[ovs-dev] [PATCH V2 3/4] datapath: Convert mask list in mask array.

Pravin B Shelar pshelar at nicira.com
Wed Apr 23 15:49:44 UTC 2014


mask caches index of mask in mask_list.  On packet recv OVS
need to traverse mask-list to get cached mask.  Therefore array
is better for retrieving cached mask.  This also allows better
cache replacement algorithm by directly checking mask's existence.

Signed-off-by: Pravin B Shelar <pshelar at nicira.com>
---
 datapath/flow.h       |    1 -
 datapath/flow_table.c |  200 ++++++++++++++++++++++++++++++++++++++-----------
 datapath/flow_table.h |    8 +-
 3 files changed, 163 insertions(+), 46 deletions(-)

diff --git a/datapath/flow.h b/datapath/flow.h
index d05a9f4..2018691 100644
--- a/datapath/flow.h
+++ b/datapath/flow.h
@@ -127,7 +127,6 @@ struct sw_flow_key_range {
 struct sw_flow_mask {
 	int ref_count;
 	struct rcu_head rcu;
-	struct list_head list;
 	struct sw_flow_key_range range;
 	struct sw_flow_key key;
 };
diff --git a/datapath/flow_table.c b/datapath/flow_table.c
index cc0eaf2..c8bd9d1 100644
--- a/datapath/flow_table.c
+++ b/datapath/flow_table.c
@@ -47,6 +47,7 @@
 #include "vlan.h"
 
 #define TBL_MIN_BUCKETS		1024
+#define MASK_ARRAY_SIZE_MIN	16
 #define REHASH_INTERVAL		(10 * 60 * HZ)
 
 #define MC_HASH_SHIFT		8
@@ -211,26 +212,83 @@ static struct table_instance *table_instance_alloc(int new_size)
 	return ti;
 }
 
+static void mask_array_rcu_cb(struct rcu_head *rcu)
+{
+	struct mask_array *ma = container_of(rcu, struct mask_array, rcu);
+
+	kfree(ma);
+}
+
+static struct mask_array *tbl_mask_array_alloc(int size)
+{
+	struct mask_array *new;
+
+	new = kzalloc(sizeof(struct mask_array) +
+		      sizeof(struct sw_flow_mask *) * size, GFP_KERNEL);
+	if (!new)
+		return NULL;
+
+	new->count = 0;
+	new->max = size;
+
+	return new;
+}
+
+static int tbl_mask_array_realloc(struct flow_table *tbl, int size)
+{
+	struct mask_array *old;
+	struct mask_array *new;
+
+	new = tbl_mask_array_alloc(size);
+	if (!new)
+		return -ENOMEM;
+
+	old = ovsl_dereference(tbl->mask_array);
+	if (old) {
+		int i;
+
+		for (i = 0; i < old->max; i++) {
+			if (old->masks[i])
+				new->masks[new->count++] = old->masks[i];
+		}
+	}
+	rcu_assign_pointer(tbl->mask_array, new);
+
+	if (old)
+		call_rcu(&old->rcu, mask_array_rcu_cb);
+
+	return 0;
+}
+
 int ovs_flow_tbl_init(struct flow_table *table)
 {
 	struct table_instance *ti;
+	struct mask_array *ma;
 
 	table->mask_cache = __alloc_percpu(sizeof(struct mask_cache_entry) *
 					  MC_HASH_ENTRIES, __alignof__(struct mask_cache_entry));
 	if (!table->mask_cache)
 		return -ENOMEM;
 
+	ma = tbl_mask_array_alloc(MASK_ARRAY_SIZE_MIN);
+	if (!ma)
+		goto free_mask_cache;
+
 	ti = table_instance_alloc(TBL_MIN_BUCKETS);
-	if (!ti) {
-		free_percpu(table->mask_cache);
-		return -ENOMEM;
-	}
+	if (!ti)
+		goto free_mask_array;
 
 	rcu_assign_pointer(table->ti, ti);
-	INIT_LIST_HEAD(&table->mask_list);
+	rcu_assign_pointer(table->mask_array, ma);
 	table->last_rehash = jiffies;
 	table->count = 0;
 	return 0;
+
+free_mask_array:
+	kfree((struct mask_array __force *)table->mask_array);
+free_mask_cache:
+	free_percpu(table->mask_cache);
+	return -ENOMEM;
 }
 
 static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu)
@@ -276,6 +334,7 @@ void ovs_flow_tbl_destroy(struct flow_table *table)
 	struct table_instance *ti = (struct table_instance __force *)table->ti;
 
 	free_percpu(table->mask_cache);
+	kfree((struct mask_array __force *)table->mask_array);
 	table_instance_destroy(ti, false);
 }
 
@@ -457,17 +516,27 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
 
 static struct sw_flow *flow_lookup(struct flow_table *tbl,
 				   struct table_instance *ti,
+				   struct mask_array *ma,
 				   const struct sw_flow_key *key,
-				   u32 *n_mask_hit)
+				   u32 *n_mask_hit,
+				   u32 *index)
 {
-	struct sw_flow_mask *mask;
 	struct sw_flow *flow;
+	int i;
 
-	list_for_each_entry_rcu(mask, &tbl->mask_list, list) {
-		flow = masked_flow_lookup(ti, key, mask, n_mask_hit);
-		if (flow)  /* Found */
-			return flow;
+	for (i = 0; i < ma->max; i++) {
+		struct sw_flow_mask *mask;
+
+		mask = rcu_dereference_ovsl(ma->masks[i]);
+		if (mask) {
+			flow = masked_flow_lookup(ti, key, mask, n_mask_hit);
+			if (flow) { /* Found */
+				*index = i;
+				return flow;
+			}
+		}
 	}
+
 	return NULL;
 }
 
@@ -483,6 +552,7 @@ struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *tbl,
 					  u32 skb_hash,
 					  u32 *n_mask_hit)
 {
+	struct mask_array *ma = rcu_dereference_ovsl(tbl->mask_array);
 	struct table_instance *ti = rcu_dereference_ovsl(tbl->ti);
 	struct mask_cache_entry  *entries, *ce, *del;
 	struct sw_flow *flow;
@@ -490,8 +560,11 @@ struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *tbl,
 	int seg;
 
 	*n_mask_hit = 0;
-	if (unlikely(!skb_hash))
-		return flow_lookup(tbl, ti, key, n_mask_hit);
+	if (unlikely(!skb_hash)) {
+		u32 __always_unused mask_index;
+
+		return flow_lookup(tbl, ti, ma, key, n_mask_hit, &mask_index);
+	}
 
 	del = NULL;
 	entries = this_cpu_ptr(tbl->mask_cache);
@@ -504,36 +577,33 @@ struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *tbl,
 
 		if (ce->skb_hash == skb_hash) {
 			struct sw_flow_mask *mask;
-			int i;
+			struct sw_flow *flow;
 
-			i = 0;
-			list_for_each_entry_rcu(mask, &tbl->mask_list, list) {
-				if (ce->mask_index == i++) {
-					flow = masked_flow_lookup(ti, key, mask,
-								  n_mask_hit);
-					if (flow)  /* Found */
-						return flow;
+			mask = rcu_dereference_ovsl(ma->masks[ce->mask_index]);
+			if (mask) {
+				flow = masked_flow_lookup(ti, key, mask,
+							  n_mask_hit);
+				if (flow)  /* Found */
+					return flow;
 
-					break;
-				}
 			}
 			del = ce;
 			break;
 		}
 
-		if (!del || (del->skb_hash && !ce->skb_hash)) {
+		if (!del || (del->skb_hash && !ce->skb_hash) ||
+		    (rcu_dereference_ovsl(ma->masks[del->mask_index]) &&
+		    !rcu_dereference_ovsl(ma->masks[ce->mask_index]))) {
 			del = ce;
 		}
 
 		hash >>= MC_HASH_SHIFT;
 	}
 
-	flow = flow_lookup(tbl, ti, key, n_mask_hit);
-
-	if (flow) {
+	flow = flow_lookup(tbl, ti, ma, key, n_mask_hit, &del->mask_index);
+	if (flow)
 		del->skb_hash = skb_hash;
-		del->mask_index = (*n_mask_hit - 1);
-	}
+
 	return flow;
 }
 
@@ -541,21 +611,20 @@ struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl,
 				    const struct sw_flow_key *key)
 {
 	struct table_instance *ti = rcu_dereference_ovsl(tbl->ti);
+	struct mask_array *ma = rcu_dereference_ovsl(tbl->mask_array);
 	u32 __always_unused n_mask_hit;
+	u32 __always_unused index;
 
 	n_mask_hit = 0;
-	return flow_lookup(tbl, ti, key, &n_mask_hit);
+	return flow_lookup(tbl, ti, ma, key, &n_mask_hit, &index);
 }
 
 int ovs_flow_tbl_num_masks(const struct flow_table *table)
 {
-	struct sw_flow_mask *mask;
-	int num = 0;
-
-	list_for_each_entry(mask, &table->mask_list, list)
-		num++;
+	struct mask_array *ma;
 
-	return num;
+	ma = rcu_dereference_ovsl(table->mask_array);
+	return ma->count;
 }
 
 static struct table_instance *table_instance_expand(struct table_instance *ti)
@@ -575,7 +644,19 @@ static void flow_mask_remove(struct flow_table *tbl, struct sw_flow_mask *mask)
 		mask->ref_count--;
 
 		if (!mask->ref_count) {
-			list_del_rcu(&mask->list);
+			struct mask_array *ma;
+			int i;
+
+			ma = ovsl_dereference(tbl->mask_array);
+			for (i = 0; i < ma->max; i++) {
+				if (mask == ovsl_dereference(ma->masks[i])) {
+					RCU_INIT_POINTER(ma->masks[i], NULL);
+					ma->count--;
+					goto free;
+				}
+			}
+			BUG();
+free:
 			call_rcu(&mask->rcu, rcu_free_sw_flow_mask_cb);
 		}
 	}
@@ -620,13 +701,16 @@ static bool mask_equal(const struct sw_flow_mask *a,
 static struct sw_flow_mask *flow_mask_find(const struct flow_table *tbl,
 					   const struct sw_flow_mask *mask)
 {
-	struct list_head *ml;
+	struct mask_array *ma;
+	int i;
+
+	ma = ovsl_dereference(tbl->mask_array);
+	for (i = 0; i < ma->max; i++) {
+		struct sw_flow_mask *t;
 
-	list_for_each(ml, &tbl->mask_list) {
-		struct sw_flow_mask *m;
-		m = container_of(ml, struct sw_flow_mask, list);
-		if (mask_equal(mask, m))
-			return m;
+		t = ovsl_dereference(ma->masks[i]);
+		if (t && mask_equal(mask, t))
+			return t;
 	}
 
 	return NULL;
@@ -637,15 +721,43 @@ static int flow_mask_insert(struct flow_table *tbl, struct sw_flow *flow,
 			    struct sw_flow_mask *new)
 {
 	struct sw_flow_mask *mask;
+
 	mask = flow_mask_find(tbl, new);
 	if (!mask) {
+		struct mask_array *ma;
+		int i;
+
 		/* Allocate a new mask if none exsits. */
 		mask = mask_alloc();
 		if (!mask)
 			return -ENOMEM;
+
 		mask->key = new->key;
 		mask->range = new->range;
-		list_add_tail_rcu(&mask->list, &tbl->mask_list);
+
+		/* Add mask to mask-list. */
+		ma = ovsl_dereference(tbl->mask_array);
+		if (ma->count >= ma->max) {
+			int err;
+
+			err = tbl_mask_array_realloc(tbl, ma->max +
+							MASK_ARRAY_SIZE_MIN);
+			if (err) {
+				kfree(mask);
+				return err;
+			}
+			ma = ovsl_dereference(tbl->mask_array);
+		}
+		for (i = 0; i < ma->max; i++) {
+			const struct sw_flow_mask *t;
+
+			t = ovsl_dereference(ma->masks[i]);
+			if (!t) {
+				rcu_assign_pointer(ma->masks[i], mask);
+				ma->count++;
+				break;
+			}
+		}
 	} else {
 		BUG_ON(!mask->ref_count);
 		mask->ref_count++;
diff --git a/datapath/flow_table.h b/datapath/flow_table.h
index 281d1da..ee86953 100644
--- a/datapath/flow_table.h
+++ b/datapath/flow_table.h
@@ -41,6 +41,12 @@ struct mask_cache_entry {
 	u32 mask_index;
 };
 
+struct mask_array {
+	struct rcu_head rcu;
+	int count, max;
+	struct sw_flow_mask __rcu *masks[];
+};
+
 struct table_instance {
 	struct flex_array *buckets;
 	unsigned int n_buckets;
@@ -53,7 +59,7 @@ struct table_instance {
 struct flow_table {
 	struct table_instance __rcu *ti;
 	struct mask_cache_entry __percpu *mask_cache;
-	struct list_head mask_list;
+	struct mask_array __rcu *mask_array;
 	unsigned long last_rehash;
 	unsigned int count;
 };
-- 
1.7.9.5




More information about the dev mailing list