summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/ipv4/fib_frontend.c13
-rw-r--r--net/ipv4/fib_rules.c3
-rw-r--r--net/ipv4/fib_trie.c92
-rw-r--r--net/switchdev/switchdev.c161
4 files changed, 268 insertions, 1 deletions
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 220c4b4af4cf..e067770235bf 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -144,6 +144,19 @@ static void fib_flush(struct net *net)
rt_cache_flush(net);
}
+void fib_flush_external(struct net *net)
+{
+ struct fib_table *tb;
+ struct hlist_head *head;
+ unsigned int h;
+
+ for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
+ head = &net->ipv4.fib_table_hash[h];
+ hlist_for_each_entry(tb, head, tb_hlist)
+ fib_table_flush_external(tb);
+ }
+}
+
/*
* Find address type as if only "dev" was present in the system. If
* on_dev is NULL then all interfaces are taken into consideration.
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index d3db718be51d..190d0d00d744 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -209,6 +209,8 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
rule4->tos = frh->tos;
net->ipv4.fib_has_custom_rules = true;
+ fib_flush_external(rule->fr_net);
+
err = 0;
errout:
return err;
@@ -224,6 +226,7 @@ static void fib4_rule_delete(struct fib_rule *rule)
net->ipv4.fib_num_tclassid_users--;
#endif
net->ipv4.fib_has_custom_rules = true;
+ fib_flush_external(rule->fr_net);
}
static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index fae34ad4bb1a..6544f1a0cfa1 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -79,6 +79,7 @@
#include <net/tcp.h>
#include <net/sock.h>
#include <net/ip_fib.h>
+#include <net/switchdev.h>
#include "fib_lookup.h"
#define MAX_STAT_DEPTH 32
@@ -1135,7 +1136,18 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
new_fa->fa_state = state & ~FA_S_ACCESSED;
new_fa->fa_slen = fa->fa_slen;
+ err = netdev_switch_fib_ipv4_add(key, plen, fi,
+ new_fa->fa_tos,
+ cfg->fc_type,
+ tb->tb_id);
+ if (err) {
+ netdev_switch_fib_ipv4_abort(fi);
+ kmem_cache_free(fn_alias_kmem, new_fa);
+ goto out;
+ }
+
hlist_replace_rcu(&fa->fa_list, &new_fa->fa_list);
+
alias_free_mem_rcu(fa);
fib_release_info(fi_drop);
@@ -1171,10 +1183,18 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
new_fa->fa_state = 0;
new_fa->fa_slen = slen;
+ /* (Optionally) offload fib entry to switch hardware. */
+ err = netdev_switch_fib_ipv4_add(key, plen, fi, tos,
+ cfg->fc_type, tb->tb_id);
+ if (err) {
+ netdev_switch_fib_ipv4_abort(fi);
+ goto out_free_new_fa;
+ }
+
/* Insert new entry to the list. */
err = fib_insert_alias(t, tp, l, new_fa, fa, key);
if (err)
- goto out_free_new_fa;
+ goto out_sw_fib_del;
if (!plen)
tb->tb_num_default++;
@@ -1185,6 +1205,8 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
succeeded:
return 0;
+out_sw_fib_del:
+ netdev_switch_fib_ipv4_del(key, plen, fi, tos, cfg->fc_type, tb->tb_id);
out_free_new_fa:
kmem_cache_free(fn_alias_kmem, new_fa);
out:
@@ -1456,6 +1478,9 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg)
if (!fa_to_delete)
return -ESRCH;
+ netdev_switch_fib_ipv4_del(key, plen, fa_to_delete->fa_info, tos,
+ cfg->fc_type, tb->tb_id);
+
rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id,
&cfg->fc_nlinfo, 0);
@@ -1536,6 +1561,67 @@ found:
return n;
}
+/* Caller must hold RTNL */
+void fib_table_flush_external(struct fib_table *tb)
+{
+ struct trie *t = (struct trie *)tb->tb_data;
+ struct fib_alias *fa;
+ struct tnode *n, *pn;
+ unsigned long cindex;
+ unsigned char slen;
+ int found = 0;
+
+ n = rcu_dereference(t->trie);
+ if (!n)
+ return;
+
+ pn = NULL;
+ cindex = 0;
+
+ while (IS_TNODE(n)) {
+ /* record pn and cindex for leaf walking */
+ pn = n;
+ cindex = 1ul << n->bits;
+backtrace:
+ /* walk trie in reverse order */
+ do {
+ while (!(cindex--)) {
+ t_key pkey = pn->key;
+
+ n = pn;
+ pn = node_parent(n);
+
+ /* resize completed node */
+ resize(t, n);
+
+ /* if we got the root we are done */
+ if (!pn)
+ return;
+
+ cindex = get_index(pkey, pn);
+ }
+
+ /* grab the next available node */
+ n = tnode_get_child(pn, cindex);
+ } while (!n);
+ }
+
+ hlist_for_each_entry(fa, &n->leaf, fa_list) {
+ struct fib_info *fi = fa->fa_info;
+
+ if (fi && (fi->fib_flags & RTNH_F_EXTERNAL)) {
+ netdev_switch_fib_ipv4_del(n->key,
+ KEYLENGTH - fa->fa_slen,
+ fi, fa->fa_tos,
+ fa->fa_type, tb->tb_id);
+ }
+ }
+
+ /* if trie is leaf only loop is completed */
+ if (pn)
+ goto backtrace;
+}
+
/* Caller must hold RTNL. */
int fib_table_flush(struct fib_table *tb)
{
@@ -1589,6 +1675,10 @@ backtrace:
struct fib_info *fi = fa->fa_info;
if (fi && (fi->fib_flags & RTNH_F_DEAD)) {
+ netdev_switch_fib_ipv4_del(n->key,
+ KEYLENGTH - fa->fa_slen,
+ fi, fa->fa_tos,
+ fa->fa_type, tb->tb_id);
hlist_del_rcu(&fa->fa_list);
fib_release_info(fa->fa_info);
alias_free_mem_rcu(fa);
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 8c1e558db118..f4fd575aa2a3 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -14,6 +14,7 @@
#include <linux/mutex.h>
#include <linux/notifier.h>
#include <linux/netdevice.h>
+#include <net/ip_fib.h>
#include <net/switchdev.h>
/**
@@ -225,3 +226,163 @@ int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev,
return ret;
}
EXPORT_SYMBOL(ndo_dflt_netdev_switch_port_bridge_dellink);
+
+static struct net_device *netdev_switch_get_lowest_dev(struct net_device *dev)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+ struct net_device *lower_dev;
+ struct net_device *port_dev;
+ struct list_head *iter;
+
+ /* Recusively search down until we find a sw port dev.
+ * (A sw port dev supports ndo_switch_parent_id_get).
+ */
+
+ if (dev->features & NETIF_F_HW_SWITCH_OFFLOAD &&
+ ops->ndo_switch_parent_id_get)
+ return dev;
+
+ netdev_for_each_lower_dev(dev, lower_dev, iter) {
+ port_dev = netdev_switch_get_lowest_dev(lower_dev);
+ if (port_dev)
+ return port_dev;
+ }
+
+ return NULL;
+}
+
+static struct net_device *netdev_switch_get_dev_by_nhs(struct fib_info *fi)
+{
+ struct netdev_phys_item_id psid;
+ struct netdev_phys_item_id prev_psid;
+ struct net_device *dev = NULL;
+ int nhsel;
+
+ /* For this route, all nexthop devs must be on the same switch. */
+
+ for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) {
+ const struct fib_nh *nh = &fi->fib_nh[nhsel];
+
+ if (!nh->nh_dev)
+ return NULL;
+
+ dev = netdev_switch_get_lowest_dev(nh->nh_dev);
+ if (!dev)
+ return NULL;
+
+ if (netdev_switch_parent_id_get(dev, &psid))
+ return NULL;
+
+ if (nhsel > 0) {
+ if (prev_psid.id_len != psid.id_len)
+ return NULL;
+ if (memcmp(prev_psid.id, psid.id, psid.id_len))
+ return NULL;
+ }
+
+ prev_psid = psid;
+ }
+
+ return dev;
+}
+
+/**
+ * netdev_switch_fib_ipv4_add - Add IPv4 route entry to switch
+ *
+ * @dst: route's IPv4 destination address
+ * @dst_len: destination address length (prefix length)
+ * @fi: route FIB info structure
+ * @tos: route TOS
+ * @type: route type
+ * @tb_id: route table ID
+ *
+ * Add IPv4 route entry to switch device.
+ */
+int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi,
+ u8 tos, u8 type, u32 tb_id)
+{
+ struct net_device *dev;
+ const struct net_device_ops *ops;
+ int err = 0;
+
+ /* Don't offload route if using custom ip rules or if
+ * IPv4 FIB offloading has been disabled completely.
+ */
+
+ if (fi->fib_net->ipv4.fib_has_custom_rules |
+ fi->fib_net->ipv4.fib_offload_disabled)
+ return 0;
+
+ dev = netdev_switch_get_dev_by_nhs(fi);
+ if (!dev)
+ return 0;
+ ops = dev->netdev_ops;
+
+ if (ops->ndo_switch_fib_ipv4_add) {
+ err = ops->ndo_switch_fib_ipv4_add(dev, htonl(dst), dst_len,
+ fi, tos, type, tb_id);
+ if (!err)
+ fi->fib_flags |= RTNH_F_EXTERNAL;
+ }
+
+ return err;
+}
+EXPORT_SYMBOL(netdev_switch_fib_ipv4_add);
+
+/**
+ * netdev_switch_fib_ipv4_del - Delete IPv4 route entry from switch
+ *
+ * @dst: route's IPv4 destination address
+ * @dst_len: destination address length (prefix length)
+ * @fi: route FIB info structure
+ * @tos: route TOS
+ * @type: route type
+ * @tb_id: route table ID
+ *
+ * Delete IPv4 route entry from switch device.
+ */
+int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi,
+ u8 tos, u8 type, u32 tb_id)
+{
+ struct net_device *dev;
+ const struct net_device_ops *ops;
+ int err = 0;
+
+ if (!(fi->fib_flags & RTNH_F_EXTERNAL))
+ return 0;
+
+ dev = netdev_switch_get_dev_by_nhs(fi);
+ if (!dev)
+ return 0;
+ ops = dev->netdev_ops;
+
+ if (ops->ndo_switch_fib_ipv4_del) {
+ err = ops->ndo_switch_fib_ipv4_del(dev, htonl(dst), dst_len,
+ fi, tos, type, tb_id);
+ if (!err)
+ fi->fib_flags &= ~RTNH_F_EXTERNAL;
+ }
+
+ return err;
+}
+EXPORT_SYMBOL(netdev_switch_fib_ipv4_del);
+
+/**
+ * netdev_switch_fib_ipv4_abort - Abort an IPv4 FIB operation
+ *
+ * @fi: route FIB info structure
+ */
+void netdev_switch_fib_ipv4_abort(struct fib_info *fi)
+{
+ /* There was a problem installing this route to the offload
+ * device. For now, until we come up with more refined
+ * policy handling, abruptly end IPv4 fib offloading for
+ * for entire net by flushing offload device(s) of all
+ * IPv4 routes, and mark IPv4 fib offloading broken from
+ * this point forward.
+ */
+
+ fib_flush_external(fi->fib_net);
+ fi->fib_net->ipv4.fib_offload_disabled = true;
+}
+EXPORT_SYMBOL(netdev_switch_fib_ipv4_abort);