* =====
*
* A flow classifier holds any number of "rules", each of which specifies
- * values to match for some fields or subfields and a priority. The primary
- * design goal for the classifier is that, given a packet, it can as quickly as
- * possible find the highest-priority rule that matches the packet.
+ * values to match for some fields or subfields and a priority. Each OpenFlow
+ * table is implemented as a flow classifier.
*
- * Each OpenFlow table is implemented as a flow classifier.
+ * The classifier has two primary design goals. The first is obvious: given a
+ * set of packet headers, as quickly as possible find the highest-priority rule
+ * that matches those headers. The following section describes the second
+ * goal.
*
*
- * Basic Design
- * ============
+ * "Un-wildcarding"
+ * ================
+ *
+ * A primary goal of the flow classifier is to produce, as a side effect of a
+ * packet lookup, a wildcard mask that indicates which bits of the packet
+ * headers were essential to the classification result. Ideally, a 1-bit in
+ * any position of this mask means that, if the corresponding bit in the packet
+ * header were flipped, then the classification result might change. A 0-bit
+ * means that changing the packet header bit would have no effect. Thus, the
+ * wildcarded bits are the ones that played no role in the classification
+ * decision.
+ *
+ * Such a wildcard mask is useful with datapaths that support installing flows
+ * that wildcard fields or subfields. If an OpenFlow lookup for a TCP flow
+ * does not actually look at the TCP source or destination ports, for example,
+ * then the switch may install into the datapath a flow that wildcards the port
+ * numbers, which in turn allows the datapath to handle packets that arrive for
+ * other TCP source or destination ports without additional help from
+ * ovs-vswitchd. This is useful for the Open vSwitch software and,
+ * potentially, for ASIC-based switches as well.
+ *
+ * Some properties of the wildcard mask:
+ *
+ * - "False 1-bits" are acceptable, that is, setting a bit in the wildcard
+ * mask to 1 will never cause a packet to be forwarded the wrong way.
+ * As a corollary, a wildcard mask composed of all 1-bits will always
+ * yield correct (but often needlessly inefficient) behavior.
+ *
+ * - "False 0-bits" can cause problems, so they must be avoided. In the
+ * extreme case, a mask of all 0-bits is only correct if the classifier
+ * contains only a single flow that matches all packets.
+ *
+ * - 0-bits are desirable because they allow the datapath to act more
+ * autonomously, relying less on ovs-vswitchd to process flow setups,
+ * thereby improving performance.
+ *
+ * - We don't know a good way to generate wildcard masks with the maximum
+ * (correct) number of 0-bits. We use various approximations, described
+ * in later sections.
+ *
+ * - Wildcard masks for lookups in a given classifier yield a
+ * non-overlapping set of rules. More specifically:
+ *
+ * Consider an classifier C1 filled with an arbitrary collection of rules
+ * and an empty classifier C2. Now take a set of packet headers H and
+ * look it up in C1, yielding a highest-priority matching rule R1 and
+ * wildcard mask M. Form a new classifier rule R2 out of packet headers
+ * H and mask M, and add R2 to C2 with a fixed priority. If one were to
+ * do this for every possible set of packet headers H, then this
+ * process would not attempt to add any overlapping rules to C2, that is,
+ * any packet lookup using the rules generated by this process matches at
+ * most one rule in C2.
+ *
+ * During the lookup process, the classifier starts out with a wildcard mask
+ * that is all 0-bits, that is, fully wildcarded. As lookup proceeds, each
+ * step tends to add constraints to the wildcard mask, that is, change
+ * wildcarded 0-bits into exact-match 1-bits. We call this "un-wildcarding".
+ * A lookup step that examines a particular field must un-wildcard that field.
+ * In general, un-wildcarding is necessary for correctness but undesirable for
+ * performance.
+ *
+ *
+ * Basic Classifier Design
+ * =======================
*
* Suppose that all the rules in a classifier had the same form. For example,
* suppose that they all matched on the source and destination Ethernet address
*
* This is how the classifier works. In a "struct classifier", each form of
* "struct cls_rule" present (based on its ->match.mask) goes into a separate
- * "struct cls_table". A lookup does a hash lookup in every "struct cls_table"
- * in the classifier and tracks the highest-priority match that it finds. The
- * tables are kept in a descending priority order according to the highest
- * priority rule in each table, which allows lookup to skip over tables that
- * can't possibly have a higher-priority match than already found.
+ * "struct cls_subtable". A lookup does a hash lookup in every "struct
+ * cls_subtable" in the classifier and tracks the highest-priority match that
+ * it finds. The subtables are kept in a descending priority order according
+ * to the highest priority rule in each subtable, which allows lookup to skip
+ * over subtables that can't possibly have a higher-priority match than already
+ * found. Eliminating lookups through priority ordering aids both classifier
+ * primary design goals: skipping lookups saves time and avoids un-wildcarding
+ * fields that those lookups would have examined.
*
* One detail: a classifier can contain multiple rules that are identical other
* than their priority. When this happens, only the highest priority rule out
* of a group of otherwise identical rules is stored directly in the "struct
- * cls_table", with the other almost-identical rules chained off a linked list
- * inside that highest-priority rule.
+ * cls_subtable", with the other almost-identical rules chained off a linked
+ * list inside that highest-priority rule.
+ *
+ *
+ * Staged Lookup (Wildcard Optimization)
+ * =====================================
+ *
+ * Subtable lookup is performed in ranges defined for struct flow, starting
+ * from metadata (registers, in_port, etc.), then L2 header, L3, and finally
+ * L4 ports. Whenever it is found that there are no matches in the current
+ * subtable, the rest of the subtable can be skipped.
*
+ * Staged lookup does not reduce lookup time, and it may increase it, because
+ * it changes a single hash table lookup into multiple hash table lookups.
+ * It reduces un-wildcarding significantly in important use cases.
*
- * Partitioning
- * ============
+ *
+ * Prefix Tracking (Wildcard Optimization)
+ * =======================================
+ *
+ * Classifier uses prefix trees ("tries") for tracking the used
+ * address space, enabling skipping classifier tables containing
+ * longer masks than necessary for the given address. This reduces
+ * un-wildcarding for datapath flows in parts of the address space
+ * without host routes, but consulting extra data structures (the
+ * tries) may slightly increase lookup time.
+ *
+ * Trie lookup is interwoven with staged lookup, so that a trie is
+ * searched only when the configured trie field becomes relevant for
+ * the lookup. The trie lookup results are retained so that each trie
+ * is checked at most once for each classifier lookup.
+ *
+ * This implementation tracks the number of rules at each address
+ * prefix for the whole classifier. More aggressive table skipping
+ * would be possible by maintaining lists of tables that have prefixes
+ * at the lengths encountered on tree traversal, or by maintaining
+ * separate tries for subsets of rules separated by metadata fields.
+ *
+ * Prefix tracking is configured via OVSDB "Flow_Table" table,
+ * "fieldspec" column. "fieldspec" is a string map where a "prefix"
+ * key tells which fields should be used for prefix tracking. The
+ * value of the "prefix" key is a comma separated list of field names.
+ *
+ * There is a maximum number of fields that can be enabled for any one
+ * flow table. Currently this limit is 3.
+ *
+ *
+ * Partitioning (Lookup Time and Wildcard Optimization)
+ * ====================================================
*
* Suppose that a given classifier is being used to handle multiple stages in a
* pipeline using "resubmit", with metadata (that is, the OpenFlow 1.1+ field
* The classifier has a special optimization to speed up matching in this
* scenario:
*
- * - Each cls_table that matches on metadata gets a tag derived from the
- * table's mask, so that it is likely that each table has a unique tag.
- * (Duplicate tags have a performance cost but do not affect
+ * - Each cls_subtable that matches on metadata gets a tag derived from the
+ * subtable's mask, so that it is likely that each subtable has a unique
+ * tag. (Duplicate tags have a performance cost but do not affect
* correctness.)
*
* - For each metadata value matched by any cls_rule, the classifier
* constructs a "struct cls_partition" indexed by the metadata value.
* The cls_partition has a 'tags' member whose value is the bitwise-OR of
- * the tags of each cls_table that contains any rule that matches on the
- * cls_partition's metadata value. In other words, struct cls_partition
- * associates metadata values with tables that need to be checked with
- * flows with that specific metadata value.
+ * the tags of each cls_subtable that contains any rule that matches on
+ * the cls_partition's metadata value. In other words, struct
+ * cls_partition associates metadata values with subtables that need to
+ * be checked with flows with that specific metadata value.
*
* Thus, a flow lookup can start by looking up the partition associated with
- * the flow's metadata, and then skip over any cls_table whose 'tag' does not
- * intersect the partition's 'tags'. (The flow must also be looked up in any
- * cls_table that doesn't match on metadata. We handle that by giving any such
- * cls_table TAG_ALL as its 'tags' so that it matches any tag.)
+ * the flow's metadata, and then skip over any cls_subtable whose 'tag' does
+ * not intersect the partition's 'tags'. (The flow must also be looked up in
+ * any cls_subtable that doesn't match on metadata. We handle that by giving
+ * any such cls_subtable TAG_ALL as its 'tags' so that it matches any tag.)
+ *
+ * Partitioning saves lookup time by reducing the number of subtable lookups.
+ * Each eliminated subtable lookup also reduces the amount of un-wildcarding.
*
*
* Thread-safety
* =============
*
- * When locked properly, the classifier is thread safe as long as the following
- * conditions are satisfied.
- * - Only the main thread calls functions requiring a write lock.
- * - Only the main thread is allowed to iterate over rules. */
+ * The classifier may safely be accessed by many reader threads concurrently or
+ * by a single writer. */
+#include "fat-rwlock.h"
#include "flow.h"
+#include "hindex.h"
#include "hmap.h"
#include "list.h"
#include "match.h"
+#include "meta-flow.h"
#include "tag.h"
#include "openflow/nicira-ext.h"
#include "openflow/openflow.h"
/* Needed only for the lock annotation in struct classifier. */
extern struct ovs_mutex ofproto_mutex;
+struct trie_node;
+
+/* Prefix trie for a 'field' */
+struct cls_trie {
+ const struct mf_field *field; /* Trie field, or NULL. */
+ struct trie_node *root; /* NULL if none. */
+};
+
+enum {
+ CLS_MAX_INDICES = 3, /* Maximum number of lookup indices per subtable. */
+ CLS_MAX_TRIES = 3 /* Maximum number of prefix trees per classifier. */
+};
/* A flow classifier. */
struct classifier {
int n_rules; /* Total number of rules. */
- struct hmap tables; /* Contains "struct cls_table"s. */
- struct list tables_priority; /* Tables in descending priority order */
+ uint8_t n_flow_segments;
+ uint8_t flow_segments[CLS_MAX_INDICES]; /* Flow segment boundaries to use
+ * for staged lookup. */
+ struct hmap subtables; /* Contains "struct cls_subtable"s. */
+ struct list subtables_priority; /* Subtables in descending priority order.
+ */
struct hmap partitions; /* Contains "struct cls_partition"s. */
- struct ovs_rwlock rwlock OVS_ACQ_AFTER(ofproto_mutex);
+ struct fat_rwlock rwlock OVS_ACQ_AFTER(ofproto_mutex);
+ struct cls_trie tries[CLS_MAX_TRIES]; /* Prefix tries. */
+ unsigned int n_tries;
};
/* A set of rules that all have the same fields wildcarded. */
-struct cls_table {
- struct hmap_node hmap_node; /* Within struct classifier 'tables' hmap. */
- struct list list_node; /* Within classifier 'tables_priority_list' */
+struct cls_subtable {
+ struct hmap_node hmap_node; /* Within struct classifier 'subtables' hmap.
+ */
+ struct list list_node; /* Within classifier 'subtables_priority' list.
+ */
struct hmap rules; /* Contains "struct cls_rule"s. */
struct minimask mask; /* Wildcards for fields. */
- int n_table_rules; /* Number of rules, including duplicates. */
- unsigned int max_priority; /* Max priority of any rule in the table. */
+ int n_rules; /* Number of rules, including duplicates. */
+ unsigned int max_priority; /* Max priority of any rule in the subtable. */
unsigned int max_count; /* Count of max_priority rules. */
tag_type tag; /* Tag generated from mask for partitioning. */
+ uint8_t n_indices; /* How many indices to use. */
+ uint8_t index_ofs[CLS_MAX_INDICES]; /* u32 flow segment boundaries. */
+ struct hindex indices[CLS_MAX_INDICES]; /* Staged lookup indices. */
+ unsigned int trie_plen[CLS_MAX_TRIES]; /* Trie prefix length in 'mask'. */
};
-/* Returns true if 'table' is a "catch-all" table that will match every
+/* Returns true if 'table' is a "catch-all" subtable that will match every
* packet (if there is no higher-priority match). */
static inline bool
-cls_table_is_catchall(const struct cls_table *table)
+cls_subtable_is_catchall(const struct cls_subtable *subtable)
{
- return minimask_is_catchall(&table->mask);
+ return minimask_is_catchall(&subtable->mask);
}
-/* A rule in a "struct classifier". */
+/* A rule in a "struct cls_subtable". */
struct cls_rule {
- struct hmap_node hmap_node; /* Within struct cls_table 'rules'. */
+ struct hmap_node hmap_node; /* Within struct cls_subtable 'rules'. */
struct list list; /* List of identical, lower-priority rules. */
struct minimatch match; /* Matching rule. */
unsigned int priority; /* Larger numbers are higher priorities. */
struct cls_partition *partition;
+ struct hindex_node index_nodes[CLS_MAX_INDICES]; /* Within subtable's
+ * 'indices'. */
};
/* Associates a metadata value (that is, a value of the OpenFlow 1.1+ metadata
- * field) with tags for the "cls_table"s that contain rules that match that
+ * field) with tags for the "cls_subtable"s that contain rules that match that
* metadata value. */
struct cls_partition {
struct hmap_node hmap_node; /* In struct classifier's 'partitions' hmap. */
ovs_be64 metadata; /* metadata value for this partition. */
- tag_type tags; /* OR of each included flow's cls_table tag. */
+ tag_type tags; /* OR of each flow's cls_subtable tag. */
struct tag_tracker tracker; /* Tracks the bits in 'tags'. */
};
bool cls_rule_is_loose_match(const struct cls_rule *rule,
const struct minimatch *criteria);
-void classifier_init(struct classifier *cls);
+void classifier_init(struct classifier *cls, const uint8_t *flow_segments);
void classifier_destroy(struct classifier *);
+void classifier_set_prefix_fields(struct classifier *cls,
+ const enum mf_field_id *trie_fields,
+ unsigned int n_trie_fields)
+ OVS_REQ_WRLOCK(cls->rwlock);
+
bool classifier_is_empty(const struct classifier *cls)
OVS_REQ_RDLOCK(cls->rwlock);
int classifier_count(const struct classifier *cls)
struct cls_cursor {
const struct classifier *cls;
- const struct cls_table *table;
+ const struct cls_subtable *subtable;
const struct cls_rule *target;
};
void cls_cursor_init(struct cls_cursor *cursor, const struct classifier *cls,
const struct cls_rule *match) OVS_REQ_RDLOCK(cls->rwlock);
struct cls_rule *cls_cursor_first(struct cls_cursor *cursor);
-struct cls_rule *cls_cursor_next(struct cls_cursor *cursor, const struct cls_rule *);
+struct cls_rule *cls_cursor_next(struct cls_cursor *, const struct cls_rule *);
#define CLS_CURSOR_FOR_EACH(RULE, MEMBER, CURSOR) \
for (ASSIGN_CONTAINER(RULE, cls_cursor_first(CURSOR), MEMBER); \