aboutsummaryrefslogtreecommitdiffstats
path: root/net/core/neighbour.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/core/neighbour.c')
-rw-r--r--net/core/neighbour.c433
1 files changed, 295 insertions, 138 deletions
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 789a73aa7bd8..a77a85e357e0 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -41,7 +41,6 @@
#include <trace/events/neigh.h>
-#define DEBUG
#define NEIGH_DEBUG 1
#define neigh_dbg(level, fmt, ...) \
do { \
@@ -112,7 +111,7 @@ static void neigh_cleanup_and_release(struct neighbour *neigh)
unsigned long neigh_rand_reach_time(unsigned long base)
{
- return base ? (prandom_u32() % base) + (base >> 1) : 0;
+ return base ? prandom_u32_max(base) + (base >> 1) : 0;
}
EXPORT_SYMBOL(neigh_rand_reach_time);
@@ -123,6 +122,8 @@ static void neigh_mark_dead(struct neighbour *n)
list_del_init(&n->gc_list);
atomic_dec(&n->tbl->gc_entries);
}
+ if (!list_empty(&n->managed_list))
+ list_del_init(&n->managed_list);
}
static void neigh_update_gc_list(struct neighbour *n)
@@ -131,6 +132,8 @@ static void neigh_update_gc_list(struct neighbour *n)
write_lock_bh(&n->tbl->lock);
write_lock(&n->lock);
+ if (n->dead)
+ goto out;
/* remove from the gc list if new state is permanent or if neighbor
* is externally learned; otherwise entry should be on the gc list
@@ -147,31 +150,59 @@ static void neigh_update_gc_list(struct neighbour *n)
list_add_tail(&n->gc_list, &n->tbl->gc_list);
atomic_inc(&n->tbl->gc_entries);
}
+out:
+ write_unlock(&n->lock);
+ write_unlock_bh(&n->tbl->lock);
+}
+
+static void neigh_update_managed_list(struct neighbour *n)
+{
+ bool on_managed_list, add_to_managed;
+
+ write_lock_bh(&n->tbl->lock);
+ write_lock(&n->lock);
+ if (n->dead)
+ goto out;
+
+ add_to_managed = n->flags & NTF_MANAGED;
+ on_managed_list = !list_empty(&n->managed_list);
+ if (!add_to_managed && on_managed_list)
+ list_del_init(&n->managed_list);
+ else if (add_to_managed && !on_managed_list)
+ list_add_tail(&n->managed_list, &n->tbl->managed_list);
+out:
write_unlock(&n->lock);
write_unlock_bh(&n->tbl->lock);
}
-static bool neigh_update_ext_learned(struct neighbour *neigh, u32 flags,
- int *notify)
+static void neigh_update_flags(struct neighbour *neigh, u32 flags, int *notify,
+ bool *gc_update, bool *managed_update)
{
- bool rc = false;
- u8 ndm_flags;
+ u32 ndm_flags, old_flags = neigh->flags;
if (!(flags & NEIGH_UPDATE_F_ADMIN))
- return rc;
+ return;
- ndm_flags = (flags & NEIGH_UPDATE_F_EXT_LEARNED) ? NTF_EXT_LEARNED : 0;
- if ((neigh->flags ^ ndm_flags) & NTF_EXT_LEARNED) {
+ ndm_flags = (flags & NEIGH_UPDATE_F_EXT_LEARNED) ? NTF_EXT_LEARNED : 0;
+ ndm_flags |= (flags & NEIGH_UPDATE_F_MANAGED) ? NTF_MANAGED : 0;
+
+ if ((old_flags ^ ndm_flags) & NTF_EXT_LEARNED) {
if (ndm_flags & NTF_EXT_LEARNED)
neigh->flags |= NTF_EXT_LEARNED;
else
neigh->flags &= ~NTF_EXT_LEARNED;
- rc = true;
*notify = 1;
+ *gc_update = true;
+ }
+ if ((old_flags ^ ndm_flags) & NTF_MANAGED) {
+ if (ndm_flags & NTF_MANAGED)
+ neigh->flags |= NTF_MANAGED;
+ else
+ neigh->flags &= ~NTF_MANAGED;
+ *notify = 1;
+ *managed_update = true;
}
-
- return rc;
}
static bool neigh_del(struct neighbour *n, struct neighbour __rcu **np,
@@ -235,6 +266,9 @@ static int neigh_forced_gc(struct neigh_table *tbl)
write_lock(&n->lock);
if ((n->nud_state == NUD_FAILED) ||
+ (n->nud_state == NUD_NOARP) ||
+ (tbl->is_multicast &&
+ tbl->is_multicast(n->primary_key)) ||
time_after(tref, n->updated))
remove = true;
write_unlock(&n->lock);
@@ -273,11 +307,35 @@ static int neigh_del_timer(struct neighbour *n)
return 0;
}
-static void pneigh_queue_purge(struct sk_buff_head *list)
+static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net)
{
+ struct sk_buff_head tmp;
+ unsigned long flags;
struct sk_buff *skb;
- while ((skb = skb_dequeue(list)) != NULL) {
+ skb_queue_head_init(&tmp);
+ spin_lock_irqsave(&list->lock, flags);
+ skb = skb_peek(list);
+ while (skb != NULL) {
+ struct sk_buff *skb_next = skb_peek_next(skb, list);
+ struct net_device *dev = skb->dev;
+
+ if (net == NULL || net_eq(dev_net(dev), net)) {
+ struct in_device *in_dev;
+
+ rcu_read_lock();
+ in_dev = __in_dev_get_rcu(dev);
+ if (in_dev)
+ in_dev->arp_parms->qlen--;
+ rcu_read_unlock();
+ __skb_unlink(skb, list);
+ __skb_queue_tail(&tmp, skb);
+ }
+ skb = skb_next;
+ }
+ spin_unlock_irqrestore(&list->lock, flags);
+
+ while ((skb = __skb_dequeue(&tmp))) {
dev_put(skb->dev);
kfree_skb(skb);
}
@@ -351,9 +409,9 @@ static int __neigh_ifdown(struct neigh_table *tbl, struct net_device *dev,
write_lock_bh(&tbl->lock);
neigh_flush_dev(tbl, dev, skip_perm);
pneigh_ifdown_and_unlock(tbl, dev);
-
- del_timer_sync(&tbl->proxy_timer);
- pneigh_queue_purge(&tbl->proxy_queue);
+ pneigh_queue_purge(&tbl->proxy_queue, dev ? dev_net(dev) : NULL);
+ if (skb_queue_empty_lockless(&tbl->proxy_queue))
+ del_timer_sync(&tbl->proxy_timer);
return 0;
}
@@ -373,7 +431,7 @@ EXPORT_SYMBOL(neigh_ifdown);
static struct neighbour *neigh_alloc(struct neigh_table *tbl,
struct net_device *dev,
- bool exempt_from_gc)
+ u32 flags, bool exempt_from_gc)
{
struct neighbour *n = NULL;
unsigned long now = jiffies;
@@ -406,6 +464,7 @@ do_alloc:
n->updated = n->used = now;
n->nud_state = NUD_NONE;
n->output = neigh_blackhole;
+ n->flags = flags;
seqlock_init(&n->hh.hh_lock);
n->parms = neigh_parms_clone(&tbl->parms);
timer_setup(&n->timer, neigh_timer_handler, 0);
@@ -415,6 +474,7 @@ do_alloc:
refcount_set(&n->refcnt, 1);
n->dead = 1;
INIT_LIST_HEAD(&n->gc_list);
+ INIT_LIST_HEAD(&n->managed_list);
atomic_inc(&tbl->entries);
out:
@@ -569,19 +629,18 @@ struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net,
}
EXPORT_SYMBOL(neigh_lookup_nodev);
-static struct neighbour *___neigh_create(struct neigh_table *tbl,
- const void *pkey,
- struct net_device *dev,
- bool exempt_from_gc, bool want_ref)
+static struct neighbour *
+___neigh_create(struct neigh_table *tbl, const void *pkey,
+ struct net_device *dev, u32 flags,
+ bool exempt_from_gc, bool want_ref)
{
- struct neighbour *n1, *rc, *n = neigh_alloc(tbl, dev, exempt_from_gc);
- u32 hash_val;
- unsigned int key_len = tbl->key_len;
- int error;
+ u32 hash_val, key_len = tbl->key_len;
+ struct neighbour *n1, *rc, *n;
struct neigh_hash_table *nht;
+ int error;
+ n = neigh_alloc(tbl, dev, flags, exempt_from_gc);
trace_neigh_create(tbl, dev, pkey, n, exempt_from_gc);
-
if (!n) {
rc = ERR_PTR(-ENOBUFS);
goto out;
@@ -589,7 +648,7 @@ static struct neighbour *___neigh_create(struct neigh_table *tbl,
memcpy(n->primary_key, pkey, key_len);
n->dev = dev;
- dev_hold(dev);
+ netdev_hold(dev, &n->dev_tracker, GFP_ATOMIC);
/* Protocol specific setup. */
if (tbl->constructor && (error = tbl->constructor(n)) < 0) {
@@ -644,7 +703,8 @@ static struct neighbour *___neigh_create(struct neigh_table *tbl,
n->dead = 0;
if (!exempt_from_gc)
list_add_tail(&n->gc_list, &n->tbl->gc_list);
-
+ if (n->flags & NTF_MANAGED)
+ list_add_tail(&n->managed_list, &n->tbl->managed_list);
if (want_ref)
neigh_hold(n);
rcu_assign_pointer(n->next,
@@ -668,7 +728,7 @@ out_neigh_release:
struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey,
struct net_device *dev, bool want_ref)
{
- return ___neigh_create(tbl, pkey, dev, false, want_ref);
+ return ___neigh_create(tbl, pkey, dev, 0, false, want_ref);
}
EXPORT_SYMBOL(__neigh_create);
@@ -727,20 +787,17 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl,
ASSERT_RTNL();
- n = kmalloc(sizeof(*n) + key_len, GFP_KERNEL);
+ n = kzalloc(sizeof(*n) + key_len, GFP_KERNEL);
if (!n)
goto out;
- n->protocol = 0;
write_pnet(&n->net, net);
memcpy(n->key, pkey, key_len);
n->dev = dev;
- if (dev)
- dev_hold(dev);
+ netdev_hold(dev, &n->dev_tracker, GFP_KERNEL);
if (tbl->pconstructor && tbl->pconstructor(n)) {
- if (dev)
- dev_put(dev);
+ netdev_put(dev, &n->dev_tracker);
kfree(n);
n = NULL;
goto out;
@@ -772,8 +829,7 @@ int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey,
write_unlock_bh(&tbl->lock);
if (tbl->pdestructor)
tbl->pdestructor(n);
- if (n->dev)
- dev_put(n->dev);
+ netdev_put(n->dev, &n->dev_tracker);
kfree(n);
return 0;
}
@@ -806,8 +862,7 @@ static int pneigh_ifdown_and_unlock(struct neigh_table *tbl,
n->next = NULL;
if (tbl->pdestructor)
tbl->pdestructor(n);
- if (n->dev)
- dev_put(n->dev);
+ netdev_put(n->dev, &n->dev_tracker);
kfree(n);
}
return -ENOENT;
@@ -848,7 +903,7 @@ void neigh_destroy(struct neighbour *neigh)
if (dev->netdev_ops->ndo_neigh_destroy)
dev->netdev_ops->ndo_neigh_destroy(dev, neigh);
- dev_put(dev);
+ netdev_put(dev, &neigh->dev_tracker);
neigh_parms_put(neigh->parms);
neigh_dbg(2, "neigh %p is destroyed\n", neigh);
@@ -1065,11 +1120,12 @@ static void neigh_timer_handler(struct timer_list *t)
neigh->updated = jiffies;
atomic_set(&neigh->probes, 0);
notify = 1;
- next = now + NEIGH_VAR(neigh->parms, RETRANS_TIME);
+ next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME),
+ HZ/100);
}
} else {
/* NUD_PROBE|NUD_INCOMPLETE */
- next = now + NEIGH_VAR(neigh->parms, RETRANS_TIME);
+ next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME), HZ/100);
}
if ((neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) &&
@@ -1081,8 +1137,8 @@ static void neigh_timer_handler(struct timer_list *t)
}
if (neigh->nud_state & NUD_IN_TIMER) {
- if (time_before(next, jiffies + HZ/2))
- next = jiffies + HZ/2;
+ if (time_before(next, jiffies + HZ/100))
+ next = jiffies + HZ/100;
if (!mod_timer(&neigh->timer, next))
neigh_hold(neigh);
}
@@ -1101,7 +1157,8 @@ out:
neigh_release(neigh);
}
-int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
+int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb,
+ const bool immediate_ok)
{
int rc;
bool immediate_probe = false;
@@ -1122,18 +1179,23 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
atomic_set(&neigh->probes,
NEIGH_VAR(neigh->parms, UCAST_PROBES));
neigh_del_timer(neigh);
- neigh->nud_state = NUD_INCOMPLETE;
+ neigh->nud_state = NUD_INCOMPLETE;
neigh->updated = now;
- next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME),
- HZ/2);
+ if (!immediate_ok) {
+ next = now + 1;
+ } else {
+ immediate_probe = true;
+ next = now + max(NEIGH_VAR(neigh->parms,
+ RETRANS_TIME),
+ HZ / 100);
+ }
neigh_add_timer(neigh, next);
- immediate_probe = true;
} else {
neigh->nud_state = NUD_FAILED;
neigh->updated = jiffies;
write_unlock_bh(&neigh->lock);
- kfree_skb(skb);
+ kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_FAILED);
return 1;
}
} else if (neigh->nud_state & NUD_STALE) {
@@ -1155,7 +1217,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
if (!buff)
break;
neigh->arp_queue_len_bytes -= buff->truesize;
- kfree_skb(buff);
+ kfree_skb_reason(buff, SKB_DROP_REASON_NEIGH_QUEUEFULL);
NEIGH_CACHE_STAT_INC(neigh->tbl, unres_discards);
}
skb_dst_force(skb);
@@ -1177,7 +1239,7 @@ out_dead:
if (neigh->nud_state & NUD_STALE)
goto out_unlock_bh;
write_unlock_bh(&neigh->lock);
- kfree_skb(skb);
+ kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_DEAD);
trace_neigh_event_send_dead(neigh, 1);
return 1;
}
@@ -1202,8 +1264,6 @@ static void neigh_update_hhs(struct neighbour *neigh)
}
}
-
-
/* Generic update routine.
-- lladdr is new lladdr or NULL, if it is not supplied.
-- new is new state.
@@ -1214,7 +1274,8 @@ static void neigh_update_hhs(struct neighbour *neigh)
lladdr instead of overriding it
if it is different.
NEIGH_UPDATE_F_ADMIN means that the change is administrative.
-
+ NEIGH_UPDATE_F_USE means that the entry is user triggered.
+ NEIGH_UPDATE_F_MANAGED means that the entry will be auto-refreshed.
NEIGH_UPDATE_F_OVERRIDE_ISROUTER allows to override existing
NTF_ROUTER flag.
NEIGH_UPDATE_F_ISROUTER indicates if the neighbour is known as
@@ -1222,17 +1283,15 @@ static void neigh_update_hhs(struct neighbour *neigh)
Caller MUST hold reference count on the entry.
*/
-
static int __neigh_update(struct neighbour *neigh, const u8 *lladdr,
u8 new, u32 flags, u32 nlmsg_pid,
struct netlink_ext_ack *extack)
{
- bool ext_learn_change = false;
- u8 old;
- int err;
- int notify = 0;
- struct net_device *dev;
+ bool gc_update = false, managed_update = false;
int update_isrouter = 0;
+ struct net_device *dev;
+ int err, notify = 0;
+ u8 old;
trace_neigh_update(neigh, lladdr, new, flags, nlmsg_pid);
@@ -1242,15 +1301,22 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr,
old = neigh->nud_state;
err = -EPERM;
- if (!(flags & NEIGH_UPDATE_F_ADMIN) &&
- (old & (NUD_NOARP | NUD_PERMANENT)))
- goto out;
if (neigh->dead) {
NL_SET_ERR_MSG(extack, "Neighbor entry is now dead");
+ new = old;
goto out;
}
+ if (!(flags & NEIGH_UPDATE_F_ADMIN) &&
+ (old & (NUD_NOARP | NUD_PERMANENT)))
+ goto out;
- ext_learn_change = neigh_update_ext_learned(neigh, flags, &notify);
+ neigh_update_flags(neigh, flags, &notify, &gc_update, &managed_update);
+ if (flags & (NEIGH_UPDATE_F_USE | NEIGH_UPDATE_F_MANAGED)) {
+ new = old & ~NUD_PERMANENT;
+ neigh->nud_state = new;
+ err = 0;
+ goto out;
+ }
if (!(new & NUD_VALID)) {
neigh_del_timer(neigh);
@@ -1376,7 +1442,7 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr,
* we can reinject the packet there.
*/
n2 = NULL;
- if (dst) {
+ if (dst && dst->obsolete != DST_OBSOLETE_DEAD) {
n2 = dst_neigh_lookup_skb(dst, skb);
if (n2)
n1 = n2;
@@ -1395,15 +1461,13 @@ out:
if (update_isrouter)
neigh_update_is_router(neigh, flags, &notify);
write_unlock_bh(&neigh->lock);
-
- if (((new ^ old) & NUD_PERMANENT) || ext_learn_change)
+ if (((new ^ old) & NUD_PERMANENT) || gc_update)
neigh_update_gc_list(neigh);
-
+ if (managed_update)
+ neigh_update_managed_list(neigh);
if (notify)
neigh_update_notify(neigh, nlmsg_pid);
-
trace_neigh_update_done(neigh, err);
-
return err;
}
@@ -1427,7 +1491,8 @@ void __neigh_set_probe_once(struct neighbour *neigh)
neigh->nud_state = NUD_INCOMPLETE;
atomic_set(&neigh->probes, neigh_max_probes(neigh));
neigh_add_timer(neigh,
- jiffies + NEIGH_VAR(neigh->parms, RETRANS_TIME));
+ jiffies + max(NEIGH_VAR(neigh->parms, RETRANS_TIME),
+ HZ/100));
}
EXPORT_SYMBOL(__neigh_set_probe_once);
@@ -1528,6 +1593,20 @@ int neigh_direct_output(struct neighbour *neigh, struct sk_buff *skb)
}
EXPORT_SYMBOL(neigh_direct_output);
+static void neigh_managed_work(struct work_struct *work)
+{
+ struct neigh_table *tbl = container_of(work, struct neigh_table,
+ managed_work.work);
+ struct neighbour *neigh;
+
+ write_lock_bh(&tbl->lock);
+ list_for_each_entry(neigh, &tbl->managed_list, managed_list)
+ neigh_event_send_probe(neigh, NULL, false);
+ queue_delayed_work(system_power_efficient_wq, &tbl->managed_work,
+ NEIGH_VAR(&tbl->parms, INTERVAL_PROBE_TIME_MS));
+ write_unlock_bh(&tbl->lock);
+}
+
static void neigh_proxy_process(struct timer_list *t)
{
struct neigh_table *tbl = from_timer(tbl, t, proxy_timer);
@@ -1542,8 +1621,15 @@ static void neigh_proxy_process(struct timer_list *t)
if (tdif <= 0) {
struct net_device *dev = skb->dev;
+ struct in_device *in_dev;
+ rcu_read_lock();
+ in_dev = __in_dev_get_rcu(dev);
+ if (in_dev)
+ in_dev->arp_parms->qlen--;
+ rcu_read_unlock();
__skb_unlink(skb, &tbl->proxy_queue);
+
if (tbl->proxy_redo && netif_running(dev)) {
rcu_read_lock();
tbl->proxy_redo(skb);
@@ -1565,12 +1651,10 @@ static void neigh_proxy_process(struct timer_list *t)
void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p,
struct sk_buff *skb)
{
- unsigned long now = jiffies;
+ unsigned long sched_next = jiffies +
+ prandom_u32_max(NEIGH_VAR(p, PROXY_DELAY));
- unsigned long sched_next = now + (prandom_u32() %
- NEIGH_VAR(p, PROXY_DELAY));
-
- if (tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)) {
+ if (p->qlen > NEIGH_VAR(p, PROXY_QLEN)) {
kfree_skb(skb);
return;
}
@@ -1586,6 +1670,7 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p,
skb_dst_drop(skb);
dev_hold(skb->dev);
__skb_queue_tail(&tbl->proxy_queue, skb);
+ p->qlen++;
mod_timer(&tbl->proxy_timer, sched_next);
spin_unlock(&tbl->proxy_queue.lock);
}
@@ -1618,13 +1703,14 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev,
refcount_set(&p->refcnt, 1);
p->reachable_time =
neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME));
- dev_hold(dev);
+ p->qlen = 0;
+ netdev_hold(dev, &p->dev_tracker, GFP_KERNEL);
p->dev = dev;
write_pnet(&p->net, net);
p->sysctl_table = NULL;
if (ops->ndo_neigh_setup && ops->ndo_neigh_setup(dev, p)) {
- dev_put(dev);
+ netdev_put(dev, &p->dev_tracker);
kfree(p);
return NULL;
}
@@ -1655,8 +1741,7 @@ void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms)
list_del(&parms->list);
parms->dead = 1;
write_unlock_bh(&tbl->lock);
- if (parms->dev)
- dev_put(parms->dev);
+ netdev_put(parms->dev, &parms->dev_tracker);
call_rcu(&parms->rcu_head, neigh_rcu_free_parms);
}
EXPORT_SYMBOL(neigh_parms_release);
@@ -1677,11 +1762,14 @@ void neigh_table_init(int index, struct neigh_table *tbl)
INIT_LIST_HEAD(&tbl->parms_list);
INIT_LIST_HEAD(&tbl->gc_list);
+ INIT_LIST_HEAD(&tbl->managed_list);
+
list_add(&tbl->parms.list, &tbl->parms_list);
write_pnet(&tbl->parms.net, &init_net);
refcount_set(&tbl->parms.refcnt, 1);
tbl->parms.reachable_time =
neigh_rand_reach_time(NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME));
+ tbl->parms.qlen = 0;
tbl->stats = alloc_percpu(struct neigh_statistics);
if (!tbl->stats)
@@ -1708,9 +1796,13 @@ void neigh_table_init(int index, struct neigh_table *tbl)
WARN_ON(tbl->entry_size % NEIGH_PRIV_ALIGN);
rwlock_init(&tbl->lock);
+
INIT_DEFERRABLE_WORK(&tbl->gc_work, neigh_periodic_work);
queue_delayed_work(system_power_efficient_wq, &tbl->gc_work,
tbl->parms.reachable_time);
+ INIT_DEFERRABLE_WORK(&tbl->managed_work, neigh_managed_work);
+ queue_delayed_work(system_power_efficient_wq, &tbl->managed_work, 0);
+
timer_setup(&tbl->proxy_timer, neigh_proxy_process, 0);
skb_queue_head_init_class(&tbl->proxy_queue,
&neigh_table_proxy_queue_class);
@@ -1726,9 +1818,10 @@ int neigh_table_clear(int index, struct neigh_table *tbl)
{
neigh_tables[index] = NULL;
/* It is not clean... Fix it to unload IPv6 module safely */
+ cancel_delayed_work_sync(&tbl->managed_work);
cancel_delayed_work_sync(&tbl->gc_work);
del_timer_sync(&tbl->proxy_timer);
- pneigh_queue_purge(&tbl->proxy_queue);
+ pneigh_queue_purge(&tbl->proxy_queue, NULL);
neigh_ifdown(tbl, NULL);
if (atomic_read(&tbl->entries))
pr_crit("neighbour leakage\n");
@@ -1760,15 +1853,13 @@ static struct neigh_table *neigh_find_table(int family)
case AF_INET6:
tbl = neigh_tables[NEIGH_ND_TABLE];
break;
- case AF_DECnet:
- tbl = neigh_tables[NEIGH_DN_TABLE];
- break;
}
return tbl;
}
const struct nla_policy nda_policy[NDA_MAX+1] = {
+ [NDA_UNSPEC] = { .strict_start_type = NDA_NH_ID },
[NDA_DST] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
[NDA_LLADDR] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
[NDA_CACHEINFO] = { .len = sizeof(struct nda_cacheinfo) },
@@ -1779,6 +1870,9 @@ const struct nla_policy nda_policy[NDA_MAX+1] = {
[NDA_IFINDEX] = { .type = NLA_U32 },
[NDA_MASTER] = { .type = NLA_U32 },
[NDA_PROTOCOL] = { .type = NLA_U8 },
+ [NDA_NH_ID] = { .type = NLA_U32 },
+ [NDA_FLAGS_EXT] = NLA_POLICY_MASK(NLA_U32, NTF_EXT_MASK),
+ [NDA_FDB_EXT_ATTRS] = { .type = NLA_NESTED },
};
static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -1850,7 +1944,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE |
- NEIGH_UPDATE_F_OVERRIDE_ISROUTER;
+ NEIGH_UPDATE_F_OVERRIDE_ISROUTER;
struct net *net = sock_net(skb->sk);
struct ndmsg *ndm;
struct nlattr *tb[NDA_MAX+1];
@@ -1859,6 +1953,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
struct neighbour *neigh;
void *dst, *lladdr;
u8 protocol = 0;
+ u32 ndm_flags;
int err;
ASSERT_RTNL();
@@ -1874,6 +1969,15 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
}
ndm = nlmsg_data(nlh);
+ ndm_flags = ndm->ndm_flags;
+ if (tb[NDA_FLAGS_EXT]) {
+ u32 ext = nla_get_u32(tb[NDA_FLAGS_EXT]);
+
+ BUILD_BUG_ON(sizeof(neigh->flags) * BITS_PER_BYTE <
+ (sizeof(ndm->ndm_flags) * BITS_PER_BYTE +
+ hweight32(NTF_EXT_MASK)));
+ ndm_flags |= (ext << NTF_EXT_SHIFT);
+ }
if (ndm->ndm_ifindex) {
dev = __dev_get_by_index(net, ndm->ndm_ifindex);
if (dev == NULL) {
@@ -1901,14 +2005,18 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
if (tb[NDA_PROTOCOL])
protocol = nla_get_u8(tb[NDA_PROTOCOL]);
-
- if (ndm->ndm_flags & NTF_PROXY) {
+ if (ndm_flags & NTF_PROXY) {
struct pneigh_entry *pn;
+ if (ndm_flags & NTF_MANAGED) {
+ NL_SET_ERR_MSG(extack, "Invalid NTF_* flag combination");
+ goto out;
+ }
+
err = -ENOBUFS;
pn = pneigh_lookup(tbl, net, dst, dev, 1);
if (pn) {
- pn->flags = ndm->ndm_flags;
+ pn->flags = ndm_flags;
if (protocol)
pn->protocol = protocol;
err = 0;
@@ -1928,16 +2036,24 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
neigh = neigh_lookup(tbl, dst, dev);
if (neigh == NULL) {
- bool exempt_from_gc;
+ bool ndm_permanent = ndm->ndm_state & NUD_PERMANENT;
+ bool exempt_from_gc = ndm_permanent ||
+ ndm_flags & NTF_EXT_LEARNED;
if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
err = -ENOENT;
goto out;
}
+ if (ndm_permanent && (ndm_flags & NTF_MANAGED)) {
+ NL_SET_ERR_MSG(extack, "Invalid NTF_* flag for permanent entry");
+ err = -EINVAL;
+ goto out;
+ }
- exempt_from_gc = ndm->ndm_state & NUD_PERMANENT ||
- ndm->ndm_flags & NTF_EXT_LEARNED;
- neigh = ___neigh_create(tbl, dst, dev, exempt_from_gc, true);
+ neigh = ___neigh_create(tbl, dst, dev,
+ ndm_flags &
+ (NTF_EXT_LEARNED | NTF_MANAGED),
+ exempt_from_gc, true);
if (IS_ERR(neigh)) {
err = PTR_ERR(neigh);
goto out;
@@ -1954,24 +2070,24 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
NEIGH_UPDATE_F_OVERRIDE_ISROUTER);
}
- if (ndm->ndm_flags & NTF_EXT_LEARNED)
+ if (protocol)
+ neigh->protocol = protocol;
+ if (ndm_flags & NTF_EXT_LEARNED)
flags |= NEIGH_UPDATE_F_EXT_LEARNED;
-
- if (ndm->ndm_flags & NTF_ROUTER)
+ if (ndm_flags & NTF_ROUTER)
flags |= NEIGH_UPDATE_F_ISROUTER;
+ if (ndm_flags & NTF_MANAGED)
+ flags |= NEIGH_UPDATE_F_MANAGED;
+ if (ndm_flags & NTF_USE)
+ flags |= NEIGH_UPDATE_F_USE;
- if (ndm->ndm_flags & NTF_USE) {
+ err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags,
+ NETLINK_CB(skb).portid, extack);
+ if (!err && ndm_flags & (NTF_USE | NTF_MANAGED)) {
neigh_event_send(neigh, NULL);
err = 0;
- } else
- err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags,
- NETLINK_CB(skb).portid, extack);
-
- if (protocol)
- neigh->protocol = protocol;
-
+ }
neigh_release(neigh);
-
out:
return err;
}
@@ -2015,7 +2131,9 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms)
nla_put_msecs(skb, NDTPA_PROXY_DELAY,
NEIGH_VAR(parms, PROXY_DELAY), NDTPA_PAD) ||
nla_put_msecs(skb, NDTPA_LOCKTIME,
- NEIGH_VAR(parms, LOCKTIME), NDTPA_PAD))
+ NEIGH_VAR(parms, LOCKTIME), NDTPA_PAD) ||
+ nla_put_msecs(skb, NDTPA_INTERVAL_PROBE_TIME_MS,
+ NEIGH_VAR(parms, INTERVAL_PROBE_TIME_MS), NDTPA_PAD))
goto nla_put_failure;
return nla_nest_end(skb, nest);
@@ -2170,6 +2288,7 @@ static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = {
[NDTPA_ANYCAST_DELAY] = { .type = NLA_U64 },
[NDTPA_PROXY_DELAY] = { .type = NLA_U64 },
[NDTPA_LOCKTIME] = { .type = NLA_U64 },
+ [NDTPA_INTERVAL_PROBE_TIME_MS] = { .type = NLA_U64, .min = 1 },
};
static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -2288,6 +2407,10 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh,
nla_get_msecs(tbp[i]));
call_netevent_notifiers(NETEVENT_DELAY_PROBE_TIME_UPDATE, p);
break;
+ case NDTPA_INTERVAL_PROBE_TIME_MS:
+ NEIGH_VAR_SET(p, INTERVAL_PROBE_TIME_MS,
+ nla_get_msecs(tbp[i]));
+ break;
case NDTPA_RETRANS_TIME:
NEIGH_VAR_SET(p, RETRANS_TIME,
nla_get_msecs(tbp[i]));
@@ -2422,6 +2545,7 @@ out:
static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh,
u32 pid, u32 seq, int type, unsigned int flags)
{
+ u32 neigh_flags, neigh_flags_ext;
unsigned long now = jiffies;
struct nda_cacheinfo ci;
struct nlmsghdr *nlh;
@@ -2431,11 +2555,14 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh,
if (nlh == NULL)
return -EMSGSIZE;
+ neigh_flags_ext = neigh->flags >> NTF_EXT_SHIFT;
+ neigh_flags = neigh->flags & NTF_OLD_MASK;
+
ndm = nlmsg_data(nlh);
ndm->ndm_family = neigh->ops->family;
ndm->ndm_pad1 = 0;
ndm->ndm_pad2 = 0;
- ndm->ndm_flags = neigh->flags;
+ ndm->ndm_flags = neigh_flags;
ndm->ndm_type = neigh->type;
ndm->ndm_ifindex = neigh->dev->ifindex;
@@ -2466,6 +2593,8 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh,
if (neigh->protocol && nla_put_u8(skb, NDA_PROTOCOL, neigh->protocol))
goto nla_put_failure;
+ if (neigh_flags_ext && nla_put_u32(skb, NDA_FLAGS_EXT, neigh_flags_ext))
+ goto nla_put_failure;
nlmsg_end(skb, nlh);
return 0;
@@ -2479,6 +2608,7 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn,
u32 pid, u32 seq, int type, unsigned int flags,
struct neigh_table *tbl)
{
+ u32 neigh_flags, neigh_flags_ext;
struct nlmsghdr *nlh;
struct ndmsg *ndm;
@@ -2486,11 +2616,14 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn,
if (nlh == NULL)
return -EMSGSIZE;
+ neigh_flags_ext = pn->flags >> NTF_EXT_SHIFT;
+ neigh_flags = pn->flags & NTF_OLD_MASK;
+
ndm = nlmsg_data(nlh);
ndm->ndm_family = tbl->family;
ndm->ndm_pad1 = 0;
ndm->ndm_pad2 = 0;
- ndm->ndm_flags = pn->flags | NTF_PROXY;
+ ndm->ndm_flags = neigh_flags | NTF_PROXY;
ndm->ndm_type = RTN_UNICAST;
ndm->ndm_ifindex = pn->dev ? pn->dev->ifindex : 0;
ndm->ndm_state = NUD_NONE;
@@ -2500,6 +2633,8 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn,
if (pn->protocol && nla_put_u8(skb, NDA_PROTOCOL, pn->protocol))
goto nla_put_failure;
+ if (neigh_flags_ext && nla_put_u32(skb, NDA_FLAGS_EXT, neigh_flags_ext))
+ goto nla_put_failure;
nlmsg_end(skb, nlh);
return 0;
@@ -2523,6 +2658,13 @@ static bool neigh_master_filtered(struct net_device *dev, int master_idx)
return false;
master = dev ? netdev_master_upper_dev_get(dev) : NULL;
+
+ /* 0 is already used to denote NDA_MASTER wasn't passed, therefore need another
+ * invalid value for ifindex to denote "no master".
+ */
+ if (master_idx == -1)
+ return !!master;
+
if (!master || master->ifindex != master_idx)
return true;
@@ -2808,6 +2950,7 @@ static inline size_t neigh_nlmsg_size(void)
+ nla_total_size(MAX_ADDR_LEN) /* NDA_LLADDR */
+ nla_total_size(sizeof(struct nda_cacheinfo))
+ nla_total_size(4) /* NDA_PROBES */
+ + nla_total_size(4) /* NDA_FLAGS_EXT */
+ nla_total_size(1); /* NDA_PROTOCOL */
}
@@ -2836,6 +2979,7 @@ static inline size_t pneigh_nlmsg_size(void)
{
return NLMSG_ALIGN(sizeof(struct ndmsg))
+ nla_total_size(MAX_ADDR_LEN) /* NDA_DST */
+ + nla_total_size(4) /* NDA_FLAGS_EXT */
+ nla_total_size(1); /* NDA_PROTOCOL */
}
@@ -3132,7 +3276,7 @@ static struct pneigh_entry *pneigh_get_first(struct seq_file *seq)
struct net *net = seq_file_net(seq);
struct neigh_table *tbl = state->tbl;
struct pneigh_entry *pn = NULL;
- int bucket = state->bucket;
+ int bucket;
state->flags |= NEIGH_SEQ_IS_PNEIGH;
for (bucket = 0; bucket <= PNEIGH_HASHMASK; bucket++) {
@@ -3264,7 +3408,7 @@ EXPORT_SYMBOL(neigh_seq_stop);
static void *neigh_stat_seq_start(struct seq_file *seq, loff_t *pos)
{
- struct neigh_table *tbl = PDE_DATA(file_inode(seq->file));
+ struct neigh_table *tbl = pde_data(file_inode(seq->file));
int cpu;
if (*pos == 0)
@@ -3281,7 +3425,7 @@ static void *neigh_stat_seq_start(struct seq_file *seq, loff_t *pos)
static void *neigh_stat_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
- struct neigh_table *tbl = PDE_DATA(file_inode(seq->file));
+ struct neigh_table *tbl = pde_data(file_inode(seq->file));
int cpu;
for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) {
@@ -3301,16 +3445,17 @@ static void neigh_stat_seq_stop(struct seq_file *seq, void *v)
static int neigh_stat_seq_show(struct seq_file *seq, void *v)
{
- struct neigh_table *tbl = PDE_DATA(file_inode(seq->file));
+ struct neigh_table *tbl = pde_data(file_inode(seq->file));
struct neigh_statistics *st = v;
if (v == SEQ_START_TOKEN) {
- seq_printf(seq, "entries allocs destroys hash_grows lookups hits res_failed rcv_probes_mcast rcv_probes_ucast periodic_gc_runs forced_gc_runs unresolved_discards table_fulls\n");
+ seq_puts(seq, "entries allocs destroys hash_grows lookups hits res_failed rcv_probes_mcast rcv_probes_ucast periodic_gc_runs forced_gc_runs unresolved_discards table_fulls\n");
return 0;
}
- seq_printf(seq, "%08x %08lx %08lx %08lx %08lx %08lx %08lx "
- "%08lx %08lx %08lx %08lx %08lx %08lx\n",
+ seq_printf(seq, "%08x %08lx %08lx %08lx %08lx %08lx %08lx "
+ "%08lx %08lx %08lx "
+ "%08lx %08lx %08lx\n",
atomic_read(&tbl->entries),
st->allocs,
@@ -3377,7 +3522,7 @@ EXPORT_SYMBOL(neigh_app_ns);
static int unres_qlen_max = INT_MAX / SKB_TRUESIZE(ETH_FRAME_LEN);
static int proc_unres_qlen(struct ctl_table *ctl, int write,
- void __user *buffer, size_t *lenp, loff_t *ppos)
+ void *buffer, size_t *lenp, loff_t *ppos)
{
int size, ret;
struct ctl_table tmp = *ctl;
@@ -3441,8 +3586,8 @@ static void neigh_proc_update(struct ctl_table *ctl, int write)
}
static int neigh_proc_dointvec_zero_intmax(struct ctl_table *ctl, int write,
- void __user *buffer,
- size_t *lenp, loff_t *ppos)
+ void *buffer, size_t *lenp,
+ loff_t *ppos)
{
struct ctl_table tmp = *ctl;
int ret;
@@ -3455,8 +3600,24 @@ static int neigh_proc_dointvec_zero_intmax(struct ctl_table *ctl, int write,
return ret;
}
-int neigh_proc_dointvec(struct ctl_table *ctl, int write,
- void __user *buffer, size_t *lenp, loff_t *ppos)
+static int neigh_proc_dointvec_ms_jiffies_positive(struct ctl_table *ctl, int write,
+ void *buffer, size_t *lenp, loff_t *ppos)
+{
+ struct ctl_table tmp = *ctl;
+ int ret;
+
+ int min = msecs_to_jiffies(1);
+
+ tmp.extra1 = &min;
+ tmp.extra2 = NULL;
+
+ ret = proc_dointvec_ms_jiffies_minmax(&tmp, write, buffer, lenp, ppos);
+ neigh_proc_update(ctl, write);
+ return ret;
+}
+
+int neigh_proc_dointvec(struct ctl_table *ctl, int write, void *buffer,
+ size_t *lenp, loff_t *ppos)
{
int ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
@@ -3465,8 +3626,7 @@ int neigh_proc_dointvec(struct ctl_table *ctl, int write,
}
EXPORT_SYMBOL(neigh_proc_dointvec);
-int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write,
- void __user *buffer,
+int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write, void *buffer,
size_t *lenp, loff_t *ppos)
{
int ret = proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos);
@@ -3477,8 +3637,8 @@ int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write,
EXPORT_SYMBOL(neigh_proc_dointvec_jiffies);
static int neigh_proc_dointvec_userhz_jiffies(struct ctl_table *ctl, int write,
- void __user *buffer,
- size_t *lenp, loff_t *ppos)
+ void *buffer, size_t *lenp,
+ loff_t *ppos)
{
int ret = proc_dointvec_userhz_jiffies(ctl, write, buffer, lenp, ppos);
@@ -3487,8 +3647,7 @@ static int neigh_proc_dointvec_userhz_jiffies(struct ctl_table *ctl, int write,
}
int neigh_proc_dointvec_ms_jiffies(struct ctl_table *ctl, int write,
- void __user *buffer,
- size_t *lenp, loff_t *ppos)
+ void *buffer, size_t *lenp, loff_t *ppos)
{
int ret = proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos);
@@ -3498,8 +3657,8 @@ int neigh_proc_dointvec_ms_jiffies(struct ctl_table *ctl, int write,
EXPORT_SYMBOL(neigh_proc_dointvec_ms_jiffies);
static int neigh_proc_dointvec_unres_qlen(struct ctl_table *ctl, int write,
- void __user *buffer,
- size_t *lenp, loff_t *ppos)
+ void *buffer, size_t *lenp,
+ loff_t *ppos)
{
int ret = proc_unres_qlen(ctl, write, buffer, lenp, ppos);
@@ -3508,8 +3667,8 @@ static int neigh_proc_dointvec_unres_qlen(struct ctl_table *ctl, int write,
}
static int neigh_proc_base_reachable_time(struct ctl_table *ctl, int write,
- void __user *buffer,
- size_t *lenp, loff_t *ppos)
+ void *buffer, size_t *lenp,
+ loff_t *ppos)
{
struct neigh_parms *p = ctl->extra2;
int ret;
@@ -3553,8 +3712,8 @@ static int neigh_proc_base_reachable_time(struct ctl_table *ctl, int write,
#define NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(attr, name) \
NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_userhz_jiffies)
-#define NEIGH_SYSCTL_MS_JIFFIES_ENTRY(attr, name) \
- NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_ms_jiffies)
+#define NEIGH_SYSCTL_MS_JIFFIES_POSITIVE_ENTRY(attr, name) \
+ NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_ms_jiffies_positive)
#define NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(attr, data_attr, name) \
NEIGH_SYSCTL_ENTRY(attr, data_attr, name, 0644, neigh_proc_dointvec_ms_jiffies)
@@ -3574,6 +3733,8 @@ static struct neigh_sysctl_table {
NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(RETRANS_TIME, "retrans_time"),
NEIGH_SYSCTL_JIFFIES_ENTRY(BASE_REACHABLE_TIME, "base_reachable_time"),
NEIGH_SYSCTL_JIFFIES_ENTRY(DELAY_PROBE_TIME, "delay_first_probe_time"),
+ NEIGH_SYSCTL_MS_JIFFIES_POSITIVE_ENTRY(INTERVAL_PROBE_TIME_MS,
+ "interval_probe_time_ms"),
NEIGH_SYSCTL_JIFFIES_ENTRY(GC_STALETIME, "gc_stale_time"),
NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(QUEUE_LEN_BYTES, "unres_qlen_bytes"),
NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(PROXY_QLEN, "proxy_qlen"),
@@ -3626,7 +3787,7 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
char neigh_path[ sizeof("net//neigh/") + IFNAMSIZ + IFNAMSIZ ];
char *p_name;
- t = kmemdup(&neigh_sysctl_template, sizeof(*t), GFP_KERNEL);
+ t = kmemdup(&neigh_sysctl_template, sizeof(*t), GFP_KERNEL_ACCOUNT);
if (!t)
goto err;
@@ -3674,10 +3835,6 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
neigh_proc_base_reachable_time;
}
- /* Don't export sysctls to unprivileged users */
- if (neigh_parms_net(p)->user_ns != &init_user_ns)
- t->neigh_vars[0].procname = NULL;
-
switch (neigh_parms_family(p)) {
case AF_INET:
p_name = "ipv4";
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.