[PATCH 10/17] xfrm: policy: add sequence count to sync with hash resize

[Steffen Klassert]

From: Florian Westphal <f...@strlen.de>

Once xfrm_policy_lookup_bytype doesn't grab xfrm_policy_lock anymore its
possible for a hash resize to occur in parallel.

Use sequence counter to block lookup in case a resize is in
progress and to also re-lookup in case hash table was altered
in the mean time (might cause use to not find the best-match).

Signed-off-by: Florian Westphal <f...@strlen.de>
Signed-off-by: Steffen Klassert <steffen.klass...@secunet.com>
---
 net/xfrm/xfrm_policy.c | 21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 4a8d90a..576d903 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -49,6 +49,7 @@ static struct xfrm_policy_afinfo __rcu 
*xfrm_policy_afinfo[NPROTO]
                                                __read_mostly;
 
 static struct kmem_cache *xfrm_dst_cache __read_mostly;
+static __read_mostly seqcount_t xfrm_policy_hash_generation;
 
 static void xfrm_init_pmtu(struct dst_entry *dst);
 static int stale_bundle(struct dst_entry *dst);
@@ -479,6 +480,10 @@ static void xfrm_bydst_resize(struct net *net, int dir)
                return;
 
        write_lock_bh(&net->xfrm.xfrm_policy_lock);
+       write_seqcount_begin(&xfrm_policy_hash_generation);
+
+       odst = rcu_dereference_protected(net->xfrm.policy_bydst[dir].table,
+                               lockdep_is_held(&net->xfrm.xfrm_policy_lock));
 
        odst = rcu_dereference_protected(net->xfrm.policy_bydst[dir].table,
                                lockdep_is_held(&net->xfrm.xfrm_policy_lock));
@@ -489,6 +494,7 @@ static void xfrm_bydst_resize(struct net *net, int dir)
        rcu_assign_pointer(net->xfrm.policy_bydst[dir].table, ndst);
        net->xfrm.policy_bydst[dir].hmask = nhashmask;
 
+       write_seqcount_end(&xfrm_policy_hash_generation);
        write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
        synchronize_rcu();
@@ -1104,7 +1110,8 @@ static struct xfrm_policy 
*xfrm_policy_lookup_bytype(struct net *net, u8 type,
        struct xfrm_policy *pol, *ret;
        const xfrm_address_t *daddr, *saddr;
        struct hlist_head *chain;
-       u32 priority = ~0U;
+       unsigned int sequence;
+       u32 priority;
 
        daddr = xfrm_flowi_daddr(fl, family);
        saddr = xfrm_flowi_saddr(fl, family);
@@ -1112,7 +1119,13 @@ static struct xfrm_policy 
*xfrm_policy_lookup_bytype(struct net *net, u8 type,
                return NULL;
 
        read_lock_bh(&net->xfrm.xfrm_policy_lock);
-       chain = policy_hash_direct(net, daddr, saddr, family, dir);
+ retry:
+       do {
+               sequence = read_seqcount_begin(&xfrm_policy_hash_generation);
+               chain = policy_hash_direct(net, daddr, saddr, family, dir);
+       } while (read_seqcount_retry(&xfrm_policy_hash_generation, sequence));
+
+       priority = ~0U;
        ret = NULL;
        hlist_for_each_entry_rcu(pol, chain, bydst) {
                err = xfrm_policy_match(pol, fl, type, family, dir);
@@ -1148,6 +1161,9 @@ static struct xfrm_policy 
*xfrm_policy_lookup_bytype(struct net *net, u8 type,
                }
        }
 
+       if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence))
+               goto retry;
+
        xfrm_pol_hold(ret);
 fail:
        read_unlock_bh(&net->xfrm.xfrm_policy_lock);
@@ -3090,6 +3106,7 @@ static struct pernet_operations __net_initdata 
xfrm_net_ops = {
 void __init xfrm_init(void)
 {
        register_pernet_subsys(&xfrm_net_ops);
+       seqcount_init(&xfrm_policy_hash_generation);
        xfrm_input_init();
 }
 
-- 
1.9.1