diff --git a/backtrace_filter.txt b/backtrace_filter.txt new file mode 100644 index 000000000..abb021561 --- /dev/null +++ b/backtrace_filter.txt @@ -0,0 +1,3 @@ +zlib +deflate +inflate diff --git a/src/cfg.c b/src/cfg.c index 7556bb599..5389c5cc0 100644 --- a/src/cfg.c +++ b/src/cfg.c @@ -1,6 +1,7 @@ #define _GNU_SOURCE #include #include +#include #include #include @@ -77,7 +78,8 @@ struct _config_t custom_tag_t** tags; unsigned max_tags; - + cfg_backtrace_t backtrace_option; + char* backtrace_filter_file; char* commanddir; unsigned processstartmsg; unsigned enhancefs; @@ -163,7 +165,6 @@ static cfg_buffer_t bufDefault[] = { DEFAULT_LS_BUF, }; - /////////////////////////////////// // Constructors Destructors /////////////////////////////////// @@ -231,6 +232,7 @@ cfgCreateDefault() c->commanddir = (DEFAULT_COMMAND_DIR) ? scope_strdup(DEFAULT_COMMAND_DIR) : NULL; c->processstartmsg = DEFAULT_PROCESS_START_MSG; c->enhancefs = DEFAULT_ENHANCE_FS; + c->backtrace_option = DEFAULT_BACKTRACE_OPTION; c->logstream.enable = DEFAULT_LOGSTREAM_ENABLE; c->logstream.cloud = DEFAULT_LOGSTREAM_CLOUD; @@ -379,6 +381,18 @@ cfgEnhanceFs(config_t* cfg) return (cfg) ? cfg->enhancefs : DEFAULT_ENHANCE_FS; } +cfg_backtrace_t +cfgBacktrace(config_t* cfg) +{ + return (cfg) ? cfg->backtrace_option : DEFAULT_BACKTRACE_OPTION; +} + +const char* +cfgBacktraceFilterFile(config_t* cfg) +{ + return (cfg) ? cfg->backtrace_filter_file : NULL; +} + const char* cfgEvtFormatValueFilter(config_t* cfg, watch_t src) { @@ -977,6 +991,27 @@ cfgLogLevelSet(config_t* cfg, cfg_log_level_t level) cfg->log.level = level; } + + +void +cfgBacktraceSet(config_t* cfg, cfg_backtrace_t backtrace) +{ + if (!cfg || backtrace < 0 || backtrace > CFG_BACKTRACE_NONE) return; + cfg->backtrace_option = backtrace; +} + +void +cfgBacktraceFilterFileSet(config_t* cfg, const char* path) +{ + if (!cfg) return; + if (cfg->backtrace_filter_file) scope_free(cfg->backtrace_filter_file); + if (!path || (path[0] == '\0')) { + return; + } + + cfg->backtrace_filter_file = scope_strdup(path); +} + void cfgPayEnableSet(config_t *cfg, unsigned int val) { diff --git a/src/cfg.h b/src/cfg.h index b25075cea..05073f1bf 100644 --- a/src/cfg.h +++ b/src/cfg.h @@ -29,6 +29,8 @@ unsigned cfgEvtEnable(config_t*); cfg_mtc_format_t cfgEventFormat(config_t*); unsigned cfgEvtRateLimit(config_t*); unsigned cfgEnhanceFs(config_t*); +cfg_backtrace_t cfgBacktrace(config_t*); +const char* cfgBacktraceFilterFile(config_t*); const char* cfgEvtFormatValueFilter(config_t*, watch_t); const char* cfgEvtFormatFieldFilter(config_t*, watch_t); const char* cfgEvtFormatNameFilter(config_t*, watch_t); @@ -81,6 +83,8 @@ void cfgTransportTlsValidateServerSet(config_t *, which_transport void cfgTransportTlsCACertPathSet(config_t *, which_transport_t, const char *); void cfgCustomTagAdd(config_t*, const char*, const char*); void cfgLogLevelSet(config_t*, cfg_log_level_t); +void cfgBacktraceSet(config_t*, cfg_backtrace_t); +void cfgBacktraceFilterFileSet(config_t*, const char*); void cfgPayEnableSet(config_t*, unsigned int); void cfgPayDirSet(config_t*, const char *); void cfgEvtFormatHeaderSet(config_t *, const char *); diff --git a/src/cfgutils.c b/src/cfgutils.c index caa74b35a..4ad4e3946 100644 --- a/src/cfgutils.c +++ b/src/cfgutils.c @@ -122,6 +122,14 @@ enum_map_t logLevelMap[] = { {NULL, -1} }; +enum_map_t backtraceLevel[] = { + {"full", CFG_BACKTRACE_FULL}, + {"filter", CFG_BACKTRACE_FILTER}, + {"openat", CFG_BACKTRACE_OPENAT}, + {"none", CFG_BACKTRACE_NONE}, + {NULL, -1} +}; + enum_map_t bufferMap[] = { {"line", CFG_BUFFER_LINE}, {"full", CFG_BUFFER_FULLY}, @@ -180,6 +188,8 @@ void cfgTransportTlsValidateServerSetFromStr(config_t *, which_transport_t, cons void cfgTransportTlsCACertPathSetFromStr(config_t *, which_transport_t, const char *); void cfgCustomTagAddFromStr(config_t*, const char*, const char*); void cfgLogLevelSetFromStr(config_t*, const char*); +void cfgBacktraceSetFromStr(config_t*, const char*); +void cfgBacktraceFilterFileSetFromStr(config_t*, const char*); void cfgPayEnableSetFromStr(config_t*, const char*); void cfgPayDirSetFromStr(config_t*, const char*); void cfgAuthTokenSetFromStr(config_t*, const char*); @@ -479,6 +489,10 @@ processEnvStyleInput(config_t *cfg, const char *env_line) cfgMtcVerbositySetFromStr(cfg, value); } else if (!scope_strcmp(env_name, "SCOPE_LOG_LEVEL")) { cfgLogLevelSetFromStr(cfg, value); + } else if (!scope_strcmp(env_name, "SCOPE_BACKTRACE")) { + cfgBacktraceSetFromStr(cfg, value); + } else if (!scope_strcmp(env_name, "SCOPE_BACKTRACE_FILTER")) { + cfgBacktraceFilterFileSetFromStr(cfg, value); } else if (!scope_strcmp(env_name, "SCOPE_METRIC_DEST")) { cfgTransportSetFromStr(cfg, CFG_MTC, value); } else if (!scope_strcmp(env_name, "SCOPE_METRIC_TLS_ENABLE")) { @@ -894,6 +908,20 @@ cfgLogLevelSetFromStr(config_t* cfg, const char* value) cfgLogLevelSet(cfg, strToVal(logLevelMap, value)); } +void +cfgBacktraceSetFromStr(config_t* cfg, const char* value) +{ + if (!cfg || !value) return; + cfgBacktraceSet(cfg, strToVal(backtraceLevel, value)); +} + +void +cfgBacktraceFilterFileSetFromStr(config_t* cfg, const char* value) +{ + if (!cfg || !value) return; + cfgBacktraceFilterFileSet(cfg, value); +} + void cfgPayEnableSetFromStr(config_t* cfg, const char* value) { diff --git a/src/dbg.c b/src/dbg.c index 7c74192b5..cbf384d12 100644 --- a/src/dbg.c +++ b/src/dbg.c @@ -10,6 +10,7 @@ #include "dbg.h" #include "utils.h" #include "scopestdlib.h" +#include "uthash.h" #define UNW_LOCAL_ONLY #include "libunwind.h" @@ -275,6 +276,146 @@ scopeLog(cfg_log_level_t level, const char *format, ...) return; } + +struct b_hash_struct { + uint64_t ip; + char *name; + UT_hash_handle hh; /* makes this structure hashable */ +}; + +struct b_hash_struct *backtrace_hash = NULL; + +static void add_backtrace_hash(uint64_t ip, const char* name) { + struct b_hash_struct* bh = (struct b_hash_struct*)scope_malloc(sizeof(struct b_hash_struct)); + bh->ip = ip; + bh->name = scope_strdup(name); + HASH_ADD_INT(backtrace_hash, ip, bh); +} + +static struct b_hash_struct *find_backtrace_hash(uint64_t ip) { + struct b_hash_struct *s; + + HASH_FIND_INT(backtrace_hash, &ip, s); + return s; +} + +void +scopeBacktraceOp(const char* func, const char* path) { + unw_cursor_t cursor; + unw_context_t uc; + unw_word_t ip; + unw_getcontext(&uc); + unw_init_local(&cursor, &uc); + unw_step(&cursor); //skip first frame + scopeLogError("%s begin", __FUNCTION__); + while(unw_step(&cursor) > 0) { + char symbol[SYMBOL_BT_NAME_LEN]; + unw_word_t offset; + + int ret = unw_get_reg(&cursor, UNW_REG_IP, &ip); + if (ret) { + continue; + } + struct b_hash_struct *test = find_backtrace_hash(ip); + if(test) { + scopeLogError("func symbol: %s, fun: %s, arg %s", test->name, func, path); + } else { + ret = unw_get_proc_name(&cursor, symbol, SYMBOL_BT_NAME_LEN, &offset); + if (!ret) { + scopeLogError("func symbol: %s, fun: %s, arg %s", symbol, func, path); + add_backtrace_hash(ip, symbol); + } else { + scopeLogError("func symbol: unknown, fun: %s, arg %s", func, path); + add_backtrace_hash(ip, "unknown"); + } + } + } + scopeLogError("%s end\n", __FUNCTION__); +} + +void +scopeBacktraceFull(long long size, const char* alloc_fun, size_t total_size) { + unw_cursor_t cursor; + unw_context_t uc; + unw_word_t ip; + unw_getcontext(&uc); + unw_init_local(&cursor, &uc); + unw_step(&cursor); //skip first frame + scopeLogError("%s begin", __FUNCTION__); + while(unw_step(&cursor) > 0) { + char symbol[SYMBOL_BT_NAME_LEN]; + unw_word_t offset; + + int ret = unw_get_reg(&cursor, UNW_REG_IP, &ip); + if (ret) { + continue; + } + struct b_hash_struct *test = find_backtrace_hash(ip); + if(test) { + scopeLogError("func symbol: %s, malloc_fun: %s, size allocated: %lld, total size allocated: %zu", test->name, alloc_fun, size, total_size); + } else { + ret = unw_get_proc_name(&cursor, symbol, SYMBOL_BT_NAME_LEN, &offset); + if (!ret) { + scopeLogError("func symbol: %s, malloc_fun: %s, size allocated: %lld, total size allocated: %zu", symbol, alloc_fun, size, total_size); + add_backtrace_hash(ip, symbol); + } else { + scopeLogError("func symbol: unknown, malloc_fun: %s, size allocated: %lld, total size allocated: %zu", alloc_fun, size, total_size); + add_backtrace_hash(ip, "unknown"); + } + } + } + scopeLogError("%s end\n", __FUNCTION__); +} + +// Dl_info info = {}; +// if (dladdr((void *)ip, &info)) +// scopeLogError(" %s:%s", info.dli_fname, info.dli_sname ? info.dli_sname : ""); + +void +scopeBacktraceFilter(const char** str, int str_size, long long size, const char* alloc_fun, size_t total_size) { + unw_cursor_t cursor; + unw_context_t uc; + unw_word_t ip; + unw_getcontext(&uc); + unw_init_local(&cursor, &uc); + unw_step(&cursor); //skip first frame + while(unw_step(&cursor) > 0) { + char symbol[SYMBOL_BT_NAME_LEN]; + unw_word_t offset; + + int ret = unw_get_reg(&cursor, UNW_REG_IP, &ip); + if (ret) { + continue; + } + struct b_hash_struct *test = find_backtrace_hash(ip); + if(test) { + for (int i=0; i < str_size; ++i) { + if(scope_strstr(test->name, str[i])) { + scopeLogError("%s begin", __FUNCTION__); + scopeLogError("func symbol: %s, malloc_fun: %s, size allocated: %lld, total size allocated: %zu", test->name, alloc_fun, size, total_size); + scopeLogError("%s end\n", __FUNCTION__); + return; + } + } + } else { + ret = unw_get_proc_name(&cursor, symbol, SYMBOL_BT_NAME_LEN, &offset); + if (!ret) { + add_backtrace_hash(ip, symbol); + for (int i=0; i < str_size; ++i) { + if(scope_strstr(symbol, str[i])) { + scopeLogError("%s begin", __FUNCTION__); + scopeLogError("func symbol: %s, malloc_fun: %s, size allocated: %lld, total size allocated: %zu", symbol, alloc_fun, size, total_size); + scopeLogError("%s end\n", __FUNCTION__); + return; + } + } + } else { + add_backtrace_hash(ip, "unknown"); + } + } + } +} + void scopeBacktrace(cfg_log_level_t level) { diff --git a/src/dbg.h b/src/dbg.h index cc4cee4ed..2cbc52b4f 100644 --- a/src/dbg.h +++ b/src/dbg.h @@ -73,6 +73,9 @@ extern bool g_ismusl; void scopeLog(cfg_log_level_t, const char *, ...) PRINTF_FORMAT(2,3); void scopeLogHex(cfg_log_level_t, const void *, size_t, const char *, ...) PRINTF_FORMAT(4,5); void scopeBacktrace(cfg_log_level_t); +void scopeBacktraceOp(const char*, const char*); +void scopeBacktraceFull(long long, const char*, size_t); +void scopeBacktraceFilter(const char**, int, long long, const char*, size_t); #define scopeLogError(...) scopeLog(CFG_LOG_ERROR, __VA_ARGS__) #define scopeLogWarn(...) scopeLog(CFG_LOG_WARN, __VA_ARGS__) diff --git a/src/fn.h b/src/fn.h index fec4d1efc..9fc5fd15e 100644 --- a/src/fn.h +++ b/src/fn.h @@ -247,6 +247,19 @@ typedef struct { DIR *(*opendir)(const char *); int (*closedir)(DIR *); struct dirent *(*readdir)(DIR *); + void *(*malloc)(size_t); + void (*free)(void *); + void *(*calloc)(size_t, size_t); + void *(*realloc)(void *, size_t); + int (*posix_memalign)(void **, size_t, size_t); + void *(*aligned_alloc)(size_t, size_t); + void *(*valloc)(size_t); + void *(*memalign)(size_t, size_t); + void *(*pvalloc)(size_t); + size_t (*malloc_usable_size)(void *); + char *(*strdup)(const char *); + void *(*mmap)(void *, size_t, int, int, int, off_t); + int (*munmap)(void *, size_t); #endif // __linux__ #if defined(__linux__) && defined(__STATX__) diff --git a/src/scopetypes.h b/src/scopetypes.h index 9f5814149..ded6cbbb7 100644 --- a/src/scopetypes.h +++ b/src/scopetypes.h @@ -14,6 +14,10 @@ typedef enum {CFG_LOG_TRACE, CFG_LOG_WARN, CFG_LOG_ERROR, CFG_LOG_NONE} cfg_log_level_t; +typedef enum {CFG_BACKTRACE_FULL, + CFG_BACKTRACE_FILTER, + CFG_BACKTRACE_OPENAT, + CFG_BACKTRACE_NONE} cfg_backtrace_t; typedef enum {CFG_BUFFER_FULLY, CFG_BUFFER_LINE} cfg_buffer_t; typedef enum {CFG_SRC_FILE, CFG_SRC_CONSOLE, @@ -125,6 +129,7 @@ typedef unsigned int bool; #define DEFAULT_MAXEVENTSPERSEC 10000 #define DEFAULT_ENHANCE_FS TRUE +#define DEFAULT_BACKTRACE_OPTION CFG_BACKTRACE_NONE #define DEFAULT_PORTBLOCK 0 #define DEFAULT_METRIC_CBUF_SIZE 50 * 1024 #define DEFAULT_PROCESS_START_MSG TRUE @@ -184,7 +189,7 @@ typedef unsigned int bool; // SCOPE_PID provided by library // SCOPE_PAYLOAD_HEADER write payload headers to files // SCOPE_ALLOW_CONSTRUCT_DBG allows debug inside the constructor -// SCOPE_ERROR_SIGNAL_HANDLER allows to register SIGSEGV&SIGBUS handler +// SCOPE_ERROR_SIGNAL_HANDLER allows to register SIGSEGV&SIGBUS&SIGABRT handler // SCOPE_QUEUE_LENGTH override default circular buffer sizes // SCOPE_ALLOW_BINARY_CONSOLE "true" outputs all console data, always diff --git a/src/uthash.h b/src/uthash.h new file mode 100644 index 000000000..ea49fc0a0 --- /dev/null +++ b/src/uthash.h @@ -0,0 +1,1138 @@ +/* +Copyright (c) 2003-2022, Troy D. Hanson https://troydhanson.github.io/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 2.3.0 +#include "scopestdlib.h" +#include /* memcmp, memset, strlen */ +#include /* ptrdiff_t */ +#include /* exit */ + +#if defined(HASH_DEFINE_OWN_STDINT) && HASH_DEFINE_OWN_STDINT +/* This codepath is provided for backward compatibility, but I plan to remove it. */ +#warning "HASH_DEFINE_OWN_STDINT is deprecated; please use HASH_NO_STDINT instead" +typedef unsigned int uint32_t; +typedef unsigned char uint8_t; +#elif defined(HASH_NO_STDINT) && HASH_NO_STDINT +#else +#include /* uint8_t, uint32_t */ +#endif + +/* 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(DECLTYPE) && !defined(NO_DECLTYPE) +#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 +#endif +#elif defined(__BORLANDC__) || defined(__ICCARM__) || defined(__LCC__) || defined(__WATCOMC__) +#define NO_DECLTYPE +#else /* GNU, Sun and other compilers */ +#define DECLTYPE(x) (__typeof(x)) +#endif +#endif + +#ifdef NO_DECLTYPE +#define DECLTYPE(x) +#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 + +#ifndef uthash_malloc +#define uthash_malloc(sz) scope_malloc(sz) /* malloc fcn */ +#endif +#ifndef uthash_free +#define uthash_free(ptr,sz) scope_free(ptr) /* free fcn */ +#endif +#ifndef uthash_bzero +#define uthash_bzero(a,n) scope_memset(a,'\0',n) +#endif +#ifndef uthash_strlen +#define uthash_strlen(s) scope_strlen(s) +#endif + +#ifndef HASH_FUNCTION +#define HASH_FUNCTION(keyptr,keylen,hashv) HASH_JEN(keyptr, keylen, hashv) +#endif + +#ifndef HASH_KEYCMP +#define HASH_KEYCMP(a,b,n) scope_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 + +#ifndef HASH_NONFATAL_OOM +#define HASH_NONFATAL_OOM 0 +#endif + +#if HASH_NONFATAL_OOM +/* malloc failures can be recovered from */ + +#ifndef uthash_nonfatal_oom +#define uthash_nonfatal_oom(obj) do {} while (0) /* non-fatal OOM error */ +#endif + +#define HASH_RECORD_OOM(oomed) do { (oomed) = 1; } while (0) +#define IF_HASH_NONFATAL_OOM(x) x + +#else +/* malloc failures result in lost memory, hash tables are unusable */ + +#ifndef uthash_fatal +#define uthash_fatal(msg) exit(-1) /* fatal OOM error */ +#endif + +#define HASH_RECORD_OOM(oomed) uthash_fatal("out of memory") +#define IF_HASH_NONFATAL_OOM(x) + +#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*)(void*)(((char*)(elp)) + ((tbl)->hho))) + +#define HASH_ROLLBACK_BKT(hh, head, itemptrhh) \ +do { \ + struct UT_hash_handle *_hd_hh_item = (itemptrhh); \ + unsigned _hd_bkt; \ + HASH_TO_BKT(_hd_hh_item->hashv, (head)->hh.tbl->num_buckets, _hd_bkt); \ + (head)->hh.tbl->buckets[_hd_bkt].count++; \ + _hd_hh_item->hh_next = NULL; \ + _hd_hh_item->hh_prev = NULL; \ +} while (0) + +#define HASH_VALUE(keyptr,keylen,hashv) \ +do { \ + HASH_FUNCTION(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 { \ + (out) = NULL; \ + if (head) { \ + 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,oomed) \ +do { \ + (tbl)->bloom_nbits = HASH_BLOOM; \ + (tbl)->bloom_bv = (uint8_t*)uthash_malloc(HASH_BLOOM_BYTELEN); \ + if (!(tbl)->bloom_bv) { \ + HASH_RECORD_OOM(oomed); \ + } else { \ + uthash_bzero((tbl)->bloom_bv, 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)((1UL << (tbl)->bloom_nbits) - 1U))) + +#define HASH_BLOOM_TEST(tbl,hashv) \ + HASH_BLOOM_BITTEST((tbl)->bloom_bv, ((hashv) & (uint32_t)((1UL << (tbl)->bloom_nbits) - 1U))) + +#else +#define HASH_BLOOM_MAKE(tbl,oomed) +#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,oomed) \ +do { \ + (head)->hh.tbl = (UT_hash_table*)uthash_malloc(sizeof(UT_hash_table)); \ + if (!(head)->hh.tbl) { \ + HASH_RECORD_OOM(oomed); \ + } else { \ + uthash_bzero((head)->hh.tbl, 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)); \ + (head)->hh.tbl->signature = HASH_SIGNATURE; \ + if (!(head)->hh.tbl->buckets) { \ + HASH_RECORD_OOM(oomed); \ + uthash_free((head)->hh.tbl, sizeof(UT_hash_table)); \ + } else { \ + uthash_bzero((head)->hh.tbl->buckets, \ + HASH_INITIAL_NUM_BUCKETS * sizeof(struct UT_hash_bucket)); \ + HASH_BLOOM_MAKE((head)->hh.tbl, oomed); \ + IF_HASH_NONFATAL_OOM( \ + if (oomed) { \ + uthash_free((head)->hh.tbl->buckets, \ + HASH_INITIAL_NUM_BUCKETS*sizeof(struct UT_hash_bucket)); \ + uthash_free((head)->hh.tbl, sizeof(UT_hash_table)); \ + } \ + ) \ + } \ + } \ +} 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_AKBI_INNER_LOOP(hh,head,add,cmpfcn) \ +do { \ + do { \ + if (cmpfcn(DECLTYPE(head)(_hs_iter), add) > 0) { \ + break; \ + } \ + } while ((_hs_iter = HH_FROM_ELMT((head)->hh.tbl, _hs_iter)->next)); \ +} while (0) + +#ifdef NO_DECLTYPE +#undef HASH_AKBI_INNER_LOOP +#define HASH_AKBI_INNER_LOOP(hh,head,add,cmpfcn) \ +do { \ + char *_hs_saved_head = (char*)(head); \ + do { \ + DECLTYPE_ASSIGN(head, _hs_iter); \ + if (cmpfcn(head, add) > 0) { \ + DECLTYPE_ASSIGN(head, _hs_saved_head); \ + break; \ + } \ + DECLTYPE_ASSIGN(head, _hs_saved_head); \ + } while ((_hs_iter = HH_FROM_ELMT((head)->hh.tbl, _hs_iter)->next)); \ +} while (0) +#endif + +#if HASH_NONFATAL_OOM + +#define HASH_ADD_TO_TABLE(hh,head,keyptr,keylen_in,hashval,add,oomed) \ +do { \ + if (!(oomed)) { \ + unsigned _ha_bkt; \ + (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], hh, &(add)->hh, oomed); \ + if (oomed) { \ + HASH_ROLLBACK_BKT(hh, head, &(add)->hh); \ + HASH_DELETE_HH(hh, head, &(add)->hh); \ + (add)->hh.tbl = NULL; \ + uthash_nonfatal_oom(add); \ + } else { \ + HASH_BLOOM_ADD((head)->hh.tbl, hashval); \ + HASH_EMIT_KEY(hh, head, keyptr, keylen_in); \ + } \ + } else { \ + (add)->hh.tbl = NULL; \ + uthash_nonfatal_oom(add); \ + } \ +} while (0) + +#else + +#define HASH_ADD_TO_TABLE(hh,head,keyptr,keylen_in,hashval,add,oomed) \ +do { \ + unsigned _ha_bkt; \ + (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], hh, &(add)->hh, oomed); \ + HASH_BLOOM_ADD((head)->hh.tbl, hashval); \ + HASH_EMIT_KEY(hh, head, keyptr, keylen_in); \ +} while (0) + +#endif + + +#define HASH_ADD_KEYPTR_BYHASHVALUE_INORDER(hh,head,keyptr,keylen_in,hashval,add,cmpfcn) \ +do { \ + IF_HASH_NONFATAL_OOM( int _ha_oomed = 0; ) \ + (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; \ + HASH_MAKE_TABLE(hh, add, _ha_oomed); \ + IF_HASH_NONFATAL_OOM( if (!_ha_oomed) { ) \ + (head) = (add); \ + IF_HASH_NONFATAL_OOM( } ) \ + } else { \ + void *_hs_iter = (head); \ + (add)->hh.tbl = (head)->hh.tbl; \ + HASH_AKBI_INNER_LOOP(hh, head, add, cmpfcn); \ + if (_hs_iter) { \ + (add)->hh.next = _hs_iter; \ + if (((add)->hh.prev = HH_FROM_ELMT((head)->hh.tbl, _hs_iter)->prev)) { \ + HH_FROM_ELMT((head)->hh.tbl, (add)->hh.prev)->next = (add); \ + } else { \ + (head) = (add); \ + } \ + HH_FROM_ELMT((head)->hh.tbl, _hs_iter)->prev = (add); \ + } else { \ + HASH_APPEND_LIST(hh, head, add); \ + } \ + } \ + HASH_ADD_TO_TABLE(hh, head, keyptr, keylen_in, hashval, add, _ha_oomed); \ + HASH_FSCK(hh, head, "HASH_ADD_KEYPTR_BYHASHVALUE_INORDER"); \ +} 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 { \ + IF_HASH_NONFATAL_OOM( int _ha_oomed = 0; ) \ + (add)->hh.hashv = (hashval); \ + (add)->hh.key = (const void*) (keyptr); \ + (add)->hh.keylen = (unsigned) (keylen_in); \ + if (!(head)) { \ + (add)->hh.next = NULL; \ + (add)->hh.prev = NULL; \ + HASH_MAKE_TABLE(hh, add, _ha_oomed); \ + IF_HASH_NONFATAL_OOM( if (!_ha_oomed) { ) \ + (head) = (add); \ + IF_HASH_NONFATAL_OOM( } ) \ + } else { \ + (add)->hh.tbl = (head)->hh.tbl; \ + HASH_APPEND_LIST(hh, head, add); \ + } \ + HASH_ADD_TO_TABLE(hh, head, keyptr, keylen_in, hashval, add, _ha_oomed); \ + HASH_FSCK(hh, head, "HASH_ADD_KEYPTR_BYHASHVALUE"); \ +} 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) \ + HASH_DELETE_HH(hh, head, &(delptr)->hh) + +#define HASH_DELETE_HH(hh,head,delptrhh) \ +do { \ + struct UT_hash_handle *_hd_hh_del = (delptrhh); \ + if ((_hd_hh_del->prev == NULL) && (_hd_hh_del->next == NULL)) { \ + HASH_BLOOM_FREE((head)->hh.tbl); \ + uthash_free((head)->hh.tbl->buckets, \ + (head)->hh.tbl->num_buckets * sizeof(struct UT_hash_bucket)); \ + uthash_free((head)->hh.tbl, sizeof(UT_hash_table)); \ + (head) = NULL; \ + } else { \ + unsigned _hd_bkt; \ + if (_hd_hh_del == (head)->hh.tbl->tail) { \ + (head)->hh.tbl->tail = HH_FROM_ELMT((head)->hh.tbl, _hd_hh_del->prev); \ + } \ + if (_hd_hh_del->prev != NULL) { \ + HH_FROM_ELMT((head)->hh.tbl, _hd_hh_del->prev)->next = _hd_hh_del->next; \ + } else { \ + DECLTYPE_ASSIGN(head, _hd_hh_del->next); \ + } \ + if (_hd_hh_del->next != NULL) { \ + HH_FROM_ELMT((head)->hh.tbl, _hd_hh_del->next)->prev = _hd_hh_del->prev; \ + } \ + HASH_TO_BKT(_hd_hh_del->hashv, (head)->hh.tbl->num_buckets, _hd_bkt); \ + HASH_DEL_IN_BKT((head)->hh.tbl->buckets[_hd_bkt], _hd_hh_del); \ + (head)->hh.tbl->num_items--; \ + } \ + HASH_FSCK(hh, head, "HASH_DELETE_HH"); \ +} while (0) + +/* convenience forms of HASH_FIND/HASH_ADD/HASH_DEL */ +#define HASH_FIND_STR(head,findstr,out) \ +do { \ + unsigned _uthash_hfstr_keylen = (unsigned)uthash_strlen(findstr); \ + HASH_FIND(hh, head, findstr, _uthash_hfstr_keylen, out); \ +} while (0) +#define HASH_ADD_STR(head,strfield,add) \ +do { \ + unsigned _uthash_hastr_keylen = (unsigned)uthash_strlen((add)->strfield); \ + HASH_ADD(hh, head, strfield[0], _uthash_hastr_keylen, add); \ +} while (0) +#define HASH_REPLACE_STR(head,strfield,add,replaced) \ +do { \ + unsigned _uthash_hrstr_keylen = (unsigned)uthash_strlen((add)->strfield); \ + HASH_REPLACE(hh, head, strfield[0], _uthash_hrstr_keylen, add, replaced); \ +} while (0) +#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 +#include /* fprintf, stderr */ +#define HASH_OOPS(...) do { fprintf(stderr, __VA_ARGS__); exit(-1); } while (0) +#define HASH_FSCK(hh,head,where) \ +do { \ + struct UT_hash_handle *_thh; \ + if (head) { \ + unsigned _bkt_i; \ + unsigned _count = 0; \ + char *_prev; \ + 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("%s: invalid hh_prev %p, actual %p\n", \ + (where), (void*)_thh->hh_prev, (void*)_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("%s: invalid bucket count %u, actual %u\n", \ + (where), (head)->hh.tbl->buckets[_bkt_i].count, _bkt_count); \ + } \ + } \ + if (_count != (head)->hh.tbl->num_items) { \ + HASH_OOPS("%s: invalid hh item count %u, actual %u\n", \ + (where), (head)->hh.tbl->num_items, _count); \ + } \ + _count = 0; \ + _prev = NULL; \ + _thh = &(head)->hh; \ + while (_thh) { \ + _count++; \ + if (_prev != (char*)_thh->prev) { \ + HASH_OOPS("%s: invalid prev %p, actual %p\n", \ + (where), (void*)_thh->prev, (void*)_prev); \ + } \ + _prev = (char*)ELMT_FROM_HH((head)->hh.tbl, _thh); \ + _thh = (_thh->next ? HH_FROM_ELMT((head)->hh.tbl, _thh->next) : NULL); \ + } \ + if (_count != (head)->hh.tbl->num_items) { \ + HASH_OOPS("%s: invalid app item count %u, actual %u\n", \ + (where), (head)->hh.tbl->num_items, _count); \ + } \ + } \ +} while (0) +#else +#define HASH_FSCK(hh,head,where) +#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 + +/* 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 + * (archive link: https://archive.is/Ivcan ) + */ +#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]; /* FALLTHROUGH */ \ + default: ; \ + } \ + 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; \ + break; \ + default: ; \ + } \ + \ + /* 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) + +/* 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 (HASH_KEYCMP((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,hh,addhh,oomed) \ +do { \ + UT_hash_bucket *_ha_head = &(head); \ + _ha_head->count++; \ + (addhh)->hh_next = _ha_head->hh_head; \ + (addhh)->hh_prev = NULL; \ + if (_ha_head->hh_head != NULL) { \ + _ha_head->hh_head->hh_prev = (addhh); \ + } \ + _ha_head->hh_head = (addhh); \ + if ((_ha_head->count >= ((_ha_head->expand_mult + 1U) * HASH_BKT_CAPACITY_THRESH)) \ + && !(addhh)->tbl->noexpand) { \ + HASH_EXPAND_BUCKETS(addhh,(addhh)->tbl, oomed); \ + IF_HASH_NONFATAL_OOM( \ + if (oomed) { \ + HASH_DEL_IN_BKT(head,addhh); \ + } \ + ) \ + } \ +} while (0) + +/* remove an item from a given bucket */ +#define HASH_DEL_IN_BKT(head,delhh) \ +do { \ + UT_hash_bucket *_hd_head = &(head); \ + _hd_head->count--; \ + if (_hd_head->hh_head == (delhh)) { \ + _hd_head->hh_head = (delhh)->hh_next; \ + } \ + if ((delhh)->hh_prev) { \ + (delhh)->hh_prev->hh_next = (delhh)->hh_next; \ + } \ + if ((delhh)->hh_next) { \ + (delhh)->hh_next->hh_prev = (delhh)->hh_prev; \ + } \ +} while (0) + +/* 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(hh,tbl,oomed) \ +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( \ + sizeof(struct UT_hash_bucket) * (tbl)->num_buckets * 2U); \ + if (!_he_new_buckets) { \ + HASH_RECORD_OOM(oomed); \ + } else { \ + uthash_bzero(_he_new_buckets, \ + sizeof(struct UT_hash_bucket) * (tbl)->num_buckets * 2U); \ + (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++; \ + if (_he_newbkt->count > _he_newbkt->expand_mult * (tbl)->ideal_chain_maxlen) { \ + _he_newbkt->expand_mult++; \ + } \ + } \ + _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 = ((_hs_q->next != NULL) ? \ + HH_FROM_ELMT((head)->hh.tbl, _hs_q->next) : NULL); \ + if (_hs_q == NULL) { \ + 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 = ((_hs_q->next != NULL) ? \ + HH_FROM_ELMT((head)->hh.tbl, _hs_q->next) : NULL); \ + _hs_qsize--; \ + } else if ((_hs_qsize == 0U) || (_hs_q == NULL)) { \ + _hs_e = _hs_p; \ + if (_hs_p != NULL) { \ + _hs_p = ((_hs_p->next != NULL) ? \ + HH_FROM_ELMT((head)->hh.tbl, _hs_p->next) : 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 = ((_hs_p->next != NULL) ? \ + HH_FROM_ELMT((head)->hh.tbl, _hs_p->next) : NULL); \ + } \ + _hs_psize--; \ + } else { \ + _hs_e = _hs_q; \ + _hs_q = ((_hs_q->next != NULL) ? \ + HH_FROM_ELMT((head)->hh.tbl, _hs_q->next) : 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, "HASH_SRT"); \ + } \ +} 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)) { \ + IF_HASH_NONFATAL_OOM( int _hs_oomed = 0; ) \ + _dst_hh = (UT_hash_handle*)(void*)(((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, _hs_oomed); \ + IF_HASH_NONFATAL_OOM( \ + if (_hs_oomed) { \ + uthash_nonfatal_oom(_elt); \ + (dst) = NULL; \ + continue; \ + } \ + ) \ + } 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], hh_dst, _dst_hh, _hs_oomed); \ + (dst)->hh_dst.tbl->num_items++; \ + IF_HASH_NONFATAL_OOM( \ + if (_hs_oomed) { \ + HASH_ROLLBACK_BKT(hh_dst, dst, _dst_hh); \ + HASH_DELETE_HH(hh_dst, dst, _dst_hh); \ + _dst_hh->tbl = NULL; \ + uthash_nonfatal_oom(_elt); \ + continue; \ + } \ + ) \ + HASH_BLOOM_ADD(_dst_hh->tbl, _dst_hh->hashv); \ + _last_elt = _elt; \ + _last_elt_hh = _dst_hh; \ + } \ + } \ + } \ + } \ + HASH_FSCK(hh_dst, dst, "HASH_SELECT"); \ +} while (0) + +#define HASH_CLEAR(hh,head) \ +do { \ + if ((head) != NULL) { \ + HASH_BLOOM_FREE((head)->hh.tbl); \ + uthash_free((head)->hh.tbl->buckets, \ + (head)->hh.tbl->num_buckets*sizeof(struct UT_hash_bucket)); \ + 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 */ + const 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/src/wrap.c b/src/wrap.c index fbcbb96ca..5fdfdefd4 100644 --- a/src/wrap.c +++ b/src/wrap.c @@ -80,6 +80,19 @@ static got_list_t hook_list[] = { static got_list_t inject_hook_list[] = { {"sigaction", NULL, &g_fn.sigaction}, + {"malloc", NULL, &g_fn.malloc}, + {"calloc", NULL, &g_fn.calloc}, + {"free", NULL, &g_fn.free}, + {"realloc", NULL, &g_fn.realloc}, + {"posix_memalign", NULL, &g_fn.posix_memalign}, + {"memalign", NULL, &g_fn.memalign}, + {"aligned_alloc", NULL, &g_fn.aligned_alloc}, + {"valloc", NULL, &g_fn.valloc}, + {"pvalloc", NULL, &g_fn.pvalloc}, + {"malloc_usable_size", NULL, &g_fn.malloc_usable_size}, + {"strdup", NULL, &g_fn.strdup}, + {"mmap", NULL, &g_fn.mmap}, + {"munmap", NULL, &g_fn.munmap}, {"open", NULL, &g_fn.open}, {"openat", NULL, &g_fn.openat}, {"fopen", NULL, &g_fn.fopen}, @@ -1615,13 +1628,102 @@ initSigErrorHandler(void) act.sa_flags = SA_RESTART | SA_SIGINFO; g_fn.sigaction(SIGSEGV, &act, NULL); g_fn.sigaction(SIGBUS, &act, NULL); + g_fn.sigaction(SIGABRT, &act, NULL); } } +void wait_in_loop(void) +{ + volatile int test = 1; + while(test){ + sleep(1); + } +} + +static size_t backtrace_search_size; +static char** backtrace_search; + +static void doBacktraceCfg(void) +{ + if (cfgBacktrace(g_cfg.staticfg) != CFG_BACKTRACE_FILTER) { + return; + } + + char buf[4096]; + int i; + const char *input_file = cfgBacktraceFilterFile(g_cfg.staticfg); + if (input_file == NULL) { + return; + } + + FILE* file_handler = scope_fopen(input_file, "r"); + if (file_handler == NULL) { + return; + } + while (scope_fgets(buf, sizeof(buf), file_handler) != NULL) { + backtrace_search_size++; + } + + scope_rewind(file_handler); + + backtrace_search = scope_malloc(backtrace_search_size * sizeof(char *)); + if ((const char **)backtrace_search == NULL) { + goto file_close; + } + + for (i = 0; i < backtrace_search_size; i++) { + scope_fgets(buf, sizeof(buf), file_handler); + + buf[scope_strcspn(buf, "\r\n")] = '\0'; + + backtrace_search[i] = scope_strdup(buf); + if ((const char **)backtrace_search[i] == NULL) { + while(i--) { + scope_free((const char **)backtrace_search[i]); + } + scope_free((const char **)backtrace_search); + goto file_close; + } + } + + file_close: + scope_fclose(file_handler); +} + + __attribute__((constructor)) void init(void) { + // wait_in_loop(); scope_init_vdso_ehdr(); + g_fn.calloc = dlsym(RTLD_NEXT, "calloc"); + if (!g_fn.calloc) g_fn.calloc = dlsym(RTLD_DEFAULT, "calloc"); + g_fn.mmap = dlsym(RTLD_NEXT, "mmap"); + if (!g_fn.mmap) g_fn.mmap = dlsym(RTLD_DEFAULT, "mmap"); + g_fn.munmap = dlsym(RTLD_NEXT, "munmap"); + if (!g_fn.munmap) g_fn.munmap = dlsym(RTLD_DEFAULT, "munmap"); + g_fn.malloc = dlsym(RTLD_NEXT, "malloc"); + if (!g_fn.malloc) g_fn.malloc = dlsym(RTLD_DEFAULT, "malloc"); + g_fn.free = dlsym(RTLD_NEXT, "free"); + if (!g_fn.free) g_fn.free = dlsym(RTLD_DEFAULT, "free"); + g_fn.realloc = dlsym(RTLD_NEXT, "realloc"); + if (!g_fn.realloc) g_fn.realloc = dlsym(RTLD_DEFAULT, "realloc"); + g_fn.strdup = dlsym(RTLD_NEXT, "strdup"); + if (!g_fn.strdup) g_fn.strdup = dlsym(RTLD_DEFAULT, "strdup"); + g_fn.posix_memalign = dlsym(RTLD_NEXT, "posix_memalign"); + if (!g_fn.posix_memalign) g_fn.posix_memalign = dlsym(RTLD_DEFAULT, "posix_memalign"); + g_fn.aligned_alloc = dlsym(RTLD_NEXT, "aligned_alloc"); + if (!g_fn.aligned_alloc) g_fn.aligned_alloc = dlsym(RTLD_DEFAULT, "aligned_alloc"); + g_fn.valloc = dlsym(RTLD_NEXT, "valloc"); + if (!g_fn.valloc) g_fn.valloc = dlsym(RTLD_DEFAULT, "valloc"); + g_fn.pvalloc = dlsym(RTLD_NEXT, "pvalloc"); + if (!g_fn.pvalloc) g_fn.pvalloc = dlsym(RTLD_DEFAULT, "pvalloc"); + g_fn.memalign = dlsym(RTLD_NEXT, "memalign"); + if (!g_fn.memalign) g_fn.memalign = dlsym(RTLD_DEFAULT, "memalign"); + + g_fn.malloc_usable_size = dlsym(RTLD_NEXT, "malloc_usable_size"); + if (!g_fn.malloc_usable_size) g_fn.malloc_usable_size = dlsym(RTLD_DEFAULT, "malloc_usable_size"); + // Bootstrapping... we need to know if we're in musl so we can // call the right initFn function... { @@ -1682,6 +1784,7 @@ init(void) g_getdelim = 0; g_cfg.staticfg = g_staticfg; + doBacktraceCfg(); g_cfg.blockconn = DEFAULT_PORTBLOCK; reportProcessStart(g_ctl, TRUE, CFG_WHICH_MAX); @@ -1725,6 +1828,235 @@ sigaction(int signum, const struct sigaction *act, struct sigaction *oldact) return g_fn.sigaction(signum, act, oldact); } +static size_t no_bytes_allocated; +static void *calloc_mem = NULL; + +EXPORTON char * +strdup(const char *s) { + WRAP_CHECK(strdup, NULL); + + char *str = g_fn.strdup(s); + + if(g_log) { + size_t allocated_size = g_fn.malloc_usable_size(str); + no_bytes_allocated += allocated_size; + + if (cfgBacktrace(g_cfg.staticfg) == CFG_BACKTRACE_FULL) { + scopeBacktraceFull((long long)allocated_size, "strdup", no_bytes_allocated); + } else if (cfgBacktrace(g_cfg.staticfg) == CFG_BACKTRACE_FILTER) { + scopeBacktraceFilter((const char **)backtrace_search, backtrace_search_size, (long long)allocated_size, "strdup", no_bytes_allocated); + } + } + + return str; +} +EXPORTON int +posix_memalign(void **memptr, size_t alignment, size_t size) { + WRAP_CHECK(posix_memalign, -1); + + int res = g_fn.posix_memalign(memptr, alignment, size); + + if(g_log) { + size_t allocated_size = g_fn.malloc_usable_size(*memptr); + no_bytes_allocated += allocated_size; + if (cfgBacktrace(g_cfg.staticfg) == CFG_BACKTRACE_FULL) { + scopeBacktraceFull((long long)allocated_size, "posix_memalign", no_bytes_allocated); + } else if (cfgBacktrace(g_cfg.staticfg) == CFG_BACKTRACE_FILTER) { + scopeBacktraceFilter((const char **)backtrace_search, backtrace_search_size, (long long)allocated_size, "posix_memalign", no_bytes_allocated); + } + } + return res; +} + +EXPORTON void* +aligned_alloc(size_t alignment, size_t size) { + WRAP_CHECK(aligned_alloc, NULL); + + void* ptr = g_fn.aligned_alloc(alignment, size); + if(g_log) { + size_t allocated_size = g_fn.malloc_usable_size(ptr); + no_bytes_allocated += allocated_size; + if (cfgBacktrace(g_cfg.staticfg) == CFG_BACKTRACE_FULL) { + scopeBacktraceFull((long long)allocated_size, "aligned_alloc", no_bytes_allocated); + } else if (cfgBacktrace(g_cfg.staticfg) == CFG_BACKTRACE_FILTER) { + scopeBacktraceFilter((const char **)backtrace_search, backtrace_search_size, (long long)allocated_size, "aligned_alloc", no_bytes_allocated); + } + } + return ptr; +} + +EXPORTON void* +valloc(size_t size) { + WRAP_CHECK(valloc, NULL); + + void* ptr = g_fn.valloc(size); + if(g_log) { + size_t allocated_size = g_fn.malloc_usable_size(ptr); + no_bytes_allocated += allocated_size; + if (cfgBacktrace(g_cfg.staticfg) == CFG_BACKTRACE_FULL) { + scopeBacktraceFull((long long)allocated_size, "valloc", no_bytes_allocated); + } else if (cfgBacktrace(g_cfg.staticfg) == CFG_BACKTRACE_FILTER) { + scopeBacktraceFilter((const char **)backtrace_search, backtrace_search_size, (long long)allocated_size, "valloc", no_bytes_allocated); + } + } + return ptr; +} + + +EXPORTON void* +pvalloc(size_t size) { + WRAP_CHECK(pvalloc, NULL); + + void* ptr = g_fn.pvalloc(size); + if(g_log) { + size_t allocated_size = g_fn.malloc_usable_size(ptr); + no_bytes_allocated += allocated_size; + if (cfgBacktrace(g_cfg.staticfg) == CFG_BACKTRACE_FULL) { + scopeBacktraceFull((long long)allocated_size, "pvalloc", no_bytes_allocated); + } else if (cfgBacktrace(g_cfg.staticfg) == CFG_BACKTRACE_FILTER) { + scopeBacktraceFilter((const char **)backtrace_search, backtrace_search_size, (long long)allocated_size, "pvalloc", no_bytes_allocated); + } + } + return ptr; +} + +EXPORTON void* +memalign(size_t alignment, size_t size) { + WRAP_CHECK(memalign, NULL); + + void* ptr = g_fn.memalign(alignment, size); + + if(g_log) { + size_t allocated_size = g_fn.malloc_usable_size(ptr); + no_bytes_allocated += allocated_size; + if (cfgBacktrace(g_cfg.staticfg) == CFG_BACKTRACE_FULL) { + scopeBacktraceFull((long long)allocated_size, "memalign", no_bytes_allocated); + } else if (cfgBacktrace(g_cfg.staticfg) == CFG_BACKTRACE_FILTER) { + scopeBacktraceFilter((const char **)backtrace_search, backtrace_search_size, (long long)allocated_size, "memalign", no_bytes_allocated); + } + } + return ptr; +} + +EXPORTON void * +malloc(size_t size) { + WRAP_CHECK(malloc, NULL); + + void *ptr = g_fn.malloc(size); + + if(g_log) { + size_t allocated_size = g_fn.malloc_usable_size(ptr); + no_bytes_allocated += allocated_size; + if (cfgBacktrace(g_cfg.staticfg) == CFG_BACKTRACE_FULL) { + scopeBacktraceFull((long long)allocated_size, "malloc", no_bytes_allocated); + } else if (cfgBacktrace(g_cfg.staticfg) == CFG_BACKTRACE_FILTER) { + scopeBacktraceFilter((const char **)backtrace_search, backtrace_search_size, (long long)allocated_size, "malloc", no_bytes_allocated); + } + } + + return ptr; +} + +EXPORTON void * +calloc(size_t nmemb, size_t size) { + + if (g_fn.calloc == NULL) { + calloc_mem = scope_calloc(nmemb, size); + return calloc_mem; + } + + WRAP_CHECK(calloc, NULL); + + void *ptr = g_fn.calloc(nmemb, size); + if(g_log) { + size_t allocated_size = g_fn.malloc_usable_size(ptr); + no_bytes_allocated += allocated_size; + if (cfgBacktrace(g_cfg.staticfg) == CFG_BACKTRACE_FULL) { + scopeBacktraceFull((long long)allocated_size, "calloc", no_bytes_allocated); + } else if (cfgBacktrace(g_cfg.staticfg) == CFG_BACKTRACE_FILTER) { + scopeBacktraceFilter((const char **)backtrace_search, backtrace_search_size, (long long)allocated_size, "calloc", no_bytes_allocated); + } + } + + return ptr; +} + +EXPORTON void * +realloc(void *ptr, size_t size) { + WRAP_CHECK(realloc, NULL); + + void *new_ptr = g_fn.realloc(ptr, size); + + if(g_log) { + size_t prev_size = g_fn.malloc_usable_size(ptr); + no_bytes_allocated -= prev_size; + + size_t new_size = g_fn.malloc_usable_size(new_ptr); + no_bytes_allocated += new_size; + if (cfgBacktrace(g_cfg.staticfg) == CFG_BACKTRACE_FULL) { + scopeBacktraceFull(((long long)(new_size)-(long long)prev_size), "realloc", no_bytes_allocated); + } else if (cfgBacktrace(g_cfg.staticfg) == CFG_BACKTRACE_FILTER) { + scopeBacktraceFilter((const char **)backtrace_search, backtrace_search_size, ((long long)(new_size)-(long long)prev_size), "realloc", no_bytes_allocated); + } + } + + return new_ptr; +} + +EXPORTON void +free(void *ptr) { + WRAP_CHECK_VOID(free); + + if(ptr) { + if(g_log) { + size_t freed_size = g_fn.malloc_usable_size(ptr); + no_bytes_allocated -= freed_size; + if (cfgBacktrace(g_cfg.staticfg) == CFG_BACKTRACE_FULL) { + scopeBacktraceFull(-((long long)freed_size), "free", no_bytes_allocated); + } else if (cfgBacktrace(g_cfg.staticfg) == CFG_BACKTRACE_FILTER) { + scopeBacktraceFilter((const char **)backtrace_search, backtrace_search_size, -((long long)freed_size), "free", no_bytes_allocated); + } + } + } + if (ptr == calloc_mem) { + scopeLogError("calloc_mem\n"); + scope_free(calloc_mem); + } else { + g_fn.free(ptr); + } +} + +EXPORTON void * +mmap(void *addr, size_t length, int prot, int flags, int fd, off_t offset) +{ + WRAP_CHECK(mmap, NULL); + void * ptr = g_fn.mmap(addr, length, prot, flags, fd, offset); + + if (ptr != MAP_FAILED) { + // no_bytes_allocated += length; + // scopeLogError("function = %s map: %zu bytes ", __FUNCTION__, length); + // scopeLogError("Total allocated size: %zu bytes", no_bytes_allocated); + } + + return ptr; +} + +EXPORTON int +munmap(void *addr, size_t length) +{ + WRAP_CHECK(munmap, -1); + + int res = g_fn.munmap(addr, length); + + if (!res) { + // no_bytes_allocated -= length; + // scopeLogError("function = %s unmap: %zu bytes ", __FUNCTION__, length); + // scopeLogError("Total allocated size: %zu bytes", no_bytes_allocated); + } + + return res; +} + EXPORTON int open(const char *pathname, int flags, ...) { @@ -1748,6 +2080,10 @@ openat(int dirfd, const char *pathname, int flags, ...) WRAP_CHECK(openat, -1); LOAD_FUNC_ARGS_VALIST(fArgs, flags); + if (cfgBacktrace(g_cfg.staticfg) == CFG_BACKTRACE_OPENAT) { + scopeBacktraceOp("openat", pathname); + } + fd = g_fn.openat(dirfd, pathname, flags, fArgs.arg[0]); doOpen(fd, pathname, FD, "openat"); @@ -2038,6 +2374,10 @@ openat64(int dirfd, const char *pathname, int flags, ...) WRAP_CHECK(openat64, -1); LOAD_FUNC_ARGS_VALIST(fArgs, flags); + if (cfgBacktrace(g_cfg.staticfg) == CFG_BACKTRACE_OPENAT) { + scopeBacktraceOp("openat64", pathname); + } + fd = g_fn.openat64(dirfd, pathname, flags, fArgs.arg[0]); doOpen(fd, pathname, FD, "openat64"); @@ -2072,6 +2412,10 @@ EXPORTON int __openat_2(int fd, const char *file, int oflag) { WRAP_CHECK(__openat_2, -1); + + if (cfgBacktrace(g_cfg.staticfg) == CFG_BACKTRACE_OPENAT) { + scopeBacktraceOp("__openat_2", file); + } fd = g_fn.__openat_2(fd, file, oflag); doOpen(fd, file, FD, "__openat_2"); @@ -3502,7 +3846,9 @@ dlopen(const char *filename, int flags) scopeLog(CFG_LOG_DEBUG, "dlopen called for %s with %s", filename, fbuf); WRAP_CHECK(dlopen, NULL); - + if (cfgBacktrace(g_cfg.staticfg) == CFG_BACKTRACE_OPENAT) { + scopeBacktraceOp("dlopen", filename); + } /* * Attempting to hook a number of GOT entries based on a static list. * Get the link map and the ELF sections once since they are used for