#include <linux/if_vlan.h>
#include <net/llc_pdu.h>
#include <linux/kernel.h>
-#include <linux/hash.h>
+#include <linux/jhash.h>
#include <linux/jiffies.h>
#include <linux/llc.h>
#include <linux/module.h>
flow->sf_acts = NULL;
flow->mask = NULL;
+ flow->id.ufid_len = 0;
+ flow->id.unmasked_key = NULL;
flow->stats_last_writer = NUMA_NO_NODE;
/* Initialize the default stat node. */
return ERR_PTR(-ENOMEM);
}
-int ovs_flow_tbl_count(struct flow_table *table)
+int ovs_flow_tbl_count(const struct flow_table *table)
{
return table->count;
}
{
int node;
- kfree((struct sw_flow_actions __force *)flow->sf_acts);
+ if (ovs_identifier_is_key(&flow->id))
+ kfree(flow->id.unmasked_key);
+ kfree(rcu_dereference_raw(flow->sf_acts));
for_each_node(node)
if (flow->stats[node])
kmem_cache_free(flow_stats_cache,
- (struct flow_stats __force *)flow->stats[node]);
+ rcu_dereference_raw(flow->stats[node]));
kmem_cache_free(flow_cache, flow);
}
{
struct mask_array *new;
+ size = max(MASK_ARRAY_SIZE_MIN, size);
new = kzalloc(sizeof(struct mask_array) +
sizeof(struct sw_flow_mask *) * size, GFP_KERNEL);
if (!new)
old = ovsl_dereference(tbl->mask_array);
if (old) {
- int i;
+ int i, count = 0;
for (i = 0; i < old->max; i++) {
- if (old->masks[i])
- new->masks[new->count++] = old->masks[i];
+ if (ovsl_dereference(old->masks[i]))
+ new->masks[count++] = old->masks[i];
}
+
+ new->count = count;
}
rcu_assign_pointer(tbl->mask_array, new);
int ovs_flow_tbl_init(struct flow_table *table)
{
- struct table_instance *ti;
+ struct table_instance *ti, *ufid_ti;
struct mask_array *ma;
table->mask_cache = __alloc_percpu(sizeof(struct mask_cache_entry) *
if (!ti)
goto free_mask_array;
+ ufid_ti = table_instance_alloc(TBL_MIN_BUCKETS);
+ if (!ufid_ti)
+ goto free_ti;
+
rcu_assign_pointer(table->ti, ti);
+ rcu_assign_pointer(table->ufid_ti, ufid_ti);
rcu_assign_pointer(table->mask_array, ma);
table->last_rehash = jiffies;
table->count = 0;
+ table->ufid_count = 0;
return 0;
+free_ti:
+ __table_instance_destroy(ti);
free_mask_array:
- kfree((struct mask_array __force *)table->mask_array);
+ kfree(ma);
free_mask_cache:
free_percpu(table->mask_cache);
return -ENOMEM;
__table_instance_destroy(ti);
}
-static void table_instance_destroy(struct table_instance *ti, bool deferred)
+static void table_instance_destroy(struct table_instance *ti,
+ struct table_instance *ufid_ti,
+ bool deferred)
{
int i;
if (!ti)
return;
+ BUG_ON(!ufid_ti);
if (ti->keep_flows)
goto skip_flows;
struct hlist_head *head = flex_array_get(ti->buckets, i);
struct hlist_node *n;
int ver = ti->node_ver;
+ int ufid_ver = ufid_ti->node_ver;
- hlist_for_each_entry_safe(flow, n, head, hash_node[ver]) {
- hlist_del_rcu(&flow->hash_node[ver]);
+ hlist_for_each_entry_safe(flow, n, head, flow_table.node[ver]) {
+ hlist_del_rcu(&flow->flow_table.node[ver]);
+ if (ovs_identifier_is_ufid(&flow->id))
+ hlist_del_rcu(&flow->ufid_table.node[ufid_ver]);
ovs_flow_free(flow, deferred);
}
}
skip_flows:
- if (deferred)
+ if (deferred) {
call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb);
- else
+ call_rcu(&ufid_ti->rcu, flow_tbl_destroy_rcu_cb);
+ } else {
__table_instance_destroy(ti);
+ __table_instance_destroy(ufid_ti);
+ }
}
/* No need for locking this function is called from RCU callback or
- * error path. */
+ * error path.
+ */
void ovs_flow_tbl_destroy(struct flow_table *table)
{
- struct table_instance *ti = (struct table_instance __force *)table->ti;
+ 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);
- kfree((struct mask_array __force *)table->mask_array);
- table_instance_destroy(ti, false);
+ kfree(rcu_dereference_raw(table->mask_array));
+ table_instance_destroy(ti, ufid_ti, false);
}
struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *ti,
while (*bucket < ti->n_buckets) {
i = 0;
head = flex_array_get(ti->buckets, *bucket);
- hlist_for_each_entry_rcu(flow, head, hash_node[ver]) {
+ hlist_for_each_entry_rcu(flow, head, flow_table.node[ver]) {
if (i < *last) {
i++;
continue;
(hash & (ti->n_buckets - 1)));
}
-static void table_instance_insert(struct table_instance *ti, struct sw_flow *flow)
+static void table_instance_insert(struct table_instance *ti,
+ struct sw_flow *flow)
+{
+ struct hlist_head *head;
+
+ head = find_bucket(ti, flow->flow_table.hash);
+ hlist_add_head_rcu(&flow->flow_table.node[ti->node_ver], head);
+}
+
+static void ufid_table_instance_insert(struct table_instance *ti,
+ struct sw_flow *flow)
{
struct hlist_head *head;
- head = find_bucket(ti, flow->hash);
- hlist_add_head_rcu(&flow->hash_node[ti->node_ver], head);
+ head = find_bucket(ti, flow->ufid_table.hash);
+ hlist_add_head_rcu(&flow->ufid_table.node[ti->node_ver], head);
}
static void flow_table_copy_flows(struct table_instance *old,
- struct table_instance *new)
+ struct table_instance *new, bool ufid)
{
int old_ver;
int i;
head = flex_array_get(old->buckets, i);
- hlist_for_each_entry(flow, head, hash_node[old_ver])
- table_instance_insert(new, flow);
+ if (ufid)
+ hlist_for_each_entry(flow, head,
+ ufid_table.node[old_ver])
+ ufid_table_instance_insert(new, flow);
+ else
+ hlist_for_each_entry(flow, head,
+ flow_table.node[old_ver])
+ table_instance_insert(new, flow);
}
old->keep_flows = true;
}
static struct table_instance *table_instance_rehash(struct table_instance *ti,
- int n_buckets)
+ int n_buckets, bool ufid)
{
struct table_instance *new_ti;
if (!new_ti)
return NULL;
- flow_table_copy_flows(ti, new_ti);
+ flow_table_copy_flows(ti, new_ti, ufid);
return new_ti;
}
int ovs_flow_tbl_flush(struct flow_table *flow_table)
{
- struct table_instance *old_ti;
- struct table_instance *new_ti;
+ struct table_instance *old_ti, *new_ti;
+ struct table_instance *old_ufid_ti, *new_ufid_ti;
- old_ti = ovsl_dereference(flow_table->ti);
new_ti = table_instance_alloc(TBL_MIN_BUCKETS);
if (!new_ti)
return -ENOMEM;
+ new_ufid_ti = table_instance_alloc(TBL_MIN_BUCKETS);
+ if (!new_ufid_ti)
+ goto err_free_ti;
+
+ old_ti = ovsl_dereference(flow_table->ti);
+ old_ufid_ti = ovsl_dereference(flow_table->ufid_ti);
rcu_assign_pointer(flow_table->ti, new_ti);
+ rcu_assign_pointer(flow_table->ufid_ti, new_ufid_ti);
flow_table->last_rehash = jiffies;
flow_table->count = 0;
+ flow_table->ufid_count = 0;
- table_instance_destroy(old_ti, true);
+ table_instance_destroy(old_ti, old_ufid_ti, true);
return 0;
+
+err_free_ti:
+ __table_instance_destroy(new_ti);
+ return -ENOMEM;
}
-static u32 flow_hash(const struct sw_flow_key *key, int key_start,
- int key_end)
+static u32 flow_hash(const struct sw_flow_key *key,
+ const struct sw_flow_key_range *range)
{
+ int key_start = range->start;
+ int key_end = range->end;
const u32 *hash_key = (const u32 *)((const u8 *)key + key_start);
int hash_u32s = (key_end - key_start) >> 2;
/* Make sure number of hash bytes are multiple of u32. */
BUILD_BUG_ON(sizeof(long) % sizeof(u32));
- return arch_fast_hash2(hash_key, hash_u32s, 0);
+ return jhash2(hash_key, hash_u32s, 0);
}
static int flow_key_start(const struct sw_flow_key *key)
static bool flow_cmp_masked_key(const struct sw_flow *flow,
const struct sw_flow_key *key,
- int key_start, int key_end)
+ const struct sw_flow_key_range *range)
{
- return cmp_key(&flow->key, key, key_start, key_end);
+ return cmp_key(&flow->key, key, range->start, range->end);
}
-bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
- struct sw_flow_match *match)
+static bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
+ const struct sw_flow_match *match)
{
struct sw_flow_key *key = match->key;
int key_start = flow_key_start(key);
int key_end = match->range.end;
- return cmp_key(&flow->unmasked_key, key, key_start, key_end);
+ BUG_ON(ovs_identifier_is_ufid(&flow->id));
+ return cmp_key(flow->id.unmasked_key, key, key_start, key_end);
}
static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
const struct sw_flow_key *unmasked,
- struct sw_flow_mask *mask,
+ const struct sw_flow_mask *mask,
u32 *n_mask_hit)
{
struct sw_flow *flow;
struct hlist_head *head;
- int key_start = mask->range.start;
- int key_end = mask->range.end;
u32 hash;
struct sw_flow_key masked_key;
ovs_flow_mask_key(&masked_key, unmasked, mask);
- hash = flow_hash(&masked_key, key_start, key_end);
+ hash = flow_hash(&masked_key, &mask->range);
head = find_bucket(ti, hash);
(*n_mask_hit)++;
- hlist_for_each_entry_rcu(flow, head, hash_node[ti->node_ver]) {
- if (flow->mask == mask && flow->hash == hash &&
- flow_cmp_masked_key(flow, &masked_key,
- key_start, key_end))
+ 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))
return flow;
}
return NULL;
}
-
+/* Flow lookup does full lookup on flow table. It starts with
+ * mask from index passed in *index.
+ */
static struct sw_flow *flow_lookup(struct flow_table *tbl,
struct table_instance *ti,
- struct mask_array *ma,
+ const struct mask_array *ma,
const struct sw_flow_key *key,
u32 *n_mask_hit,
u32 *index)
{
+ struct sw_flow_mask *mask;
struct sw_flow *flow;
int i;
- for (i = 0; i < ma->max; i++) {
- struct sw_flow_mask *mask;
-
- mask = rcu_dereference_ovsl(ma->masks[i]);
+ if (*index < ma->max) {
+ mask = rcu_dereference_ovsl(ma->masks[*index]);
if (mask) {
flow = masked_flow_lookup(ti, key, mask, n_mask_hit);
- if (flow) { /* Found */
- *index = i;
+ if (flow)
return flow;
- }
+ }
+ }
+
+ for (i = 0; i < ma->max; i++) {
+
+ if (i == *index)
+ continue;
+
+ mask = rcu_dereference_ovsl(ma->masks[i]);
+ if (!mask)
+ continue;
+
+ flow = masked_flow_lookup(ti, key, mask, n_mask_hit);
+ if (flow) { /* Found */
+ *index = i;
+ return flow;
}
}
* cache entry in mask cache.
* This is per cpu cache and is divided in MC_HASH_SEGS segments.
* In case of a hash collision the entry is hashed in next segment.
- * */
+ */
struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *tbl,
const struct sw_flow_key *key,
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 mask_array *ma = rcu_dereference(tbl->mask_array);
+ struct table_instance *ti = rcu_dereference(tbl->ti);
+ struct mask_cache_entry *entries, *ce;
struct sw_flow *flow;
- u32 hash = skb_hash;
+ u32 hash;
int seg;
*n_mask_hit = 0;
if (unlikely(!skb_hash)) {
- u32 __always_unused mask_index;
+ u32 mask_index = 0;
return flow_lookup(tbl, ti, ma, key, n_mask_hit, &mask_index);
}
- del = NULL;
+ /* Pre and post recirulation flows usually have the same skb_hash
+ * value. To avoid hash collisions, rehash the 'skb_hash' with
+ * 'recirc_id'. */
+ if (key->recirc_id)
+ skb_hash = jhash_1word(skb_hash, key->recirc_id);
+
+ ce = NULL;
+ hash = skb_hash;
entries = this_cpu_ptr(tbl->mask_cache);
+ /* Find the cache entry 'ce' to operate on. */
for (seg = 0; seg < MC_HASH_SEGS; seg++) {
- int index;
-
- index = hash & (MC_HASH_ENTRIES - 1);
- ce = &entries[index];
-
- if (ce->skb_hash == skb_hash) {
- struct sw_flow_mask *mask;
-
- 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;
-
- }
- del = ce;
- break;
+ int index = hash & (MC_HASH_ENTRIES - 1);
+ struct mask_cache_entry *e;
+
+ e = &entries[index];
+ if (e->skb_hash == skb_hash) {
+ flow = flow_lookup(tbl, ti, ma, key, n_mask_hit,
+ &e->mask_index);
+ if (!flow)
+ e->skb_hash = 0;
+ return flow;
}
- 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;
- }
+ if (!ce || e->skb_hash < ce->skb_hash)
+ ce = e; /* A better replacement cache candidate. */
hash >>= MC_HASH_SHIFT;
}
- flow = flow_lookup(tbl, ti, ma, key, n_mask_hit, &del->mask_index);
+ /* Cache miss, do full lookup. */
+ flow = flow_lookup(tbl, ti, ma, key, n_mask_hit, &ce->mask_index);
if (flow)
- del->skb_hash = skb_hash;
+ ce->skb_hash = skb_hash;
return flow;
}
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;
+ u32 index = 0;
- n_mask_hit = 0;
return flow_lookup(tbl, ti, ma, key, &n_mask_hit, &index);
}
+struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl,
+ const struct sw_flow_match *match)
+{
+ struct mask_array *ma = ovsl_dereference(tbl->mask_array);
+ int i;
+
+ /* Always called under ovs-mutex. */
+ for (i = 0; i < ma->max; i++) {
+ struct table_instance *ti = ovsl_dereference(tbl->ti);
+ u32 __always_unused n_mask_hit;
+ struct sw_flow_mask *mask;
+ struct sw_flow *flow;
+
+ mask = ovsl_dereference(ma->masks[i]);
+ if (!mask)
+ continue;
+ flow = masked_flow_lookup(ti, match->key, mask, &n_mask_hit);
+ if (flow && ovs_identifier_is_key(&flow->id) &&
+ ovs_flow_cmp_unmasked_key(flow, match))
+ return flow;
+ }
+ return NULL;
+}
+
+static u32 ufid_hash(const struct sw_flow_id *sfid)
+{
+ return jhash(sfid->ufid, sfid->ufid_len, 0);
+}
+
+static bool ovs_flow_cmp_ufid(const struct sw_flow *flow,
+ const struct sw_flow_id *sfid)
+{
+ if (flow->id.ufid_len != sfid->ufid_len)
+ return false;
+
+ return !memcmp(flow->id.ufid, sfid->ufid, sfid->ufid_len);
+}
+
+bool ovs_flow_cmp(const struct sw_flow *flow, const struct sw_flow_match *match)
+{
+ if (ovs_identifier_is_ufid(&flow->id))
+ return flow_cmp_masked_key(flow, match->key, &match->range);
+
+ return ovs_flow_cmp_unmasked_key(flow, match);
+}
+
+struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *tbl,
+ const struct sw_flow_id *ufid)
+{
+ struct table_instance *ti = rcu_dereference_ovsl(tbl->ufid_ti);
+ struct sw_flow *flow;
+ struct hlist_head *head;
+ u32 hash;
+
+ hash = ufid_hash(ufid);
+ head = find_bucket(ti, hash);
+ hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver]) {
+ if (flow->ufid_table.hash == hash &&
+ ovs_flow_cmp_ufid(flow, ufid))
+ return flow;
+ }
+ return NULL;
+}
+
int ovs_flow_tbl_num_masks(const struct flow_table *table)
{
struct mask_array *ma;
return ma->count;
}
-static struct table_instance *table_instance_expand(struct table_instance *ti)
+static struct table_instance *table_instance_expand(struct table_instance *ti,
+ bool ufid)
+{
+ return table_instance_rehash(ti, ti->n_buckets * 2, ufid);
+}
+
+static void tbl_mask_array_delete_mask(struct mask_array *ma,
+ struct sw_flow_mask *mask)
{
- return table_instance_rehash(ti, ti->n_buckets * 2);
+ int i;
+
+ /* Remove the deleted mask pointers from the array */
+ for (i = 0; i < ma->max; i++) {
+ if (mask == ovsl_dereference(ma->masks[i])) {
+ RCU_INIT_POINTER(ma->masks[i], NULL);
+ ma->count--;
+ call_rcu(&mask->rcu, rcu_free_sw_flow_mask_cb);
+ return;
+ }
+ }
+ BUG();
}
/* Remove 'mask' from the mask list, if it is not needed any more. */
if (!mask->ref_count) {
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);
+ tbl_mask_array_delete_mask(ma, mask);
+
+ /* Shrink the mask array if necessary. */
+ if (ma->max >= (MASK_ARRAY_SIZE_MIN * 2) &&
+ ma->count <= (ma->max / 3))
+ tbl_mask_array_realloc(tbl, ma->max / 2);
+
}
}
}
void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow)
{
struct table_instance *ti = ovsl_dereference(table->ti);
+ struct table_instance *ufid_ti = ovsl_dereference(table->ufid_ti);
BUG_ON(table->count == 0);
- hlist_del_rcu(&flow->hash_node[ti->node_ver]);
+ hlist_del_rcu(&flow->flow_table.node[ti->node_ver]);
table->count--;
+ if (ovs_identifier_is_ufid(&flow->id)) {
+ hlist_del_rcu(&flow->ufid_table.node[ufid_ti->node_ver]);
+ table->ufid_count--;
+ }
/* RCU delete the mask. 'flow->mask' is not NULLed, as it should be
- * accessible as long as the RCU read lock is held. */
+ * accessible as long as the RCU read lock is held.
+ */
flow_mask_remove(table, flow->mask);
}
/* Add 'mask' into the mask list, if it is not already there. */
static int flow_mask_insert(struct flow_table *tbl, struct sw_flow *flow,
- struct sw_flow_mask *new)
+ const struct sw_flow_mask *new)
{
struct sw_flow_mask *mask;
int err;
err = tbl_mask_array_realloc(tbl, ma->max +
- MASK_ARRAY_SIZE_MIN);
+ 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;
+ struct sw_flow_mask *t;
t = ovsl_dereference(ma->masks[i]);
if (!t) {
break;
}
}
+
} else {
BUG_ON(!mask->ref_count);
mask->ref_count++;
}
/* Must be called with OVS mutex held. */
-int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
- struct sw_flow_mask *mask)
+static void flow_key_insert(struct flow_table *table, struct sw_flow *flow)
{
struct table_instance *new_ti = NULL;
struct table_instance *ti;
- int err;
-
- err = flow_mask_insert(table, flow, mask);
- if (err)
- return err;
- flow->hash = flow_hash(&flow->key, flow->mask->range.start,
- flow->mask->range.end);
+ flow->flow_table.hash = flow_hash(&flow->key, &flow->mask->range);
ti = ovsl_dereference(table->ti);
table_instance_insert(ti, flow);
table->count++;
/* Expand table, if necessary, to make room. */
if (table->count > ti->n_buckets)
- new_ti = table_instance_expand(ti);
+ new_ti = table_instance_expand(ti, false);
else if (time_after(jiffies, table->last_rehash + REHASH_INTERVAL))
- new_ti = table_instance_rehash(ti, ti->n_buckets);
+ new_ti = table_instance_rehash(ti, ti->n_buckets, false);
if (new_ti) {
rcu_assign_pointer(table->ti, new_ti);
- table_instance_destroy(ti, true);
+ call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb);
table->last_rehash = jiffies;
}
+}
+
+/* Must be called with OVS mutex held. */
+static void flow_ufid_insert(struct flow_table *table, struct sw_flow *flow)
+{
+ struct table_instance *ti;
+
+ flow->ufid_table.hash = ufid_hash(&flow->id);
+ ti = ovsl_dereference(table->ufid_ti);
+ ufid_table_instance_insert(ti, flow);
+ table->ufid_count++;
+
+ /* Expand table, if necessary, to make room. */
+ if (table->ufid_count > ti->n_buckets) {
+ struct table_instance *new_ti;
+
+ new_ti = table_instance_expand(ti, true);
+ if (new_ti) {
+ rcu_assign_pointer(table->ufid_ti, new_ti);
+ call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb);
+ }
+ }
+}
+
+/* Must be called with OVS mutex held. */
+int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
+ const struct sw_flow_mask *mask)
+{
+ int err;
+
+ err = flow_mask_insert(table, flow, mask);
+ if (err)
+ return err;
+ flow_key_insert(table, flow);
+ if (ovs_identifier_is_ufid(&flow->id))
+ flow_ufid_insert(table, flow);
+
return 0;
}
/* Initializes the flow module.
- * Returns zero if successful or a negative error code. */
+ * Returns zero if successful or a negative error code.
+ */
int ovs_flow_init(void)
{
BUILD_BUG_ON(__alignof__(struct sw_flow_key) % __alignof__(long));