsg_pid = 0; - req.nlh.nlmsg_seq = 0; + cfg.fc_table = tb->tb_id; - req.rtm.rtm_dst_len = dst_len; - req.rtm.rtm_table = tb->tb_id; - req.rtm.rtm_protocol = RTPROT_KERNEL; - req.rtm.rtm_scope = (type != RTN_LOCAL ? RT_SCOPE_LINK : RT_SCOPE_HOST); - req.rtm.rtm_type = type; - - rta.rta_dst = &dst; - rta.rta_prefsrc = &ifa->ifa_local; - rta.rta_oif = &ifa->ifa_dev->dev->ifindex; + if (type != RTN_LOCAL) + cfg.fc_scope = RT_SCOPE_LINK; + else + cfg.fc_scope = RT_SCOPE_HOST; if (cmd == RTM_NEWROUTE) - tb->tb_insert(tb, &req.rtm, &rta, &req.nlh, NULL); + tb->tb_insert(tb, &cfg); else - tb->tb_delete(tb, &req.rtm, &rta, &req.nlh, NULL); + tb->tb_delete(tb, &cfg); } void fib_add_ifaddr(struct in_ifaddr *ifa) diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c index b5bee1a71e5..357557549ce 100644 --- a/net/ipv4/fib_hash.c +++ b/net/ipv4/fib_hash.c @@ -379,42 +379,39 @@ static struct fib_node *fib_find_node(struct fn_zone *fz, u32 key) return NULL; } -static int -fn_hash_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, - struct nlmsghdr *n, struct netlink_skb_parms *req) +static int fn_hash_insert(struct fib_table *tb, struct fib_config *cfg) { struct fn_hash *table = (struct fn_hash *) tb->tb_data; struct fib_node *new_f, *f; struct fib_alias *fa, *new_fa; struct fn_zone *fz; struct fib_info *fi; - int z = r->rtm_dst_len; - int type = r->rtm_type; - u8 tos = r->rtm_tos; + u8 tos = cfg->fc_tos; u32 key; int err; - if (z > 32) + if (cfg->fc_dst_len > 32) return -EINVAL; - fz = table->fn_zones[z]; - if (!fz && !(fz = fn_new_zone(table, z))) + + fz = table->fn_zones[cfg->fc_dst_len]; + if (!fz && !(fz = fn_new_zone(table, cfg->fc_dst_len))) return -ENOBUFS; key = 0; - if (rta->rta_dst) { - u32 dst; - memcpy(&dst, rta->rta_dst, 4); - if (dst & ~FZ_MASK(fz)) + if (cfg->fc_dst) { + if (cfg->fc_dst & ~FZ_MASK(fz)) return -EINVAL; - key = fz_key(dst, fz); + key = fz_key(cfg->fc_dst, fz); } - if ((fi = fib_create_info(r, rta, n, &err)) == NULL) - return err; + fi = fib_create_info(cfg); + if (IS_ERR(fi)) + return PTR_ERR(fi); if (fz->fz_nent > (fz->fz_divisor<<1) && fz->fz_divisor < FZ_MAX_DIVISOR && - (z==32 || (1< fz->fz_divisor)) + (cfg->fc_dst_len == 32 || + (1 << cfg->fc_dst_len) > fz->fz_divisor)) fn_rehash_zone(fz); f = fib_find_node(fz, key); @@ -440,18 +437,18 @@ fn_hash_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, struct fib_alias *fa_orig; err = -EEXIST; - if (n->nlmsg_flags & NLM_F_EXCL) + if (cfg->fc_nlflags & NLM_F_EXCL) goto out; - if (n->nlmsg_flags & NLM_F_REPLACE) { + if (cfg->fc_nlflags & NLM_F_REPLACE) { struct fib_info *fi_drop; u8 state; write_lock_bh(&fib_hash_lock); fi_drop = fa->fa_info; fa->fa_info = fi; - fa->fa_type = type; - fa->fa_scope = r->rtm_scope; + fa->fa_type = cfg->fc_type; + fa->fa_scope = cfg->fc_scope; state = fa->fa_state; fa->fa_state &= ~FA_S_ACCESSED; fib_hash_genid++; @@ -474,17 +471,17 @@ fn_hash_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, break; if (fa->fa_info->fib_priority != fi->fib_priority) break; - if (fa->fa_type == type && - fa->fa_scope == r->rtm_scope && + if (fa->fa_type == cfg->fc_type && + fa->fa_scope == cfg->fc_scope && fa->fa_info == fi) goto out; } - if (!(n->nlmsg_flags & NLM_F_APPEND)) + if (!(cfg->fc_nlflags & NLM_F_APPEND)) fa = fa_orig; } err = -ENOENT; - if (!(n->nlmsg_flags&NLM_F_CREATE)) + if (!(cfg->fc_nlflags & NLM_F_CREATE)) goto out; err = -ENOBUFS; @@ -506,8 +503,8 @@ fn_hash_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, new_fa->fa_info = fi; new_fa->fa_tos = tos; - new_fa->fa_type = type; - new_fa->fa_scope = r->rtm_scope; + new_fa->fa_type = cfg->fc_type; + new_fa->fa_scope = cfg->fc_scope; new_fa->fa_state = 0; /* @@ -526,7 +523,8 @@ fn_hash_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, fz->fz_nent++; rt_cache_flush(-1); - rtmsg_fib(RTM_NEWROUTE, key, new_fa, z, tb->tb_id, n, req); + rtmsg_fib(RTM_NEWROUTE, key, new_fa, cfg->fc_dst_len, tb->tb_id, + &cfg->fc_nlinfo); return 0; out_free_new_fa: @@ -537,30 +535,25 @@ out: } -static int -fn_hash_delete(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, - struct nlmsghdr *n, struct netlink_skb_parms *req) +static int fn_hash_delete(struct fib_table *tb, struct fib_config *cfg) { struct fn_hash *table = (struct fn_hash*)tb->tb_data; struct fib_node *f; struct fib_alias *fa, *fa_to_delete; - int z = r->rtm_dst_len; struct fn_zone *fz; u32 key; - u8 tos = r->rtm_tos; - if (z > 32) + if (cfg->fc_dst_len > 32) return -EINVAL; - if ((fz = table->fn_zones[z]) == NULL) + + if ((fz = table->fn_zones[cfg->fc_dst_len]) == NULL) return -ESRCH; key = 0; - if (rta->rta_dst) { - u32 dst; - memcpy(&dst, rta->rta_dst, 4); - if (dst & ~FZ_MASK(fz)) + if (cfg->fc_dst) { + if (cfg->fc_dst & ~FZ_MASK(fz)) return -EINVAL; - key = fz_key(dst, fz); + key = fz_key(cfg->fc_dst, fz); } f = fib_find_node(fz, key); @@ -568,7 +561,7 @@ fn_hash_delete(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, if (!f) fa = NULL; else - fa = fib_find_alias(&f->fn_alias, tos, 0); + fa = fib_find_alias(&f->fn_alias, cfg->fc_tos, 0); if (!fa) return -ESRCH; @@ -577,16 +570,16 @@ fn_hash_delete(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, list_for_each_entry_continue(fa, &f->fn_alias, fa_list) { struct fib_info *fi = fa->fa_info; - if (fa->fa_tos != tos) + if (fa->fa_tos != cfg->fc_tos) break; - if ((!r->rtm_type || - fa->fa_type == r->rtm_type) && - (r->rtm_scope == RT_SCOPE_NOWHERE || - fa->fa_scope == r->rtm_scope) && - (!r->rtm_protocol || - fi->fib_protocol == r->rtm_protocol) && - fib_nh_match(r, n, rta, fi) == 0) { + if ((!cfg->fc_type || + fa->fa_type == cfg->fc_type) && + (cfg->fc_scope == RT_SCOPE_NOWHERE || + fa->fa_scope == cfg->fc_scope) && + (!cfg->fc_protocol || + fi->fib_protocol == cfg->fc_protocol) && + fib_nh_match(cfg, fi) == 0) { fa_to_delete = fa; break; } @@ -596,7 +589,8 @@ fn_hash_delete(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, int kill_fn; fa = fa_to_delete; - rtmsg_fib(RTM_DELROUTE, key, fa, z, tb->tb_id, n, req); + rtmsg_fib(RTM_DELROUTE, key, fa, cfg->fc_dst_len, + tb->tb_id, &cfg->fc_nlinfo); kill_fn = 0; write_lock_bh(&fib_hash_lock); diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index ddd52496b45..d6d1a89e400 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -23,19 +23,14 @@ extern int fib_semantic_match(struct list_head *head, struct fib_result *res, __u32 zone, __u32 mask, int prefixlen); extern void fib_release_info(struct fib_info *); -extern struct fib_info *fib_create_info(const struct rtmsg *r, - struct kern_rta *rta, - const struct nlmsghdr *, - int *err); -extern int fib_nh_match(struct rtmsg *r, struct nlmsghdr *, - struct kern_rta *rta, struct fib_info *fi); +extern struct fib_info *fib_create_info(struct fib_config *cfg); +extern int fib_nh_match(struct fib_config *cfg, struct fib_info *fi); extern int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, u32 tb_id, u8 type, u8 scope, void *dst, int dst_len, u8 tos, struct fib_info *fi, unsigned int); extern void rtmsg_fib(int event, u32 key, struct fib_alias *fa, - int z, u32 tb_id, - struct nlmsghdr *n, struct netlink_skb_parms *req); + int dst_len, u32 tb_id, struct nl_info *info); extern struct fib_alias *fib_find_alias(struct list_head *fah, u8 tos, u32 prio); extern int fib_detect_death(struct fib_info *fi, int order, diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 5dfdad5cbcd..340f9db389e 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -44,6 +44,7 @@ #include #include #include +#include #include "fib_lookup.h" @@ -273,27 +274,27 @@ int ip_fib_check_default(u32 gw, struct net_device *dev) } void rtmsg_fib(int event, u32 key, struct fib_alias *fa, - int z, u32 tb_id, - struct nlmsghdr *n, struct netlink_skb_parms *req) + int dst_len, u32 tb_id, struct nl_info *info) { struct sk_buff *skb; - u32 pid = req ? req->pid : n->nlmsg_pid; int payload = sizeof(struct rtmsg) + 256; + u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; int err = -ENOBUFS; skb = nlmsg_new(nlmsg_total_size(payload), GFP_KERNEL); if (skb == NULL) goto errout; - err = fib_dump_info(skb, pid, n->nlmsg_seq, event, tb_id, - fa->fa_type, fa->fa_scope, &key, z, fa->fa_tos, - fa->fa_info, 0); + err = fib_dump_info(skb, info->pid, seq, event, tb_id, + fa->fa_type, fa->fa_scope, &key, dst_len, + fa->fa_tos, fa->fa_info, 0); if (err < 0) { kfree_skb(skb); goto errout; } - err = rtnl_notify(skb, pid, RTNLGRP_IPV4_ROUTE, n, GFP_KERNEL); + err = rtnl_notify(skb, info->pid, RTNLGRP_IPV4_ROUTE, + info->nlh, GFP_KERNEL); errout: if (err < 0) rtnl_set_sk_err(RTNLGRP_IPV4_ROUTE, err); @@ -342,102 +343,100 @@ int fib_detect_death(struct fib_info *fi, int order, #ifdef CONFIG_IP_ROUTE_MULTIPATH -static u32 fib_get_attr32(struct rtattr *attr, int attrlen, int type) -{ - while (RTA_OK(attr,attrlen)) { - if (attr->rta_type == type) - return *(u32*)RTA_DATA(attr); - attr = RTA_NEXT(attr, attrlen); - } - return 0; -} - -static int -fib_count_nexthops(struct rtattr *rta) +static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining) { int nhs = 0; - struct rtnexthop *nhp = RTA_DATA(rta); - int nhlen = RTA_PAYLOAD(rta); - while (nhlen >= (int)sizeof(struct rtnexthop)) { - if ((nhlen -= nhp->rtnh_len) < 0) - return 0; + while (rtnh_ok(rtnh, remaining)) { nhs++; - nhp = RTNH_NEXT(nhp); - }; - return nhs; + rtnh = rtnh_next(rtnh, &remaining); + } + + /* leftover implies invalid nexthop configuration, discard it */ + return remaining > 0 ? 0 : nhs; } -static int -fib_get_nhs(struct fib_info *fi, const struct rtattr *rta, const struct rtmsg *r) +static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, + int remaining, struct fib_config *cfg) { - struct rtnexthop *nhp = RTA_DATA(rta); - int nhlen = RTA_PAYLOAD(rta); - change_nexthops(fi) { - int attrlen = nhlen - sizeof(struct rtnexthop); - if (attrlen < 0 || (nhlen -= nhp->rtnh_len) < 0) + int attrlen; + + if (!rtnh_ok(rtnh, remaining)) return -EINVAL; - nh->nh_flags = (r->rtm_flags&~0xFF) | nhp->rtnh_flags; - nh->nh_oif = nhp->rtnh_ifindex; - nh->nh_weight = nhp->rtnh_hops + 1; - if (attrlen) { - nh->nh_gw = fib_get_attr32(RTNH_DATA(nhp), attrlen, RTA_GATEWAY); + + nh->nh_flags = (cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags; + nh->nh_oif = rtnh->rtnh_ifindex; + nh->nh_weight = rtnh->rtnh_hops + 1; + + attrlen = rtnh_attrlen(rtnh); + if (attrlen > 0) { + struct nlattr *nla, *attrs = rtnh_attrs(rtnh); + + nla = nla_find(attrs, attrlen, RTA_GATEWAY); + nh->nh_gw = nla ? nla_get_u32(nla) : 0; #ifdef CONFIG_NET_CLS_ROUTE - nh->nh_tclassid = fib_get_attr32(RTNH_DATA(nhp), attrlen, RTA_FLOW); + nla = nla_find(attrs, attrlen, RTA_FLOW); + nh->nh_tclassid = nla ? nla_get_u32(nla) : 0; #endif } - nhp = RTNH_NEXT(nhp); + + rtnh = rtnh_next(rtnh, &remaining); } endfor_nexthops(fi); + return 0; } #endif -int fib_nh_match(struct rtmsg *r, struct nlmsghdr *nlh, struct kern_rta *rta, - struct fib_info *fi) +int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) { #ifdef CONFIG_IP_ROUTE_MULTIPATH - struct rtnexthop *nhp; - int nhlen; + struct rtnexthop *rtnh; + int remaining; #endif - if (rta->rta_priority && - *rta->rta_priority != fi->fib_priority) + if (cfg->fc_priority && cfg->fc_priority != fi->fib_priority) return 1; - if (rta->rta_oif || rta->rta_gw) { - if ((!rta->rta_oif || *rta->rta_oif == fi->fib_nh->nh_oif) && - (!rta->rta_gw || memcmp(rta->rta_gw, &fi->fib_nh->nh_gw, 4) == 0)) + if (cfg->fc_oif || cfg->fc_gw) { + if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) && + (!cfg->fc_gw || cfg->fc_gw == fi->fib_nh->nh_gw)) return 0; return 1; } #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (rta->rta_mp == NULL) + if (cfg->fc_mp == NULL) return 0; - nhp = RTA_DATA(rta->rta_mp); - nhlen = RTA_PAYLOAD(rta->rta_mp); + + rtnh = cfg->fc_mp; + remaining = cfg->fc_mp_len; for_nexthops(fi) { - int attrlen = nhlen - sizeof(struct rtnexthop); - u32 gw; + int attrlen; - if (attrlen < 0 || (nhlen -= nhp->rtnh_len) < 0) + if (!rtnh_ok(rtnh, remaining)) return -EINVAL; - if (nhp->rtnh_ifindex && nhp->rtnh_ifindex != nh->nh_oif) + + if (rtnh->rtnh_ifindex && rtnh->rtnh_ifindex != nh->nh_oif) return 1; - if (attrlen) { - gw = fib_get_attr32(RTNH_DATA(nhp), attrlen, RTA_GATEWAY); - if (gw && gw != nh->nh_gw) + + attrlen = rtnh_attrlen(rtnh); + if (attrlen < 0) { + struct nlattr *nla, *attrs = rtnh_attrs(rtnh); + + nla = nla_find(attrs, attrlen, RTA_GATEWAY); + if (nla && nla_get_u32(nla) != nh->nh_gw) return 1; #ifdef CONFIG_NET_CLS_ROUTE - gw = fib_get_attr32(RTNH_DATA(nhp), attrlen, RTA_FLOW); - if (gw && gw != nh->nh_tclassid) + nla = nla_find(attrs, attrlen, RTA_FLOW); + if (nla && nla_get_u32(nla) != nh->nh_tclassid) return 1; #endif } - nhp = RTNH_NEXT(nhp); + + rtnh = rtnh_next(rtnh, &remaining); } endfor_nexthops(fi); #endif return 0; @@ -488,7 +487,8 @@ int fib_nh_match(struct rtmsg *r, struct nlmsghdr *nlh, struct kern_rta *rta, |-> {local prefix} (terminal node) */ -static int fib_check_nh(const struct rtmsg *r, struct fib_info *fi, struct fib_nh *nh) +static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, + struct fib_nh *nh) { int err; @@ -502,7 +502,7 @@ static int fib_check_nh(const struct rtmsg *r, struct fib_info *fi, struct fib_n if (nh->nh_flags&RTNH_F_ONLINK) { struct net_device *dev; - if (r->rtm_scope >= RT_SCOPE_LINK) + if (cfg->fc_scope >= RT_SCOPE_LINK) return -EINVAL; if (inet_addr_type(nh->nh_gw) != RTN_UNICAST) return -EINVAL; @@ -516,10 +516,15 @@ static int fib_check_nh(const struct rtmsg *r, struct fib_info *fi, struct fib_n return 0; } { - struct flowi fl = { .nl_u = { .ip4_u = - { .daddr = nh->nh_gw, - .scope = r->rtm_scope + 1 } }, - .oif = nh->nh_oif }; + struct flowi fl = { + .nl_u = { + .ip4_u = { + .daddr = nh->nh_gw, + .scope = cfg->fc_scope + 1, + }, + }, + .oif = nh->nh_oif, + }; /* It is not necessary, but requires a bit of thinking */ if (fl.fl4_scope < RT_SCOPE_LINK) @@ -646,39 +651,28 @@ static void fib_hash_move(struct hlist_head *new_info_hash, fib_hash_free(old_laddrhash, bytes); } -struct fib_info * -fib_create_info(const struct rtmsg *r, struct kern_rta *rta, - const struct nlmsghdr *nlh, int *errp) +struct fib_info *fib_create_info(struct fib_config *cfg) { int err; struct fib_info *fi = NULL; struct fib_info *ofi; -#ifdef CONFIG_IP_ROUTE_MULTIPATH int nhs = 1; -#else - const int nhs = 1; -#endif -#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED - u32 mp_alg = IP_MP_ALG_NONE; -#endif /* Fast check to catch the most weird cases */ - if (fib_props[r->rtm_type].scope > r->rtm_scope) + if (fib_props[cfg->fc_type].scope > cfg->fc_scope) goto err_inval; #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (rta->rta_mp) { - nhs = fib_count_nexthops(rta->rta_mp); + if (cfg->fc_mp) { + nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len); if (nhs == 0) goto err_inval; } #endif #ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED - if (rta->rta_mp_alg) { - mp_alg = *rta->rta_mp_alg; - - if (mp_alg < IP_MP_ALG_NONE || - mp_alg > IP_MP_ALG_MAX) + if (cfg->fc_mp_alg) { + if (cfg->fc_mp_alg < IP_MP_ALG_NONE || + cfg->fc_mp_alg > IP_MP_ALG_MAX) goto err_inval; } #endif @@ -714,43 +708,42 @@ fib_create_info(const struct rtmsg *r, struct kern_rta *rta, goto failure; fib_info_cnt++; - fi->fib_protocol = r->rtm_protocol; + fi->fib_protocol = cfg->fc_protocol; + fi->fib_flags = cfg->fc_flags; + fi->fib_priority = cfg->fc_priority; + fi->fib_prefsrc = cfg->fc_prefsrc; fi->fib_nhs = nhs; change_nexthops(fi) { nh->nh_parent = fi; } endfor_nexthops(fi) - fi->fib_flags = r->rtm_flags; - if (rta->rta_priority) - fi->fib_priority = *rta->rta_priority; - if (rta->rta_mx) { - int attrlen = RTA_PAYLOAD(rta->rta_mx); - struct rtattr *attr = RTA_DATA(rta->rta_mx); - - while (RTA_OK(attr, attrlen)) { - unsigned flavor = attr->rta_type; - if (flavor) { - if (flavor > RTAX_MAX) + if (cfg->fc_mx) { + struct nlattr *nla; + int remaining; + + nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) { + int type = nla->nla_type; + + if (type) { + if (type > RTAX_MAX) goto err_inval; - fi->fib_metrics[flavor-1] = *(unsigned*)RTA_DATA(attr); + fi->fib_metrics[type - 1] = nla_get_u32(nla); } - attr = RTA_NEXT(attr, attrlen); } } - if (rta->rta_prefsrc) - memcpy(&fi->fib_prefsrc, rta->rta_prefsrc, 4); - if (rta->rta_mp) { + if (cfg->fc_mp) { #ifdef CONFIG_IP_ROUTE_MULTIPATH - if ((err = fib_get_nhs(fi, rta->rta_mp, r)) != 0) + err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg); + if (err != 0) goto failure; - if (rta->rta_oif && fi->fib_nh->nh_oif != *rta->rta_oif) + if (cfg->fc_oif && fi->fib_nh->nh_oif != cfg->fc_oif) goto err_inval; - if (rta->rta_gw && memcmp(&fi->fib_nh->nh_gw, rta->rta_gw, 4)) + if (cfg->fc_gw && fi->fib_nh->nh_gw != cfg->fc_gw) goto err_inval; #ifdef CONFIG_NET_CLS_ROUTE - if (rta->rta_flow && memcmp(&fi->fib_nh->nh_tclassid, rta->rta_flow, 4)) + if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow) goto err_inval; #endif #else @@ -758,34 +751,32 @@ fib_create_info(const struct rtmsg *r, struct kern_rta *rta, #endif } else { struct fib_nh *nh = fi->fib_nh; - if (rta->rta_oif) - nh->nh_oif = *rta->rta_oif; - if (rta->rta_gw) - memcpy(&nh->nh_gw, rta->rta_gw, 4); + + nh->nh_oif = cfg->fc_oif; + nh->nh_gw = cfg->fc_gw; + nh->nh_flags = cfg->fc_flags; #ifdef CONFIG_NET_CLS_ROUTE - if (rta->rta_flow) - memcpy(&nh->nh_tclassid, rta->rta_flow, 4); + nh->nh_tclassid = cfg->fc_flow; #endif - nh->nh_flags = r->rtm_flags; #ifdef CONFIG_IP_ROUTE_MULTIPATH nh->nh_weight = 1; #endif } #ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED - fi->fib_mp_alg = mp_alg; + fi->fib_mp_alg = cfg->fc_mp_alg; #endif - if (fib_props[r->rtm_type].error) { - if (rta->rta_gw || rta->rta_oif || rta->rta_mp) + if (fib_props[cfg->fc_type].error) { + if (cfg->fc_gw || cfg->fc_oif || cfg->fc_mp) goto err_inval; goto link_it; } - if (r->rtm_scope > RT_SCOPE_HOST) + if (cfg->fc_scope > RT_SCOPE_HOST) goto err_inval; - if (r->rtm_scope == RT_SCOPE_HOST) { + if (cfg->fc_scope == RT_SCOPE_HOST) { struct fib_nh *nh = fi->fib_nh; /* Local address is added. */ @@ -798,14 +789,14 @@ fib_create_info(const struct rtmsg *r, struct kern_rta *rta, goto failure; } else { change_nexthops(fi) { - if ((err = fib_check_nh(r, fi, nh)) != 0) + if ((err = fib_check_nh(cfg, fi, nh)) != 0) goto failure; } endfor_nexthops(fi) } if (fi->fib_prefsrc) { - if (r->rtm_type != RTN_LOCAL || rta->rta_dst == NULL || - memcmp(&fi->fib_prefsrc, rta->rta_dst, 4)) + if (cfg->fc_type != RTN_LOCAL || !cfg->fc_dst || + fi->fib_prefsrc != cfg->fc_dst) if (inet_addr_type(fi->fib_prefsrc) != RTN_LOCAL) goto err_inval; } @@ -846,12 +837,12 @@ err_inval: err = -EINVAL; failure: - *errp = err; if (fi) { fi->fib_dead = 1; free_fib_info(fi); } - return NULL; + + return ERR_PTR(err); } /* Note! fib_semantic_match intentionally uses RCU list functions. */ @@ -1012,150 +1003,6 @@ rtattr_failure: return -1; } -#ifndef CONFIG_IP_NOSIOCRT - -int -fib_convert_rtentry(int cmd, struct nlmsghdr *nl, struct rtmsg *rtm, - struct kern_rta *rta, struct rtentry *r) -{ - int plen; - u32 *ptr; - - memset(rtm, 0, sizeof(*rtm)); - memset(rta, 0, sizeof(*rta)); - - if (r->rt_dst.sa_family != AF_INET) - return -EAFNOSUPPORT; - - /* Check mask for validity: - a) it must be contiguous. - b) destination must have all host bits clear. - c) if application forgot to set correct family (AF_INET), - reject request unless it is absolutely clear i.e. - both family and mask are zero. - */ - plen = 32; - ptr = &((struct sockaddr_in*)&r->rt_dst)->sin_addr.s_addr; - if (!(r->rt_flags&RTF_HOST)) { - u32 mask = ((struct sockaddr_in*)&r->rt_genmask)->sin_addr.s_addr; - if (r->rt_genmask.sa_family != AF_INET) { - if (mask || r->rt_genmask.sa_family) - return -EAFNOSUPPORT; - } - if (bad_mask(mask, *ptr)) - return -EINVAL; - plen = inet_mask_len(mask); - } - - nl->nlmsg_flags = NLM_F_REQUEST; - nl->nlmsg_pid = 0; - nl->nlmsg_seq = 0; - nl->nlmsg_len = NLMSG_LENGTH(sizeof(*rtm)); - if (cmd == SIOCDELRT) { - nl->nlmsg_type = RTM_DELROUTE; - nl->nlmsg_flags = 0; - } else { - nl->nlmsg_type = RTM_NEWROUTE; - nl->nlmsg_flags = NLM_F_REQUEST|NLM_F_CREATE; - rtm->rtm_protocol = RTPROT_BOOT; - } - - rtm->rtm_dst_len = plen; - rta->rta_dst = ptr; - - if (r->rt_metric) { - *(u32*)&r->rt_pad3 = r->rt_metric - 1; - rta->rta_priority = (u32*)&r->rt_pad3; - } - if (r->rt_flags&RTF_REJECT) { - rtm->rtm_scope = RT_SCOPE_HOST; - rtm->rtm_type = RTN_UNREACHABLE; - return 0; - } - rtm->rtm_scope = RT_SCOPE_NOWHERE; - rtm->rtm_type = RTN_UNICAST; - - if (r->rt_dev) { - char *colon; - struct net_device *dev; - char devname[IFNAMSIZ]; - - if (copy_from_user(devname, r->rt_dev, IFNAMSIZ-1)) - return -EFAULT; - devname[IFNAMSIZ-1] = 0; - colon = strchr(devname, ':'); - if (colon) - *colon = 0; - dev = __dev_get_by_name(devname); - if (!dev) - return -ENODEV; - rta->rta_oif = &dev->ifindex; - if (colon) { - struct in_ifaddr *ifa; - struct in_device *in_dev = __in_dev_get_rtnl(dev); - if (!in_dev) - return -ENODEV; - *colon = ':'; - for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) - if (strcmp(ifa->ifa_label, devname) == 0) - break; - if (ifa == NULL) - return -ENODEV; - rta->rta_prefsrc = &ifa->ifa_local; - } - } - - ptr = &((struct sockaddr_in*)&r->rt_gateway)->sin_addr.s_addr; - if (r->rt_gateway.sa_family == AF_INET && *ptr) { - rta->rta_gw = ptr; - if (r->rt_flags&RTF_GATEWAY && inet_addr_type(*ptr) == RTN_UNICAST) - rtm->rtm_scope = RT_SCOPE_UNIVERSE; - } - - if (cmd == SIOCDELRT) - return 0; - - if (r->rt_flags&RTF_GATEWAY && rta->rta_gw == NULL) - return -EINVAL; - - if (rtm->rtm_scope == RT_SCOPE_NOWHERE) - rtm->rtm_scope = RT_SCOPE_LINK; - - if (r->rt_flags&(RTF_MTU|RTF_WINDOW|RTF_IRTT)) { - struct rtattr *rec; - struct rtattr *mx = kmalloc(RTA_LENGTH(3*RTA_LENGTH(4)), GFP_KERNEL); - if (mx == NULL) - return -ENOMEM; - rta->rta_mx = mx; - mx->rta_type = RTA_METRICS; - mx->rta_len = RTA_LENGTH(0); - if (r->rt_flags&RTF_MTU) { - rec = (void*)((char*)mx + RTA_ALIGN(mx->rta_len)); - rec->rta_type = RTAX_ADVMSS; - rec->rta_len = RTA_LENGTH(4); - mx->rta_len += RTA_LENGTH(4); - *(u32*)RTA_DATA(rec) = r->rt_mtu - 40; - } - if (r->rt_flags&RTF_WINDOW) { - rec = (void*)((char*)mx + RTA_ALIGN(mx->rta_len)); - rec->rta_type = RTAX_WINDOW; - rec->rta_len = RTA_LENGTH(4); - mx->rta_len += RTA_LENGTH(4); - *(u32*)RTA_DATA(rec) = r->rt_window; - } - if (r->rt_flags&RTF_IRTT) { - rec = (void*)((char*)mx + RTA_ALIGN(mx->rta_len)); - rec->rta_type = RTAX_RTT; - rec->rta_len = RTA_LENGTH(4); - mx->rta_len += RTA_LENGTH(4); - *(u32*)RTA_DATA(rec) = r->rt_irtt<<3; - } - } - return 0; -} - -#endif - /* Update FIB if: - local address disappeared -> we must delete all the entries diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 2a580eb2579..41bef0a88ab 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1124,17 +1124,14 @@ err: return fa_head; } -static int -fn_trie_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, - struct nlmsghdr *nlhdr, struct netlink_skb_parms *req) +static int fn_trie_insert(struct fib_table *tb, struct fib_config *cfg) { struct trie *t = (struct trie *) tb->tb_data; struct fib_alias *fa, *new_fa; struct list_head *fa_head = NULL; struct fib_info *fi; - int plen = r->rtm_dst_len; - int type = r->rtm_type; - u8 tos = r->rtm_tos; + int plen = cfg->fc_dst_len; + u8 tos = cfg->fc_tos; u32 key, mask; int err; struct leaf *l; @@ -1142,11 +1139,7 @@ fn_trie_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, if (plen > 32) return -EINVAL; - key = 0; - if (rta->rta_dst) - memcpy(&key, rta->rta_dst, 4); - - key = ntohl(key); + key = ntohl(cfg->fc_dst); pr_debug("Insert table=%u %08x/%d\n", tb->tb_id, key, plen); @@ -1157,10 +1150,11 @@ fn_trie_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, key = key & mask; - fi = fib_create_info(r, rta, nlhdr, &err); - - if (!fi) + fi = fib_create_info(cfg); + if (IS_ERR(fi)) { + err = PTR_ERR(fi); goto err; + } l = fib_find_node(t, key); fa = NULL; @@ -1185,10 +1179,10 @@ fn_trie_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, struct fib_alias *fa_orig; err = -EEXIST; - if (nlhdr->nlmsg_flags & NLM_F_EXCL) + if (cfg->fc_nlflags & NLM_F_EXCL) goto out; - if (nlhdr->nlmsg_flags & NLM_F_REPLACE) { + if (cfg->fc_nlflags & NLM_F_REPLACE) { struct fib_info *fi_drop; u8 state; @@ -1200,8 +1194,8 @@ fn_trie_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, fi_drop = fa->fa_info; new_fa->fa_tos = fa->fa_tos; new_fa->fa_info = fi; - new_fa->fa_type = type; - new_fa->fa_scope = r->rtm_scope; + 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; @@ -1224,17 +1218,17 @@ fn_trie_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, break; if (fa->fa_info->fib_priority != fi->fib_priority) break; - if (fa->fa_type == type && - fa->fa_scope == r->rtm_scope && + if (fa->fa_type == cfg->fc_type && + fa->fa_scope == cfg->fc_scope && fa->fa_info == fi) { goto out; } } - if (!(nlhdr->nlmsg_flags & NLM_F_APPEND)) + if (!(cfg->fc_nlflags & NLM_F_APPEND)) fa = fa_orig; } err = -ENOENT; - if (!(nlhdr->nlmsg_flags & NLM_F_CREATE)) + if (!(cfg->fc_nlflags & NLM_F_CREATE)) goto out; err = -ENOBUFS; @@ -1244,8 +1238,8 @@ fn_trie_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, new_fa->fa_info = fi; new_fa->fa_tos = tos; - new_fa->fa_type = type; - new_fa->fa_scope = r->rtm_scope; + 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. @@ -1262,7 +1256,8 @@ fn_trie_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, (fa ? &fa->fa_list : fa_head)); rt_cache_flush(-1); - rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, nlhdr, req); + rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, + &cfg->fc_nlinfo); succeeded: return 0; @@ -1548,28 +1543,21 @@ static int trie_leaf_remove(struct trie *t, t_key key) return 1; } -static int -fn_trie_delete(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, - struct nlmsghdr *nlhdr, struct netlink_skb_parms *req) +static int fn_trie_delete(struct fib_table *tb, struct fib_config *cfg) { struct trie *t = (struct trie *) tb->tb_data; u32 key, mask; - int plen = r->rtm_dst_len; - u8 tos = r->rtm_tos; + int plen = cfg->fc_dst_len; + u8 tos = cfg->fc_tos; struct fib_alias *fa, *fa_to_delete; struct list_head *fa_head; struct leaf *l; struct leaf_info *li; - if (plen > 32) return -EINVAL; - key = 0; - if (rta->rta_dst) - memcpy(&key, rta->rta_dst, 4); - - key = ntohl(key); + key = ntohl(cfg->fc_dst); mask = ntohl(inet_make_mask(plen)); if (key & ~mask) @@ -1598,13 +1586,12 @@ fn_trie_delete(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, if (fa->fa_tos != tos) break; - if ((!r->rtm_type || - fa->fa_type == r->rtm_type) && - (r->rtm_scope == RT_SCOPE_NOWHERE || - fa->fa_scope == r->rtm_scope) && - (!r->rtm_protocol || - fi->fib_protocol == r->rtm_protocol) && - fib_nh_match(r, nlhdr, rta, fi) == 0) { + if ((!cfg->fc_type || fa->fa_type == cfg->fc_type) && + (cfg->fc_scope == RT_SCOPE_NOWHERE || + fa->fa_scope == cfg->fc_scope) && + (!cfg->fc_protocol || + fi->fib_protocol == cfg->fc_protocol) && + fib_nh_match(cfg, fi) == 0) { fa_to_delete = fa; break; } @@ -1614,7 +1601,8 @@ fn_trie_delete(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta, return -ESRCH; fa = fa_to_delete; - rtmsg_fib(RTM_DELROUTE, htonl(key), fa, plen, tb->tb_id, nlhdr, req); + rtmsg_fib(RTM_DELROUTE, htonl(key), fa, plen, tb->tb_id, + &cfg->fc_nlinfo); l = fib_find_node(t, key); li = find_leaf_info(l, plen); -- cgit v1.2.3-70-g09d2 From be403ea1856f1428b5912b42184acbba808c41d6 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Thu, 17 Aug 2006 18:15:17 -0700 Subject: [IPv4]: Convert FIB dumping to use new netlink api Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- net/ipv4/fib_frontend.c | 4 +-- net/ipv4/fib_hash.c | 2 +- net/ipv4/fib_lookup.h | 2 +- net/ipv4/fib_semantics.c | 88 ++++++++++++++++++++++++++---------------------- net/ipv4/fib_trie.c | 2 +- net/ipv4/route.c | 68 ++++++++++++++++++------------------- 6 files changed, 86 insertions(+), 80 deletions(-) (limited to 'net/ipv4/fib_frontend.c') diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index acc18bdf2de..d537c933abe 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -591,8 +591,8 @@ int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) 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) + if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) && + ((struct rtmsg *) nlmsg_data(cb->nlh))->rtm_flags & RTM_F_CLONED) return ip_rt_dump(skb, cb); s_h = cb->args[0]; diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c index 357557549ce..88133b383dc 100644 --- a/net/ipv4/fib_hash.c +++ b/net/ipv4/fib_hash.c @@ -693,7 +693,7 @@ fn_hash_dump_bucket(struct sk_buff *skb, struct netlink_callback *cb, tb->tb_id, fa->fa_type, fa->fa_scope, - &f->fn_key, + f->fn_key, fz->fz_order, fa->fa_tos, fa->fa_info, diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index d6d1a89e400..fd6f7769f8a 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -26,7 +26,7 @@ extern void fib_release_info(struct fib_info *); extern struct fib_info *fib_create_info(struct fib_config *cfg); extern int fib_nh_match(struct fib_config *cfg, struct fib_info *fi); extern int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, - u32 tb_id, u8 type, u8 scope, void *dst, + u32 tb_id, u8 type, u8 scope, u32 dst, int dst_len, u8 tos, struct fib_info *fi, unsigned int); extern void rtmsg_fib(int event, u32 key, struct fib_alias *fa, diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 340f9db389e..2ead09543f6 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -286,7 +286,7 @@ void rtmsg_fib(int event, u32 key, struct fib_alias *fa, goto errout; err = fib_dump_info(skb, info->pid, seq, event, tb_id, - fa->fa_type, fa->fa_scope, &key, dst_len, + fa->fa_type, fa->fa_scope, key, dst_len, fa->fa_tos, fa->fa_info, 0); if (err < 0) { kfree_skb(skb); @@ -928,79 +928,87 @@ u32 __fib_res_prefsrc(struct fib_result *res) return inet_select_addr(FIB_RES_DEV(*res), FIB_RES_GW(*res), res->scope); } -int -fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, - u32 tb_id, u8 type, u8 scope, void *dst, int dst_len, u8 tos, - struct fib_info *fi, unsigned int flags) +int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, + u32 tb_id, u8 type, u8 scope, u32 dst, int dst_len, u8 tos, + struct fib_info *fi, unsigned int flags) { + struct nlmsghdr *nlh; struct rtmsg *rtm; - struct nlmsghdr *nlh; - unsigned char *b = skb->tail; - nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*rtm), flags); - rtm = NLMSG_DATA(nlh); + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*rtm), flags); + if (nlh == NULL) + return -ENOBUFS; + + rtm = nlmsg_data(nlh); rtm->rtm_family = AF_INET; rtm->rtm_dst_len = dst_len; rtm->rtm_src_len = 0; rtm->rtm_tos = tos; rtm->rtm_table = tb_id; - RTA_PUT_U32(skb, RTA_TABLE, tb_id); + NLA_PUT_U32(skb, RTA_TABLE, tb_id); rtm->rtm_type = type; rtm->rtm_flags = fi->fib_flags; rtm->rtm_scope = scope; - if (rtm->rtm_dst_len) - RTA_PUT(skb, RTA_DST, 4, dst); rtm->rtm_protocol = fi->fib_protocol; + + if (rtm->rtm_dst_len) + NLA_PUT_U32(skb, RTA_DST, dst); + if (fi->fib_priority) - RTA_PUT(skb, RTA_PRIORITY, 4, &fi->fib_priority); + NLA_PUT_U32(skb, RTA_PRIORITY, fi->fib_priority); + if (rtnetlink_put_metrics(skb, fi->fib_metrics) < 0) - goto rtattr_failure; + goto nla_put_failure; + if (fi->fib_prefsrc) - RTA_PUT(skb, RTA_PREFSRC, 4, &fi->fib_prefsrc); + NLA_PUT_U32(skb, RTA_PREFSRC, fi->fib_prefsrc); + if (fi->fib_nhs == 1) { if (fi->fib_nh->nh_gw) - RTA_PUT(skb, RTA_GATEWAY, 4, &fi->fib_nh->nh_gw); + NLA_PUT_U32(skb, RTA_GATEWAY, fi->fib_nh->nh_gw); + if (fi->fib_nh->nh_oif) - RTA_PUT(skb, RTA_OIF, sizeof(int), &fi->fib_nh->nh_oif); + NLA_PUT_U32(skb, RTA_OIF, fi->fib_nh->nh_oif); #ifdef CONFIG_NET_CLS_ROUTE if (fi->fib_nh[0].nh_tclassid) - RTA_PUT(skb, RTA_FLOW, 4, &fi->fib_nh[0].nh_tclassid); + NLA_PUT_U32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid); #endif } #ifdef CONFIG_IP_ROUTE_MULTIPATH if (fi->fib_nhs > 1) { - struct rtnexthop *nhp; - struct rtattr *mp_head; - if (skb_tailroom(skb) <= RTA_SPACE(0)) - goto rtattr_failure; - mp_head = (struct rtattr*)skb_put(skb, RTA_SPACE(0)); + struct rtnexthop *rtnh; + struct nlattr *mp; + + mp = nla_nest_start(skb, RTA_MULTIPATH); + if (mp == NULL) + goto nla_put_failure; for_nexthops(fi) { - if (skb_tailroom(skb) < RTA_ALIGN(RTA_ALIGN(sizeof(*nhp)) + 4)) - goto rtattr_failure; - nhp = (struct rtnexthop*)skb_put(skb, RTA_ALIGN(sizeof(*nhp))); - nhp->rtnh_flags = nh->nh_flags & 0xFF; - nhp->rtnh_hops = nh->nh_weight-1; - nhp->rtnh_ifindex = nh->nh_oif; + rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh)); + if (rtnh == NULL) + goto nla_put_failure; + + rtnh->rtnh_flags = nh->nh_flags & 0xFF; + rtnh->rtnh_hops = nh->nh_weight - 1; + rtnh->rtnh_ifindex = nh->nh_oif; + if (nh->nh_gw) - RTA_PUT(skb, RTA_GATEWAY, 4, &nh->nh_gw); + NLA_PUT_U32(skb, RTA_GATEWAY, nh->nh_gw); #ifdef CONFIG_NET_CLS_ROUTE if (nh->nh_tclassid) - RTA_PUT(skb, RTA_FLOW, 4, &nh->nh_tclassid); + NLA_PUT_U32(skb, RTA_FLOW, nh->nh_tclassid); #endif - nhp->rtnh_len = skb->tail - (unsigned char*)nhp; + /* length of rtnetlink header + attributes */ + rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh; } endfor_nexthops(fi); - mp_head->rta_type = RTA_MULTIPATH; - mp_head->rta_len = skb->tail - (u8*)mp_head; + + nla_nest_end(skb, mp); } #endif - nlh->nlmsg_len = skb->tail - b; - return skb->len; + return nlmsg_end(skb, nlh); -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; +nla_put_failure: + return nlmsg_cancel(skb, nlh); } /* diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 41bef0a88ab..9c3ff6ba6e2 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1854,7 +1854,7 @@ static int fn_trie_dump_fa(t_key key, int plen, struct list_head *fah, struct fi tb->tb_id, fa->fa_type, fa->fa_scope, - &xkey, + xkey, plen, fa->fa_tos, fa->fa_info, 0) < 0) { diff --git a/net/ipv4/route.c b/net/ipv4/route.c index b8f6cadc5b3..31b67059ac2 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2639,52 +2639,54 @@ static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event, { struct rtable *rt = (struct rtable*)skb->dst; struct rtmsg *r; - struct nlmsghdr *nlh; - unsigned char *b = skb->tail; + struct nlmsghdr *nlh; struct rta_cacheinfo ci; -#ifdef CONFIG_IP_MROUTE - struct rtattr *eptr; -#endif - nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*r), flags); - r = NLMSG_DATA(nlh); + + nlh = nlmsg_put(skb, pid, seq, event, sizeof(*r), flags); + if (nlh == NULL) + return -ENOBUFS; + + r = nlmsg_data(nlh); r->rtm_family = AF_INET; r->rtm_dst_len = 32; r->rtm_src_len = 0; r->rtm_tos = rt->fl.fl4_tos; r->rtm_table = RT_TABLE_MAIN; - RTA_PUT_U32(skb, RTA_TABLE, RT_TABLE_MAIN); + NLA_PUT_U32(skb, RTA_TABLE, RT_TABLE_MAIN); r->rtm_type = rt->rt_type; r->rtm_scope = RT_SCOPE_UNIVERSE; r->rtm_protocol = RTPROT_UNSPEC; r->rtm_flags = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED; if (rt->rt_flags & RTCF_NOTIFY) r->rtm_flags |= RTM_F_NOTIFY; - RTA_PUT(skb, RTA_DST, 4, &rt->rt_dst); + + NLA_PUT_U32(skb, RTA_DST, rt->rt_dst); + if (rt->fl.fl4_src) { r->rtm_src_len = 32; - RTA_PUT(skb, RTA_SRC, 4, &rt->fl.fl4_src); + NLA_PUT_U32(skb, RTA_SRC, rt->fl.fl4_src); } if (rt->u.dst.dev) - RTA_PUT(skb, RTA_OIF, sizeof(int), &rt->u.dst.dev->ifindex); + NLA_PUT_U32(skb, RTA_OIF, rt->u.dst.dev->ifindex); #ifdef CONFIG_NET_CLS_ROUTE if (rt->u.dst.tclassid) - RTA_PUT(skb, RTA_FLOW, 4, &rt->u.dst.tclassid); + NLA_PUT_U32(skb, RTA_FLOW, rt->u.dst.tclassid); #endif #ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED - if (rt->rt_multipath_alg != IP_MP_ALG_NONE) { - __u32 alg = rt->rt_multipath_alg; - - RTA_PUT(skb, RTA_MP_ALGO, 4, &alg); - } + if (rt->rt_multipath_alg != IP_MP_ALG_NONE) + NLA_PUT_U32(skb, RTA_MP_ALGO, rt->rt_multipath_alg); #endif if (rt->fl.iif) - RTA_PUT(skb, RTA_PREFSRC, 4, &rt->rt_spec_dst); + NLA_PUT_U32(skb, RTA_PREFSRC, rt->rt_spec_dst); else if (rt->rt_src != rt->fl.fl4_src) - RTA_PUT(skb, RTA_PREFSRC, 4, &rt->rt_src); + NLA_PUT_U32(skb, RTA_PREFSRC, rt->rt_src); + if (rt->rt_dst != rt->rt_gateway) - RTA_PUT(skb, RTA_GATEWAY, 4, &rt->rt_gateway); + NLA_PUT_U32(skb, RTA_GATEWAY, rt->rt_gateway); + if (rtnetlink_put_metrics(skb, rt->u.dst.metrics) < 0) - goto rtattr_failure; + goto nla_put_failure; + ci.rta_lastuse = jiffies_to_clock_t(jiffies - rt->u.dst.lastuse); ci.rta_used = rt->u.dst.__use; ci.rta_clntref = atomic_read(&rt->u.dst.__refcnt); @@ -2701,10 +2703,7 @@ static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event, ci.rta_tsage = xtime.tv_sec - rt->peer->tcp_ts_stamp; } } -#ifdef CONFIG_IP_MROUTE - eptr = (struct rtattr*)skb->tail; -#endif - RTA_PUT(skb, RTA_CACHEINFO, sizeof(ci), &ci); + if (rt->fl.iif) { #ifdef CONFIG_IP_MROUTE u32 dst = rt->rt_dst; @@ -2716,25 +2715,24 @@ static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event, if (!nowait) { if (err == 0) return 0; - goto nlmsg_failure; + goto nla_put_failure; } else { if (err == -EMSGSIZE) - goto nlmsg_failure; - ((struct rta_cacheinfo*)RTA_DATA(eptr))->rta_error = err; + goto nla_put_failure; + ci.rta_error = err; } } } else #endif - RTA_PUT(skb, RTA_IIF, sizeof(int), &rt->fl.iif); + NLA_PUT_U32(skb, RTA_IIF, rt->fl.iif); } - nlh->nlmsg_len = skb->tail - b; - return skb->len; + NLA_PUT(skb, RTA_CACHEINFO, sizeof(ci), &ci); + + return nlmsg_end(skb, nlh); -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; +nla_put_failure: + return nlmsg_cancel(skb, nlh); } int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) -- cgit v1.2.3-70-g09d2 From d889ce3b29e55b91257964b4c9aac70b91fedd91 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Thu, 17 Aug 2006 18:15:44 -0700 Subject: [IPv4]: Convert route get to new netlink api Fixes various unvalidated netlink attributes causing memory corruptions when left empty by userspace applications. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/net/ip_fib.h | 1 + net/ipv4/fib_frontend.c | 2 +- net/ipv4/route.c | 84 ++++++++++++++++++++++++++----------------------- 3 files changed, 47 insertions(+), 40 deletions(-) (limited to 'net/ipv4/fib_frontend.c') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 42ed96fab3f..fcc159a4ac1 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -216,6 +216,7 @@ extern void fib_select_default(const struct flowi *flp, struct fib_result *res); #endif /* CONFIG_IP_MULTIPLE_TABLES */ /* Exported by fib_frontend.c */ +extern struct nla_policy rtm_ipv4_policy[]; extern void ip_fib_init(void); extern int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg); extern int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index d537c933abe..d0abeab16e6 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -453,7 +453,7 @@ int ip_rt_ioctl(unsigned int cmd, void *arg) #endif -static struct nla_policy rtm_ipv4_policy[RTA_MAX+1] __read_mostly = { +struct nla_policy rtm_ipv4_policy[RTA_MAX+1] __read_mostly = { [RTA_DST] = { .type = NLA_U32 }, [RTA_SRC] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 31b67059ac2..a4d4cb85a16 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2737,18 +2737,24 @@ nla_put_failure: int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) { - struct rtattr **rta = arg; - struct rtmsg *rtm = NLMSG_DATA(nlh); + struct rtmsg *rtm; + struct nlattr *tb[RTA_MAX+1]; struct rtable *rt = NULL; - u32 dst = 0; - u32 src = 0; - int iif = 0; - int err = -ENOBUFS; + u32 dst, src, iif; + int err; struct sk_buff *skb; + err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy); + if (err < 0) + goto errout; + + rtm = nlmsg_data(nlh); + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (!skb) - goto out; + if (skb == NULL) { + err = -ENOBUFS; + goto errout; + } /* Reserve room for dummy headers, this skb can pass through good chunk of routing engine. @@ -2759,61 +2765,61 @@ int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) skb->nh.iph->protocol = IPPROTO_ICMP; skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr)); - if (rta[RTA_SRC - 1]) - memcpy(&src, RTA_DATA(rta[RTA_SRC - 1]), 4); - if (rta[RTA_DST - 1]) - memcpy(&dst, RTA_DATA(rta[RTA_DST - 1]), 4); - if (rta[RTA_IIF - 1]) - memcpy(&iif, RTA_DATA(rta[RTA_IIF - 1]), sizeof(int)); + src = tb[RTA_SRC] ? nla_get_u32(tb[RTA_SRC]) : 0; + dst = tb[RTA_DST] ? nla_get_u32(tb[RTA_DST]) : 0; + iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0; if (iif) { - struct net_device *dev = __dev_get_by_index(iif); - err = -ENODEV; - if (!dev) - goto out_free; + struct net_device *dev; + + dev = __dev_get_by_index(iif); + if (dev == NULL) { + err = -ENODEV; + goto errout_free; + } + skb->protocol = htons(ETH_P_IP); skb->dev = dev; local_bh_disable(); err = ip_route_input(skb, dst, src, rtm->rtm_tos, dev); local_bh_enable(); - rt = (struct rtable*)skb->dst; - if (!err && rt->u.dst.error) + + rt = (struct rtable*) skb->dst; + if (err == 0 && rt->u.dst.error) err = -rt->u.dst.error; } else { - struct flowi fl = { .nl_u = { .ip4_u = { .daddr = dst, - .saddr = src, - .tos = rtm->rtm_tos } } }; - int oif = 0; - if (rta[RTA_OIF - 1]) - memcpy(&oif, RTA_DATA(rta[RTA_OIF - 1]), sizeof(int)); - fl.oif = oif; + struct flowi fl = { + .nl_u = { + .ip4_u = { + .daddr = dst, + .saddr = src, + .tos = rtm->rtm_tos, + }, + }, + .oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0, + }; err = ip_route_output_key(&rt, &fl); } + if (err) - goto out_free; + goto errout_free; skb->dst = &rt->u.dst; if (rtm->rtm_flags & RTM_F_NOTIFY) rt->rt_flags |= RTCF_NOTIFY; - NETLINK_CB(skb).dst_pid = NETLINK_CB(in_skb).pid; - err = rt_fill_info(skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, RTM_NEWROUTE, 0, 0); - if (!err) - goto out_free; - if (err < 0) { - err = -EMSGSIZE; - goto out_free; - } + if (err <= 0) + goto errout_free; err = rtnl_unicast(skb, NETLINK_CB(in_skb).pid); -out: +errout: return err; -out_free: +errout_free: kfree_skb(skb); - goto out; + goto errout; } int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb) -- cgit v1.2.3-70-g09d2 From 5176f91ea83f1a59eba4dba88634a4729d51d1ac Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Sat, 26 Aug 2006 20:13:18 -0700 Subject: [NETLINK]: Make use of NLA_STRING/NLA_NUL_STRING attribute validation Converts existing NLA_STRING attributes to use the new validation features, saving a couple of temporary buffers. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- net/core/fib_rules.c | 8 +------- net/core/rtnetlink.c | 9 ++++----- net/decnet/dn_rules.c | 2 +- net/ipv4/devinet.c | 2 +- net/ipv4/fib_frontend.c | 2 +- net/ipv4/fib_rules.c | 2 +- net/ipv6/fib6_rules.c | 6 +++--- net/ipv6/route.c | 2 +- net/netlink/genetlink.c | 10 ++++------ 9 files changed, 17 insertions(+), 26 deletions(-) (limited to 'net/ipv4/fib_frontend.c') diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 7b2e9bb1a60..a99d87d82b7 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -161,9 +161,6 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (err < 0) goto errout; - if (tb[FRA_IFNAME] && nla_len(tb[FRA_IFNAME]) > IFNAMSIZ) - goto errout; - rule = kzalloc(ops->rule_size, GFP_KERNEL); if (rule == NULL) { err = -ENOMEM; @@ -177,10 +174,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) struct net_device *dev; rule->ifindex = -1; - if (nla_strlcpy(rule->ifname, tb[FRA_IFNAME], - IFNAMSIZ) >= IFNAMSIZ) - goto errout_free; - + nla_strlcpy(rule->ifname, tb[FRA_IFNAME], IFNAMSIZ); dev = __dev_get_by_name(rule->ifname); if (dev) rule->ifindex = dev->ifindex; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 8f225499e32..0ebcf8488e9 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -371,8 +371,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) } static struct nla_policy ifla_policy[IFLA_MAX+1] __read_mostly = { - [IFLA_IFNAME] = { .type = NLA_STRING }, - [IFLA_MAP] = { .minlen = sizeof(struct rtnl_link_ifmap) }, + [IFLA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ-1 }, + [IFLA_MAP] = { .len = sizeof(struct rtnl_link_ifmap) }, [IFLA_MTU] = { .type = NLA_U32 }, [IFLA_TXQLEN] = { .type = NLA_U32 }, [IFLA_WEIGHT] = { .type = NLA_U32 }, @@ -392,9 +392,8 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if (err < 0) goto errout; - if (tb[IFLA_IFNAME] && - nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ) >= IFNAMSIZ) - return -EINVAL; + if (tb[IFLA_IFNAME]) + nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); err = -EINVAL; ifm = nlmsg_data(nlh); diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c index 63ad63dfd25..3e0c882c90b 100644 --- a/net/decnet/dn_rules.c +++ b/net/decnet/dn_rules.c @@ -112,7 +112,7 @@ errout: } static struct nla_policy dn_fib_rule_policy[FRA_MAX+1] __read_mostly = { - [FRA_IFNAME] = { .type = NLA_STRING }, + [FRA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, [FRA_PRIORITY] = { .type = NLA_U32 }, [FRA_SRC] = { .type = NLA_U16 }, [FRA_DST] = { .type = NLA_U16 }, diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 0487677729c..8e8d1f17d77 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -85,7 +85,7 @@ static struct nla_policy ifa_ipv4_policy[IFA_MAX+1] __read_mostly = { [IFA_ADDRESS] = { .type = NLA_U32 }, [IFA_BROADCAST] = { .type = NLA_U32 }, [IFA_ANYCAST] = { .type = NLA_U32 }, - [IFA_LABEL] = { .type = NLA_STRING }, + [IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, }; static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index d0abeab16e6..cfb527c060e 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -462,7 +462,7 @@ struct nla_policy rtm_ipv4_policy[RTA_MAX+1] __read_mostly = { [RTA_PRIORITY] = { .type = NLA_U32 }, [RTA_PREFSRC] = { .type = NLA_U32 }, [RTA_METRICS] = { .type = NLA_NESTED }, - [RTA_MULTIPATH] = { .minlen = sizeof(struct rtnexthop) }, + [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, [RTA_PROTOINFO] = { .type = NLA_U32 }, [RTA_FLOW] = { .type = NLA_U32 }, [RTA_MP_ALGO] = { .type = NLA_U32 }, diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 280f424ca9c..52b2adae4f2 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -179,7 +179,7 @@ static struct fib_table *fib_empty_table(void) } static struct nla_policy fib4_rule_policy[FRA_MAX+1] __read_mostly = { - [FRA_IFNAME] = { .type = NLA_STRING }, + [FRA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, [FRA_PRIORITY] = { .type = NLA_U32 }, [FRA_SRC] = { .type = NLA_U32 }, [FRA_DST] = { .type = NLA_U32 }, diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 2fbc71d9018..34f5bfaddfc 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -137,10 +137,10 @@ static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) } static struct nla_policy fib6_rule_policy[FRA_MAX+1] __read_mostly = { - [FRA_IFNAME] = { .type = NLA_STRING }, + [FRA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, [FRA_PRIORITY] = { .type = NLA_U32 }, - [FRA_SRC] = { .minlen = sizeof(struct in6_addr) }, - [FRA_DST] = { .minlen = sizeof(struct in6_addr) }, + [FRA_SRC] = { .len = sizeof(struct in6_addr) }, + [FRA_DST] = { .len = sizeof(struct in6_addr) }, [FRA_FWMARK] = { .type = NLA_U32 }, [FRA_FWMASK] = { .type = NLA_U32 }, [FRA_TABLE] = { .type = NLA_U32 }, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index ba1b3d11865..75f4bb9611c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1865,7 +1865,7 @@ void rt6_mtu_change(struct net_device *dev, unsigned mtu) } static struct nla_policy rtm_ipv6_policy[RTA_MAX+1] __read_mostly = { - [RTA_GATEWAY] = { .minlen = sizeof(struct in6_addr) }, + [RTA_GATEWAY] = { .len = sizeof(struct in6_addr) }, [RTA_OIF] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, [RTA_PRIORITY] = { .type = NLA_U32 }, diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index d32599116c5..3ac942cdb67 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -455,7 +455,8 @@ static struct sk_buff *ctrl_build_msg(struct genl_family *family, u32 pid, static struct nla_policy ctrl_policy[CTRL_ATTR_MAX+1] __read_mostly = { [CTRL_ATTR_FAMILY_ID] = { .type = NLA_U16 }, - [CTRL_ATTR_FAMILY_NAME] = { .type = NLA_STRING }, + [CTRL_ATTR_FAMILY_NAME] = { .type = NLA_NUL_STRING, + .len = GENL_NAMSIZ - 1 }, }; static int ctrl_getfamily(struct sk_buff *skb, struct genl_info *info) @@ -470,12 +471,9 @@ static int ctrl_getfamily(struct sk_buff *skb, struct genl_info *info) } if (info->attrs[CTRL_ATTR_FAMILY_NAME]) { - char name[GENL_NAMSIZ]; - - if (nla_strlcpy(name, info->attrs[CTRL_ATTR_FAMILY_NAME], - GENL_NAMSIZ) >= GENL_NAMSIZ) - goto errout; + char *name; + name = nla_data(info->attrs[CTRL_ATTR_FAMILY_NAME]); res = genl_family_find_byname(name); } -- cgit v1.2.3-70-g09d2