openvswitch: Use exact lookup for flow_get and flow_del.

Due to the race condition in userspace, there is chance that two
overlapping megaflows could be installed in datapath.  And this
causes userspace unable to delete the less inclusive megaflow flow
even after it timeout, since the flow_del logic will stop at the
first match of masked flow.

This commit fixes the bug by making the kernel flow_del and flow_get
logic check all masks in that case.

Introduced by 07f23f89e (openvswitch: Mega flow implementation).

Signed-off-by: Alex Wang <alexw@nicira.com>
Acked-by: Andy Zhou <azhou@nicira.com>
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index a863678c50acce3b6acaa5bc58c946c0f9322de1..9db4bf6740d1e1dc08c60200f1fe8f82f4a370d5 100644 (file)
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -889,8 +889,11 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
                }
                /* The unmasked key has to be the same for flow updates. */
                if (unlikely(!ovs_flow_cmp_unmasked_key(flow, &match))) {
-                       error = -EEXIST;
-                       goto err_unlock_ovs;
+                       flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
+                       if (!flow) {
+                               error = -ENOENT;
+                               goto err_unlock_ovs;
+                       }
                }
                /* Update actions. */
                old_acts = ovsl_dereference(flow->sf_acts);
@@ -981,16 +984,12 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
                goto err_unlock_ovs;
        }
        /* Check that the flow exists. */
-       flow = ovs_flow_tbl_lookup(&dp->table, &key);
+       flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
        if (unlikely(!flow)) {
                error = -ENOENT;
                goto err_unlock_ovs;
        }
-       /* The unmasked key has to be the same for flow updates. */
-       if (unlikely(!ovs_flow_cmp_unmasked_key(flow, &match))) {
-               error = -EEXIST;
-               goto err_unlock_ovs;
-       }
+
        /* Update actions, if present. */
        if (likely(acts)) {
                old_acts = ovsl_dereference(flow->sf_acts);
@@ -1063,8 +1062,8 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info)
                goto unlock;
        }
 
-       flow = ovs_flow_tbl_lookup(&dp->table, &key);
-       if (!flow || !ovs_flow_cmp_unmasked_key(flow, &match)) {
+       flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
+       if (!flow) {
                err = -ENOENT;
                goto unlock;
        }
@@ -1113,8 +1112,8 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
                goto unlock;
        }
 
-       flow = ovs_flow_tbl_lookup(&dp->table, &key);
-       if (unlikely(!flow || !ovs_flow_cmp_unmasked_key(flow, &match))) {
+       flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
+       if (unlikely(!flow)) {
                err = -ENOENT;
                goto unlock;
        }

diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index 574c3abc9b307ef6609f8f8dc09ade4b3253b814..cf2d853646f05dc61a1c8f9093782196860ab9bc 100644 (file)
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -456,6 +456,22 @@ struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl,
        return ovs_flow_tbl_lookup_stats(tbl, key, &n_mask_hit);
 }
 
+struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl,
+                                         struct sw_flow_match *match)
+{
+       struct table_instance *ti = rcu_dereference_ovsl(tbl->ti);
+       struct sw_flow_mask *mask;
+       struct sw_flow *flow;
+
+       /* Always called under ovs-mutex. */
+       list_for_each_entry(mask, &tbl->mask_list, list) {
+               flow = masked_flow_lookup(ti, match->key, mask);
+               if (flow && ovs_flow_cmp_unmasked_key(flow, match))  /* Found */
+                       return flow;
+       }
+       return NULL;
+}
+
 int ovs_flow_tbl_num_masks(const struct flow_table *table)
 {
        struct sw_flow_mask *mask;

diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h
index ca8a5820f6153f67fb9ad987c4c156be882c92ea..5918bff7f3f6cfee2fd58bcd15101446b44469d8 100644 (file)
--- a/net/openvswitch/flow_table.h
+++ b/net/openvswitch/flow_table.h
@@ -76,7 +76,8 @@ struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *,
                                    u32 *n_mask_hit);
 struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *,
                                    const struct sw_flow_key *);
-
+struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl,
+                                         struct sw_flow_match *match);
 bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
                               struct sw_flow_match *match);