@@ -40,6 +40,12 @@ struct nh_config {
struct nlattr *nh_grp;
u16 nh_grp_type;
+ u16 nh_grp_res_num_buckets;
+ unsigned long nh_grp_res_idle_timer;
+ unsigned long nh_grp_res_unbalanced_timer;
+ bool nh_grp_res_has_num_buckets;
+ bool nh_grp_res_has_idle_timer;
+ bool nh_grp_res_has_unbalanced_timer;
struct nlattr *nh_encap;
u16 nh_encap_type;
@@ -63,6 +69,32 @@ struct nh_info {
};
};
+struct nh_res_bucket {
+ struct nh_grp_entry __rcu *nh_entry;
+ atomic_long_t used_time;
+ unsigned long migrated_time;
+ bool occupied;
+ u8 nh_flags;
+};
+
+struct nh_res_table {
+ struct net *net;
+ u32 nhg_id;
+ struct delayed_work upkeep_dw;
+
+ /* List of NHGEs that have too few buckets ("uw" for underweight).
+ * Reclaimed buckets will be given to entries in this list.
+ */
+ struct list_head uw_nh_entries;
+ unsigned long unbalanced_since;
+
+ u32 idle_timer;
+ u32 unbalanced_timer;
+
+ u16 num_nh_buckets;
+ struct nh_res_bucket nh_buckets[];
+};
+
struct nh_grp_entry {
struct nexthop *nh;
u8 weight;
@@ -71,6 +103,13 @@ struct nh_grp_entry {
struct {
atomic_t upper_bound;
} mpath;
+ struct {
+ /* Member on uw_nh_entries. */
+ struct list_head uw_nh_entry;
+
+ u16 count_buckets;
+ u16 wants_buckets;
+ } res;
};
struct list_head nh_list;
@@ -82,8 +121,11 @@ struct nh_group {
u16 num_nh;
bool is_multipath;
bool mpath;
+ bool resilient;
bool fdb_nh;
bool has_v4;
+
+ struct nh_res_table __rcu *res_table;
struct nh_grp_entry nh_entries[];
};
@@ -183,6 +183,30 @@ static int call_nexthop_notifiers(struct net *net,
return notifier_to_errno(err);
}
+/* There are three users of RES_TABLE, and NHs etc. referenced from there:
+ *
+ * 1) a collection of callbacks for NH maintenance. This operates under
+ * RTNL,
+ * 2) the delayed work that gradually balances the resilient table,
+ * 3) and nexthop_select_path(), operating under RCU.
+ *
+ * Both the delayed work and the RTNL block are writers, and need to
+ * maintain mutual exclusion. Since there are only two and well-known
+ * writers for each table, the RTNL code can make sure it has exclusive
+ * access thus:
+ *
+ * - Have the DW operate without locking;
+ * - synchronously cancel the DW;
+ * - do the writing;
+ * - if the write was not actually a delete, call upkeep, which schedules
+ * DW again if necessary.
+ *
+ * The functions that are always called from the RTNL context use
+ * rtnl_dereference(). The functions that can also be called from the DW do
+ * a raw dereference and rely on the above mutual exclusion scheme.
+ */
+#define nh_res_dereference(p) (rcu_dereference_raw(p))
+
static int call_nexthop_notifier(struct notifier_block *nb, struct net *net,
enum nexthop_event_type event_type,
struct nexthop *nh,
@@ -241,6 +265,9 @@ static void nexthop_free_group(struct nexthop *nh)
WARN_ON(nhg->spare == nhg);
+ if (nhg->resilient)
+ vfree(rcu_dereference_raw(nhg->res_table));
+
kfree(nhg->spare);
kfree(nhg);
}
@@ -299,6 +326,30 @@ static struct nh_group *nexthop_grp_alloc(u16 num_nh)
return nhg;
}
+static void nh_res_table_upkeep_dw(struct work_struct *work);
+
+static struct nh_res_table *
+nexthop_res_table_alloc(struct net *net, u32 nhg_id, struct nh_config *cfg)
+{
+ const u16 num_nh_buckets = cfg->nh_grp_res_num_buckets;
+ struct nh_res_table *res_table;
+ unsigned long size;
+
+ size = struct_size(res_table, nh_buckets, num_nh_buckets);
+ res_table = __vmalloc(size, GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN);
+ if (!res_table)
+ return NULL;
+
+ res_table->net = net;
+ res_table->nhg_id = nhg_id;
+ INIT_DELAYED_WORK(&res_table->upkeep_dw, &nh_res_table_upkeep_dw);
+ INIT_LIST_HEAD(&res_table->uw_nh_entries);
+ res_table->idle_timer = cfg->nh_grp_res_idle_timer;
+ res_table->unbalanced_timer = cfg->nh_grp_res_unbalanced_timer;
+ res_table->num_nh_buckets = num_nh_buckets;
+ return res_table;
+}
+
static void nh_base_seq_inc(struct net *net)
{
while (++net->nexthop.seq == 0)
@@ -347,6 +398,13 @@ static u32 nh_find_unused_id(struct net *net)
return 0;
}
+static void nh_res_time_set_deadline(unsigned long next_time,
+ unsigned long *deadline)
+{
+ if (time_before(next_time, *deadline))
+ *deadline = next_time;
+}
+
static int nla_put_nh_group(struct sk_buff *skb, struct nh_group *nhg)
{
struct nexthop_grp *p;
@@ -540,20 +598,62 @@ static void nexthop_notify(int event, struct nexthop *nh, struct nl_info *info)
rtnl_set_sk_err(info->nl_net, RTNLGRP_NEXTHOP, err);
}
+static unsigned long nh_res_bucket_used_time(const struct nh_res_bucket *bucket)
+{
+ return (unsigned long)atomic_long_read(&bucket->used_time);
+}
+
+static unsigned long
+nh_res_bucket_idle_point(const struct nh_res_table *res_table,
+ const struct nh_res_bucket *bucket,
+ unsigned long now)
+{
+ unsigned long time = nh_res_bucket_used_time(bucket);
+
+ /* Bucket was not used since it was migrated. The idle time is now. */
+ if (time == bucket->migrated_time)
+ return now;
+
+ return time + res_table->idle_timer;
+}
+
+static unsigned long
+nh_res_table_unb_point(const struct nh_res_table *res_table)
+{
+ return res_table->unbalanced_since + res_table->unbalanced_timer;
+}
+
+static void nh_res_bucket_set_idle(const struct nh_res_table *res_table,
+ struct nh_res_bucket *bucket)
+{
+ unsigned long now = jiffies;
+
+ atomic_long_set(&bucket->used_time, (long)now);
+ bucket->migrated_time = now;
+}
+
+static void nh_res_bucket_set_busy(struct nh_res_bucket *bucket)
+{
+ atomic_long_set(&bucket->used_time, (long)jiffies);
+}
+
static bool valid_group_nh(struct nexthop *nh, unsigned int npaths,
bool *is_fdb, struct netlink_ext_ack *extack)
{
if (nh->is_group) {
struct nh_group *nhg = rtnl_dereference(nh->nh_grp);
- /* nested multipath (group within a group) is not
- * supported
- */
+ /* Nesting groups within groups is not supported. */
if (nhg->mpath) {
NL_SET_ERR_MSG(extack,
"Multipath group can not be a nexthop within a group");
return false;
}
+ if (nhg->resilient) {
+ NL_SET_ERR_MSG(extack,
+ "Resilient group can not be a nexthop within a group");
+ return false;
+ }
*is_fdb = nhg->fdb_nh;
} else {
struct nh_info *nhi = rtnl_dereference(nh->nh_info);
@@ -734,6 +834,22 @@ static struct nexthop *nexthop_select_path_mp(struct nh_group *nhg, int hash)
return rc;
}
+static struct nexthop *nexthop_select_path_res(struct nh_group *nhg, int hash)
+{
+ struct nh_res_table *res_table = rcu_dereference(nhg->res_table);
+ u16 bucket_index = hash % res_table->num_nh_buckets;
+ struct nh_res_bucket *bucket;
+ struct nh_grp_entry *nhge;
+
+ /* nexthop_select_path() is expected to return a non-NULL value, so
+ * skip protocol validation and just hand out whatever there is.
+ */
+ bucket = &res_table->nh_buckets[bucket_index];
+ nh_res_bucket_set_busy(bucket);
+ nhge = rcu_dereference(bucket->nh_entry);
+ return nhge->nh;
+}
+
struct nexthop *nexthop_select_path(struct nexthop *nh, int hash)
{
struct nh_group *nhg;
@@ -744,6 +860,8 @@ struct nexthop *nexthop_select_path(struct nexthop *nh, int hash)
nhg = rcu_dereference(nh->nh_grp);
if (nhg->mpath)
return nexthop_select_path_mp(nhg, hash);
+ else if (nhg->resilient)
+ return nexthop_select_path_res(nhg, hash);
/* Unreachable. */
return NULL;
@@ -926,7 +1044,289 @@ static int fib_check_nh_list(struct nexthop *old, struct nexthop *new,
return 0;
}
-static void nh_group_rebalance(struct nh_group *nhg)
+static bool nh_res_nhge_is_balanced(const struct nh_grp_entry *nhge)
+{
+ return nhge->res.count_buckets == nhge->res.wants_buckets;
+}
+
+static bool nh_res_nhge_is_ow(const struct nh_grp_entry *nhge)
+{
+ return nhge->res.count_buckets > nhge->res.wants_buckets;
+}
+
+static bool nh_res_nhge_is_uw(const struct nh_grp_entry *nhge)
+{
+ return nhge->res.count_buckets < nhge->res.wants_buckets;
+}
+
+static bool nh_res_table_is_balanced(const struct nh_res_table *res_table)
+{
+ return list_empty(&res_table->uw_nh_entries);
+}
+
+static void nh_res_bucket_unset_nh(struct nh_res_bucket *bucket)
+{
+ struct nh_grp_entry *nhge;
+
+ if (bucket->occupied) {
+ nhge = nh_res_dereference(bucket->nh_entry);
+ nhge->res.count_buckets--;
+ bucket->occupied = false;
+ }
+}
+
+static void nh_res_bucket_set_nh(struct nh_res_bucket *bucket,
+ struct nh_grp_entry *nhge)
+{
+ nh_res_bucket_unset_nh(bucket);
+
+ bucket->occupied = true;
+ rcu_assign_pointer(bucket->nh_entry, nhge);
+ nhge->res.count_buckets++;
+}
+
+static bool nh_res_bucket_should_migrate(struct nh_res_table *res_table,
+ struct nh_res_bucket *bucket,
+ unsigned long *deadline, bool *force)
+{
+ unsigned long now = jiffies;
+ struct nh_grp_entry *nhge;
+ unsigned long idle_point;
+
+ if (!bucket->occupied) {
+ /* The bucket is not occupied, its NHGE pointer is either
+ * NULL or obsolete. We _have to_ migrate: set force.
+ */
+ *force = true;
+ return true;
+ }
+
+ nhge = nh_res_dereference(bucket->nh_entry);
+
+ /* If the bucket is populated by an underweight or balanced
+ * nexthop, do not migrate.
+ */
+ if (!nh_res_nhge_is_ow(nhge))
+ return false;
+
+ /* At this point we know that the bucket is populated with an
+ * overweight nexthop. It needs to be migrated to a new nexthop if
+ * the idle timer of unbalanced timer expired.
+ */
+
+ idle_point = nh_res_bucket_idle_point(res_table, bucket, now);
+ if (time_after_eq(now, idle_point)) {
+ /* The bucket is idle. We _can_ migrate: unset force. */
+ *force = false;
+ return true;
+ }
+
+ /* Unbalanced timer of 0 means "never force". */
+ if (res_table->unbalanced_timer) {
+ unsigned long unb_point;
+
+ unb_point = nh_res_table_unb_point(res_table);
+ if (time_after(now, unb_point)) {
+ /* The bucket is not idle, but the unbalanced timer
+ * expired. We _can_ migrate, but set force anyway,
+ * so that drivers know to ignore activity reports
+ * from the HW.
+ */
+ *force = true;
+ return true;
+ }
+
+ nh_res_time_set_deadline(unb_point, deadline);
+ }
+
+ nh_res_time_set_deadline(idle_point, deadline);
+ return false;
+}
+
+static bool nh_res_bucket_migrate(struct nh_res_table *res_table,
+ u16 bucket_index, bool force)
+{
+ struct nh_res_bucket *bucket = &res_table->nh_buckets[bucket_index];
+ struct nh_grp_entry *new_nhge;
+
+ new_nhge = list_first_entry_or_null(&res_table->uw_nh_entries,
+ struct nh_grp_entry,
+ res.uw_nh_entry);
+ if (WARN_ON_ONCE(!new_nhge))
+ /* If this function is called, "bucket" is either not
+ * occupied, or it belongs to a next hop that is
+ * overweight. In either case, there ought to be a
+ * corresponding underweight next hop.
+ */
+ return false;
+
+ nh_res_bucket_set_nh(bucket, new_nhge);
+ nh_res_bucket_set_idle(res_table, bucket);
+
+ if (nh_res_nhge_is_balanced(new_nhge))
+ list_del(&new_nhge->res.uw_nh_entry);
+ return true;
+}
+
+#define NH_RES_UPKEEP_DW_MINIMUM_INTERVAL (HZ / 2)
+
+static void nh_res_table_upkeep(struct nh_res_table *res_table)
+{
+ unsigned long now = jiffies;
+ unsigned long deadline;
+ u16 i;
+
+ /* Deadline is the next time that upkeep should be run. It is the
+ * earliest time at which one of the buckets might be migrated.
+ * Start at the most pessimistic estimate: either unbalanced_timer
+ * from now, or if there is none, idle_timer from now. For each
+ * encountered time point, call nh_res_time_set_deadline() to
+ * refine the estimate.
+ */
+ if (res_table->unbalanced_timer)
+ deadline = now + res_table->unbalanced_timer;
+ else
+ deadline = now + res_table->idle_timer;
+
+ for (i = 0; i < res_table->num_nh_buckets; i++) {
+ struct nh_res_bucket *bucket = &res_table->nh_buckets[i];
+ bool force;
+
+ if (nh_res_bucket_should_migrate(res_table, bucket,
+ &deadline, &force)) {
+ if (!nh_res_bucket_migrate(res_table, i, force)) {
+ unsigned long idle_point;
+
+ /* A driver can override the migration
+ * decision if the HW reports that the
+ * bucket is actually not idle. Therefore
+ * remark the bucket as busy again and
+ * update the deadline.
+ */
+ nh_res_bucket_set_busy(bucket);
+ idle_point = nh_res_bucket_idle_point(res_table,
+ bucket,
+ now);
+ nh_res_time_set_deadline(idle_point, &deadline);
+ }
+ }
+ }
+
+ /* If the group is still unbalanced, schedule the next upkeep to
+ * either the deadline computed above, or the minimum deadline,
+ * whichever comes later.
+ */
+ if (!nh_res_table_is_balanced(res_table)) {
+ unsigned long now = jiffies;
+ unsigned long min_deadline;
+
+ min_deadline = now + NH_RES_UPKEEP_DW_MINIMUM_INTERVAL;
+ if (time_before(deadline, min_deadline))
+ deadline = min_deadline;
+
+ queue_delayed_work(system_power_efficient_wq,
+ &res_table->upkeep_dw, deadline - now);
+ }
+}
+
+static void nh_res_table_upkeep_dw(struct work_struct *work)
+{
+ struct delayed_work *dw = to_delayed_work(work);
+ struct nh_res_table *res_table;
+
+ res_table = container_of(dw, struct nh_res_table, upkeep_dw);
+ nh_res_table_upkeep(res_table);
+}
+
+static void nh_res_table_cancel_upkeep(struct nh_res_table *res_table)
+{
+ cancel_delayed_work_sync(&res_table->upkeep_dw);
+}
+
+static void nh_res_group_rebalance(struct nh_group *nhg,
+ struct nh_res_table *res_table)
+{
+ int prev_upper_bound = 0;
+ int total = 0;
+ int w = 0;
+ int i;
+
+ INIT_LIST_HEAD(&res_table->uw_nh_entries);
+
+ for (i = 0; i < nhg->num_nh; ++i)
+ total += nhg->nh_entries[i].weight;
+
+ for (i = 0; i < nhg->num_nh; ++i) {
+ struct nh_grp_entry *nhge = &nhg->nh_entries[i];
+ int upper_bound;
+
+ w += nhge->weight;
+ upper_bound = DIV_ROUND_CLOSEST(res_table->num_nh_buckets * w,
+ total);
+ nhge->res.wants_buckets = upper_bound - prev_upper_bound;
+ prev_upper_bound = upper_bound;
+
+ if (nh_res_nhge_is_uw(nhge)) {
+ if (list_empty(&res_table->uw_nh_entries))
+ res_table->unbalanced_since = jiffies;
+ list_add(&nhge->res.uw_nh_entry,
+ &res_table->uw_nh_entries);
+ }
+ }
+}
+
+/* Migrate buckets in res_table so that they reference NHGE's from NHG with
+ * the right NH ID. Set those buckets that do not have a corresponding NHGE
+ * entry in NHG as not occupied.
+ */
+static void nh_res_table_migrate_buckets(struct nh_res_table *res_table,
+ struct nh_group *nhg)
+{
+ u16 i;
+
+ for (i = 0; i < res_table->num_nh_buckets; i++) {
+ struct nh_res_bucket *bucket = &res_table->nh_buckets[i];
+ u32 id = rtnl_dereference(bucket->nh_entry)->nh->id;
+ bool found = false;
+ int j;
+
+ for (j = 0; j < nhg->num_nh; j++) {
+ struct nh_grp_entry *nhge = &nhg->nh_entries[j];
+
+ if (nhge->nh->id == id) {
+ nh_res_bucket_set_nh(bucket, nhge);
+ found = true;
+ break;
+ }
+ }
+
+ if (!found)
+ nh_res_bucket_unset_nh(bucket);
+ }
+}
+
+static void replace_nexthop_grp_res(struct nh_group *oldg,
+ struct nh_group *newg)
+{
+ /* For NH group replacement, the new NHG might only have a stub
+ * hash table with 0 buckets, because the number of buckets was not
+ * specified. For NH removal, oldg and newg both reference the same
+ * res_table. So in any case, in the following, we want to work
+ * with oldg->res_table.
+ */
+ struct nh_res_table *old_res_table = rtnl_dereference(oldg->res_table);
+ unsigned long prev_unbalanced_since = old_res_table->unbalanced_since;
+ bool prev_has_uw = !list_empty(&old_res_table->uw_nh_entries);
+
+ nh_res_table_cancel_upkeep(old_res_table);
+ nh_res_table_migrate_buckets(old_res_table, newg);
+ nh_res_group_rebalance(newg, old_res_table);
+ if (prev_has_uw && !list_empty(&old_res_table->uw_nh_entries))
+ old_res_table->unbalanced_since = prev_unbalanced_since;
+ nh_res_table_upkeep(old_res_table);
+}
+
+static void nh_mp_group_rebalance(struct nh_group *nhg)
{
int total = 0;
int w = 0;
@@ -969,6 +1369,7 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge,
newg->has_v4 = false;
newg->is_multipath = nhg->is_multipath;
newg->mpath = nhg->mpath;
+ newg->resilient = nhg->resilient;
newg->fdb_nh = nhg->fdb_nh;
newg->num_nh = nhg->num_nh;
@@ -996,7 +1397,11 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge,
j++;
}
- nh_group_rebalance(newg);
+ if (newg->mpath)
+ nh_mp_group_rebalance(newg);
+ else if (newg->resilient)
+ replace_nexthop_grp_res(nhg, newg);
+
rcu_assign_pointer(nhp->nh_grp, newg);
list_del(&nhge->nh_list);
@@ -1025,6 +1430,7 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh,
static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo)
{
struct nh_group *nhg = rcu_dereference_rtnl(nh->nh_grp);
+ struct nh_res_table *res_table;
int i, num_nh = nhg->num_nh;
for (i = 0; i < num_nh; ++i) {
@@ -1035,6 +1441,11 @@ static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo)
list_del_init(&nhge->nh_list);
}
+
+ if (nhg->resilient) {
+ res_table = rtnl_dereference(nhg->res_table);
+ nh_res_table_cancel_upkeep(res_table);
+ }
}
/* not called for nexthop replace */
@@ -1113,6 +1524,9 @@ static int replace_nexthop_grp(struct net *net, struct nexthop *old,
struct nexthop *new, const struct nh_config *cfg,
struct netlink_ext_ack *extack)
{
+ struct nh_res_table *tmp_table = NULL;
+ struct nh_res_table *new_res_table;
+ struct nh_res_table *old_res_table;
struct nh_group *oldg, *newg;
int i, err;
@@ -1121,19 +1535,57 @@ static int replace_nexthop_grp(struct net *net, struct nexthop *old,
return -EINVAL;
}
- err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new, extack);
- if (err)
- return err;
-
oldg = rtnl_dereference(old->nh_grp);
newg = rtnl_dereference(new->nh_grp);
+ if (newg->mpath != oldg->mpath) {
+ NL_SET_ERR_MSG(extack, "Can not replace a nexthop group with one of a different type.");
+ return -EINVAL;
+ }
+
+ if (newg->mpath) {
+ err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new,
+ extack);
+ if (err)
+ return err;
+ } else if (newg->resilient) {
+ new_res_table = rtnl_dereference(newg->res_table);
+ old_res_table = rtnl_dereference(oldg->res_table);
+
+ /* Accept if num_nh_buckets was not given, but if it was
+ * given, demand that the value be correct.
+ */
+ if (cfg->nh_grp_res_has_num_buckets &&
+ cfg->nh_grp_res_num_buckets !=
+ old_res_table->num_nh_buckets) {
+ NL_SET_ERR_MSG(extack, "Can not change number of buckets of a resilient nexthop group.");
+ return -EINVAL;
+ }
+
+ if (cfg->nh_grp_res_has_idle_timer)
+ old_res_table->idle_timer = cfg->nh_grp_res_idle_timer;
+ if (cfg->nh_grp_res_has_unbalanced_timer)
+ old_res_table->unbalanced_timer =
+ cfg->nh_grp_res_unbalanced_timer;
+
+ replace_nexthop_grp_res(oldg, newg);
+
+ tmp_table = new_res_table;
+ rcu_assign_pointer(newg->res_table, old_res_table);
+ rcu_assign_pointer(newg->spare->res_table, old_res_table);
+ }
+
/* update parents - used by nexthop code for cleanup */
for (i = 0; i < newg->num_nh; i++)
newg->nh_entries[i].nh_parent = old;
rcu_assign_pointer(old->nh_grp, newg);
+ if (newg->resilient) {
+ rcu_assign_pointer(oldg->res_table, tmp_table);
+ rcu_assign_pointer(oldg->spare->res_table, tmp_table);
+ }
+
for (i = 0; i < oldg->num_nh; i++)
oldg->nh_entries[i].nh_parent = new;
@@ -1383,6 +1835,27 @@ static int insert_nexthop(struct net *net, struct nexthop *new_nh,
goto out;
}
+ if (new_nh->is_group) {
+ struct nh_group *nhg = rtnl_dereference(new_nh->nh_grp);
+ struct nh_res_table *res_table;
+
+ if (nhg->resilient) {
+ res_table = rtnl_dereference(nhg->res_table);
+
+ /* Not passing the number of buckets is OK when
+ * replacing, but not when creating a new group.
+ */
+ if (!cfg->nh_grp_res_has_num_buckets) {
+ NL_SET_ERR_MSG(extack, "Number of buckets not specified for nexthop group insertion");
+ rc = -EINVAL;
+ goto out;
+ }
+
+ nh_res_group_rebalance(nhg, res_table);
+ nh_res_table_upkeep(res_table);
+ }
+ }
+
rb_link_node_rcu(&new_nh->rb_node, parent, pp);
rb_insert_color(&new_nh->rb_node, root);
@@ -1445,6 +1918,7 @@ static struct nexthop *nexthop_create_group(struct net *net,
u16 num_nh = nla_len(grps_attr) / sizeof(*entry);
struct nh_group *nhg;
struct nexthop *nh;
+ int err;
int i;
if (WARN_ON(!num_nh))
@@ -1476,8 +1950,10 @@ static struct nexthop *nexthop_create_group(struct net *net,
struct nh_info *nhi;
nhe = nexthop_find_by_id(net, entry[i].id);
- if (!nexthop_get(nhe))
+ if (!nexthop_get(nhe)) {
+ err = -ENOENT;
goto out_no_nh;
+ }
nhi = rtnl_dereference(nhe->nh_info);
if (nhi->family == AF_INET)
@@ -1493,13 +1969,28 @@ static struct nexthop *nexthop_create_group(struct net *net,
nhg->mpath = 1;
nhg->is_multipath = true;
} else if (cfg->nh_grp_type == NEXTHOP_GRP_TYPE_RES) {
+ struct nh_res_table *res_table;
+
+ /* Bounce resilient groups for now. */
+ err = -EINVAL;
goto out_no_nh;
+
+ res_table = nexthop_res_table_alloc(net, cfg->nh_id, cfg);
+ if (!res_table) {
+ err = -ENOMEM;
+ goto out_no_nh;
+ }
+
+ rcu_assign_pointer(nhg->spare->res_table, res_table);
+ rcu_assign_pointer(nhg->res_table, res_table);
+ nhg->resilient = true;
+ nhg->is_multipath = true;
}
- WARN_ON_ONCE(nhg->mpath != 1);
+ WARN_ON_ONCE(nhg->mpath + nhg->resilient != 1);
if (nhg->mpath)
- nh_group_rebalance(nhg);
+ nh_mp_group_rebalance(nhg);
if (cfg->nh_fdb)
nhg->fdb_nh = 1;
@@ -1518,7 +2009,7 @@ static struct nexthop *nexthop_create_group(struct net *net,
kfree(nhg);
kfree(nh);
- return ERR_PTR(-ENOENT);
+ return ERR_PTR(err);
}
static int nh_create_ipv4(struct net *net, struct nexthop *nh,