[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <1496173944-82125-1-git-send-email-sowmini.varadhan@oracle.com>
Date: Tue, 30 May 2017 12:52:24 -0700
From: Sowmini Varadhan <sowmini.varadhan@...cle.com>
To: sowmini.varadhan@...cle.com
Cc: davem@...emloft.net, stephen@...workplumber.org,
sowmini.varadhan@...cle.com
Subject: [PATCH net-next] neigh: Really delete an arp/neigh entry on "ip neigh delete" or "arp -d"
The command
# arp -s 62.2.0.1 a:b:c:d:e:f dev eth2
adds an entry like the following (listed by "arp -an")
? (62.2.0.1) at 0a:0b:0c:0d:0e:0f [ether] PERM on eth2
but the symmetric deletion command
# arp -i eth2 -d 62.2.0.1
does not remove the PERM entry from the table, and instead leaves behind
? (62.2.0.1) at <incomplete> on eth2
The reason is that there is a refcnt of 1 for the arp_tbl itself
(neigh_alloc starts off the entry with a refcnt of 1), thus
the neigh_release() call from arp_invalidate() will (at best) just
decrement the ref to 1, but will never actually free it from the
table.
To fix this, we need to do something like neigh_forced_gc: if
the refcnt is 1 (i.e., on the table's ref), remove the entry from
the table and free it. This patch refactors and shares common code
between neigh_forced_gc() and the newly added neigh_remove_one().
A similar issue exists for IPv6 Neighbor Cache entries, and is fixed
in a similar manner by this patch.
Signed-off-by: Sowmini Varadhan <sowmini.varadhan@...cle.com>
---
include/net/neighbour.h | 1 +
net/core/neighbour.c | 63 ++++++++++++++++++++++++++++++++++++++--------
net/ipv4/arp.c | 1 +
3 files changed, 54 insertions(+), 11 deletions(-)
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index e4dd3a2..639b675 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -317,6 +317,7 @@ struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey,
int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags,
u32 nlmsg_pid);
void __neigh_set_probe_once(struct neighbour *neigh);
+bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl);
void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev);
int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index d274f81..a445089 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -118,6 +118,55 @@ unsigned long neigh_rand_reach_time(unsigned long base)
EXPORT_SYMBOL(neigh_rand_reach_time);
+static bool neigh_del(struct neighbour *n, __u8 state,
+ struct neighbour __rcu **np)
+{
+ bool retval = false;
+
+ write_lock(&n->lock);
+ if (atomic_read(&n->refcnt) == 1 && !(n->nud_state & state)) {
+ rcu_assign_pointer(*np,
+ rcu_dereference_protected(n->next,
+ lockdep_is_held(&tbl->lock)));
+ n->dead = 1;
+ retval = true;
+ }
+ write_unlock(&n->lock);
+ if (retval)
+ neigh_cleanup_and_release(n);
+ return retval;
+}
+
+bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl)
+{
+ struct neigh_hash_table *nht;
+ void *pkey = ndel->primary_key;
+ u32 hash_val;
+ struct neighbour *n;
+ struct neighbour __rcu **np;
+ bool retval = false;
+
+ write_lock_bh(&tbl->lock);
+ nht = rcu_dereference_protected(tbl->nht,
+ lockdep_is_held(&tbl->lock));
+ hash_val = tbl->hash(pkey, ndel->dev, nht->hash_rnd);
+ hash_val = hash_val >> (32 - nht->hash_shift);
+
+ np = &nht->hash_buckets[hash_val];
+ while ((n = rcu_dereference_protected(*np,
+ lockdep_is_held(&tbl->lock))) != NULL) {
+ if (n == ndel) {
+ retval = neigh_del(n, 0, np);
+ write_unlock_bh(&tbl->lock);
+ return retval;
+ }
+ np = &n->next;
+ }
+ write_unlock_bh(&tbl->lock);
+ return retval;
+}
+EXPORT_SYMBOL(neigh_remove_one);
+
static int neigh_forced_gc(struct neigh_table *tbl)
{
int shrunk = 0;
@@ -140,19 +189,10 @@ static int neigh_forced_gc(struct neigh_table *tbl)
* - nobody refers to it.
* - it is not permanent
*/
- write_lock(&n->lock);
- if (atomic_read(&n->refcnt) == 1 &&
- !(n->nud_state & NUD_PERMANENT)) {
- rcu_assign_pointer(*np,
- rcu_dereference_protected(n->next,
- lockdep_is_held(&tbl->lock)));
- n->dead = 1;
- shrunk = 1;
- write_unlock(&n->lock);
- neigh_cleanup_and_release(n);
+ if (neigh_del(n, NUD_PERMANENT, np)) {
+ shrunk = 1;
continue;
}
- write_unlock(&n->lock);
np = &n->next;
}
}
@@ -1650,6 +1690,7 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh,
NEIGH_UPDATE_F_ADMIN,
NETLINK_CB(skb).portid);
neigh_release(neigh);
+ neigh_remove_one(neigh, tbl);
out:
return err;
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index e9f3386..5264004 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1120,6 +1120,7 @@ static int arp_invalidate(struct net_device *dev, __be32 ip)
NEIGH_UPDATE_F_OVERRIDE|
NEIGH_UPDATE_F_ADMIN, 0);
neigh_release(neigh);
+ neigh_remove_one(neigh, &arp_tbl);
}
return err;
--
1.7.1
Powered by blists - more mailing lists