flow: virtualize flow cache entry methods

This allows to validate the cached object before returning it.
It also allows to destruct object properly, if the last reference
was held in flow cache. This is also a prepartion for caching
bundles in the flow cache.

In return for virtualizing the methods, we save on:
- not having to regenerate the whole flow cache on policy removal:
  each flow matching a killed policy gets refreshed as the getter
  function notices it smartly.
- we do not have to call flow_cache_flush from policy gc, since the
  flow cache now properly deletes the object if it had any references

Signed-off-by: Timo Teras <timo.teras@iki.fi>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 74 insertions, 38 deletions

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 82789cf1c632..7722baeb140d 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -216,6 +216,35 @@ expired:
 	xfrm_pol_put(xp);
 }
 
+static struct flow_cache_object *xfrm_policy_flo_get(struct flow_cache_object *flo)
+{
+	struct xfrm_policy *pol = container_of(flo, struct xfrm_policy, flo);
+
+	if (unlikely(pol->walk.dead))
+		flo = NULL;
+	else
+		xfrm_pol_hold(pol);
+
+	return flo;
+}
+
+static int xfrm_policy_flo_check(struct flow_cache_object *flo)
+{
+	struct xfrm_policy *pol = container_of(flo, struct xfrm_policy, flo);
+
+	return !pol->walk.dead;
+}
+
+static void xfrm_policy_flo_delete(struct flow_cache_object *flo)
+{
+	xfrm_pol_put(container_of(flo, struct xfrm_policy, flo));
+}
+
+static const struct flow_cache_ops xfrm_policy_fc_ops = {
+	.get = xfrm_policy_flo_get,
+	.check = xfrm_policy_flo_check,
+	.delete = xfrm_policy_flo_delete,
+};
 
 /* Allocate xfrm_policy. Not used here, it is supposed to be used by pfkeyv2
  * SPD calls.
@@ -236,6 +265,7 @@ struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp)
 		atomic_set(&policy->refcnt, 1);
 		setup_timer(&policy->timer, xfrm_policy_timer,
 				(unsigned long)policy);
+		policy->flo.ops = &xfrm_policy_fc_ops;
 	}
 	return policy;
 }
@@ -269,9 +299,6 @@ static void xfrm_policy_gc_kill(struct xfrm_policy *policy)
 	if (del_timer(&policy->timer))
 		atomic_dec(&policy->refcnt);
 
-	if (atomic_read(&policy->refcnt) > 1)
-		flow_cache_flush();
-
 	xfrm_pol_put(policy);
 }
 
@@ -661,10 +688,8 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type,
 	}
 	write_unlock_bh(&xfrm_policy_lock);
 
-	if (ret && delete) {
-		atomic_inc(&flow_cache_genid);
+	if (ret && delete)
 		xfrm_policy_kill(ret);
-	}
 	return ret;
 }
 EXPORT_SYMBOL(xfrm_policy_bysel_ctx);
@@ -703,10 +728,8 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type,
 	}
 	write_unlock_bh(&xfrm_policy_lock);
 
-	if (ret && delete) {
-		atomic_inc(&flow_cache_genid);
+	if (ret && delete)
 		xfrm_policy_kill(ret);
-	}
 	return ret;
 }
 EXPORT_SYMBOL(xfrm_policy_byid);
@@ -822,7 +845,6 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info)
 	}
 	if (!cnt)
 		err = -ESRCH;
-	atomic_inc(&flow_cache_genid);
 out:
 	write_unlock_bh(&xfrm_policy_lock);
 	return err;
@@ -976,32 +998,35 @@ fail:
 	return ret;
 }
 
-static int xfrm_policy_lookup(struct net *net, struct flowi *fl, u16 family,
-			      u8 dir, void **objp, atomic_t **obj_refp)
+static struct flow_cache_object *
+xfrm_policy_lookup(struct net *net, struct flowi *fl, u16 family,
+		   u8 dir, struct flow_cache_object *old_obj, void *ctx)
 {
 	struct xfrm_policy *pol;
-	int err = 0;
+
+	if (old_obj)
+		xfrm_pol_put(container_of(old_obj, struct xfrm_policy, flo));
 
 #ifdef CONFIG_XFRM_SUB_POLICY
 	pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family, dir);
-	if (IS_ERR(pol)) {
-		err = PTR_ERR(pol);
-		pol = NULL;
-	}
-	if (pol || err)
-		goto end;
+	if (IS_ERR(pol))
+		return ERR_CAST(pol);
+	if (pol)
+		goto found;
 #endif
 	pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family, dir);
-	if (IS_ERR(pol)) {
-		err = PTR_ERR(pol);
-		pol = NULL;
-	}
-#ifdef CONFIG_XFRM_SUB_POLICY
-end:
-#endif
-	if ((*objp = (void *) pol) != NULL)
-		*obj_refp = &pol->refcnt;
-	return err;
+	if (IS_ERR(pol))
+		return ERR_CAST(pol);
+	if (pol)
+		goto found;
+	return NULL;
+
+found:
+	/* Resolver returns two references:
+	 * one for cache and one for caller of flow_cache_lookup() */
+	xfrm_pol_hold(pol);
+
+	return &pol->flo;
 }
 
 static inline int policy_to_flow_dir(int dir)
@@ -1091,8 +1116,6 @@ int xfrm_policy_delete(struct xfrm_policy *pol, int dir)
 	pol = __xfrm_policy_unlink(pol, dir);
 	write_unlock_bh(&xfrm_policy_lock);
 	if (pol) {
-		if (dir < XFRM_POLICY_MAX)
-			atomic_inc(&flow_cache_genid);
 		xfrm_policy_kill(pol);
 		return 0;
 	}
@@ -1578,18 +1601,24 @@ restart:
 	}
 
 	if (!policy) {
+		struct flow_cache_object *flo;
+
 		/* To accelerate a bit...  */
 		if ((dst_orig->flags & DST_NOXFRM) ||
 		    !net->xfrm.policy_count[XFRM_POLICY_OUT])
 			goto nopol;
 
-		policy = flow_cache_lookup(net, fl, dst_orig->ops->family,
-					   dir, xfrm_policy_lookup);
-		err = PTR_ERR(policy);
-		if (IS_ERR(policy)) {
+		flo = flow_cache_lookup(net, fl, dst_orig->ops->family,
+					dir, xfrm_policy_lookup, NULL);
+		err = PTR_ERR(flo);
+		if (IS_ERR(flo)) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR);
 			goto dropdst;
 		}
+		if (flo)
+			policy = container_of(flo, struct xfrm_policy, flo);
+		else
+			policy = NULL;
 	}
 
 	if (!policy)
@@ -1939,9 +1968,16 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 		}
 	}
 
-	if (!pol)
-		pol = flow_cache_lookup(net, &fl, family, fl_dir,
-					xfrm_policy_lookup);
+	if (!pol) {
+		struct flow_cache_object *flo;
+
+		flo = flow_cache_lookup(net, &fl, family, fl_dir,
+					xfrm_policy_lookup, NULL);
+		if (IS_ERR_OR_NULL(flo))
+			pol = ERR_CAST(flo);
+		else
+			pol = container_of(flo, struct xfrm_policy, flo);
+	}
 
 	if (IS_ERR(pol)) {
 		XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR);