#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>
#include <linux/in.h>
#include <linux/rcupdate.h>
+#include <linux/cpumask.h>
#include <linux/if_arp.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <net/ipv6.h>
#include <net/ndisc.h>
-#include "vlan.h"
+#include "flow_netlink.h"
#define TBL_MIN_BUCKETS 1024
+#define MASK_ARRAY_SIZE_MIN 16
#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;
static u16 range_n_bytes(const struct sw_flow_key_range *range)
{
}
void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
- const struct sw_flow_mask *mask)
+ bool full, const struct sw_flow_mask *mask)
{
- const long *m = (long *)((u8 *)&mask->key + mask->range.start);
- const long *s = (long *)((u8 *)src + mask->range.start);
- long *d = (long *)((u8 *)dst + mask->range.start);
+ int start = full ? 0 : mask->range.start;
+ int len = full ? sizeof *dst : range_n_bytes(&mask->range);
+ const long *m = (const long *)((const u8 *)&mask->key + start);
+ const long *s = (const long *)((const u8 *)src + start);
+ long *d = (long *)((u8 *)dst + start);
int i;
- /* The memory outside of the 'mask->range' are not set since
- * further operations on 'dst' only uses contents within
- * 'mask->range'.
+ /* If 'full' is true then all of 'dst' is fully initialized. Otherwise,
+ * if 'full' is false the memory outside of the 'mask->range' is left
+ * uninitialized. This can be used as an optimization when further
+ * operations on 'dst' only use contents within 'mask->range'.
*/
- for (i = 0; i < range_n_bytes(&mask->range); i += sizeof(long))
+ for (i = 0; i < len; i += sizeof(long))
*d++ = *s++ & *m++;
}
-struct sw_flow *ovs_flow_alloc(bool percpu_stats)
+struct sw_flow *ovs_flow_alloc(void)
{
struct sw_flow *flow;
- int cpu;
+ struct flow_stats *stats;
- flow = kmem_cache_alloc(flow_cache, GFP_KERNEL);
+ flow = kmem_cache_zalloc(flow_cache, GFP_KERNEL);
if (!flow)
return ERR_PTR(-ENOMEM);
- flow->sf_acts = NULL;
- flow->mask = NULL;
+ flow->stats_last_writer = -1;
- flow->stats.is_percpu = percpu_stats;
+ /* Initialize the default stat node. */
+ stats = kmem_cache_alloc_node(flow_stats_cache,
+ GFP_KERNEL | __GFP_ZERO,
+ node_online(0) ? 0 : NUMA_NO_NODE);
+ if (!stats)
+ goto err;
- if (!percpu_stats) {
- flow->stats.stat = kzalloc(sizeof(*flow->stats.stat), GFP_KERNEL);
- if (!flow->stats.stat)
- goto err;
+ spin_lock_init(&stats->lock);
- spin_lock_init(&flow->stats.stat->lock);
- } else {
- flow->stats.cpu_stats = alloc_percpu(struct flow_stats);
- if (!flow->stats.cpu_stats)
- goto err;
+ RCU_INIT_POINTER(flow->stats[0], stats);
- for_each_possible_cpu(cpu) {
- struct flow_stats *cpu_stats;
+ cpumask_set_cpu(0, &flow->cpu_used_mask);
- cpu_stats = per_cpu_ptr(flow->stats.cpu_stats, cpu);
- spin_lock_init(&cpu_stats->lock);
- }
- }
return flow;
err:
kmem_cache_free(flow_cache, flow);
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;
}
-static struct flex_array *alloc_buckets(unsigned int n_buckets)
-{
- struct flex_array *buckets;
- int i, err;
-
- buckets = flex_array_alloc(sizeof(struct hlist_head),
- n_buckets, GFP_KERNEL);
- if (!buckets)
- return NULL;
-
- err = flex_array_prealloc(buckets, 0, n_buckets, GFP_KERNEL);
- if (err) {
- flex_array_free(buckets);
- return NULL;
- }
-
- for (i = 0; i < n_buckets; i++)
- INIT_HLIST_HEAD((struct hlist_head *)
- flex_array_get(buckets, i));
-
- return buckets;
-}
-
static void flow_free(struct sw_flow *flow)
{
- kfree((struct sf_flow_acts __force *)flow->sf_acts);
- if (flow->stats.is_percpu)
- free_percpu(flow->stats.cpu_stats);
- else
- kfree(flow->stats.stat);
+ int cpu;
+
+ if (ovs_identifier_is_key(&flow->id))
+ kfree(flow->id.unmasked_key);
+ if (flow->sf_acts)
+ ovs_nla_free_flow_actions((struct sw_flow_actions __force *)flow->sf_acts);
+ /* We open code this to make sure cpu 0 is always considered */
+ for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask))
+ if (flow->stats[cpu])
+ kmem_cache_free(flow_stats_cache,
+ rcu_dereference_raw(flow->stats[cpu]));
kmem_cache_free(flow_cache, flow);
}
flow_free(flow);
}
-static void rcu_free_sw_flow_mask_cb(struct rcu_head *rcu)
-{
- struct sw_flow_mask *mask = container_of(rcu, struct sw_flow_mask, rcu);
-
- kfree(mask);
-}
-
void ovs_flow_free(struct sw_flow *flow, bool deferred)
{
if (!flow)
return;
- ASSERT_OVSL();
-
- if (flow->mask) {
- struct sw_flow_mask *mask = flow->mask;
-
- BUG_ON(!mask->ref_count);
- mask->ref_count--;
-
- if (!mask->ref_count) {
- list_del_rcu(&mask->list);
- if (deferred)
- call_rcu(&mask->rcu, rcu_free_sw_flow_mask_cb);
- else
- kfree(mask);
- }
- }
-
if (deferred)
call_rcu(&flow->rcu, rcu_free_flow_callback);
else
flow_free(flow);
}
-static void free_buckets(struct flex_array *buckets)
-{
- flex_array_free(buckets);
-}
-
-
static void __table_instance_destroy(struct table_instance *ti)
{
- free_buckets(ti->buckets);
+ kvfree(ti->buckets);
kfree(ti);
}
static struct table_instance *table_instance_alloc(int new_size)
{
struct table_instance *ti = kmalloc(sizeof(*ti), GFP_KERNEL);
+ int i;
if (!ti)
return NULL;
- ti->buckets = alloc_buckets(new_size);
-
+ ti->buckets = kvmalloc_array(new_size, sizeof(struct hlist_head),
+ GFP_KERNEL);
if (!ti->buckets) {
kfree(ti);
return NULL;
}
+
+ for (i = 0; i < new_size; i++)
+ INIT_HLIST_HEAD(&ti->buckets[i]);
+
ti->n_buckets = new_size;
ti->node_ver = 0;
ti->keep_flows = false;
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;
+
+ size = max(MASK_ARRAY_SIZE_MIN, size);
+ 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, count = 0;
+
+ for (i = 0; i < old->max; i++) {
+ if (ovsl_dereference(old->masks[i]))
+ new->masks[count++] = old->masks[i];
+ }
+
+ new->count = count;
+ }
+ 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 table_instance *ti, *ufid_ti;
+ struct mask_array *ma;
- 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;
+ ma = tbl_mask_array_alloc(MASK_ARRAY_SIZE_MIN);
+ if (!ma)
+ goto free_mask_cache;
+
+ ti = table_instance_alloc(TBL_MIN_BUCKETS);
if (!ti)
- return -ENOMEM;
+ goto free_mask_array;
+
+ ufid_ti = table_instance_alloc(TBL_MIN_BUCKETS);
+ if (!ufid_ti)
+ goto free_ti;
rcu_assign_pointer(table->ti, ti);
- INIT_LIST_HEAD(&table->mask_list);
+ 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(ma);
+free_mask_cache:
+ free_percpu(table->mask_cache);
+ return -ENOMEM;
}
static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu)
__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;
for (i = 0; i < ti->n_buckets; i++) {
struct sw_flow *flow;
- struct hlist_head *head = flex_array_get(ti->buckets, i);
+ struct hlist_head *head = &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);
+ }
}
-void ovs_flow_tbl_destroy(struct flow_table *table, bool deferred)
+/* No need for locking this function is called from RCU callback or
+ * error path.
+ */
+void ovs_flow_tbl_destroy(struct flow_table *table)
{
- struct table_instance *ti = ovsl_dereference(table->ti);
+ struct table_instance *ti = rcu_dereference_raw(table->ti);
+ struct table_instance *ufid_ti = rcu_dereference_raw(table->ufid_ti);
- table_instance_destroy(ti, deferred);
+ free_percpu(table->mask_cache);
+ 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,
ver = ti->node_ver;
while (*bucket < ti->n_buckets) {
i = 0;
- head = flex_array_get(ti->buckets, *bucket);
- hlist_for_each_entry_rcu(flow, head, hash_node[ver]) {
+ head = &ti->buckets[*bucket];
+ hlist_for_each_entry_rcu(flow, head, flow_table.node[ver]) {
if (i < *last) {
i++;
continue;
static struct hlist_head *find_bucket(struct table_instance *ti, u32 hash)
{
hash = jhash_1word(hash, ti->hash_seed);
- return flex_array_get(ti->buckets,
- (hash & (ti->n_buckets - 1)));
+ return &ti->buckets[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->hash);
- hlist_add_head_rcu(&flow->hash_node[ti->node_ver], 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->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;
/* Insert in new table. */
for (i = 0; i < old->n_buckets; i++) {
struct sw_flow *flow;
- struct hlist_head *head;
-
- head = flex_array_get(old->buckets, i);
-
- hlist_for_each_entry(flow, head, hash_node[old_ver])
- table_instance_insert(new, flow);
+ struct hlist_head *head = &old->buckets[i];
+
+ 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)
{
- u32 *hash_key = (u32 *)((u8 *)key + key_start);
+ 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)
{
- if (key->tun_key.ipv4_dst)
+ if (key->tun_proto)
return 0;
else
return rounddown(offsetof(struct sw_flow_key, phy),
const struct sw_flow_key *key2,
int key_start, int key_end)
{
- const long *cp1 = (long *)((u8 *)key1 + key_start);
- const long *cp2 = (long *)((u8 *)key2 + key_start);
+ const long *cp1 = (const long *)((const u8 *)key1 + key_start);
+ const long *cp2 = (const long *)((const u8 *)key2 + key_start);
long diffs = 0;
int i;
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);
+ ovs_flow_mask_key(&masked_key, unmasked, false, mask);
+ hash = flow_hash(&masked_key, &mask->range);
head = find_bucket(ti, hash);
- 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))
+ (*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))
return flow;
}
return NULL;
}
-struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *tbl,
- const struct sw_flow_key *key,
- u32 *n_mask_hit)
+/* 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,
+ const struct mask_array *ma,
+ const struct sw_flow_key *key,
+ u32 *n_mask_hit,
+ u32 *index)
{
- struct table_instance *ti = rcu_dereference_ovsl(tbl->ti);
struct sw_flow_mask *mask;
struct sw_flow *flow;
+ int i;
- *n_mask_hit = 0;
- list_for_each_entry_rcu(mask, &tbl->mask_list, list) {
- (*n_mask_hit)++;
- flow = masked_flow_lookup(ti, key, mask);
- if (flow) /* Found */
+ 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)
+ 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;
+ }
}
+
return NULL;
}
+/*
+ * mask_cache maps flow to probable mask. This cache is not tightly
+ * coupled cache, It means updates to mask list can result in inconsistent
+ * 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(tbl->mask_array);
+ struct table_instance *ti = rcu_dereference(tbl->ti);
+ struct mask_cache_entry *entries, *ce;
+ struct sw_flow *flow;
+ u32 hash;
+ int seg;
+
+ *n_mask_hit = 0;
+ if (unlikely(!skb_hash)) {
+ u32 mask_index = 0;
+
+ return flow_lookup(tbl, ti, ma, key, n_mask_hit, &mask_index);
+ }
+
+ /* 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 = 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 (!ce || e->skb_hash < ce->skb_hash)
+ ce = e; /* A better replacement cache candidate. */
+
+ hash >>= MC_HASH_SHIFT;
+ }
+
+ /* Cache miss, do full lookup. */
+ flow = flow_lookup(tbl, ti, ma, key, n_mask_hit, &ce->mask_index);
+ if (flow)
+ ce->skb_hash = skb_hash;
+
+ return flow;
+}
+
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 index = 0;
- return ovs_flow_tbl_lookup_stats(tbl, key, &n_mask_hit);
+ 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 sw_flow_mask *mask;
- int num = 0;
+ struct mask_array *ma;
+
+ ma = rcu_dereference_ovsl(table->mask_array);
+ return ma->count;
+}
+
+static struct table_instance *table_instance_expand(struct table_instance *ti,
+ bool ufid)
+{
+ return table_instance_rehash(ti, ti->n_buckets * 2, ufid);
+}
- list_for_each_entry(mask, &table->mask_list, list)
- num++;
+static void tbl_mask_array_delete_mask(struct mask_array *ma,
+ struct sw_flow_mask *mask)
+{
+ int i;
- return num;
+ /* 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--;
+ kfree_rcu(mask, rcu);
+ return;
+ }
+ }
+ BUG();
}
-static struct table_instance *table_instance_expand(struct table_instance *ti)
+/* Remove 'mask' from the mask list, if it is not needed any more. */
+static void flow_mask_remove(struct flow_table *tbl, struct sw_flow_mask *mask)
{
- return table_instance_rehash(ti, ti->n_buckets * 2);
+ if (mask) {
+ /* ovs-lock is required to protect mask-refcount and
+ * mask list.
+ */
+ ASSERT_OVSL();
+ BUG_ON(!mask->ref_count);
+ mask->ref_count--;
+
+ if (!mask->ref_count) {
+ struct mask_array *ma;
+
+ ma = ovsl_dereference(tbl->mask_array);
+ 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);
+
+ }
+ }
}
+/* Must be called with OVS mutex held. */
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.
+ */
+ flow_mask_remove(table, flow->mask);
}
static struct sw_flow_mask *mask_alloc(void)
static bool mask_equal(const struct sw_flow_mask *a,
const struct sw_flow_mask *b)
{
- u8 *a_ = (u8 *)&a->key + a->range.start;
- u8 *b_ = (u8 *)&b->key + b->range.start;
+ const u8 *a_ = (const u8 *)&a->key + a->range.start;
+ const u8 *b_ = (const u8 *)&b->key + b->range.start;
return (a->range.end == b->range.end)
&& (a->range.start == b->range.start)
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;
- 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;
+ ma = ovsl_dereference(tbl->mask_array);
+ for (i = 0; i < ma->max; i++) {
+ struct sw_flow_mask *t;
+
+ t = ovsl_dereference(ma->masks[i]);
+ if (t && mask_equal(mask, t))
+ return t;
}
return NULL;
/* 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;
+
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_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++) {
+ 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++;
return 0;
}
-int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
- struct sw_flow_mask *mask)
+/* Must be called with OVS mutex held. */
+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));
BUILD_BUG_ON(sizeof(struct sw_flow_key) % sizeof(long));
- flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow), 0,
- 0, NULL);
+ flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow)
+ + (nr_cpu_ids
+ * sizeof(struct flow_stats *)),
+ 0, 0, NULL);
if (flow_cache == NULL)
return -ENOMEM;
+ flow_stats_cache
+ = kmem_cache_create("sw_flow_stats", sizeof(struct flow_stats),
+ 0, SLAB_HWCACHE_ALIGN, NULL);
+ if (flow_stats_cache == NULL) {
+ kmem_cache_destroy(flow_cache);
+ flow_cache = NULL;
+ return -ENOMEM;
+ }
+
return 0;
}
/* Uninitializes the flow module. */
void ovs_flow_exit(void)
{
+ kmem_cache_destroy(flow_stats_cache);
kmem_cache_destroy(flow_cache);
}