summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
authorJulian Anastasov <ja@ssi.bg>2023-02-02 18:25:51 +0300
committerDavid S. Miller <davem@davemloft.net>2023-02-06 11:44:31 +0300
commitc1d2ecdf5e38e3489ce8328238b558b3b2866fe1 (patch)
tree809a4cf0cfe8d3c15df1e831d0e077555c99c4cb /net/core
parenta05e7a67986c6be900f7d3310fa5bb1e0c55bb4c (diff)
downloadlinux-c1d2ecdf5e38e3489ce8328238b558b3b2866fe1.tar.xz
neigh: make sure used and confirmed times are valid
Entries can linger in cache without timer for days, thanks to the gc_thresh1 limit. As result, without traffic, the confirmed time can be outdated and to appear to be in the future. Later, on traffic, NUD_STALE entries can switch to NUD_DELAY and start the timer which can see the invalid confirmed time and wrongly switch to NUD_REACHABLE state instead of NUD_PROBE. As result, timer is set many days in the future. This is more visible on 32-bit platforms, with higher HZ value. Why this is a problem? While we expect unused entries to expire, such entries stay in REACHABLE state for too long, locked in cache. They are not expired normally, only when cache is full. Problem and the wrong state change reported by Zhang Changzhong: 172.16.1.18 dev bond0 lladdr 0a:0e:0f:01:12:01 ref 1 used 350521/15994171/350520 probes 4 REACHABLE 350520 seconds have elapsed since this entry was last updated, but it is still in the REACHABLE state (base_reachable_time_ms is 30000), preventing lladdr from being updated through probe. Fix it by ensuring timer is started with valid used/confirmed times. Considering the valid time range is LONG_MAX jiffies, we try not to go too much in the past while we are in DELAY/PROBE state. There are also places that need used/updated times to be validated while timer is not running. Reported-by: Zhang Changzhong <zhangchangzhong@huawei.com> Signed-off-by: Julian Anastasov <ja@ssi.bg> Tested-by: Zhang Changzhong <zhangchangzhong@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/core')
-rw-r--r--net/core/neighbour.c18
1 files changed, 15 insertions, 3 deletions
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index f00a79fc301b..4edd2176e238 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -269,7 +269,7 @@ static int neigh_forced_gc(struct neigh_table *tbl)
(n->nud_state == NUD_NOARP) ||
(tbl->is_multicast &&
tbl->is_multicast(n->primary_key)) ||
- time_after(tref, n->updated))
+ !time_in_range(n->updated, tref, jiffies))
remove = true;
write_unlock(&n->lock);
@@ -289,7 +289,17 @@ static int neigh_forced_gc(struct neigh_table *tbl)
static void neigh_add_timer(struct neighbour *n, unsigned long when)
{
+ /* Use safe distance from the jiffies - LONG_MAX point while timer
+ * is running in DELAY/PROBE state but still show to user space
+ * large times in the past.
+ */
+ unsigned long mint = jiffies - (LONG_MAX - 86400 * HZ);
+
neigh_hold(n);
+ if (!time_in_range(n->confirmed, mint, jiffies))
+ n->confirmed = mint;
+ if (time_before(n->used, n->confirmed))
+ n->used = n->confirmed;
if (unlikely(mod_timer(&n->timer, when))) {
printk("NEIGH: BUG, double timer add, state is %x\n",
n->nud_state);
@@ -1001,12 +1011,14 @@ static void neigh_periodic_work(struct work_struct *work)
goto next_elt;
}
- if (time_before(n->used, n->confirmed))
+ if (time_before(n->used, n->confirmed) &&
+ time_is_before_eq_jiffies(n->confirmed))
n->used = n->confirmed;
if (refcount_read(&n->refcnt) == 1 &&
(state == NUD_FAILED ||
- time_after(jiffies, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) {
+ !time_in_range_open(jiffies, n->used,
+ n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) {
*np = n->next;
neigh_mark_dead(n);
write_unlock(&n->lock);