diff --git a/scripts/no_heap_baseline.txt b/scripts/no_heap_baseline.txt index 961f4f98..588f387b 100644 --- a/scripts/no_heap_baseline.txt +++ b/scripts/no_heap_baseline.txt @@ -10,7 +10,7 @@ src/manager.cpp 14 src/plugin.cpp 3 src/process.cpp 26 src/redir.cpp 1 -src/rule.cpp 2 +src/rule.cpp 1 src/server.cpp 3 src/ssurl.cpp 3 src/tunnel.cpp 1 diff --git a/src/CMakeLists.txt b/src/CMakeLists.txt index fe5558de..68dcbdf7 100644 --- a/src/CMakeLists.txt +++ b/src/CMakeLists.txt @@ -70,7 +70,6 @@ endif () set(LIBSHADOWSOCKS_LIBEV_SOURCE ${SS_SHARED_SOURCES} - cache.cpp local.cpp ssurl.cpp ${SS_RELAY_SOURCE} @@ -86,7 +85,6 @@ set(SS_LOCAL_SOURCE set(SS_TUNNEL_SOURCE ${SS_SHARED_SOURCES} - cache.cpp tunnel.cpp ${SS_RELAY_SOURCE} ${SS_CRYPTO_SOURCE} @@ -95,7 +93,6 @@ set(SS_TUNNEL_SOURCE set(SS_SERVER_SOURCE ${SS_SHARED_SOURCES} - cache.cpp server.cpp ${SS_RELAY_SOURCE} ${SS_CRYPTO_SOURCE} @@ -110,7 +107,6 @@ set(SS_MANAGER_SOURCE set(SS_REDIR_SOURCE ${SS_SHARED_SOURCES} - cache.cpp redir.cpp ${SS_RELAY_SOURCE} ${SS_CRYPTO_SOURCE} @@ -131,7 +127,7 @@ if(ENABLE_NFTABLES) endif() # Modules rewritten in C++ compile with the stricter warning set. -ss_strict_warnings(cache.cpp ${SS_RELAY_SOURCE}) +ss_strict_warnings(${SS_RELAY_SOURCE}) function(ss_program name module sources) add_executable(${name} ${sources}) diff --git a/src/acl.cpp b/src/acl.cpp index 13e9b7e1..ab315a5c 100644 --- a/src/acl.cpp +++ b/src/acl.cpp @@ -41,14 +41,14 @@ static struct ss_ipset white_list_ipv6; static struct ss_ipset black_list_ipv4; static struct ss_ipset black_list_ipv6; -static struct ss_list black_list_rules; -static struct ss_list white_list_rules; +static rule_list_t black_list_rules; +static rule_list_t white_list_rules; static int acl_mode = BLACK_LIST; static struct ss_ipset outbound_block_list_ipv4; static struct ss_ipset outbound_block_list_ipv6; -static struct ss_list outbound_block_list_rules; +static rule_list_t outbound_block_list_rules; static int parse_addr_cidr(const char *str, char *host, size_t host_len, int *cidr) @@ -125,13 +125,10 @@ init_acl(const char *path) ss_ipset_clear(&outbound_block_list_ipv4); ss_ipset_clear(&outbound_block_list_ipv6); - ss_list_init(&black_list_rules); - ss_list_init(&white_list_rules); - ss_list_init(&outbound_block_list_rules); struct ss_ipset *list_ipv4 = &black_list_ipv4; struct ss_ipset *list_ipv6 = &black_list_ipv6; - struct ss_list *rules = &black_list_rules; + rule_list_t *rules = &black_list_rules; FILE *f = fopen(path, "r"); if (f == NULL) { @@ -264,13 +261,11 @@ init_acl(const char *path) } void -free_rules(struct ss_list *rules) +free_rules(rule_list_t *rules) { - struct ss_list_item *iter; - while ((iter = ss_list_head(rules)) != NULL) { - rule_t *rule = ss_container_of(iter, rule_t, entries); + rule_t *rule; + while ((rule = rules->front()) != NULL) remove_rule(rule); - } } void diff --git a/src/core.h b/src/core.h index b9b8d764..f67b7541 100644 --- a/src/core.h +++ b/src/core.h @@ -10,53 +10,6 @@ extern "C" { #endif -#define ss_container_of(ptr, type, member) ((type *)((char *)(ptr) - offsetof(type, member))) - -struct ss_list_item { - struct ss_list_item *next, *prev; -}; -struct ss_list { - struct ss_list_item head; -}; -static inline void -ss_list_init(struct ss_list *list) -{ - list->head.next = list->head.prev = &list->head; -} -static inline void -ss_list_add(struct ss_list *list, struct ss_list_item *item) -{ - item->prev = list->head.prev; - item->next = &list->head; - item->prev->next = item; - list->head.prev = item; -} -static inline void -ss_list_remove(struct ss_list_item *item) -{ - item->prev->next = item->next; - item->next->prev = item->prev; -} -static inline struct ss_list_item * -ss_list_start(const struct ss_list *list) -{ - return list->head.next; -} -static inline bool -ss_list_is_end(const struct ss_list *list, const struct ss_list_item *item) -{ - return item == &list->head; -} -static inline struct ss_list_item * -ss_list_head(const struct ss_list *list) -{ - return ss_list_is_end(list, list->head.next) ? NULL : list->head.next; -} -/* Cache the next link before the body so the current item may be freed. */ -#define ss_list_foreach_void(list, item, after) \ - for ((item) = ss_list_start(list), (after) = (item)->next; \ - !ss_list_is_end((list), (item)); (item) = (after), (after) = (item)->next) - struct ss_ip { unsigned version; uint8_t bytes[16]; diff --git a/src/core/intrusive_list.hpp b/src/core/intrusive_list.hpp index 89e4de74..ed682e23 100644 --- a/src/core/intrusive_list.hpp +++ b/src/core/intrusive_list.hpp @@ -84,6 +84,13 @@ public: T *front() noexcept { return empty() ? nullptr : owner(head_.next_); } T *back() noexcept { return empty() ? nullptr : owner(head_.prev_); } + // The element after `item` (which must be on this list), or null. + T *next(T &item) noexcept + { + Node *n = node(item)->next_; + return n == &head_ ? nullptr : owner(n); + } + T *pop_front() noexcept { T *item = front(); @@ -114,6 +121,18 @@ public: } } + // The first element `pred` accepts, or null. + template + T *find_if(P &&pred) + { + for (Node *p = head_.next_; p != &head_; p = p->next_) { + if (pred(*owner(p))) { + return owner(p); + } + } + return nullptr; + } + private: static Node *node(T &item) noexcept { return static_cast(&item); } static T *owner(Node *n) noexcept { return static_cast(n); } diff --git a/src/manager.cpp b/src/manager.cpp index 3654d25c..0aa67c08 100644 --- a/src/manager.cpp +++ b/src/manager.cpp @@ -43,6 +43,7 @@ #include #include +#include #include #include #include @@ -79,18 +80,12 @@ size_t working_dir_size = 0; /* The managed servers, looked up by port. There are at most MAX_PORT_NUM, * and lookups only happen on control messages, so a list does. */ -static struct ss_list server_table; +static ss::IntrusiveList server_table; static struct server * find_server(const char *port) { - struct ss_list_item *curr, *next; - ss_list_foreach_void(&server_table, curr, next) { - struct server *server = ss_container_of(curr, struct server, entries); - if (strcmp(server->port, port) == 0) - return server; - } - return NULL; + return server_table.find_if([port](struct server &server) { return strcmp(server.port, port) == 0; }); } static int @@ -142,6 +137,14 @@ destroy_server(struct server *server) ss_free(server->mode); } +static void +free_server(struct server *server) +{ + destroy_server(server); + server->~server(); // unlinks it from server_table + ss_free(server); +} + static void write_json_string(FILE *f, const char *str) { @@ -616,8 +619,7 @@ get_server(char *buf, int len) return NULL; } - struct server *server = (struct server *)ss_malloc(sizeof(struct server)); - memset(server, 0, sizeof(struct server)); + struct server *server = ::new (ss_malloc(sizeof(struct server))) struct server(); int valid = 1; if (obj->type == json_object) { int i = 0; @@ -685,8 +687,7 @@ get_server(char *buf, int len) json_value_free(obj); if (!valid) { - destroy_server(server); - ss_free(server); + free_server(server); return NULL; } return server; @@ -864,12 +865,8 @@ add_server(struct manager_ctx *manager, struct server *server) struct server *replaced = find_server(server->port); if (replaced != NULL) - ss_list_remove(&replaced->entries); - ss_list_add(&server_table, &server->entries); - if (replaced != NULL) { - destroy_server(replaced); - ss_free(replaced); - } + free_server(replaced); + server_table.push_back(*server); return 0; } @@ -945,9 +942,7 @@ remove_server(char *prefix, char *port) old_server = find_server(port); if (old_server != NULL) { - ss_list_remove(&old_server->entries); - destroy_server(old_server); - ss_free(old_server); + free_server(old_server); } stop_server(prefix, port); @@ -1003,8 +998,7 @@ manager_recv_cb(void *ctx) noexcept if (server == NULL || server->port[0] == 0 || server->password[0] == 0) { LOGE("invalid command: %s:%s", buf, get_data(buf, r)); if (server != NULL) { - destroy_server(server); - ss_free(server); + free_server(server); } goto ERROR_MSG; } @@ -1018,8 +1012,7 @@ manager_recv_cb(void *ctx) noexcept if (ret == -1) { msg = (char *)"port is not available"; msg_len = 21; - destroy_server(server); - ss_free(server); + free_server(server); } else { msg = (char *)"ok"; msg_len = 2; @@ -1029,13 +1022,12 @@ manager_recv_cb(void *ctx) noexcept ERROR("add_sendto"); } } else if (strcmp(action, "list") == 0) { - struct ss_list_item *curr, *next; char buf[BUF_SIZE]; memset(buf, 0, BUF_SIZE); strcpy(buf, "["); - ss_list_foreach_void(&server_table, curr, next) { - struct server *server = ss_container_of(curr, struct server, entries); + for (struct server *server = server_table.front(), *next; server != NULL; server = next) { + next = server_table.next(*server); char *method = server->method ? server->method : manager->method; char entry_buf[BUF_SIZE]; size_t entry_pos = 0; @@ -1069,15 +1061,13 @@ manager_recv_cb(void *ctx) noexcept if (server == NULL || server->port[0] == 0) { LOGE("invalid command: %s:%s", buf, get_data(buf, r)); if (server != NULL) { - destroy_server(server); - ss_free(server); + free_server(server); } goto ERROR_MSG; } remove_server(working_dir, server->port); - destroy_server(server); - ss_free(server); + free_server(server); char msg[3] = "ok"; if (sendto(manager->fd, msg, 2, 0, (struct sockaddr *)&claddr, len) != 2) { @@ -1095,8 +1085,6 @@ manager_recv_cb(void *ctx) noexcept update_stat(port, traffic); } else if (strcmp(action, "ping") == 0) { - struct ss_list_item *curr, *next; - char buf[BUF_SIZE]; size_t pos = 0; @@ -1105,8 +1093,8 @@ manager_recv_cb(void *ctx) noexcept goto ERROR_MSG; } - ss_list_foreach_void(&server_table, curr, next) { - struct server *server = ss_container_of(curr, struct server, entries); + for (struct server *server = server_table.front(), *next; server != NULL; server = next) { + next = server_table.next(*server); char entry_buf[64]; int entry_len = snprintf(entry_buf, sizeof(entry_buf), "\"%s\":%" PRIu64 ",", @@ -1769,22 +1757,20 @@ Same behavior as `-d`; see that option for details. Short alias: `-d`. FATAL("Couldn't open the directory"); } - ss_list_init(&server_table); if (conf != NULL) { for (i = 0; i < conf->port_password_num; i++) { - struct server *server = (struct server *)ss_malloc(sizeof(struct server)); - memset(server, 0, sizeof(struct server)); + struct server *server = ::new (ss_malloc(sizeof(struct server))) struct server(); if (copy_port(server->port, sizeof(server->port), conf->port_password[i].port, strlen(conf->port_password[i].port)) == -1) { LOGE("invalid port_password port"); - ss_free(server); + free_server(server); continue; } if (strlen(conf->port_password[i].password) >= sizeof(server->password)) { LOGE("port_password password is too long"); - ss_free(server); + free_server(server); continue; } strcpy(server->password, conf->port_password[i].password); @@ -1846,13 +1832,9 @@ Same behavior as `-d`; see that option for details. Short alias: `-d`. } // Clean up - struct ss_list_item *curr, *next; - ss_list_foreach_void(&server_table, curr, next) { - struct server *server = ss_container_of(curr, struct server, entries); + while (struct server *server = server_table.front()) { stop_server(working_dir, server->port); - ss_list_remove(&server->entries); - destroy_server(server); - ss_free(server); + free_server(server); } program.close(); diff --git a/src/manager.h b/src/manager.h index 25d6f8c9..9199e823 100644 --- a/src/manager.h +++ b/src/manager.h @@ -25,7 +25,7 @@ #include #include "core.h" -#include "core.h" +#include "core/intrusive_list.hpp" #include "jconf.h" @@ -63,17 +63,17 @@ struct manager_ctx { #endif }; -struct server { - struct ss_list_item entries; /* in server_table, at most MAX_PORT_NUM */ - char port[8]; - char password[128]; - char fast_open[8]; - char no_delay[8]; - char *mode; - char *method; - char *plugin; - char *plugin_opts; - uint64_t traffic; +/* A managed ss-server, linked into server_table (at most MAX_PORT_NUM). */ +struct server : ss::ListNode<> { + char port[8] = {}; + char password[128] = {}; + char fast_open[8] = {}; + char no_delay[8] = {}; + char *mode = nullptr; + char *method = nullptr; + char *plugin = nullptr; + char *plugin_opts = nullptr; + uint64_t traffic = 0; }; #ifdef __cplusplus diff --git a/src/rule.cpp b/src/rule.cpp index c76dade2..551cbe07 100644 --- a/src/rule.cpp +++ b/src/rule.cpp @@ -32,21 +32,21 @@ #include #include +#include + #include "rule.h" #include "utils.h" rule_t * new_rule() { - rule_t *rule; - - rule = (rule_t *)calloc(1, sizeof(rule_t)); - if (rule == NULL) { + void *mem = malloc(sizeof(rule_t)); // heap-ok: ACL rules are built at startup + if (mem == NULL) { ERROR("malloc"); return NULL; } - return rule; + return ::new (mem) rule_t(); } int @@ -67,9 +67,9 @@ accept_rule_arg(rule_t *rule, const char *arg) } void -add_rule(struct ss_list *rules, rule_t *rule) +add_rule(rule_list_t *rules, rule_t *rule) { - ss_list_add(rules, &rule->entries); + rules->push_back(*rule); } int @@ -124,42 +124,38 @@ literal_equal(const char *a, const char *b, size_t length) return true; } -rule_t * -lookup_rule(const struct ss_list *rules, const char *name, size_t name_len) +static bool +rule_matches(rule_t *rule, const char *name, size_t name_len) { - struct ss_list_item *curr, *next; + if (rule->kind != 0) { + size_t length = strlen(rule->literal); + return name_len >= length && + (name_len == length || (rule->kind == 2 && name[name_len - length - 1] == '.')) && + literal_equal(name + name_len - length, rule->literal, length); + } +#if SS_ENABLE_REGEX + return pcre2_match(rule->pattern_re, (PCRE2_SPTR)name, + name_len, 0, 0, rule->match_data, NULL) >= 0; +#else + return false; +#endif +} +rule_t * +lookup_rule(rule_list_t *rules, const char *name, size_t name_len) +{ if (name == NULL) { name = ""; name_len = 0; } - for (curr = ss_list_start(rules); !ss_list_is_end(rules, curr); - curr = next) { - next = curr->next; - rule_t *rule = ss_container_of(curr, rule_t, entries); - if (rule->kind != 0) { - size_t length = strlen(rule->literal); - if (name_len >= length && - (name_len == length || (rule->kind == 2 && name[name_len - length - 1] == '.')) && - literal_equal(name + name_len - length, rule->literal, length)) return rule; - continue; - } -#if SS_ENABLE_REGEX - if (pcre2_match(rule->pattern_re, (PCRE2_SPTR)name, - name_len, 0, 0, rule->match_data, NULL) >= 0) - return rule; -#endif - } - - return NULL; + return rules->find_if([&](rule_t &rule) { return rule_matches(&rule, name, name_len); }); } void remove_rule(rule_t *rule) { - ss_list_remove(&rule->entries); - free_rule(rule); + free_rule(rule); // the destructor unlinks it } void @@ -175,5 +171,6 @@ free_rule(rule_t *rule) if (rule->pattern_re != NULL) pcre2_code_free(rule->pattern_re); #endif + rule->~rule_t(); ss_free(rule); } diff --git a/src/rule.h b/src/rule.h index 45f19c4f..330b9b63 100644 --- a/src/rule.h +++ b/src/rule.h @@ -32,41 +32,37 @@ #endif #include "core.h" +#include "core/intrusive_list.hpp" #if SS_ENABLE_REGEX #define PCRE2_CODE_UNIT_WIDTH 8 #include #endif -#ifdef __cplusplus -extern "C" { -#endif - -typedef struct rule { - struct ss_list_item entries; - - char *pattern; +/* A domain rule, linked into one of the ACL's rule lists. Rules are built + * while the ACL loads and are immutable afterwards. Destroying a rule + * unlinks it. */ +typedef struct rule : ss::ListNode<> { + char *pattern = nullptr; /* 0: regex, 1: full domain, 2: domain suffix (including the apex). */ - unsigned kind; - const char *literal; + unsigned kind = 0; + const char *literal = nullptr; #if SS_ENABLE_REGEX /* Runtime fields */ - pcre2_code *pattern_re; - pcre2_match_data *match_data; + pcre2_code *pattern_re = nullptr; + pcre2_match_data *match_data = nullptr; #endif } rule_t; -void add_rule(struct ss_list *, rule_t *); +using rule_list_t = ss::IntrusiveList; + +void add_rule(rule_list_t *, rule_t *); int init_rule(rule_t *); -rule_t *lookup_rule(const struct ss_list *, const char *, size_t); +rule_t *lookup_rule(rule_list_t *, const char *, size_t); void free_rule(rule_t *); void remove_rule(rule_t *); rule_t *new_rule(); int accept_rule_arg(rule_t *, const char *); -#ifdef __cplusplus -} -#endif - #endif diff --git a/src/uthash.h b/src/uthash.h deleted file mode 100644 index 45d1f9fc..00000000 --- a/src/uthash.h +++ /dev/null @@ -1,1074 +0,0 @@ -/* -Copyright (c) 2003-2016, Troy D. Hanson http://troydhanson.github.com/uthash/ -All rights reserved. - -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright - notice, this list of conditions and the following disclaimer. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS -IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED -TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A -PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER -OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, -EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, -PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR -PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF -LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING -NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS -SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. -*/ - -#ifndef UTHASH_H -#define UTHASH_H - -#define UTHASH_VERSION 2.0.1 - -#include /* memcmp,strlen */ -#include /* ptrdiff_t */ -#include /* exit() */ - -/* These macros use decltype or the earlier __typeof GNU extension. - As decltype is only available in newer compilers (VS2010 or gcc 4.3+ - when compiling c++ source) this code uses whatever method is needed - or, for VS2008 where neither is available, uses casting workarounds. */ -#if defined(_MSC_VER) /* MS compiler */ -#if _MSC_VER >= 1600 && defined(__cplusplus) /* VS2010 or newer in C++ mode */ -#define DECLTYPE(x) (decltype(x)) -#else /* VS2008 or older (or VS2010 in C mode) */ -#define NO_DECLTYPE -#define DECLTYPE(x) -#endif -#elif defined(__BORLANDC__) || defined(__LCC__) || defined(__WATCOMC__) -#define NO_DECLTYPE -#define DECLTYPE(x) -#else /* GNU, Sun and other compilers */ -#define DECLTYPE(x) (__typeof(x)) -#endif - -#ifdef NO_DECLTYPE -#define DECLTYPE_ASSIGN(dst,src) \ -do { \ - char **_da_dst = (char**)(&(dst)); \ - *_da_dst = (char*)(src); \ -} while (0) -#else -#define DECLTYPE_ASSIGN(dst,src) \ -do { \ - (dst) = DECLTYPE(dst)(src); \ -} while (0) -#endif - -/* a number of the hash function use uint32_t which isn't defined on Pre VS2010 */ -#if defined(_WIN32) -#if defined(_MSC_VER) && _MSC_VER >= 1600 -#include -#elif defined(__WATCOMC__) || defined(__MINGW32__) || defined(__CYGWIN__) -#include -#else -typedef unsigned int uint32_t; -typedef unsigned char uint8_t; -#endif -#elif defined(__GNUC__) && !defined(__VXWORKS__) -#include -#else -typedef unsigned int uint32_t; -typedef unsigned char uint8_t; -#endif - -#ifndef uthash_fatal -#define uthash_fatal(msg) exit(-1) /* fatal error (out of memory,etc) */ -#endif -#ifndef uthash_malloc -#define uthash_malloc(sz) malloc(sz) /* malloc fcn */ -#endif -#ifndef uthash_free -#define uthash_free(ptr,sz) free(ptr) /* free fcn */ -#endif -#ifndef uthash_strlen -#define uthash_strlen(s) strlen(s) -#endif -#ifndef uthash_memcmp -#define uthash_memcmp(a,b,n) memcmp(a,b,n) -#endif - -#ifndef uthash_noexpand_fyi -#define uthash_noexpand_fyi(tbl) /* can be defined to log noexpand */ -#endif -#ifndef uthash_expand_fyi -#define uthash_expand_fyi(tbl) /* can be defined to log expands */ -#endif - -/* initial number of buckets */ -#define HASH_INITIAL_NUM_BUCKETS 32U /* initial number of buckets */ -#define HASH_INITIAL_NUM_BUCKETS_LOG2 5U /* lg2 of initial number of buckets */ -#define HASH_BKT_CAPACITY_THRESH 10U /* expand when bucket count reaches */ - -/* calculate the element whose hash handle address is hhp */ -#define ELMT_FROM_HH(tbl,hhp) ((void*)(((char*)(hhp)) - ((tbl)->hho))) -/* calculate the hash handle from element address elp */ -#define HH_FROM_ELMT(tbl,elp) ((UT_hash_handle *)(((char*)(elp)) + ((tbl)->hho))) - -#define HASH_VALUE(keyptr,keylen,hashv) \ -do { \ - HASH_FCN(keyptr, keylen, hashv); \ -} while (0) - -#define HASH_FIND_BYHASHVALUE(hh,head,keyptr,keylen,hashval,out) \ -do { \ - (out) = NULL; \ - if (head) { \ - unsigned _hf_bkt; \ - HASH_TO_BKT(hashval, (head)->hh.tbl->num_buckets, _hf_bkt); \ - if (HASH_BLOOM_TEST((head)->hh.tbl, hashval) != 0) { \ - HASH_FIND_IN_BKT((head)->hh.tbl, hh, (head)->hh.tbl->buckets[ _hf_bkt ], keyptr, keylen, hashval, out); \ - } \ - } \ -} while (0) - -#define HASH_FIND(hh,head,keyptr,keylen,out) \ -do { \ - unsigned _hf_hashv; \ - HASH_VALUE(keyptr, keylen, _hf_hashv); \ - HASH_FIND_BYHASHVALUE(hh, head, keyptr, keylen, _hf_hashv, out); \ -} while (0) - -#ifdef HASH_BLOOM -#define HASH_BLOOM_BITLEN (1UL << HASH_BLOOM) -#define HASH_BLOOM_BYTELEN (HASH_BLOOM_BITLEN/8UL) + (((HASH_BLOOM_BITLEN%8UL)!=0UL) ? 1UL : 0UL) -#define HASH_BLOOM_MAKE(tbl) \ -do { \ - (tbl)->bloom_nbits = HASH_BLOOM; \ - (tbl)->bloom_bv = (uint8_t*)uthash_malloc(HASH_BLOOM_BYTELEN); \ - if (!((tbl)->bloom_bv)) { uthash_fatal( "out of memory"); } \ - memset((tbl)->bloom_bv, 0, HASH_BLOOM_BYTELEN); \ - (tbl)->bloom_sig = HASH_BLOOM_SIGNATURE; \ -} while (0) - -#define HASH_BLOOM_FREE(tbl) \ -do { \ - uthash_free((tbl)->bloom_bv, HASH_BLOOM_BYTELEN); \ -} while (0) - -#define HASH_BLOOM_BITSET(bv,idx) (bv[(idx)/8U] |= (1U << ((idx)%8U))) -#define HASH_BLOOM_BITTEST(bv,idx) (bv[(idx)/8U] & (1U << ((idx)%8U))) - -#define HASH_BLOOM_ADD(tbl,hashv) \ - HASH_BLOOM_BITSET((tbl)->bloom_bv, (hashv & (uint32_t)((1ULL << (tbl)->bloom_nbits) - 1U))) - -#define HASH_BLOOM_TEST(tbl,hashv) \ - HASH_BLOOM_BITTEST((tbl)->bloom_bv, (hashv & (uint32_t)((1ULL << (tbl)->bloom_nbits) - 1U))) - -#else -#define HASH_BLOOM_MAKE(tbl) -#define HASH_BLOOM_FREE(tbl) -#define HASH_BLOOM_ADD(tbl,hashv) -#define HASH_BLOOM_TEST(tbl,hashv) (1) -#define HASH_BLOOM_BYTELEN 0U -#endif - -#define HASH_MAKE_TABLE(hh,head) \ -do { \ - (head)->hh.tbl = (UT_hash_table*)uthash_malloc( \ - sizeof(UT_hash_table)); \ - if (!((head)->hh.tbl)) { uthash_fatal( "out of memory"); } \ - memset((head)->hh.tbl, 0, sizeof(UT_hash_table)); \ - (head)->hh.tbl->tail = &((head)->hh); \ - (head)->hh.tbl->num_buckets = HASH_INITIAL_NUM_BUCKETS; \ - (head)->hh.tbl->log2_num_buckets = HASH_INITIAL_NUM_BUCKETS_LOG2; \ - (head)->hh.tbl->hho = (char*)(&(head)->hh) - (char*)(head); \ - (head)->hh.tbl->buckets = (UT_hash_bucket*)uthash_malloc( \ - HASH_INITIAL_NUM_BUCKETS*sizeof(struct UT_hash_bucket)); \ - if (! (head)->hh.tbl->buckets) { uthash_fatal( "out of memory"); } \ - memset((head)->hh.tbl->buckets, 0, \ - HASH_INITIAL_NUM_BUCKETS*sizeof(struct UT_hash_bucket)); \ - HASH_BLOOM_MAKE((head)->hh.tbl); \ - (head)->hh.tbl->signature = HASH_SIGNATURE; \ -} while (0) - -#define HASH_REPLACE_BYHASHVALUE_INORDER(hh,head,fieldname,keylen_in,hashval,add,replaced,cmpfcn) \ -do { \ - (replaced) = NULL; \ - HASH_FIND_BYHASHVALUE(hh, head, &((add)->fieldname), keylen_in, hashval, replaced); \ - if (replaced) { \ - HASH_DELETE(hh, head, replaced); \ - } \ - HASH_ADD_KEYPTR_BYHASHVALUE_INORDER(hh, head, &((add)->fieldname), keylen_in, hashval, add, cmpfcn); \ -} while (0) - -#define HASH_REPLACE_BYHASHVALUE(hh,head,fieldname,keylen_in,hashval,add,replaced) \ -do { \ - (replaced) = NULL; \ - HASH_FIND_BYHASHVALUE(hh, head, &((add)->fieldname), keylen_in, hashval, replaced); \ - if (replaced) { \ - HASH_DELETE(hh, head, replaced); \ - } \ - HASH_ADD_KEYPTR_BYHASHVALUE(hh, head, &((add)->fieldname), keylen_in, hashval, add); \ -} while (0) - -#define HASH_REPLACE(hh,head,fieldname,keylen_in,add,replaced) \ -do { \ - unsigned _hr_hashv; \ - HASH_VALUE(&((add)->fieldname), keylen_in, _hr_hashv); \ - HASH_REPLACE_BYHASHVALUE(hh, head, fieldname, keylen_in, _hr_hashv, add, replaced); \ -} while (0) - -#define HASH_REPLACE_INORDER(hh,head,fieldname,keylen_in,add,replaced,cmpfcn) \ -do { \ - unsigned _hr_hashv; \ - HASH_VALUE(&((add)->fieldname), keylen_in, _hr_hashv); \ - HASH_REPLACE_BYHASHVALUE_INORDER(hh, head, fieldname, keylen_in, _hr_hashv, add, replaced, cmpfcn); \ -} while (0) - -#define HASH_APPEND_LIST(hh, head, add) \ -do { \ - (add)->hh.next = NULL; \ - (add)->hh.prev = ELMT_FROM_HH((head)->hh.tbl, (head)->hh.tbl->tail); \ - (head)->hh.tbl->tail->next = (add); \ - (head)->hh.tbl->tail = &((add)->hh); \ -} while (0) - -#define HASH_ADD_KEYPTR_BYHASHVALUE_INORDER(hh,head,keyptr,keylen_in,hashval,add,cmpfcn) \ -do { \ - unsigned _ha_bkt; \ - (add)->hh.hashv = (hashval); \ - (add)->hh.key = (char*) (keyptr); \ - (add)->hh.keylen = (unsigned) (keylen_in); \ - if (!(head)) { \ - (add)->hh.next = NULL; \ - (add)->hh.prev = NULL; \ - (head) = (add); \ - HASH_MAKE_TABLE(hh, head); \ - } else { \ - struct UT_hash_handle *_hs_iter = &(head)->hh; \ - (add)->hh.tbl = (head)->hh.tbl; \ - do { \ - if (cmpfcn(DECLTYPE(head) ELMT_FROM_HH((head)->hh.tbl, _hs_iter), add) > 0) \ - break; \ - } while ((_hs_iter = _hs_iter->next)); \ - if (_hs_iter) { \ - (add)->hh.next = _hs_iter; \ - if (((add)->hh.prev = _hs_iter->prev)) { \ - HH_FROM_ELMT((head)->hh.tbl, _hs_iter->prev)->next = (add); \ - } else { \ - (head) = (add); \ - } \ - _hs_iter->prev = (add); \ - } else { \ - HASH_APPEND_LIST(hh, head, add); \ - } \ - } \ - (head)->hh.tbl->num_items++; \ - HASH_TO_BKT(hashval, (head)->hh.tbl->num_buckets, _ha_bkt); \ - HASH_ADD_TO_BKT((head)->hh.tbl->buckets[_ha_bkt], &(add)->hh); \ - HASH_BLOOM_ADD((head)->hh.tbl, hashval); \ - HASH_EMIT_KEY(hh, head, keyptr, keylen_in); \ - HASH_FSCK(hh, head); \ -} while (0) - -#define HASH_ADD_KEYPTR_INORDER(hh,head,keyptr,keylen_in,add,cmpfcn) \ -do { \ - unsigned _hs_hashv; \ - HASH_VALUE(keyptr, keylen_in, _hs_hashv); \ - HASH_ADD_KEYPTR_BYHASHVALUE_INORDER(hh, head, keyptr, keylen_in, _hs_hashv, add, cmpfcn); \ -} while (0) - -#define HASH_ADD_BYHASHVALUE_INORDER(hh,head,fieldname,keylen_in,hashval,add,cmpfcn) \ - HASH_ADD_KEYPTR_BYHASHVALUE_INORDER(hh, head, &((add)->fieldname), keylen_in, hashval, add, cmpfcn) - -#define HASH_ADD_INORDER(hh,head,fieldname,keylen_in,add,cmpfcn) \ - HASH_ADD_KEYPTR_INORDER(hh, head, &((add)->fieldname), keylen_in, add, cmpfcn) - -#define HASH_ADD_KEYPTR_BYHASHVALUE(hh,head,keyptr,keylen_in,hashval,add) \ -do { \ - unsigned _ha_bkt; \ - (add)->hh.hashv = (hashval); \ - (add)->hh.key = (char*) (keyptr); \ - (add)->hh.keylen = (unsigned) (keylen_in); \ - if (!(head)) { \ - (add)->hh.next = NULL; \ - (add)->hh.prev = NULL; \ - (head) = (add); \ - HASH_MAKE_TABLE(hh, head); \ - } else { \ - (add)->hh.tbl = (head)->hh.tbl; \ - HASH_APPEND_LIST(hh, head, add); \ - } \ - (head)->hh.tbl->num_items++; \ - HASH_TO_BKT(hashval, (head)->hh.tbl->num_buckets, _ha_bkt); \ - HASH_ADD_TO_BKT((head)->hh.tbl->buckets[_ha_bkt], &(add)->hh); \ - HASH_BLOOM_ADD((head)->hh.tbl, hashval); \ - HASH_EMIT_KEY(hh, head, keyptr, keylen_in); \ - HASH_FSCK(hh, head); \ -} while (0) - -#define HASH_ADD_KEYPTR(hh,head,keyptr,keylen_in,add) \ -do { \ - unsigned _ha_hashv; \ - HASH_VALUE(keyptr, keylen_in, _ha_hashv); \ - HASH_ADD_KEYPTR_BYHASHVALUE(hh, head, keyptr, keylen_in, _ha_hashv, add); \ -} while (0) - -#define HASH_ADD_BYHASHVALUE(hh,head,fieldname,keylen_in,hashval,add) \ - HASH_ADD_KEYPTR_BYHASHVALUE(hh, head, &((add)->fieldname), keylen_in, hashval, add) - -#define HASH_ADD(hh,head,fieldname,keylen_in,add) \ - HASH_ADD_KEYPTR(hh, head, &((add)->fieldname), keylen_in, add) - -#define HASH_TO_BKT(hashv,num_bkts,bkt) \ -do { \ - bkt = ((hashv) & ((num_bkts) - 1U)); \ -} while (0) - -/* delete "delptr" from the hash table. - * "the usual" patch-up process for the app-order doubly-linked-list. - * The use of _hd_hh_del below deserves special explanation. - * These used to be expressed using (delptr) but that led to a bug - * if someone used the same symbol for the head and deletee, like - * HASH_DELETE(hh,users,users); - * We want that to work, but by changing the head (users) below - * we were forfeiting our ability to further refer to the deletee (users) - * in the patch-up process. Solution: use scratch space to - * copy the deletee pointer, then the latter references are via that - * scratch pointer rather than through the repointed (users) symbol. - */ -#define HASH_DELETE(hh,head,delptr) \ -do { \ - struct UT_hash_handle *_hd_hh_del; \ - if ( ((delptr)->hh.prev == NULL) && ((delptr)->hh.next == NULL) ) { \ - uthash_free((head)->hh.tbl->buckets, \ - (head)->hh.tbl->num_buckets*sizeof(struct UT_hash_bucket) ); \ - HASH_BLOOM_FREE((head)->hh.tbl); \ - uthash_free((head)->hh.tbl, sizeof(UT_hash_table)); \ - head = NULL; \ - } else { \ - unsigned _hd_bkt; \ - _hd_hh_del = &((delptr)->hh); \ - if ((delptr) == ELMT_FROM_HH((head)->hh.tbl,(head)->hh.tbl->tail)) { \ - (head)->hh.tbl->tail = \ - (UT_hash_handle*)((ptrdiff_t)((delptr)->hh.prev) + \ - (head)->hh.tbl->hho); \ - } \ - if ((delptr)->hh.prev != NULL) { \ - ((UT_hash_handle*)((ptrdiff_t)((delptr)->hh.prev) + \ - (head)->hh.tbl->hho))->next = (delptr)->hh.next; \ - } else { \ - DECLTYPE_ASSIGN(head,(delptr)->hh.next); \ - } \ - if (_hd_hh_del->next != NULL) { \ - ((UT_hash_handle*)((ptrdiff_t)_hd_hh_del->next + \ - (head)->hh.tbl->hho))->prev = \ - _hd_hh_del->prev; \ - } \ - HASH_TO_BKT( _hd_hh_del->hashv, (head)->hh.tbl->num_buckets, _hd_bkt); \ - HASH_DEL_IN_BKT(hh,(head)->hh.tbl->buckets[_hd_bkt], _hd_hh_del); \ - (head)->hh.tbl->num_items--; \ - } \ - HASH_FSCK(hh,head); \ -} while (0) - - -/* convenience forms of HASH_FIND/HASH_ADD/HASH_DEL */ -#define HASH_FIND_STR(head,findstr,out) \ - HASH_FIND(hh,head,findstr,(unsigned)uthash_strlen(findstr),out) -#define HASH_ADD_STR(head,strfield,add) \ - HASH_ADD(hh,head,strfield[0],(unsigned)uthash_strlen(add->strfield),add) -#define HASH_REPLACE_STR(head,strfield,add,replaced) \ - HASH_REPLACE(hh,head,strfield[0],(unsigned)uthash_strlen(add->strfield),add,replaced) -#define HASH_FIND_INT(head,findint,out) \ - HASH_FIND(hh,head,findint,sizeof(int),out) -#define HASH_ADD_INT(head,intfield,add) \ - HASH_ADD(hh,head,intfield,sizeof(int),add) -#define HASH_REPLACE_INT(head,intfield,add,replaced) \ - HASH_REPLACE(hh,head,intfield,sizeof(int),add,replaced) -#define HASH_FIND_PTR(head,findptr,out) \ - HASH_FIND(hh,head,findptr,sizeof(void *),out) -#define HASH_ADD_PTR(head,ptrfield,add) \ - HASH_ADD(hh,head,ptrfield,sizeof(void *),add) -#define HASH_REPLACE_PTR(head,ptrfield,add,replaced) \ - HASH_REPLACE(hh,head,ptrfield,sizeof(void *),add,replaced) -#define HASH_DEL(head,delptr) \ - HASH_DELETE(hh,head,delptr) - -/* HASH_FSCK checks hash integrity on every add/delete when HASH_DEBUG is defined. - * This is for uthash developer only; it compiles away if HASH_DEBUG isn't defined. - */ -#ifdef HASH_DEBUG -#define HASH_OOPS(...) do { fprintf(stderr,__VA_ARGS__); exit(-1); } while (0) -#define HASH_FSCK(hh,head) \ -do { \ - struct UT_hash_handle *_thh; \ - if (head) { \ - unsigned _bkt_i; \ - unsigned _count; \ - char *_prev; \ - _count = 0; \ - for( _bkt_i = 0; _bkt_i < (head)->hh.tbl->num_buckets; _bkt_i++) { \ - unsigned _bkt_count = 0; \ - _thh = (head)->hh.tbl->buckets[_bkt_i].hh_head; \ - _prev = NULL; \ - while (_thh) { \ - if (_prev != (char*)(_thh->hh_prev)) { \ - HASH_OOPS("invalid hh_prev %p, actual %p\n", \ - _thh->hh_prev, _prev ); \ - } \ - _bkt_count++; \ - _prev = (char*)(_thh); \ - _thh = _thh->hh_next; \ - } \ - _count += _bkt_count; \ - if ((head)->hh.tbl->buckets[_bkt_i].count != _bkt_count) { \ - HASH_OOPS("invalid bucket count %u, actual %u\n", \ - (head)->hh.tbl->buckets[_bkt_i].count, _bkt_count); \ - } \ - } \ - if (_count != (head)->hh.tbl->num_items) { \ - HASH_OOPS("invalid hh item count %u, actual %u\n", \ - (head)->hh.tbl->num_items, _count ); \ - } \ - /* traverse hh in app order; check next/prev integrity, count */ \ - _count = 0; \ - _prev = NULL; \ - _thh = &(head)->hh; \ - while (_thh) { \ - _count++; \ - if (_prev !=(char*)(_thh->prev)) { \ - HASH_OOPS("invalid prev %p, actual %p\n", \ - _thh->prev, _prev ); \ - } \ - _prev = (char*)ELMT_FROM_HH((head)->hh.tbl, _thh); \ - _thh = ( _thh->next ? (UT_hash_handle*)((char*)(_thh->next) + \ - (head)->hh.tbl->hho) : NULL ); \ - } \ - if (_count != (head)->hh.tbl->num_items) { \ - HASH_OOPS("invalid app item count %u, actual %u\n", \ - (head)->hh.tbl->num_items, _count ); \ - } \ - } \ -} while (0) -#else -#define HASH_FSCK(hh,head) -#endif - -/* When compiled with -DHASH_EMIT_KEYS, length-prefixed keys are emitted to - * the descriptor to which this macro is defined for tuning the hash function. - * The app can #include to get the prototype for write(2). */ -#ifdef HASH_EMIT_KEYS -#define HASH_EMIT_KEY(hh,head,keyptr,fieldlen) \ -do { \ - unsigned _klen = fieldlen; \ - write(HASH_EMIT_KEYS, &_klen, sizeof(_klen)); \ - write(HASH_EMIT_KEYS, keyptr, (unsigned long)fieldlen); \ -} while (0) -#else -#define HASH_EMIT_KEY(hh,head,keyptr,fieldlen) -#endif - -/* default to Jenkin's hash unless overridden e.g. DHASH_FUNCTION=HASH_SAX */ -#ifdef HASH_FUNCTION -#define HASH_FCN HASH_FUNCTION -#else -#define HASH_FCN HASH_JEN -#endif - -/* The Bernstein hash function, used in Perl prior to v5.6. Note (x<<5+x)=x*33. */ -#define HASH_BER(key,keylen,hashv) \ -do { \ - unsigned _hb_keylen=(unsigned)keylen; \ - const unsigned char *_hb_key=(const unsigned char*)(key); \ - (hashv) = 0; \ - while (_hb_keylen-- != 0U) { \ - (hashv) = (((hashv) << 5) + (hashv)) + *_hb_key++; \ - } \ -} while (0) - - -/* SAX/FNV/OAT/JEN hash functions are macro variants of those listed at - * http://eternallyconfuzzled.com/tuts/algorithms/jsw_tut_hashing.aspx */ -#define HASH_SAX(key,keylen,hashv) \ -do { \ - unsigned _sx_i; \ - const unsigned char *_hs_key=(const unsigned char*)(key); \ - hashv = 0; \ - for(_sx_i=0; _sx_i < keylen; _sx_i++) { \ - hashv ^= (hashv << 5) + (hashv >> 2) + _hs_key[_sx_i]; \ - } \ -} while (0) -/* FNV-1a variation */ -#define HASH_FNV(key,keylen,hashv) \ -do { \ - unsigned _fn_i; \ - const unsigned char *_hf_key=(const unsigned char*)(key); \ - hashv = 2166136261U; \ - for(_fn_i=0; _fn_i < keylen; _fn_i++) { \ - hashv = hashv ^ _hf_key[_fn_i]; \ - hashv = hashv * 16777619U; \ - } \ -} while (0) - -#define HASH_OAT(key,keylen,hashv) \ -do { \ - unsigned _ho_i; \ - const unsigned char *_ho_key=(const unsigned char*)(key); \ - hashv = 0; \ - for(_ho_i=0; _ho_i < keylen; _ho_i++) { \ - hashv += _ho_key[_ho_i]; \ - hashv += (hashv << 10); \ - hashv ^= (hashv >> 6); \ - } \ - hashv += (hashv << 3); \ - hashv ^= (hashv >> 11); \ - hashv += (hashv << 15); \ -} while (0) - -#define HASH_JEN_MIX(a,b,c) \ -do { \ - a -= b; a -= c; a ^= ( c >> 13 ); \ - b -= c; b -= a; b ^= ( a << 8 ); \ - c -= a; c -= b; c ^= ( b >> 13 ); \ - a -= b; a -= c; a ^= ( c >> 12 ); \ - b -= c; b -= a; b ^= ( a << 16 ); \ - c -= a; c -= b; c ^= ( b >> 5 ); \ - a -= b; a -= c; a ^= ( c >> 3 ); \ - b -= c; b -= a; b ^= ( a << 10 ); \ - c -= a; c -= b; c ^= ( b >> 15 ); \ -} while (0) - -#define HASH_JEN(key,keylen,hashv) \ -do { \ - unsigned _hj_i,_hj_j,_hj_k; \ - unsigned const char *_hj_key=(unsigned const char*)(key); \ - hashv = 0xfeedbeefu; \ - _hj_i = _hj_j = 0x9e3779b9u; \ - _hj_k = (unsigned)(keylen); \ - while (_hj_k >= 12U) { \ - _hj_i += (_hj_key[0] + ( (unsigned)_hj_key[1] << 8 ) \ - + ( (unsigned)_hj_key[2] << 16 ) \ - + ( (unsigned)_hj_key[3] << 24 ) ); \ - _hj_j += (_hj_key[4] + ( (unsigned)_hj_key[5] << 8 ) \ - + ( (unsigned)_hj_key[6] << 16 ) \ - + ( (unsigned)_hj_key[7] << 24 ) ); \ - hashv += (_hj_key[8] + ( (unsigned)_hj_key[9] << 8 ) \ - + ( (unsigned)_hj_key[10] << 16 ) \ - + ( (unsigned)_hj_key[11] << 24 ) ); \ - \ - HASH_JEN_MIX(_hj_i, _hj_j, hashv); \ - \ - _hj_key += 12; \ - _hj_k -= 12U; \ - } \ - hashv += (unsigned)(keylen); \ - switch ( _hj_k ) { \ - case 11: hashv += ( (unsigned)_hj_key[10] << 24 ); /* FALLTHROUGH */ \ - case 10: hashv += ( (unsigned)_hj_key[9] << 16 ); /* FALLTHROUGH */ \ - case 9: hashv += ( (unsigned)_hj_key[8] << 8 ); /* FALLTHROUGH */ \ - case 8: _hj_j += ( (unsigned)_hj_key[7] << 24 ); /* FALLTHROUGH */ \ - case 7: _hj_j += ( (unsigned)_hj_key[6] << 16 ); /* FALLTHROUGH */ \ - case 6: _hj_j += ( (unsigned)_hj_key[5] << 8 ); /* FALLTHROUGH */ \ - case 5: _hj_j += _hj_key[4]; /* FALLTHROUGH */ \ - case 4: _hj_i += ( (unsigned)_hj_key[3] << 24 ); /* FALLTHROUGH */ \ - case 3: _hj_i += ( (unsigned)_hj_key[2] << 16 ); /* FALLTHROUGH */ \ - case 2: _hj_i += ( (unsigned)_hj_key[1] << 8 ); /* FALLTHROUGH */ \ - case 1: _hj_i += _hj_key[0]; \ - } \ - HASH_JEN_MIX(_hj_i, _hj_j, hashv); \ -} while (0) - -/* The Paul Hsieh hash function */ -#undef get16bits -#if (defined(__GNUC__) && defined(__i386__)) || defined(__WATCOMC__) \ - || defined(_MSC_VER) || defined (__BORLANDC__) || defined (__TURBOC__) -#define get16bits(d) (*((const uint16_t *) (d))) -#endif - -#if !defined (get16bits) -#define get16bits(d) ((((uint32_t)(((const uint8_t *)(d))[1])) << 8) \ - +(uint32_t)(((const uint8_t *)(d))[0]) ) -#endif -#define HASH_SFH(key,keylen,hashv) \ -do { \ - unsigned const char *_sfh_key=(unsigned const char*)(key); \ - uint32_t _sfh_tmp, _sfh_len = (uint32_t)keylen; \ - \ - unsigned _sfh_rem = _sfh_len & 3U; \ - _sfh_len >>= 2; \ - hashv = 0xcafebabeu; \ - \ - /* Main loop */ \ - for (;_sfh_len > 0U; _sfh_len--) { \ - hashv += get16bits (_sfh_key); \ - _sfh_tmp = ((uint32_t)(get16bits (_sfh_key+2)) << 11) ^ hashv; \ - hashv = (hashv << 16) ^ _sfh_tmp; \ - _sfh_key += 2U*sizeof (uint16_t); \ - hashv += hashv >> 11; \ - } \ - \ - /* Handle end cases */ \ - switch (_sfh_rem) { \ - case 3: hashv += get16bits (_sfh_key); \ - hashv ^= hashv << 16; \ - hashv ^= (uint32_t)(_sfh_key[sizeof (uint16_t)]) << 18; \ - hashv += hashv >> 11; \ - break; \ - case 2: hashv += get16bits (_sfh_key); \ - hashv ^= hashv << 11; \ - hashv += hashv >> 17; \ - break; \ - case 1: hashv += *_sfh_key; \ - hashv ^= hashv << 10; \ - hashv += hashv >> 1; \ - } \ - \ - /* Force "avalanching" of final 127 bits */ \ - hashv ^= hashv << 3; \ - hashv += hashv >> 5; \ - hashv ^= hashv << 4; \ - hashv += hashv >> 17; \ - hashv ^= hashv << 25; \ - hashv += hashv >> 6; \ -} while (0) - -#ifdef HASH_USING_NO_STRICT_ALIASING -/* The MurmurHash exploits some CPU's (x86,x86_64) tolerance for unaligned reads. - * For other types of CPU's (e.g. Sparc) an unaligned read causes a bus error. - * MurmurHash uses the faster approach only on CPU's where we know it's safe. - * - * Note the preprocessor built-in defines can be emitted using: - * - * gcc -m64 -dM -E - < /dev/null (on gcc) - * cc -## a.c (where a.c is a simple test file) (Sun Studio) - */ -#if (defined(__i386__) || defined(__x86_64__) || defined(_M_IX86)) -#define MUR_GETBLOCK(p,i) p[i] -#else /* non intel */ -#define MUR_PLUS0_ALIGNED(p) (((unsigned long)p & 3UL) == 0UL) -#define MUR_PLUS1_ALIGNED(p) (((unsigned long)p & 3UL) == 1UL) -#define MUR_PLUS2_ALIGNED(p) (((unsigned long)p & 3UL) == 2UL) -#define MUR_PLUS3_ALIGNED(p) (((unsigned long)p & 3UL) == 3UL) -#define WP(p) ((uint32_t*)((unsigned long)(p) & ~3UL)) -#if (defined(__BIG_ENDIAN__) || defined(SPARC) || defined(__ppc__) || defined(__ppc64__)) -#define MUR_THREE_ONE(p) ((((*WP(p))&0x00ffffff) << 8) | (((*(WP(p)+1))&0xff000000) >> 24)) -#define MUR_TWO_TWO(p) ((((*WP(p))&0x0000ffff) <<16) | (((*(WP(p)+1))&0xffff0000) >> 16)) -#define MUR_ONE_THREE(p) ((((*WP(p))&0x000000ff) <<24) | (((*(WP(p)+1))&0xffffff00) >> 8)) -#else /* assume little endian non-intel */ -#define MUR_THREE_ONE(p) ((((*WP(p))&0xffffff00) >> 8) | (((*(WP(p)+1))&0x000000ff) << 24)) -#define MUR_TWO_TWO(p) ((((*WP(p))&0xffff0000) >>16) | (((*(WP(p)+1))&0x0000ffff) << 16)) -#define MUR_ONE_THREE(p) ((((*WP(p))&0xff000000) >>24) | (((*(WP(p)+1))&0x00ffffff) << 8)) -#endif -#define MUR_GETBLOCK(p,i) (MUR_PLUS0_ALIGNED(p) ? ((p)[i]) : \ - (MUR_PLUS1_ALIGNED(p) ? MUR_THREE_ONE(p) : \ - (MUR_PLUS2_ALIGNED(p) ? MUR_TWO_TWO(p) : \ - MUR_ONE_THREE(p)))) -#endif -#define MUR_ROTL32(x,r) (((x) << (r)) | ((x) >> (32 - (r)))) -#define MUR_FMIX(_h) \ -do { \ - _h ^= _h >> 16; \ - _h *= 0x85ebca6bu; \ - _h ^= _h >> 13; \ - _h *= 0xc2b2ae35u; \ - _h ^= _h >> 16; \ -} while (0) - -#define HASH_MUR(key,keylen,hashv) \ -do { \ - const uint8_t *_mur_data = (const uint8_t*)(key); \ - const int _mur_nblocks = (int)(keylen) / 4; \ - uint32_t _mur_h1 = 0xf88D5353u; \ - uint32_t _mur_c1 = 0xcc9e2d51u; \ - uint32_t _mur_c2 = 0x1b873593u; \ - uint32_t _mur_k1 = 0; \ - const uint8_t *_mur_tail; \ - const uint32_t *_mur_blocks = (const uint32_t*)(_mur_data+(_mur_nblocks*4)); \ - int _mur_i; \ - for(_mur_i = -_mur_nblocks; _mur_i!=0; _mur_i++) { \ - _mur_k1 = MUR_GETBLOCK(_mur_blocks,_mur_i); \ - _mur_k1 *= _mur_c1; \ - _mur_k1 = MUR_ROTL32(_mur_k1,15); \ - _mur_k1 *= _mur_c2; \ - \ - _mur_h1 ^= _mur_k1; \ - _mur_h1 = MUR_ROTL32(_mur_h1,13); \ - _mur_h1 = (_mur_h1*5U) + 0xe6546b64u; \ - } \ - _mur_tail = (const uint8_t*)(_mur_data + (_mur_nblocks*4)); \ - _mur_k1=0; \ - switch((keylen) & 3U) { \ - case 3: _mur_k1 ^= (uint32_t)_mur_tail[2] << 16; /* FALLTHROUGH */ \ - case 2: _mur_k1 ^= (uint32_t)_mur_tail[1] << 8; /* FALLTHROUGH */ \ - case 1: _mur_k1 ^= (uint32_t)_mur_tail[0]; \ - _mur_k1 *= _mur_c1; \ - _mur_k1 = MUR_ROTL32(_mur_k1,15); \ - _mur_k1 *= _mur_c2; \ - _mur_h1 ^= _mur_k1; \ - } \ - _mur_h1 ^= (uint32_t)(keylen); \ - MUR_FMIX(_mur_h1); \ - hashv = _mur_h1; \ -} while (0) -#endif /* HASH_USING_NO_STRICT_ALIASING */ - -/* iterate over items in a known bucket to find desired item */ -#define HASH_FIND_IN_BKT(tbl,hh,head,keyptr,keylen_in,hashval,out) \ -do { \ - if ((head).hh_head != NULL) { \ - DECLTYPE_ASSIGN(out, ELMT_FROM_HH(tbl, (head).hh_head)); \ - } else { \ - (out) = NULL; \ - } \ - while ((out) != NULL) { \ - if ((out)->hh.hashv == (hashval) && (out)->hh.keylen == (keylen_in)) { \ - if (uthash_memcmp((out)->hh.key, keyptr, keylen_in) == 0) { \ - break; \ - } \ - } \ - if ((out)->hh.hh_next != NULL) { \ - DECLTYPE_ASSIGN(out, ELMT_FROM_HH(tbl, (out)->hh.hh_next)); \ - } else { \ - (out) = NULL; \ - } \ - } \ -} while (0) - -/* add an item to a bucket */ -#define HASH_ADD_TO_BKT(head,addhh) \ -do { \ - head.count++; \ - (addhh)->hh_next = head.hh_head; \ - (addhh)->hh_prev = NULL; \ - if (head.hh_head != NULL) { (head).hh_head->hh_prev = (addhh); } \ - (head).hh_head=addhh; \ - if ((head.count >= ((head.expand_mult+1U) * HASH_BKT_CAPACITY_THRESH)) \ - && ((addhh)->tbl->noexpand != 1U)) { \ - HASH_EXPAND_BUCKETS((addhh)->tbl); \ - } \ -} while (0) - -/* remove an item from a given bucket */ -#define HASH_DEL_IN_BKT(hh,head,hh_del) \ - (head).count--; \ - if ((head).hh_head == hh_del) { \ - (head).hh_head = hh_del->hh_next; \ - } \ - if (hh_del->hh_prev) { \ - hh_del->hh_prev->hh_next = hh_del->hh_next; \ - } \ - if (hh_del->hh_next) { \ - hh_del->hh_next->hh_prev = hh_del->hh_prev; \ - } - -/* Bucket expansion has the effect of doubling the number of buckets - * and redistributing the items into the new buckets. Ideally the - * items will distribute more or less evenly into the new buckets - * (the extent to which this is true is a measure of the quality of - * the hash function as it applies to the key domain). - * - * With the items distributed into more buckets, the chain length - * (item count) in each bucket is reduced. Thus by expanding buckets - * the hash keeps a bound on the chain length. This bounded chain - * length is the essence of how a hash provides constant time lookup. - * - * The calculation of tbl->ideal_chain_maxlen below deserves some - * explanation. First, keep in mind that we're calculating the ideal - * maximum chain length based on the *new* (doubled) bucket count. - * In fractions this is just n/b (n=number of items,b=new num buckets). - * Since the ideal chain length is an integer, we want to calculate - * ceil(n/b). We don't depend on floating point arithmetic in this - * hash, so to calculate ceil(n/b) with integers we could write - * - * ceil(n/b) = (n/b) + ((n%b)?1:0) - * - * and in fact a previous version of this hash did just that. - * But now we have improved things a bit by recognizing that b is - * always a power of two. We keep its base 2 log handy (call it lb), - * so now we can write this with a bit shift and logical AND: - * - * ceil(n/b) = (n>>lb) + ( (n & (b-1)) ? 1:0) - * - */ -#define HASH_EXPAND_BUCKETS(tbl) \ -do { \ - unsigned _he_bkt; \ - unsigned _he_bkt_i; \ - struct UT_hash_handle *_he_thh, *_he_hh_nxt; \ - UT_hash_bucket *_he_new_buckets, *_he_newbkt; \ - _he_new_buckets = (UT_hash_bucket*)uthash_malloc( \ - 2UL * tbl->num_buckets * sizeof(struct UT_hash_bucket)); \ - if (!_he_new_buckets) { uthash_fatal( "out of memory"); } \ - memset(_he_new_buckets, 0, \ - 2UL * tbl->num_buckets * sizeof(struct UT_hash_bucket)); \ - tbl->ideal_chain_maxlen = \ - (tbl->num_items >> (tbl->log2_num_buckets+1U)) + \ - (((tbl->num_items & ((tbl->num_buckets*2U)-1U)) != 0U) ? 1U : 0U); \ - tbl->nonideal_items = 0; \ - for(_he_bkt_i = 0; _he_bkt_i < tbl->num_buckets; _he_bkt_i++) \ - { \ - _he_thh = tbl->buckets[ _he_bkt_i ].hh_head; \ - while (_he_thh != NULL) { \ - _he_hh_nxt = _he_thh->hh_next; \ - HASH_TO_BKT( _he_thh->hashv, tbl->num_buckets*2U, _he_bkt); \ - _he_newbkt = &(_he_new_buckets[ _he_bkt ]); \ - if (++(_he_newbkt->count) > tbl->ideal_chain_maxlen) { \ - tbl->nonideal_items++; \ - _he_newbkt->expand_mult = _he_newbkt->count / \ - tbl->ideal_chain_maxlen; \ - } \ - _he_thh->hh_prev = NULL; \ - _he_thh->hh_next = _he_newbkt->hh_head; \ - if (_he_newbkt->hh_head != NULL) { _he_newbkt->hh_head->hh_prev = \ - _he_thh; } \ - _he_newbkt->hh_head = _he_thh; \ - _he_thh = _he_hh_nxt; \ - } \ - } \ - uthash_free( tbl->buckets, tbl->num_buckets*sizeof(struct UT_hash_bucket) ); \ - tbl->num_buckets *= 2U; \ - tbl->log2_num_buckets++; \ - tbl->buckets = _he_new_buckets; \ - tbl->ineff_expands = (tbl->nonideal_items > (tbl->num_items >> 1)) ? \ - (tbl->ineff_expands+1U) : 0U; \ - if (tbl->ineff_expands > 1U) { \ - tbl->noexpand=1; \ - uthash_noexpand_fyi(tbl); \ - } \ - uthash_expand_fyi(tbl); \ -} while (0) - - -/* This is an adaptation of Simon Tatham's O(n log(n)) mergesort */ -/* Note that HASH_SORT assumes the hash handle name to be hh. - * HASH_SRT was added to allow the hash handle name to be passed in. */ -#define HASH_SORT(head,cmpfcn) HASH_SRT(hh,head,cmpfcn) -#define HASH_SRT(hh,head,cmpfcn) \ -do { \ - unsigned _hs_i; \ - unsigned _hs_looping,_hs_nmerges,_hs_insize,_hs_psize,_hs_qsize; \ - struct UT_hash_handle *_hs_p, *_hs_q, *_hs_e, *_hs_list, *_hs_tail; \ - if (head != NULL) { \ - _hs_insize = 1; \ - _hs_looping = 1; \ - _hs_list = &((head)->hh); \ - while (_hs_looping != 0U) { \ - _hs_p = _hs_list; \ - _hs_list = NULL; \ - _hs_tail = NULL; \ - _hs_nmerges = 0; \ - while (_hs_p != NULL) { \ - _hs_nmerges++; \ - _hs_q = _hs_p; \ - _hs_psize = 0; \ - for ( _hs_i = 0; _hs_i < _hs_insize; _hs_i++ ) { \ - _hs_psize++; \ - _hs_q = (UT_hash_handle*)((_hs_q->next != NULL) ? \ - ((void*)((char*)(_hs_q->next) + \ - (head)->hh.tbl->hho)) : NULL); \ - if (! (_hs_q) ) { break; } \ - } \ - _hs_qsize = _hs_insize; \ - while ((_hs_psize > 0U) || ((_hs_qsize > 0U) && (_hs_q != NULL))) {\ - if (_hs_psize == 0U) { \ - _hs_e = _hs_q; \ - _hs_q = (UT_hash_handle*)((_hs_q->next != NULL) ? \ - ((void*)((char*)(_hs_q->next) + \ - (head)->hh.tbl->hho)) : NULL); \ - _hs_qsize--; \ - } else if ( (_hs_qsize == 0U) || (_hs_q == NULL) ) { \ - _hs_e = _hs_p; \ - if (_hs_p != NULL){ \ - _hs_p = (UT_hash_handle*)((_hs_p->next != NULL) ? \ - ((void*)((char*)(_hs_p->next) + \ - (head)->hh.tbl->hho)) : NULL); \ - } \ - _hs_psize--; \ - } else if (( \ - cmpfcn(DECLTYPE(head)(ELMT_FROM_HH((head)->hh.tbl,_hs_p)), \ - DECLTYPE(head)(ELMT_FROM_HH((head)->hh.tbl,_hs_q))) \ - ) <= 0) { \ - _hs_e = _hs_p; \ - if (_hs_p != NULL){ \ - _hs_p = (UT_hash_handle*)((_hs_p->next != NULL) ? \ - ((void*)((char*)(_hs_p->next) + \ - (head)->hh.tbl->hho)) : NULL); \ - } \ - _hs_psize--; \ - } else { \ - _hs_e = _hs_q; \ - _hs_q = (UT_hash_handle*)((_hs_q->next != NULL) ? \ - ((void*)((char*)(_hs_q->next) + \ - (head)->hh.tbl->hho)) : NULL); \ - _hs_qsize--; \ - } \ - if ( _hs_tail != NULL ) { \ - _hs_tail->next = ((_hs_e != NULL) ? \ - ELMT_FROM_HH((head)->hh.tbl,_hs_e) : NULL); \ - } else { \ - _hs_list = _hs_e; \ - } \ - if (_hs_e != NULL) { \ - _hs_e->prev = ((_hs_tail != NULL) ? \ - ELMT_FROM_HH((head)->hh.tbl,_hs_tail) : NULL); \ - } \ - _hs_tail = _hs_e; \ - } \ - _hs_p = _hs_q; \ - } \ - if (_hs_tail != NULL){ \ - _hs_tail->next = NULL; \ - } \ - if ( _hs_nmerges <= 1U ) { \ - _hs_looping=0; \ - (head)->hh.tbl->tail = _hs_tail; \ - DECLTYPE_ASSIGN(head,ELMT_FROM_HH((head)->hh.tbl, _hs_list)); \ - } \ - _hs_insize *= 2U; \ - } \ - HASH_FSCK(hh,head); \ - } \ -} while (0) - -/* This function selects items from one hash into another hash. - * The end result is that the selected items have dual presence - * in both hashes. There is no copy of the items made; rather - * they are added into the new hash through a secondary hash - * hash handle that must be present in the structure. */ -#define HASH_SELECT(hh_dst, dst, hh_src, src, cond) \ -do { \ - unsigned _src_bkt, _dst_bkt; \ - void *_last_elt=NULL, *_elt; \ - UT_hash_handle *_src_hh, *_dst_hh, *_last_elt_hh=NULL; \ - ptrdiff_t _dst_hho = ((char*)(&(dst)->hh_dst) - (char*)(dst)); \ - if (src != NULL) { \ - for(_src_bkt=0; _src_bkt < (src)->hh_src.tbl->num_buckets; _src_bkt++) { \ - for(_src_hh = (src)->hh_src.tbl->buckets[_src_bkt].hh_head; \ - _src_hh != NULL; \ - _src_hh = _src_hh->hh_next) { \ - _elt = ELMT_FROM_HH((src)->hh_src.tbl, _src_hh); \ - if (cond(_elt)) { \ - _dst_hh = (UT_hash_handle*)(((char*)_elt) + _dst_hho); \ - _dst_hh->key = _src_hh->key; \ - _dst_hh->keylen = _src_hh->keylen; \ - _dst_hh->hashv = _src_hh->hashv; \ - _dst_hh->prev = _last_elt; \ - _dst_hh->next = NULL; \ - if (_last_elt_hh != NULL) { _last_elt_hh->next = _elt; } \ - if (dst == NULL) { \ - DECLTYPE_ASSIGN(dst,_elt); \ - HASH_MAKE_TABLE(hh_dst,dst); \ - } else { \ - _dst_hh->tbl = (dst)->hh_dst.tbl; \ - } \ - HASH_TO_BKT(_dst_hh->hashv, _dst_hh->tbl->num_buckets, _dst_bkt); \ - HASH_ADD_TO_BKT(_dst_hh->tbl->buckets[_dst_bkt],_dst_hh); \ - (dst)->hh_dst.tbl->num_items++; \ - _last_elt = _elt; \ - _last_elt_hh = _dst_hh; \ - } \ - } \ - } \ - } \ - HASH_FSCK(hh_dst,dst); \ -} while (0) - -#define HASH_CLEAR(hh,head) \ -do { \ - if (head != NULL) { \ - uthash_free((head)->hh.tbl->buckets, \ - (head)->hh.tbl->num_buckets*sizeof(struct UT_hash_bucket)); \ - HASH_BLOOM_FREE((head)->hh.tbl); \ - uthash_free((head)->hh.tbl, sizeof(UT_hash_table)); \ - (head)=NULL; \ - } \ -} while (0) - -#define HASH_OVERHEAD(hh,head) \ - ((head != NULL) ? ( \ - (size_t)(((head)->hh.tbl->num_items * sizeof(UT_hash_handle)) + \ - ((head)->hh.tbl->num_buckets * sizeof(UT_hash_bucket)) + \ - sizeof(UT_hash_table) + \ - (HASH_BLOOM_BYTELEN))) : 0U) - -#ifdef NO_DECLTYPE -#define HASH_ITER(hh,head,el,tmp) \ -for(((el)=(head)), ((*(char**)(&(tmp)))=(char*)((head!=NULL)?(head)->hh.next:NULL)); \ - (el) != NULL; ((el)=(tmp)), ((*(char**)(&(tmp)))=(char*)((tmp!=NULL)?(tmp)->hh.next:NULL))) -#else -#define HASH_ITER(hh,head,el,tmp) \ -for(((el)=(head)), ((tmp)=DECLTYPE(el)((head!=NULL)?(head)->hh.next:NULL)); \ - (el) != NULL; ((el)=(tmp)), ((tmp)=DECLTYPE(el)((tmp!=NULL)?(tmp)->hh.next:NULL))) -#endif - -/* obtain a count of items in the hash */ -#define HASH_COUNT(head) HASH_CNT(hh,head) -#define HASH_CNT(hh,head) ((head != NULL)?((head)->hh.tbl->num_items):0U) - -typedef struct UT_hash_bucket { - struct UT_hash_handle *hh_head; - unsigned count; - - /* expand_mult is normally set to 0. In this situation, the max chain length - * threshold is enforced at its default value, HASH_BKT_CAPACITY_THRESH. (If - * the bucket's chain exceeds this length, bucket expansion is triggered). - * However, setting expand_mult to a non-zero value delays bucket expansion - * (that would be triggered by additions to this particular bucket) - * until its chain length reaches a *multiple* of HASH_BKT_CAPACITY_THRESH. - * (The multiplier is simply expand_mult+1). The whole idea of this - * multiplier is to reduce bucket expansions, since they are expensive, in - * situations where we know that a particular bucket tends to be overused. - * It is better to let its chain length grow to a longer yet-still-bounded - * value, than to do an O(n) bucket expansion too often. - */ - unsigned expand_mult; - -} UT_hash_bucket; - -/* random signature used only to find hash tables in external analysis */ -#define HASH_SIGNATURE 0xa0111fe1u -#define HASH_BLOOM_SIGNATURE 0xb12220f2u - -typedef struct UT_hash_table { - UT_hash_bucket *buckets; - unsigned num_buckets, log2_num_buckets; - unsigned num_items; - struct UT_hash_handle *tail; /* tail hh in app order, for fast append */ - ptrdiff_t hho; /* hash handle offset (byte pos of hash handle in element */ - - /* in an ideal situation (all buckets used equally), no bucket would have - * more than ceil(#items/#buckets) items. that's the ideal chain length. */ - unsigned ideal_chain_maxlen; - - /* nonideal_items is the number of items in the hash whose chain position - * exceeds the ideal chain maxlen. these items pay the penalty for an uneven - * hash distribution; reaching them in a chain traversal takes >ideal steps */ - unsigned nonideal_items; - - /* ineffective expands occur when a bucket doubling was performed, but - * afterward, more than half the items in the hash had nonideal chain - * positions. If this happens on two consecutive expansions we inhibit any - * further expansion, as it's not helping; this happens when the hash - * function isn't a good fit for the key domain. When expansion is inhibited - * the hash will still work, albeit no longer in constant time. */ - unsigned ineff_expands, noexpand; - - uint32_t signature; /* used only to find hash tables in external analysis */ -#ifdef HASH_BLOOM - uint32_t bloom_sig; /* used only to test bloom exists in external analysis */ - uint8_t *bloom_bv; - uint8_t bloom_nbits; -#endif - -} UT_hash_table; - -typedef struct UT_hash_handle { - struct UT_hash_table *tbl; - void *prev; /* prev element in app order */ - void *next; /* next element in app order */ - struct UT_hash_handle *hh_prev; /* previous hh in bucket order */ - struct UT_hash_handle *hh_next; /* next hh in bucket order */ - void *key; /* ptr to enclosing struct's key */ - unsigned keylen; /* enclosing struct's key len */ - unsigned hashv; /* result of hash-fcn(key) */ -} UT_hash_handle; - -#endif /* UTHASH_H */ diff --git a/tests/CMakeLists.txt b/tests/CMakeLists.txt index 8cee9319..60736209 100644 --- a/tests/CMakeLists.txt +++ b/tests/CMakeLists.txt @@ -145,14 +145,14 @@ ss_add_test(test_netutils # test_cache - expiration uses a platform monotonic clock ss_add_test(test_cache - "test_cache.c;${PROJECT_SOURCE_DIR}/src/cache.cpp;${PROJECT_SOURCE_DIR}/src/utils.cpp" + "test_cache.c;${CMAKE_CURRENT_SOURCE_DIR}/reference/cache.cpp;${PROJECT_SOURCE_DIR}/src/utils.cpp" "ss_sodium") # test_cache_cpp - fixed-capacity cache edge cases ss_add_test(test_cache_cpp - "test_cache_cpp.cpp;${PROJECT_SOURCE_DIR}/src/cache.cpp" + "test_cache_cpp.cpp;${CMAKE_CURRENT_SOURCE_DIR}/reference/cache.cpp" "ss_sodium") -ss_strict_warnings(test_cache_cpp.cpp ${PROJECT_SOURCE_DIR}/src/cache.cpp) +ss_strict_warnings(test_cache_cpp.cpp ${CMAKE_CURRENT_SOURCE_DIR}/reference/cache.cpp) # test_ppbloom - needs bloom set(TEST_PPBLOOM_LIBS "") @@ -167,8 +167,8 @@ set(TEST_RULE_LIBS ss_pcre2 ss_sodium ) -ss_add_test(test_rule - "test_rule.c;${PROJECT_SOURCE_DIR}/src/rule.cpp;${PROJECT_SOURCE_DIR}/src/utils.cpp" +ss_add_test(test_rule_cpp + "test_rule_cpp.cpp;${PROJECT_SOURCE_DIR}/src/rule.cpp;${PROJECT_SOURCE_DIR}/src/utils.cpp" "${TEST_RULE_LIBS}") # test_acl - ACL precedence and prefix matching @@ -199,7 +199,7 @@ set(SS_CRYPTO_TEST_SOURCES ${CMAKE_CURRENT_SOURCE_DIR}/reference/aead2022.cpp ${CMAKE_CURRENT_SOURCE_DIR}/reference/aead2022_udp.cpp ${PROJECT_SOURCE_DIR}/src/ppbloom.cpp - ${PROJECT_SOURCE_DIR}/src/cache.cpp + ${CMAKE_CURRENT_SOURCE_DIR}/reference/cache.cpp ${PROJECT_SOURCE_DIR}/src/base64.cpp ${PROJECT_SOURCE_DIR}/src/utils.cpp ) diff --git a/src/cache.cpp b/tests/reference/cache.cpp similarity index 100% rename from src/cache.cpp rename to tests/reference/cache.cpp diff --git a/src/cache.h b/tests/reference/cache.h similarity index 97% rename from src/cache.h rename to tests/reference/cache.h index 99711e1c..c00ff518 100644 --- a/src/cache.h +++ b/tests/reference/cache.h @@ -22,7 +22,7 @@ /* * The first implementation was by Oliver Lorenz (ol), olli@olorenz.org, - * https://olorenz.org, on top of uthash. + * https://olorenz.org, originally on top of uthash; now a fixed slab. */ #ifndef _CACHE_ diff --git a/tests/test_acl_literal.c b/tests/test_acl_literal.c index 9cf4ac6a..55dd0a8f 100644 --- a/tests/test_acl_literal.c +++ b/tests/test_acl_literal.c @@ -1,8 +1,10 @@ +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif #include #include #include #include "acl.h" -#include "rule.h" int verbose = 0; int diff --git a/tests/test_rule.c b/tests/test_rule.c deleted file mode 100644 index 82670ad3..00000000 --- a/tests/test_rule.c +++ /dev/null @@ -1,113 +0,0 @@ -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include -#include -#include - -int verbose = 0; - -#include "rule.h" -#include "utils.h" - -static void -test_new_rule(void) -{ - rule_t *rule = new_rule(); - assert(rule != NULL); - assert(rule->pattern == NULL); - assert(rule->pattern_re == NULL); - free(rule); -} - -static void -test_accept_rule_arg(void) -{ - rule_t *rule = new_rule(); - assert(rule != NULL); - - int ret = accept_rule_arg(rule, "^example\\.com$"); - assert(ret == 1); - assert(rule->pattern != NULL); - assert(strcmp(rule->pattern, "^example\\.com$") == 0); - - /* Second call should fail - pattern already set */ - ret = accept_rule_arg(rule, "another"); - assert(ret == -1); - (void)ret; - - free_rule(rule); -} - -static void -test_init_rule(void) -{ - rule_t *rule = new_rule(); - accept_rule_arg(rule, "^test.*$"); - - int ret = init_rule(rule); - assert(ret == 1); - (void)ret; - assert(rule->pattern_re != NULL); - - free_rule(rule); -} - -static void -test_init_rule_invalid(void) -{ - rule_t *rule = new_rule(); - accept_rule_arg(rule, "[invalid"); /* Unclosed bracket */ - - int ret = init_rule(rule); - assert(ret == 0); /* Should fail */ - (void)ret; - - free_rule(rule); -} - -static void -test_lookup_rule(void) -{ - struct ss_list rules; - ss_list_init(&rules); - - rule_t *rule1 = new_rule(); - accept_rule_arg(rule1, "^google\\.com$"); - init_rule(rule1); - add_rule(&rules, rule1); - - rule_t *rule2 = new_rule(); - accept_rule_arg(rule2, ".*\\.example\\.com$"); - init_rule(rule2); - add_rule(&rules, rule2); - - /* Should match rule1 */ - rule_t *found = lookup_rule(&rules, "google.com", 10); - assert(found == rule1); - - /* Should match rule2 */ - found = lookup_rule(&rules, "sub.example.com", 15); - assert(found == rule2); - - /* Should not match */ - found = lookup_rule(&rules, "other.net", 9); - assert(found == NULL); - (void)found; - - /* Clean up */ - free_rule(rule1); - free_rule(rule2); -} - -int -main(void) -{ - test_new_rule(); - test_accept_rule_arg(); - test_init_rule(); - test_init_rule_invalid(); - test_lookup_rule(); - return 0; -} diff --git a/tests/test_rule_cpp.cpp b/tests/test_rule_cpp.cpp new file mode 100644 index 00000000..9f26986e --- /dev/null +++ b/tests/test_rule_cpp.cpp @@ -0,0 +1,101 @@ +/* SPDX-License-Identifier: GPL-3.0-or-later */ +// Domain rules (src/rule.cpp): parsing, compilation and lookup on an +// intrusive rule list. +#include + +#include "rule.h" +#include "test_helpers.hpp" +#include "utils.h" + +extern "C" { +int verbose = 0; +} + +namespace { + +void test_new_rule() +{ + rule_t *rule = new_rule(); + SS_CHECK(rule != nullptr && rule->pattern == nullptr && !rule->linked()); +#if SS_ENABLE_REGEX + SS_CHECK(rule->pattern_re == nullptr); +#endif + free_rule(rule); +} + +void test_accept_rule_arg() +{ + rule_t *rule = new_rule(); + SS_CHECK(accept_rule_arg(rule, "^example\\.com$") == 1); + SS_CHECK(rule->pattern != nullptr && std::strcmp(rule->pattern, "^example\\.com$") == 0); + // The pattern is already set. + SS_CHECK(accept_rule_arg(rule, "another") == -1); + free_rule(rule); +} + +void test_literal_rules() +{ + rule_list_t rules; + rule_t *full = new_rule(); + SS_CHECK(accept_rule_arg(full, "full:Example.com") == 1 && init_rule(full) == 1); + add_rule(&rules, full); + rule_t *suffix = new_rule(); + SS_CHECK(accept_rule_arg(suffix, "suffix:test.org") == 1 && init_rule(suffix) == 1); + add_rule(&rules, suffix); + + SS_CHECK(lookup_rule(&rules, "example.com", 11) == full); // case-insensitive + SS_CHECK(lookup_rule(&rules, "a.example.com", 13) == nullptr); + SS_CHECK(lookup_rule(&rules, "test.org", 8) == suffix); // the apex + SS_CHECK(lookup_rule(&rules, "x.test.org", 10) == suffix); + SS_CHECK(lookup_rule(&rules, "xtest.org", 9) == nullptr); + SS_CHECK(lookup_rule(&rules, nullptr, 0) == nullptr); + + rule_t *empty = new_rule(); + SS_CHECK(accept_rule_arg(empty, "full:") == 1 && init_rule(empty) == 0); + free_rule(empty); + + remove_rule(full); + SS_CHECK(lookup_rule(&rules, "example.com", 11) == nullptr && rules.size() == 1); + remove_rule(suffix); + SS_CHECK(rules.empty()); +} + +#if SS_ENABLE_REGEX +void test_regex_rules() +{ + rule_t *bad = new_rule(); + SS_CHECK(accept_rule_arg(bad, "[invalid") == 1 && init_rule(bad) == 0); + free_rule(bad); + + rule_list_t rules; + rule_t *rule1 = new_rule(); + SS_CHECK(accept_rule_arg(rule1, "^google\\.com$") == 1 && init_rule(rule1) == 1); + SS_CHECK(rule1->pattern_re != nullptr); + add_rule(&rules, rule1); + rule_t *rule2 = new_rule(); + SS_CHECK(accept_rule_arg(rule2, ".*\\.example\\.com$") == 1 && init_rule(rule2) == 1); + add_rule(&rules, rule2); + + SS_CHECK(lookup_rule(&rules, "google.com", 10) == rule1); + SS_CHECK(lookup_rule(&rules, "sub.example.com", 15) == rule2); + SS_CHECK(lookup_rule(&rules, "other.net", 9) == nullptr); + + // Freeing a linked rule unlinks it. + free_rule(rule1); + free_rule(rule2); + SS_CHECK(rules.empty()); +} +#endif + +} // namespace + +int main() +{ + SS_RUN(test_new_rule); + SS_RUN(test_accept_rule_arg); + SS_RUN(test_literal_rules); +#if SS_ENABLE_REGEX + SS_RUN(test_regex_rules); +#endif + return 0; +} diff --git a/third_party/README.md b/third_party/README.md index fc57c586..d92fedcd 100644 --- a/third_party/README.md +++ b/third_party/README.md @@ -15,7 +15,6 @@ signature verification. commit 437e1add5a2b9a87797d8c648df7cf5f3ee155a8. BSD-2-Clause; license and MurmurHash2 source notices retained alongside the sources. - BLAKE3 remains in src/blake3; its existing license files remain there. -- uthash remains in src/uthash.h with its upstream copyright/license notice. Mbed TLS, c-ares, libuv and PCRE2 use their upstream CMake builds. The local libsodium CMake adapter compiles the portable C backends listed in upstream Makefile.am;