/*
- * Copyright (c) 2009, 2010 Nicira Networks.
+ * Copyright (c) 2009, 2010, 2011, 2012, 2013 Nicira, Inc.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
/* Flow classifier.
*
- * This flow classifier assumes that we can arrange the fields in a flow in an
- * order such that the set of wildcarded fields in a rule tend to fall toward
- * the end of the ordering. That is, if field F is wildcarded, then all the
- * fields after F tend to be wildcarded as well. If this assumption is
- * violated, then the classifier will still classify flows correctly, but its
- * performance will suffer.
- *
- * The classifier uses a collection of CLS_N_FIELDS hash tables for wildcarded
- * flows. Each of these tables contains the flows that wildcard a given field
- * and do not wildcard any of the fields that precede F in the ordering. The
- * key for each hash table is the value of the fields preceding F that are not
- * wildcarded. All the flows that fall within a table and have the same key
- * are kept as a linked list ordered from highest to lowest priority.
- *
- * The classifier also maintains a separate hash table of exact-match flows.
- *
- * To search the classifier we first search the table of exact-match flows,
- * since exact-match flows always have highest priority. If there is a match,
- * we're done. Otherwise, we search each of the CLS_N_FIELDS hash tables in
- * turn, looking for the highest-priority match, and return it (if any).
- */
+ *
+ * What?
+ * =====
+ *
+ * A flow classifier holds any number of "rules", each of which specifies
+ * values to match for some fields or subfields and a priority. 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.
+ *
+ *
+ * "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
+ * and wildcarded all the other fields. Then the obvious way to implement a
+ * classifier would be a hash table on the source and destination Ethernet
+ * addresses. If new classification rules came along with a different form,
+ * you could add a second hash table that hashed on the fields matched in those
+ * rules. With two hash tables, you look up a given flow in each hash table.
+ * If there are no matches, the classifier didn't contain a match; if you find
+ * a match in one of them, that's the result; if you find a match in both of
+ * them, then the result is the rule with the higher priority.
+ *
+ * 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_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_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.
+ *
+ *
+ * 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
+ * named "metadata") distinguishing between the different stages. For example,
+ * metadata value 1 might identify ingress rules, metadata value 2 might
+ * identify ACLs, and metadata value 3 might identify egress rules. Such a
+ * classifier is essentially partitioned into multiple sub-classifiers on the
+ * basis of the metadata value.
+ *
+ * The classifier has a special optimization to speed up matching in this
+ * scenario:
+ *
+ * - 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_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_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
+ * =============
+ *
+ * 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"
+#include "ovs-thread.h"
+#include "util.h"
-/* Number of bytes of fields in a rule. */
-#define CLS_N_BYTES 37
-
-/* Fields in a rule.
- *
- * This definition sets the ordering of fields, which is important for
- * performance (see above). To adjust the ordering, change the order of the
- * lines. */
-#define CLS_FIELDS \
- /* struct flow all-caps */ \
- /* wildcard bit(s) member name name */ \
- /* ----------------- ----------- -------- */ \
- CLS_FIELD(OFPFW_IN_PORT, in_port, IN_PORT) \
- CLS_FIELD(NXFW_TUN_ID, tun_id, TUN_ID) \
- CLS_FIELD(OFPFW_DL_VLAN, dl_vlan, DL_VLAN) \
- CLS_FIELD(OFPFW_DL_VLAN_PCP, dl_vlan_pcp, DL_VLAN_PCP) \
- CLS_FIELD(OFPFW_DL_SRC, dl_src, DL_SRC) \
- CLS_FIELD(OFPFW_DL_DST, dl_dst, DL_DST) \
- CLS_FIELD(OFPFW_DL_TYPE, dl_type, DL_TYPE) \
- CLS_FIELD(OFPFW_NW_SRC_MASK, nw_src, NW_SRC) \
- CLS_FIELD(OFPFW_NW_DST_MASK, nw_dst, NW_DST) \
- CLS_FIELD(OFPFW_NW_PROTO, nw_proto, NW_PROTO) \
- CLS_FIELD(OFPFW_NW_TOS, nw_tos, NW_TOS) \
- CLS_FIELD(OFPFW_TP_SRC, tp_src, TP_SRC) \
- CLS_FIELD(OFPFW_TP_DST, tp_dst, TP_DST)
-
-/* Field indexes.
- *
- * (These are also indexed into struct classifier's 'tables' array.) */
-enum {
-#define CLS_FIELD(WILDCARDS, MEMBER, NAME) CLS_F_IDX_##NAME,
- CLS_FIELDS
-#undef CLS_FIELD
- CLS_F_IDX_EXACT, /* Exact-match table. */
- CLS_N_FIELDS = CLS_F_IDX_EXACT
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* 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. */
};
-/* Field information. */
-struct cls_field {
- int ofs; /* Offset in struct flow. */
- int len; /* Length in bytes. */
- uint32_t wildcards; /* OFPFW_* bit or bits for this field. */
- const char *name; /* Name (for debugging). */
+enum {
+ CLS_MAX_INDICES = 3, /* Maximum number of lookup indices per subtable. */
+ CLS_MAX_TRIES = 3 /* Maximum number of prefix trees per classifier. */
};
-extern const struct cls_field cls_fields[CLS_N_FIELDS + 1];
/* A flow classifier. */
struct classifier {
- int n_rules; /* Sum of hmap_count() over tables[]. */
- struct hmap tables[CLS_N_FIELDS]; /* Contain cls_bucket elements. */
- struct hmap exact_table; /* Contain cls_rule elements. */
+ int n_rules; /* Total number of rules. */
+ 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 fat_rwlock rwlock OVS_ACQ_AFTER(ofproto_mutex);
+ struct cls_trie tries[CLS_MAX_TRIES]; /* Prefix tries. */
+ unsigned int n_tries;
};
-/* A group of rules with the same fixed values for initial fields. */
-struct cls_bucket {
- struct hmap_node hmap_node; /* Within struct classifier 'tables'. */
- struct list rules; /* In order from highest to lowest priority. */
- struct flow fixed; /* Values for fixed fields. */
+/* A set of rules that all have the same fields wildcarded. */
+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_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'. */
};
-/* A flow classification rule.
- *
- * Use cls_rule_from_flow() or cls_rule_from_match() to initialize a cls_rule
- * or you will almost certainly not initialize 'table_idx' correctly, with
- * disastrous results! */
+/* 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_subtable_is_catchall(const struct cls_subtable *subtable)
+{
+ return minimask_is_catchall(&subtable->mask);
+}
+
+/* A rule in a "struct cls_subtable". */
struct cls_rule {
- union {
- struct list list; /* Within struct cls_bucket 'rules'. */
- struct hmap_node hmap; /* Within struct classifier 'exact_table'. */
- } node;
- struct flow flow; /* All field values. */
- struct flow_wildcards wc; /* Wildcards for fields. */
+ 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. */
- unsigned int table_idx; /* Index into struct classifier 'tables'. */
+ 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_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 flow's cls_subtable tag. */
+ struct tag_tracker tracker; /* Tracks the bits in 'tags'. */
};
-void cls_rule_from_flow(const struct flow *, uint32_t wildcards,
- unsigned int priority, struct cls_rule *);
-void cls_rule_from_match(const struct ofp_match *, unsigned int priority,
- bool tun_id_from_cookie, uint64_t cookie,
- struct cls_rule *);
-char *cls_rule_to_string(const struct cls_rule *);
-void cls_rule_print(const struct cls_rule *);
+void cls_rule_init(struct cls_rule *, const struct match *,
+ unsigned int priority);
+void cls_rule_init_from_minimatch(struct cls_rule *, const struct minimatch *,
+ unsigned int priority);
+void cls_rule_clone(struct cls_rule *, const struct cls_rule *);
+void cls_rule_move(struct cls_rule *dst, struct cls_rule *src);
+void cls_rule_destroy(struct cls_rule *);
+
+bool cls_rule_equal(const struct cls_rule *, const struct cls_rule *);
+uint32_t cls_rule_hash(const struct cls_rule *, uint32_t basis);
+
+void cls_rule_format(const struct cls_rule *, struct ds *);
+
+bool cls_rule_is_catchall(const struct cls_rule *);
+
+bool cls_rule_is_loose_match(const struct cls_rule *rule,
+ const struct minimatch *criteria);
-void classifier_init(struct classifier *);
+void classifier_init(struct classifier *cls, const uint8_t *flow_segments);
void classifier_destroy(struct classifier *);
-bool classifier_is_empty(const struct classifier *);
-int classifier_count(const struct classifier *);
-int classifier_count_exact(const struct classifier *);
-struct cls_rule *classifier_insert(struct classifier *, struct cls_rule *);
-void classifier_insert_exact(struct classifier *, struct cls_rule *);
-void classifier_remove(struct classifier *, struct cls_rule *);
-struct cls_rule *classifier_lookup(const struct classifier *,
- const struct flow *);
-struct cls_rule *classifier_lookup_wild(const struct classifier *,
- const struct flow *);
-struct cls_rule *classifier_lookup_exact(const struct classifier *,
- const struct flow *);
-bool classifier_rule_overlaps(const struct classifier *, const struct flow *,
- uint32_t wildcards, unsigned int priority);
+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)
+ OVS_REQ_RDLOCK(cls->rwlock);
+void classifier_insert(struct classifier *cls, struct cls_rule *)
+ OVS_REQ_WRLOCK(cls->rwlock);
+struct cls_rule *classifier_replace(struct classifier *cls, struct cls_rule *)
+ OVS_REQ_WRLOCK(cls->rwlock);
+void classifier_remove(struct classifier *cls, struct cls_rule *)
+ OVS_REQ_WRLOCK(cls->rwlock);
+struct cls_rule *classifier_lookup(const struct classifier *cls,
+ const struct flow *,
+ struct flow_wildcards *)
+ OVS_REQ_RDLOCK(cls->rwlock);
+bool classifier_rule_overlaps(const struct classifier *cls,
+ const struct cls_rule *)
+ OVS_REQ_RDLOCK(cls->rwlock);
typedef void cls_cb_func(struct cls_rule *, void *aux);
-enum {
- CLS_INC_EXACT = 1 << 0, /* Include exact-match flows? */
- CLS_INC_WILD = 1 << 1, /* Include flows with wildcards? */
- CLS_INC_ALL = CLS_INC_EXACT | CLS_INC_WILD
+struct cls_rule *classifier_find_rule_exactly(const struct classifier *cls,
+ const struct cls_rule *)
+ OVS_REQ_RDLOCK(cls->rwlock);
+struct cls_rule *classifier_find_match_exactly(const struct classifier *cls,
+ const struct match *,
+ unsigned int priority)
+ OVS_REQ_RDLOCK(cls->rwlock);
+\f
+/* Iteration. */
+
+struct cls_cursor {
+ const struct classifier *cls;
+ const struct cls_subtable *subtable;
+ const struct cls_rule *target;
};
-void classifier_for_each(const struct classifier *, int include,
- cls_cb_func *, void *aux);
-void classifier_for_each_match(const struct classifier *,
- const struct cls_rule *,
- int include, cls_cb_func *, void *aux);
-struct cls_rule *classifier_find_rule_exactly(const struct classifier *,
- const struct flow *target,
- uint32_t wildcards,
- unsigned int priority);
-
-#define CLASSIFIER_FOR_EACH_EXACT_RULE(RULE, MEMBER, CLS) \
- HMAP_FOR_EACH (RULE, MEMBER.node.hmap, &(CLS)->exact_table)
-
-#define CLASSIFIER_FOR_EACH_EXACT_RULE_SAFE(RULE, NEXT, MEMBER, CLS) \
- HMAP_FOR_EACH_SAFE (RULE, NEXT, MEMBER.node.hmap, &(CLS)->exact_table)
+
+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 *, const struct cls_rule *);
+
+#define CLS_CURSOR_FOR_EACH(RULE, MEMBER, CURSOR) \
+ for (ASSIGN_CONTAINER(RULE, cls_cursor_first(CURSOR), MEMBER); \
+ RULE != OBJECT_CONTAINING(NULL, RULE, MEMBER); \
+ ASSIGN_CONTAINER(RULE, cls_cursor_next(CURSOR, &(RULE)->MEMBER), \
+ MEMBER))
+
+#define CLS_CURSOR_FOR_EACH_SAFE(RULE, NEXT, MEMBER, CURSOR) \
+ for (ASSIGN_CONTAINER(RULE, cls_cursor_first(CURSOR), MEMBER); \
+ (RULE != OBJECT_CONTAINING(NULL, RULE, MEMBER) \
+ ? ASSIGN_CONTAINER(NEXT, cls_cursor_next(CURSOR, &(RULE)->MEMBER), \
+ MEMBER), 1 \
+ : 0); \
+ (RULE) = (NEXT))
+
+#ifdef __cplusplus
+}
+#endif
#endif /* classifier.h */