summaryrefslogtreecommitdiff
path: root/net/ipv4/fib_semantics.c
diff options
context:
space:
mode:
authorArtem Bityutskiy <Artem.Bityutskiy@nokia.com>2011-03-25 17:41:20 +0200
committerArtem Bityutskiy <Artem.Bityutskiy@nokia.com>2011-03-25 17:41:20 +0200
commit7bf7e370d5919112c223a269462cd0b546903829 (patch)
tree03ccc715239df14ae168277dbccc9d9cf4d8a2c8 /net/ipv4/fib_semantics.c
parent68b1a1e786f29c900fa1c516a402e24f0ece622a (diff)
parentd39dd11c3e6a7af5c20bfac40594db36cf270f42 (diff)
Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6 into for-linus-1
* 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6: (9356 commits) [media] rc: update for bitop name changes fs: simplify iget & friends fs: pull inode->i_lock up out of writeback_single_inode fs: rename inode_lock to inode_hash_lock fs: move i_wb_list out from under inode_lock fs: move i_sb_list out from under inode_lock fs: remove inode_lock from iput_final and prune_icache fs: Lock the inode LRU list separately fs: factor inode disposal fs: protect inode->i_state with inode->i_lock lib, arch: add filter argument to show_mem and fix private implementations SLUB: Write to per cpu data when allocating it slub: Fix debugobjects with lockless fastpath autofs4: Do not potentially dereference NULL pointer returned by fget() in autofs_dev_ioctl_setpipefd() autofs4 - remove autofs4_lock autofs4 - fix d_manage() return on rcu-walk autofs4 - fix autofs4_expire_indirect() traversal autofs4 - fix dentry leak in autofs4_expire_direct() autofs4 - reinstate last used update on access vfs - check non-mountpoint dentry might block in __follow_mount_rcu() ... NOTE! This merge commit was created to fix compilation error. The block tree was merged upstream and removed the 'elv_queue_empty()' function which the new 'mtdswap' driver is using. So a simple merge of the mtd tree with upstream does not compile. And the mtd tree has already be published, so re-basing it is not an option. To fix this unfortunate situation, I had to merge upstream into the mtd-2.6.git tree without committing, put the fixup patch on top of this, and then commit this. The result is that we do not have commits which do not compile. In other words, this merge commit "merges" 3 things: the MTD tree, the upstream tree, and the fixup patch.
Diffstat (limited to 'net/ipv4/fib_semantics.c')
-rw-r--r--net/ipv4/fib_semantics.c257
1 files changed, 139 insertions, 118 deletions
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 12d3dc3df1b7..622ac4c95026 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -49,7 +49,7 @@
static DEFINE_SPINLOCK(fib_info_lock);
static struct hlist_head *fib_info_hash;
static struct hlist_head *fib_info_laddrhash;
-static unsigned int fib_hash_size;
+static unsigned int fib_info_hash_size;
static unsigned int fib_info_cnt;
#define DEVINDEX_HASHBITS 8
@@ -90,11 +90,7 @@ static DEFINE_SPINLOCK(fib_multipath_lock);
#define endfor_nexthops(fi) }
-static const struct
-{
- int error;
- u8 scope;
-} fib_props[RTN_MAX + 1] = {
+const struct fib_prop fib_props[RTN_MAX + 1] = {
[RTN_UNSPEC] = {
.error = 0,
.scope = RT_SCOPE_NOWHERE,
@@ -152,6 +148,8 @@ static void free_fib_info_rcu(struct rcu_head *head)
{
struct fib_info *fi = container_of(head, struct fib_info, rcu);
+ if (fi->fib_metrics != (u32 *) dst_default_metrics)
+ kfree(fi->fib_metrics);
kfree(fi);
}
@@ -200,7 +198,7 @@ static inline int nh_comp(const struct fib_info *fi, const struct fib_info *ofi)
#ifdef CONFIG_IP_ROUTE_MULTIPATH
nh->nh_weight != onh->nh_weight ||
#endif
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
nh->nh_tclassid != onh->nh_tclassid ||
#endif
((nh->nh_flags ^ onh->nh_flags) & ~RTNH_F_DEAD))
@@ -221,7 +219,7 @@ static inline unsigned int fib_devindex_hashfn(unsigned int val)
static inline unsigned int fib_info_hashfn(const struct fib_info *fi)
{
- unsigned int mask = (fib_hash_size - 1);
+ unsigned int mask = (fib_info_hash_size - 1);
unsigned int val = fi->fib_nhs;
val ^= fi->fib_protocol;
@@ -422,7 +420,7 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
nla = nla_find(attrs, attrlen, RTA_GATEWAY);
nexthop_nh->nh_gw = nla ? nla_get_be32(nla) : 0;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
nla = nla_find(attrs, attrlen, RTA_FLOW);
nexthop_nh->nh_tclassid = nla ? nla_get_u32(nla) : 0;
#endif
@@ -476,7 +474,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi)
nla = nla_find(attrs, attrlen, RTA_GATEWAY);
if (nla && nla_get_be32(nla) != nh->nh_gw)
return 1;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
nla = nla_find(attrs, attrlen, RTA_FLOW);
if (nla && nla_get_u32(nla) != nh->nh_tclassid)
return 1;
@@ -562,16 +560,16 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi,
}
rcu_read_lock();
{
- struct flowi fl = {
- .fl4_dst = nh->nh_gw,
- .fl4_scope = cfg->fc_scope + 1,
- .oif = nh->nh_oif,
+ struct flowi4 fl4 = {
+ .daddr = nh->nh_gw,
+ .flowi4_scope = cfg->fc_scope + 1,
+ .flowi4_oif = nh->nh_oif,
};
/* It is not necessary, but requires a bit of thinking */
- if (fl.fl4_scope < RT_SCOPE_LINK)
- fl.fl4_scope = RT_SCOPE_LINK;
- err = fib_lookup(net, &fl, &res);
+ if (fl4.flowi4_scope < RT_SCOPE_LINK)
+ fl4.flowi4_scope = RT_SCOPE_LINK;
+ err = fib_lookup(net, &fl4, &res);
if (err) {
rcu_read_unlock();
return err;
@@ -613,14 +611,14 @@ out:
static inline unsigned int fib_laddr_hashfn(__be32 val)
{
- unsigned int mask = (fib_hash_size - 1);
+ unsigned int mask = (fib_info_hash_size - 1);
return ((__force u32)val ^
((__force u32)val >> 7) ^
((__force u32)val >> 14)) & mask;
}
-static struct hlist_head *fib_hash_alloc(int bytes)
+static struct hlist_head *fib_info_hash_alloc(int bytes)
{
if (bytes <= PAGE_SIZE)
return kzalloc(bytes, GFP_KERNEL);
@@ -630,7 +628,7 @@ static struct hlist_head *fib_hash_alloc(int bytes)
get_order(bytes));
}
-static void fib_hash_free(struct hlist_head *hash, int bytes)
+static void fib_info_hash_free(struct hlist_head *hash, int bytes)
{
if (!hash)
return;
@@ -641,18 +639,18 @@ static void fib_hash_free(struct hlist_head *hash, int bytes)
free_pages((unsigned long) hash, get_order(bytes));
}
-static void fib_hash_move(struct hlist_head *new_info_hash,
- struct hlist_head *new_laddrhash,
- unsigned int new_size)
+static void fib_info_hash_move(struct hlist_head *new_info_hash,
+ struct hlist_head *new_laddrhash,
+ unsigned int new_size)
{
struct hlist_head *old_info_hash, *old_laddrhash;
- unsigned int old_size = fib_hash_size;
+ unsigned int old_size = fib_info_hash_size;
unsigned int i, bytes;
spin_lock_bh(&fib_info_lock);
old_info_hash = fib_info_hash;
old_laddrhash = fib_info_laddrhash;
- fib_hash_size = new_size;
+ fib_info_hash_size = new_size;
for (i = 0; i < old_size; i++) {
struct hlist_head *head = &fib_info_hash[i];
@@ -693,8 +691,8 @@ static void fib_hash_move(struct hlist_head *new_info_hash,
spin_unlock_bh(&fib_info_lock);
bytes = old_size * sizeof(struct hlist_head *);
- fib_hash_free(old_info_hash, bytes);
- fib_hash_free(old_laddrhash, bytes);
+ fib_info_hash_free(old_info_hash, bytes);
+ fib_info_hash_free(old_laddrhash, bytes);
}
struct fib_info *fib_create_info(struct fib_config *cfg)
@@ -705,6 +703,9 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
int nhs = 1;
struct net *net = cfg->fc_nlinfo.nl_net;
+ if (cfg->fc_type > RTN_MAX)
+ goto err_inval;
+
/* Fast check to catch the most weird cases */
if (fib_props[cfg->fc_type].scope > cfg->fc_scope)
goto err_inval;
@@ -718,8 +719,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
#endif
err = -ENOBUFS;
- if (fib_info_cnt >= fib_hash_size) {
- unsigned int new_size = fib_hash_size << 1;
+ if (fib_info_cnt >= fib_info_hash_size) {
+ unsigned int new_size = fib_info_hash_size << 1;
struct hlist_head *new_info_hash;
struct hlist_head *new_laddrhash;
unsigned int bytes;
@@ -727,21 +728,27 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
if (!new_size)
new_size = 1;
bytes = new_size * sizeof(struct hlist_head *);
- new_info_hash = fib_hash_alloc(bytes);
- new_laddrhash = fib_hash_alloc(bytes);
+ new_info_hash = fib_info_hash_alloc(bytes);
+ new_laddrhash = fib_info_hash_alloc(bytes);
if (!new_info_hash || !new_laddrhash) {
- fib_hash_free(new_info_hash, bytes);
- fib_hash_free(new_laddrhash, bytes);
+ fib_info_hash_free(new_info_hash, bytes);
+ fib_info_hash_free(new_laddrhash, bytes);
} else
- fib_hash_move(new_info_hash, new_laddrhash, new_size);
+ fib_info_hash_move(new_info_hash, new_laddrhash, new_size);
- if (!fib_hash_size)
+ if (!fib_info_hash_size)
goto failure;
}
fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
if (fi == NULL)
goto failure;
+ if (cfg->fc_mx) {
+ fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
+ if (!fi->fib_metrics)
+ goto failure;
+ } else
+ fi->fib_metrics = (u32 *) dst_default_metrics;
fib_info_cnt++;
fi->fib_net = hold_net(net);
@@ -779,7 +786,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
goto err_inval;
if (cfg->fc_gw && fi->fib_nh->nh_gw != cfg->fc_gw)
goto err_inval;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow)
goto err_inval;
#endif
@@ -792,7 +799,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
nh->nh_oif = cfg->fc_oif;
nh->nh_gw = cfg->fc_gw;
nh->nh_flags = cfg->fc_flags;
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
nh->nh_tclassid = cfg->fc_flow;
#endif
#ifdef CONFIG_IP_ROUTE_MULTIPATH
@@ -804,6 +811,17 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
if (cfg->fc_gw || cfg->fc_oif || cfg->fc_mp)
goto err_inval;
goto link_it;
+ } else {
+ switch (cfg->fc_type) {
+ case RTN_UNICAST:
+ case RTN_LOCAL:
+ case RTN_BROADCAST:
+ case RTN_ANYCAST:
+ case RTN_MULTICAST:
+ break;
+ default:
+ goto err_inval;
+ }
}
if (cfg->fc_scope > RT_SCOPE_HOST)
@@ -835,6 +853,13 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
goto err_inval;
}
+ change_nexthops(fi) {
+ nexthop_nh->nh_cfg_scope = cfg->fc_scope;
+ nexthop_nh->nh_saddr = inet_select_addr(nexthop_nh->nh_dev,
+ nexthop_nh->nh_gw,
+ nexthop_nh->nh_cfg_scope);
+ } endfor_nexthops(fi)
+
link_it:
ofi = fib_find_info(fi);
if (ofi) {
@@ -880,84 +905,6 @@ failure:
return ERR_PTR(err);
}
-/* Note! fib_semantic_match intentionally uses RCU list functions. */
-int fib_semantic_match(struct list_head *head, const struct flowi *flp,
- struct fib_result *res, int prefixlen, int fib_flags)
-{
- struct fib_alias *fa;
- int nh_sel = 0;
-
- list_for_each_entry_rcu(fa, head, fa_list) {
- int err;
-
- if (fa->fa_tos &&
- fa->fa_tos != flp->fl4_tos)
- continue;
-
- if (fa->fa_scope < flp->fl4_scope)
- continue;
-
- fib_alias_accessed(fa);
-
- err = fib_props[fa->fa_type].error;
- if (err == 0) {
- struct fib_info *fi = fa->fa_info;
-
- if (fi->fib_flags & RTNH_F_DEAD)
- continue;
-
- switch (fa->fa_type) {
- case RTN_UNICAST:
- case RTN_LOCAL:
- case RTN_BROADCAST:
- case RTN_ANYCAST:
- case RTN_MULTICAST:
- for_nexthops(fi) {
- if (nh->nh_flags & RTNH_F_DEAD)
- continue;
- if (!flp->oif || flp->oif == nh->nh_oif)
- break;
- }
-#ifdef CONFIG_IP_ROUTE_MULTIPATH
- if (nhsel < fi->fib_nhs) {
- nh_sel = nhsel;
- goto out_fill_res;
- }
-#else
- if (nhsel < 1)
- goto out_fill_res;
-#endif
- endfor_nexthops(fi);
- continue;
-
- default:
- pr_warning("fib_semantic_match bad type %#x\n",
- fa->fa_type);
- return -EINVAL;
- }
- }
- return err;
- }
- return 1;
-
-out_fill_res:
- res->prefixlen = prefixlen;
- res->nh_sel = nh_sel;
- res->type = fa->fa_type;
- res->scope = fa->fa_scope;
- res->fi = fa->fa_info;
- if (!(fib_flags & FIB_LOOKUP_NOREF))
- atomic_inc(&res->fi->fib_clntref);
- return 0;
-}
-
-/* Find appropriate source address to this destination */
-
-__be32 __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, __be32 dst, int dst_len, u8 tos,
struct fib_info *fi, unsigned int flags)
@@ -1002,7 +949,7 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
if (fi->fib_nh->nh_oif)
NLA_PUT_U32(skb, RTA_OIF, fi->fib_nh->nh_oif);
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
if (fi->fib_nh[0].nh_tclassid)
NLA_PUT_U32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid);
#endif
@@ -1027,7 +974,7 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
if (nh->nh_gw)
NLA_PUT_BE32(skb, RTA_GATEWAY, nh->nh_gw);
-#ifdef CONFIG_NET_CLS_ROUTE
+#ifdef CONFIG_IP_ROUTE_CLASSID
if (nh->nh_tclassid)
NLA_PUT_U32(skb, RTA_FLOW, nh->nh_tclassid);
#endif
@@ -1125,6 +1072,80 @@ int fib_sync_down_dev(struct net_device *dev, int force)
return ret;
}
+/* Must be invoked inside of an RCU protected region. */
+void fib_select_default(struct fib_result *res)
+{
+ struct fib_info *fi = NULL, *last_resort = NULL;
+ struct list_head *fa_head = res->fa_head;
+ struct fib_table *tb = res->table;
+ int order = -1, last_idx = -1;
+ struct fib_alias *fa;
+
+ list_for_each_entry_rcu(fa, fa_head, fa_list) {
+ struct fib_info *next_fi = fa->fa_info;
+
+ if (fa->fa_scope != res->scope ||
+ fa->fa_type != RTN_UNICAST)
+ continue;
+
+ if (next_fi->fib_priority > res->fi->fib_priority)
+ break;
+ if (!next_fi->fib_nh[0].nh_gw ||
+ next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK)
+ continue;
+
+ fib_alias_accessed(fa);
+
+ if (fi == NULL) {
+ if (next_fi != res->fi)
+ break;
+ } else if (!fib_detect_death(fi, order, &last_resort,
+ &last_idx, tb->tb_default)) {
+ fib_result_assign(res, fi);
+ tb->tb_default = order;
+ goto out;
+ }
+ fi = next_fi;
+ order++;
+ }
+
+ if (order <= 0 || fi == NULL) {
+ tb->tb_default = -1;
+ goto out;
+ }
+
+ if (!fib_detect_death(fi, order, &last_resort, &last_idx,
+ tb->tb_default)) {
+ fib_result_assign(res, fi);
+ tb->tb_default = order;
+ goto out;
+ }
+
+ if (last_idx >= 0)
+ fib_result_assign(res, last_resort);
+ tb->tb_default = last_idx;
+out:
+ return;
+}
+
+void fib_update_nh_saddrs(struct net_device *dev)
+{
+ struct hlist_head *head;
+ struct hlist_node *node;
+ struct fib_nh *nh;
+ unsigned int hash;
+
+ hash = fib_devindex_hashfn(dev->ifindex);
+ head = &fib_info_devhash[hash];
+ hlist_for_each_entry(nh, node, head, nh_hash) {
+ if (nh->nh_dev != dev)
+ continue;
+ nh->nh_saddr = inet_select_addr(nh->nh_dev,
+ nh->nh_gw,
+ nh->nh_cfg_scope);
+ }
+}
+
#ifdef CONFIG_IP_ROUTE_MULTIPATH
/*
@@ -1189,7 +1210,7 @@ int fib_sync_up(struct net_device *dev)
* The algorithm is suboptimal, but it provides really
* fair weighted route distribution.
*/
-void fib_select_multipath(const struct flowi *flp, struct fib_result *res)
+void fib_select_multipath(struct fib_result *res)
{
struct fib_info *fi = res->fi;
int w;