From: Tonghao Zhang
The idea of this optimization comes from a patch which
is committed in 2014, openvswitch community. The author
is Pravin B Shelar. In order to get high performance, I
implement it again. Later patches will use it.
Pravin B Shelar, says:
| On every packet OVS needs to lookup flow-table with every
| mask until it finds a match. The packet flow-key is first
| masked with mask in the list and then the masked key is
| looked up in flow-table. Therefore number of masks can
| affect packet processing performance.
Link:
https://github.com/openvswitch/ovs/commit/5604935e4e1cbc16611d2d97f50b717aa31e8ec5
Signed-off-by: Tonghao Zhang
Tested-by: Greg Rose
Acked-by: William Tu
---
net/openvswitch/datapath.c | 3 +-
net/openvswitch/flow_table.c | 109 +--
net/openvswitch/flow_table.h | 11 -
3 files changed, 107 insertions(+), 16 deletions(-)
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index f30e406..9fea7e1 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -227,7 +227,8 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct
sw_flow_key *key)
stats = this_cpu_ptr(dp->stats_percpu);
/* Look up flow. */
- flow = ovs_flow_tbl_lookup_stats(&dp->table, key, &n_mask_hit);
+ flow = ovs_flow_tbl_lookup_stats(&dp->table, key, skb_get_hash(skb),
+&n_mask_hit);
if (unlikely(!flow)) {
struct dp_upcall_info upcall;
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index cf3582c..3d515c0 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -36,6 +36,10 @@
#define TBL_MIN_BUCKETS1024
#define REHASH_INTERVAL(10 * 60 * HZ)
+#define MC_HASH_SHIFT 8
+#define MC_HASH_ENTRIES(1u << MC_HASH_SHIFT)
+#define MC_HASH_SEGS ((sizeof(uint32_t) * 8) / MC_HASH_SHIFT)
+
static struct kmem_cache *flow_cache;
struct kmem_cache *flow_stats_cache __read_mostly;
@@ -168,10 +172,15 @@ int ovs_flow_tbl_init(struct flow_table *table)
{
struct table_instance *ti, *ufid_ti;
- ti = table_instance_alloc(TBL_MIN_BUCKETS);
+ table->mask_cache = __alloc_percpu(sizeof(struct mask_cache_entry) *
+ MC_HASH_ENTRIES,
+ __alignof__(struct
mask_cache_entry));
+ if (!table->mask_cache)
+ return -ENOMEM;
+ ti = table_instance_alloc(TBL_MIN_BUCKETS);
if (!ti)
- return -ENOMEM;
+ goto free_mask_cache;
ufid_ti = table_instance_alloc(TBL_MIN_BUCKETS);
if (!ufid_ti)
@@ -187,6 +196,8 @@ int ovs_flow_tbl_init(struct flow_table *table)
free_ti:
__table_instance_destroy(ti);
+free_mask_cache:
+ free_percpu(table->mask_cache);
return -ENOMEM;
}
@@ -243,6 +254,7 @@ void ovs_flow_tbl_destroy(struct flow_table *table)
struct table_instance *ti = rcu_dereference_raw(table->ti);
struct table_instance *ufid_ti = rcu_dereference_raw(table->ufid_ti);
+ free_percpu(table->mask_cache);
table_instance_destroy(ti, ufid_ti, false);
}
@@ -425,7 +437,8 @@ static bool ovs_flow_cmp_unmasked_key(const struct sw_flow
*flow,
static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
const struct sw_flow_key *unmasked,
- const struct sw_flow_mask *mask)
+ const struct sw_flow_mask *mask,
+ u32 *n_mask_hit)
{
struct sw_flow *flow;
struct hlist_head *head;
@@ -435,6 +448,8 @@ static struct sw_flow *masked_flow_lookup(struct
table_instance *ti,
ovs_flow_mask_key(&masked_key, unmasked, false, mask);
hash = flow_hash(&masked_key, &mask->range);
head = find_bucket(ti, hash);
+ (*n_mask_hit)++;
+
hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver]) {
if (flow->mask == mask && flow->flow_table.hash == hash &&
flow_cmp_masked_key(flow, &masked_key, &mask->range))
@@ -443,30 +458,97 @@ static struct sw_flow *masked_flow_lookup(struct
table_instance *ti,
return NULL;
}
-struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *tbl,
- const struct sw_flow_key *key,
- u32 *n_mask_hit)
+static struct sw_flow *flow_lookup(struct flow_table *tbl,
+ struct table_instance *ti,
+ const struct sw_flow_key *key,
+ u32 *n_mask_hit)
{
- struct table_instance *ti = rcu_dereference_ovsl(tbl->ti);
struct sw_flow_mask *mask;
struct sw_flow *flow;
- *n
