diff options
Diffstat (limited to 'compat')
43 files changed, 8558 insertions, 100 deletions
diff --git a/compat/basename.c b/compat/basename.c new file mode 100644 index 0000000000..d8f8a3c6dc --- /dev/null +++ b/compat/basename.c @@ -0,0 +1,15 @@ +#include "../git-compat-util.h" + +/* Adapted from libiberty's basename.c. */ +char *gitbasename (char *path) +{ + const char *base; + /* Skip over the disk name in MSDOS pathnames. */ + if (has_dos_drive_prefix(path)) + path += 2; + for (base = path; *path; path++) { + if (is_dir_sep(*path)) + base = path + 1; + } + return (char *)base; +} diff --git a/compat/bswap.h b/compat/bswap.h new file mode 100644 index 0000000000..f3b8c44181 --- /dev/null +++ b/compat/bswap.h @@ -0,0 +1,46 @@ +/* + * Let's make sure we always have a sane definition for ntohl()/htonl(). + * Some libraries define those as a function call, just to perform byte + * shifting, bringing significant overhead to what should be a simple + * operation. + */ + +/* + * Default version that the compiler ought to optimize properly with + * constant values. + */ +static inline uint32_t default_swab32(uint32_t val) +{ + return (((val & 0xff000000) >> 24) | + ((val & 0x00ff0000) >> 8) | + ((val & 0x0000ff00) << 8) | + ((val & 0x000000ff) << 24)); +} + +#if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__)) + +#define bswap32(x) ({ \ + uint32_t __res; \ + if (__builtin_constant_p(x)) { \ + __res = default_swab32(x); \ + } else { \ + __asm__("bswap %0" : "=r" (__res) : "0" ((uint32_t)(x))); \ + } \ + __res; }) + +#elif defined(_MSC_VER) && (defined(_M_IX86) || defined(_M_X64)) + +#include <stdlib.h> + +#define bswap32(x) _byteswap_ulong(x) + +#endif + +#ifdef bswap32 + +#undef ntohl +#undef htonl +#define ntohl(x) bswap32(x) +#define htonl(x) bswap32(x) + +#endif diff --git a/compat/cygwin.c b/compat/cygwin.c index ebac148392..b4a51b958c 100644 --- a/compat/cygwin.c +++ b/compat/cygwin.c @@ -89,10 +89,10 @@ static int cygwin_stat(const char *path, struct stat *buf) /* * At start up, we are trying to determine whether Win32 API or cygwin stat * functions should be used. The choice is determined by core.ignorecygwinfstricks. - * Reading this option is not always possible immediately as git_dir may be + * Reading this option is not always possible immediately as git_dir may * not be set yet. So until it is set, use cygwin lstat/stat functions. * However, if core.filemode is set, we must use the Cygwin posix - * stat/lstat as the Windows stat fuctions do not determine posix filemode. + * stat/lstat as the Windows stat functions do not determine posix filemode. * * Note that git_cygwin_config() does NOT call git_default_config() and this * is deliberate. Many commands read from config to establish initial diff --git a/compat/fnmatch/fnmatch.c b/compat/fnmatch/fnmatch.c index 1f4ead5f98..14feac7fe1 100644 --- a/compat/fnmatch/fnmatch.c +++ b/compat/fnmatch/fnmatch.c @@ -39,7 +39,7 @@ # include <stdlib.h> #endif -/* For platform which support the ISO C amendement 1 functionality we +/* For platforms which support the ISO C amendment 1 functionality we support user defined character classes. */ #if defined _LIBC || (defined HAVE_WCTYPE_H && defined HAVE_WCHAR_H) /* Solaris 2.5 has a bug: <wchar.h> must be included before <wctype.h>. */ @@ -90,7 +90,7 @@ # if defined _LIBC || (defined HAVE_WCTYPE_H && defined HAVE_WCHAR_H) /* The GNU C library provides support for user-defined character classes - and the functions from ISO C amendement 1. */ + and the functions from ISO C amendment 1. */ # ifdef CHARCLASS_NAME_MAX # define CHAR_CLASS_MAX_LENGTH CHARCLASS_NAME_MAX # else diff --git a/compat/memmem.c b/compat/memmem.c index cd0d877364..56bcb4277f 100644 --- a/compat/memmem.c +++ b/compat/memmem.c @@ -5,6 +5,8 @@ void *gitmemmem(const void *haystack, size_t haystack_len, { const char *begin = haystack; const char *last_possible = begin + haystack_len - needle_len; + const char *tail = needle; + char point; /* * The first occurrence of the empty string is deemed to occur at @@ -20,8 +22,9 @@ void *gitmemmem(const void *haystack, size_t haystack_len, if (haystack_len < needle_len) return NULL; + point = *tail++; for (; begin <= last_possible; begin++) { - if (!memcmp(begin, needle, needle_len)) + if (*begin == point && !memcmp(begin + 1, tail, needle_len - 1)) return (void *)begin; } diff --git a/compat/mingw.c b/compat/mingw.c index 27bcf3fd6b..c5bfb39b39 100644 --- a/compat/mingw.c +++ b/compat/mingw.c @@ -1,21 +1,137 @@ #include "../git-compat-util.h" #include "win32.h" +#include <conio.h> #include "../strbuf.h" -unsigned int _CRT_fmode = _O_BINARY; +int err_win_to_posix(DWORD winerr) +{ + int error = ENOSYS; + switch(winerr) { + case ERROR_ACCESS_DENIED: error = EACCES; break; + case ERROR_ACCOUNT_DISABLED: error = EACCES; break; + case ERROR_ACCOUNT_RESTRICTION: error = EACCES; break; + case ERROR_ALREADY_ASSIGNED: error = EBUSY; break; + case ERROR_ALREADY_EXISTS: error = EEXIST; break; + case ERROR_ARITHMETIC_OVERFLOW: error = ERANGE; break; + case ERROR_BAD_COMMAND: error = EIO; break; + case ERROR_BAD_DEVICE: error = ENODEV; break; + case ERROR_BAD_DRIVER_LEVEL: error = ENXIO; break; + case ERROR_BAD_EXE_FORMAT: error = ENOEXEC; break; + case ERROR_BAD_FORMAT: error = ENOEXEC; break; + case ERROR_BAD_LENGTH: error = EINVAL; break; + case ERROR_BAD_PATHNAME: error = ENOENT; break; + case ERROR_BAD_PIPE: error = EPIPE; break; + case ERROR_BAD_UNIT: error = ENODEV; break; + case ERROR_BAD_USERNAME: error = EINVAL; break; + case ERROR_BROKEN_PIPE: error = EPIPE; break; + case ERROR_BUFFER_OVERFLOW: error = ENAMETOOLONG; break; + case ERROR_BUSY: error = EBUSY; break; + case ERROR_BUSY_DRIVE: error = EBUSY; break; + case ERROR_CALL_NOT_IMPLEMENTED: error = ENOSYS; break; + case ERROR_CANNOT_MAKE: error = EACCES; break; + case ERROR_CANTOPEN: error = EIO; break; + case ERROR_CANTREAD: error = EIO; break; + case ERROR_CANTWRITE: error = EIO; break; + case ERROR_CRC: error = EIO; break; + case ERROR_CURRENT_DIRECTORY: error = EACCES; break; + case ERROR_DEVICE_IN_USE: error = EBUSY; break; + case ERROR_DEV_NOT_EXIST: error = ENODEV; break; + case ERROR_DIRECTORY: error = EINVAL; break; + case ERROR_DIR_NOT_EMPTY: error = ENOTEMPTY; break; + case ERROR_DISK_CHANGE: error = EIO; break; + case ERROR_DISK_FULL: error = ENOSPC; break; + case ERROR_DRIVE_LOCKED: error = EBUSY; break; + case ERROR_ENVVAR_NOT_FOUND: error = EINVAL; break; + case ERROR_EXE_MARKED_INVALID: error = ENOEXEC; break; + case ERROR_FILENAME_EXCED_RANGE: error = ENAMETOOLONG; break; + case ERROR_FILE_EXISTS: error = EEXIST; break; + case ERROR_FILE_INVALID: error = ENODEV; break; + case ERROR_FILE_NOT_FOUND: error = ENOENT; break; + case ERROR_GEN_FAILURE: error = EIO; break; + case ERROR_HANDLE_DISK_FULL: error = ENOSPC; break; + case ERROR_INSUFFICIENT_BUFFER: error = ENOMEM; break; + case ERROR_INVALID_ACCESS: error = EACCES; break; + case ERROR_INVALID_ADDRESS: error = EFAULT; break; + case ERROR_INVALID_BLOCK: error = EFAULT; break; + case ERROR_INVALID_DATA: error = EINVAL; break; + case ERROR_INVALID_DRIVE: error = ENODEV; break; + case ERROR_INVALID_EXE_SIGNATURE: error = ENOEXEC; break; + case ERROR_INVALID_FLAGS: error = EINVAL; break; + case ERROR_INVALID_FUNCTION: error = ENOSYS; break; + case ERROR_INVALID_HANDLE: error = EBADF; break; + case ERROR_INVALID_LOGON_HOURS: error = EACCES; break; + case ERROR_INVALID_NAME: error = EINVAL; break; + case ERROR_INVALID_OWNER: error = EINVAL; break; + case ERROR_INVALID_PARAMETER: error = EINVAL; break; + case ERROR_INVALID_PASSWORD: error = EPERM; break; + case ERROR_INVALID_PRIMARY_GROUP: error = EINVAL; break; + case ERROR_INVALID_SIGNAL_NUMBER: error = EINVAL; break; + case ERROR_INVALID_TARGET_HANDLE: error = EIO; break; + case ERROR_INVALID_WORKSTATION: error = EACCES; break; + case ERROR_IO_DEVICE: error = EIO; break; + case ERROR_IO_INCOMPLETE: error = EINTR; break; + case ERROR_LOCKED: error = EBUSY; break; + case ERROR_LOCK_VIOLATION: error = EACCES; break; + case ERROR_LOGON_FAILURE: error = EACCES; break; + case ERROR_MAPPED_ALIGNMENT: error = EINVAL; break; + case ERROR_META_EXPANSION_TOO_LONG: error = E2BIG; break; + case ERROR_MORE_DATA: error = EPIPE; break; + case ERROR_NEGATIVE_SEEK: error = ESPIPE; break; + case ERROR_NOACCESS: error = EFAULT; break; + case ERROR_NONE_MAPPED: error = EINVAL; break; + case ERROR_NOT_ENOUGH_MEMORY: error = ENOMEM; break; + case ERROR_NOT_READY: error = EAGAIN; break; + case ERROR_NOT_SAME_DEVICE: error = EXDEV; break; + case ERROR_NO_DATA: error = EPIPE; break; + case ERROR_NO_MORE_SEARCH_HANDLES: error = EIO; break; + case ERROR_NO_PROC_SLOTS: error = EAGAIN; break; + case ERROR_NO_SUCH_PRIVILEGE: error = EACCES; break; + case ERROR_OPEN_FAILED: error = EIO; break; + case ERROR_OPEN_FILES: error = EBUSY; break; + case ERROR_OPERATION_ABORTED: error = EINTR; break; + case ERROR_OUTOFMEMORY: error = ENOMEM; break; + case ERROR_PASSWORD_EXPIRED: error = EACCES; break; + case ERROR_PATH_BUSY: error = EBUSY; break; + case ERROR_PATH_NOT_FOUND: error = ENOENT; break; + case ERROR_PIPE_BUSY: error = EBUSY; break; + case ERROR_PIPE_CONNECTED: error = EPIPE; break; + case ERROR_PIPE_LISTENING: error = EPIPE; break; + case ERROR_PIPE_NOT_CONNECTED: error = EPIPE; break; + case ERROR_PRIVILEGE_NOT_HELD: error = EACCES; break; + case ERROR_READ_FAULT: error = EIO; break; + case ERROR_SEEK: error = EIO; break; + case ERROR_SEEK_ON_DEVICE: error = ESPIPE; break; + case ERROR_SHARING_BUFFER_EXCEEDED: error = ENFILE; break; + case ERROR_SHARING_VIOLATION: error = EACCES; break; + case ERROR_STACK_OVERFLOW: error = ENOMEM; break; + case ERROR_SWAPERROR: error = ENOENT; break; + case ERROR_TOO_MANY_MODULES: error = EMFILE; break; + case ERROR_TOO_MANY_OPEN_FILES: error = EMFILE; break; + case ERROR_UNRECOGNIZED_MEDIA: error = ENXIO; break; + case ERROR_UNRECOGNIZED_VOLUME: error = ENODEV; break; + case ERROR_WAIT_NO_CHILDREN: error = ECHILD; break; + case ERROR_WRITE_FAULT: error = EIO; break; + case ERROR_WRITE_PROTECT: error = EROFS; break; + } + return error; +} #undef open int mingw_open (const char *filename, int oflags, ...) { va_list args; unsigned mode; + int fd; + va_start(args, oflags); mode = va_arg(args, int); va_end(args); if (!strcmp(filename, "/dev/null")) filename = "nul"; - int fd = open(filename, oflags, mode); + + fd = open(filename, oflags, mode); + if (fd < 0 && (oflags & O_CREAT) && errno == EACCES) { DWORD attrs = GetFileAttributes(filename); if (attrs != INVALID_FILE_ATTRIBUTES && (attrs & FILE_ATTRIBUTE_DIRECTORY)) @@ -24,12 +140,36 @@ int mingw_open (const char *filename, int oflags, ...) return fd; } -static inline time_t filetime_to_time_t(const FILETIME *ft) +#undef fopen +FILE *mingw_fopen (const char *filename, const char *otype) +{ + if (!strcmp(filename, "/dev/null")) + filename = "nul"; + return fopen(filename, otype); +} + +#undef freopen +FILE *mingw_freopen (const char *filename, const char *otype, FILE *stream) +{ + if (filename && !strcmp(filename, "/dev/null")) + filename = "nul"; + return freopen(filename, otype, stream); +} + +/* + * The unit of FILETIME is 100-nanoseconds since January 1, 1601, UTC. + * Returns the 100-nanoseconds ("hekto nanoseconds") since the epoch. + */ +static inline long long filetime_to_hnsec(const FILETIME *ft) { long long winTime = ((long long)ft->dwHighDateTime << 32) + ft->dwLowDateTime; - winTime -= 116444736000000000LL; /* Windows to Unix Epoch conversion */ - winTime /= 10000000; /* Nano to seconds resolution */ - return (time_t)winTime; + /* Windows to Unix Epoch conversion */ + return winTime - 116444736000000000LL; +} + +static inline time_t filetime_to_time_t(const FILETIME *ft) +{ + return (time_t)(filetime_to_hnsec(ft) / 10000000); } /* We keep the do_lstat code in a separate function to avoid recursion. @@ -165,64 +305,37 @@ int mkstemp(char *template) int gettimeofday(struct timeval *tv, void *tz) { - SYSTEMTIME st; - struct tm tm; - GetSystemTime(&st); - tm.tm_year = st.wYear-1900; - tm.tm_mon = st.wMonth-1; - tm.tm_mday = st.wDay; - tm.tm_hour = st.wHour; - tm.tm_min = st.wMinute; - tm.tm_sec = st.wSecond; - tv->tv_sec = tm_to_time_t(&tm); - if (tv->tv_sec < 0) - return -1; - tv->tv_usec = st.wMilliseconds*1000; + FILETIME ft; + long long hnsec; + + GetSystemTimeAsFileTime(&ft); + hnsec = filetime_to_hnsec(&ft); + tv->tv_sec = hnsec / 10000000; + tv->tv_usec = (hnsec % 10000000) / 10; return 0; } int pipe(int filedes[2]) { - int fd; - HANDLE h[2], parent; + HANDLE h[2]; - if (_pipe(filedes, 8192, 0) < 0) - return -1; - - parent = GetCurrentProcess(); - - if (!DuplicateHandle (parent, (HANDLE)_get_osfhandle(filedes[0]), - parent, &h[0], 0, FALSE, DUPLICATE_SAME_ACCESS)) { - close(filedes[0]); - close(filedes[1]); + /* this creates non-inheritable handles */ + if (!CreatePipe(&h[0], &h[1], NULL, 8192)) { + errno = err_win_to_posix(GetLastError()); return -1; } - if (!DuplicateHandle (parent, (HANDLE)_get_osfhandle(filedes[1]), - parent, &h[1], 0, FALSE, DUPLICATE_SAME_ACCESS)) { - close(filedes[0]); - close(filedes[1]); - CloseHandle(h[0]); - return -1; - } - fd = _open_osfhandle((int)h[0], O_NOINHERIT); - if (fd < 0) { - close(filedes[0]); - close(filedes[1]); + filedes[0] = _open_osfhandle((int)h[0], O_NOINHERIT); + if (filedes[0] < 0) { CloseHandle(h[0]); CloseHandle(h[1]); return -1; } - close(filedes[0]); - filedes[0] = fd; - fd = _open_osfhandle((int)h[1], O_NOINHERIT); - if (fd < 0) { + filedes[1] = _open_osfhandle((int)h[1], O_NOINHERIT); + if (filedes[0] < 0) { close(filedes[0]); - close(filedes[1]); CloseHandle(h[1]); return -1; } - close(filedes[1]); - filedes[1] = fd; return 0; } @@ -283,7 +396,7 @@ repeat: * its own input data to become available. But since * the process (pack-objects) is itself CPU intensive, * it will happily pick up the time slice that we are - * relinguishing here. + * relinquishing here. */ Sleep(0); goto repeat; @@ -344,7 +457,7 @@ static const char *quote_arg(const char *arg) const char *p = arg; if (!*p) force_quotes = 1; while (*p) { - if (isspace(*p) || *p == '*' || *p == '?' || *p == '{') + if (isspace(*p) || *p == '*' || *p == '?' || *p == '{' || *p == '\'') force_quotes = 1; else if (*p == '"') n++; @@ -412,8 +525,8 @@ static const char *parse_interpreter(const char *cmd) if (buf[0] != '#' || buf[1] != '!') return NULL; buf[n] = '\0'; - p = strchr(buf, '\n'); - if (!p) + p = buf + strcspn(buf, "\r\n"); + if (!*p) return NULL; *p = '\0'; @@ -449,7 +562,7 @@ static char **get_path_split(void) if (!n) return NULL; - path = xmalloc((n+1)*sizeof(char*)); + path = xmalloc((n+1)*sizeof(char *)); p = envpath; i = 0; do { @@ -466,10 +579,11 @@ static char **get_path_split(void) static void free_path_split(char **path) { + char **p = path; + if (!path) return; - char **p = path; while (*p) free(*p++); free(path); @@ -519,8 +633,8 @@ static int env_compare(const void *a, const void *b) return strcasecmp(*ea, *eb); } -static pid_t mingw_spawnve(const char *cmd, const char **argv, char **env, - int prepend_cmd) +static pid_t mingw_spawnve_fd(const char *cmd, const char **argv, char **env, + int prepend_cmd, int fhin, int fhout, int fherr) { STARTUPINFO si; PROCESS_INFORMATION pi; @@ -556,9 +670,9 @@ static pid_t mingw_spawnve(const char *cmd, const char **argv, char **env, memset(&si, 0, sizeof(si)); si.cb = sizeof(si); si.dwFlags = STARTF_USESTDHANDLES; - si.hStdInput = (HANDLE) _get_osfhandle(0); - si.hStdOutput = (HANDLE) _get_osfhandle(1); - si.hStdError = (HANDLE) _get_osfhandle(2); + si.hStdInput = (HANDLE) _get_osfhandle(fhin); + si.hStdOutput = (HANDLE) _get_osfhandle(fhout); + si.hStdError = (HANDLE) _get_osfhandle(fherr); /* concatenate argv, quoting args as we go */ strbuf_init(&args, 0); @@ -613,7 +727,14 @@ static pid_t mingw_spawnve(const char *cmd, const char **argv, char **env, return (pid_t)pi.hProcess; } -pid_t mingw_spawnvpe(const char *cmd, const char **argv, char **env) +static pid_t mingw_spawnve(const char *cmd, const char **argv, char **env, + int prepend_cmd) +{ + return mingw_spawnve_fd(cmd, argv, env, prepend_cmd, 0, 1, 2); +} + +pid_t mingw_spawnvpe(const char *cmd, const char **argv, char **env, + int fhin, int fhout, int fherr) { pid_t pid; char **path = get_path_split(); @@ -635,13 +756,15 @@ pid_t mingw_spawnvpe(const char *cmd, const char **argv, char **env) pid = -1; } else { - pid = mingw_spawnve(iprog, argv, env, 1); + pid = mingw_spawnve_fd(iprog, argv, env, 1, + fhin, fhout, fherr); free(iprog); } argv[0] = argv0; } else - pid = mingw_spawnve(prog, argv, env, 0); + pid = mingw_spawnve_fd(prog, argv, env, 0, + fhin, fhout, fherr); free(prog); } free_path_split(path); @@ -710,7 +833,7 @@ void mingw_execvp(const char *cmd, char *const *argv) free_path_split(path); } -char **copy_environ() +static char **copy_environ(void) { char **env; int i = 0; @@ -747,7 +870,7 @@ static int lookup_env(char **env, const char *name, size_t nmln) /* * If name contains '=', then sets the variable, otherwise it unsets it */ -char **env_setenv(char **env, const char *name) +static char **env_setenv(char **env, const char *name) { char *eq = strchrnul(name, '='); int i = lookup_env(env, name, eq-name); @@ -772,19 +895,207 @@ char **env_setenv(char **env, const char *name) return env; } -/* this is the first function to call into WS_32; initialize it */ -#undef gethostbyname -struct hostent *mingw_gethostbyname(const char *host) +/* + * Copies global environ and adjusts variables as specified by vars. + */ +char **make_augmented_environ(const char *const *vars) +{ + char **env = copy_environ(); + + while (*vars) + env = env_setenv(env, *vars++); + return env; +} + +/* + * Note, this isn't a complete replacement for getaddrinfo. It assumes + * that service contains a numerical port, or that it it is null. It + * does a simple search using gethostbyname, and returns one IPv4 host + * if one was found. + */ +static int WSAAPI getaddrinfo_stub(const char *node, const char *service, + const struct addrinfo *hints, + struct addrinfo **res) +{ + struct hostent *h = gethostbyname(node); + struct addrinfo *ai; + struct sockaddr_in *sin; + + if (!h) + return WSAGetLastError(); + + ai = xmalloc(sizeof(struct addrinfo)); + *res = ai; + ai->ai_flags = 0; + ai->ai_family = AF_INET; + ai->ai_socktype = hints->ai_socktype; + switch (hints->ai_socktype) { + case SOCK_STREAM: + ai->ai_protocol = IPPROTO_TCP; + break; + case SOCK_DGRAM: + ai->ai_protocol = IPPROTO_UDP; + break; + default: + ai->ai_protocol = 0; + break; + } + ai->ai_addrlen = sizeof(struct sockaddr_in); + ai->ai_canonname = strdup(h->h_name); + + sin = xmalloc(ai->ai_addrlen); + memset(sin, 0, ai->ai_addrlen); + sin->sin_family = AF_INET; + if (service) + sin->sin_port = htons(atoi(service)); + sin->sin_addr = *(struct in_addr *)h->h_addr; + ai->ai_addr = (struct sockaddr *)sin; + ai->ai_next = 0; + return 0; +} + +static void WSAAPI freeaddrinfo_stub(struct addrinfo *res) +{ + free(res->ai_canonname); + free(res->ai_addr); + free(res); +} + +static int WSAAPI getnameinfo_stub(const struct sockaddr *sa, socklen_t salen, + char *host, DWORD hostlen, + char *serv, DWORD servlen, int flags) +{ + const struct sockaddr_in *sin = (const struct sockaddr_in *)sa; + if (sa->sa_family != AF_INET) + return EAI_FAMILY; + if (!host && !serv) + return EAI_NONAME; + + if (host && hostlen > 0) { + struct hostent *ent = NULL; + if (!(flags & NI_NUMERICHOST)) + ent = gethostbyaddr((const char *)&sin->sin_addr, + sizeof(sin->sin_addr), AF_INET); + + if (ent) + snprintf(host, hostlen, "%s", ent->h_name); + else if (flags & NI_NAMEREQD) + return EAI_NONAME; + else + snprintf(host, hostlen, "%s", inet_ntoa(sin->sin_addr)); + } + + if (serv && servlen > 0) { + struct servent *ent = NULL; + if (!(flags & NI_NUMERICSERV)) + ent = getservbyport(sin->sin_port, + flags & NI_DGRAM ? "udp" : "tcp"); + + if (ent) + snprintf(serv, servlen, "%s", ent->s_name); + else + snprintf(serv, servlen, "%d", ntohs(sin->sin_port)); + } + + return 0; +} + +static HMODULE ipv6_dll = NULL; +static void (WSAAPI *ipv6_freeaddrinfo)(struct addrinfo *res); +static int (WSAAPI *ipv6_getaddrinfo)(const char *node, const char *service, + const struct addrinfo *hints, + struct addrinfo **res); +static int (WSAAPI *ipv6_getnameinfo)(const struct sockaddr *sa, socklen_t salen, + char *host, DWORD hostlen, + char *serv, DWORD servlen, int flags); +/* + * gai_strerror is an inline function in the ws2tcpip.h header, so we + * don't need to try to load that one dynamically. + */ + +static void socket_cleanup(void) +{ + WSACleanup(); + if (ipv6_dll) + FreeLibrary(ipv6_dll); + ipv6_dll = NULL; + ipv6_freeaddrinfo = freeaddrinfo_stub; + ipv6_getaddrinfo = getaddrinfo_stub; + ipv6_getnameinfo = getnameinfo_stub; +} + +static void ensure_socket_initialization(void) { WSADATA wsa; + static int initialized = 0; + const char *libraries[] = { "ws2_32.dll", "wship6.dll", NULL }; + const char **name; + + if (initialized) + return; if (WSAStartup(MAKEWORD(2,2), &wsa)) die("unable to initialize winsock subsystem, error %d", WSAGetLastError()); - atexit((void(*)(void)) WSACleanup); + + for (name = libraries; *name; name++) { + ipv6_dll = LoadLibrary(*name); + if (!ipv6_dll) + continue; + + ipv6_freeaddrinfo = (void (WSAAPI *)(struct addrinfo *)) + GetProcAddress(ipv6_dll, "freeaddrinfo"); + ipv6_getaddrinfo = (int (WSAAPI *)(const char *, const char *, + const struct addrinfo *, + struct addrinfo **)) + GetProcAddress(ipv6_dll, "getaddrinfo"); + ipv6_getnameinfo = (int (WSAAPI *)(const struct sockaddr *, + socklen_t, char *, DWORD, + char *, DWORD, int)) + GetProcAddress(ipv6_dll, "getnameinfo"); + if (!ipv6_freeaddrinfo || !ipv6_getaddrinfo || !ipv6_getnameinfo) { + FreeLibrary(ipv6_dll); + ipv6_dll = NULL; + } else + break; + } + if (!ipv6_freeaddrinfo || !ipv6_getaddrinfo || !ipv6_getnameinfo) { + ipv6_freeaddrinfo = freeaddrinfo_stub; + ipv6_getaddrinfo = getaddrinfo_stub; + ipv6_getnameinfo = getnameinfo_stub; + } + + atexit(socket_cleanup); + initialized = 1; +} + +#undef gethostbyname +struct hostent *mingw_gethostbyname(const char *host) +{ + ensure_socket_initialization(); return gethostbyname(host); } +void mingw_freeaddrinfo(struct addrinfo *res) +{ + ipv6_freeaddrinfo(res); +} + +int mingw_getaddrinfo(const char *node, const char *service, + const struct addrinfo *hints, struct addrinfo **res) +{ + ensure_socket_initialization(); + return ipv6_getaddrinfo(node, service, hints, res); +} + +int mingw_getnameinfo(const struct sockaddr *sa, socklen_t salen, + char *host, DWORD hostlen, char *serv, DWORD servlen, + int flags) +{ + ensure_socket_initialization(); + return ipv6_getnameinfo(sa, salen, host, hostlen, serv, servlen, flags); +} + int mingw_socket(int domain, int type, int protocol) { int sockfd; @@ -821,7 +1132,9 @@ int mingw_connect(int sockfd, struct sockaddr *sa, size_t sz) #undef rename int mingw_rename(const char *pold, const char *pnew) { - DWORD attrs; + DWORD attrs, gle; + int tries = 0; + static const int delay[] = { 0, 1, 10, 20, 40 }; /* * Try native rename() first to get errno right. @@ -831,10 +1144,12 @@ int mingw_rename(const char *pold, const char *pnew) return 0; if (errno != EEXIST) return -1; +repeat: if (MoveFileEx(pold, pnew, MOVEFILE_REPLACE_EXISTING)) return 0; /* TODO: translate more errors */ - if (GetLastError() == ERROR_ACCESS_DENIED && + gle = GetLastError(); + if (gle == ERROR_ACCESS_DENIED && (attrs = GetFileAttributes(pnew)) != INVALID_FILE_ATTRIBUTES) { if (attrs & FILE_ATTRIBUTE_DIRECTORY) { errno = EISDIR; @@ -844,14 +1159,39 @@ int mingw_rename(const char *pold, const char *pnew) SetFileAttributes(pnew, attrs & ~FILE_ATTRIBUTE_READONLY)) { if (MoveFileEx(pold, pnew, MOVEFILE_REPLACE_EXISTING)) return 0; + gle = GetLastError(); /* revert file attributes on failure */ SetFileAttributes(pnew, attrs); } } + if (tries < ARRAY_SIZE(delay) && gle == ERROR_ACCESS_DENIED) { + /* + * We assume that some other process had the source or + * destination file open at the wrong moment and retry. + * In order to give the other process a higher chance to + * complete its operation, we give up our time slice now. + * If we have to retry again, we do sleep a bit. + */ + Sleep(delay[tries]); + tries++; + goto repeat; + } errno = EACCES; return -1; } +/* + * Note that this doesn't return the actual pagesize, but + * the allocation granularity. If future Windows specific git code + * needs the real getpagesize function, we need to find another solution. + */ +int mingw_getpagesize(void) +{ + SYSTEM_INFO si; + GetSystemInfo(&si); + return si.dwAllocationGranularity; +} + struct passwd *getpwuid(int uid) { static char user_name[100]; @@ -881,7 +1221,7 @@ static sig_handler_t timer_fn = SIG_DFL; * length to call the signal handler. */ -static __stdcall unsigned ticktack(void *dummy) +static unsigned __stdcall ticktack(void *dummy) { while (WaitForSingleObject(timer_event, timer_interval) == WAIT_TIMEOUT) { if (timer_fn == SIG_DFL) @@ -977,9 +1317,9 @@ int sigaction(int sig, struct sigaction *in, struct sigaction *out) #undef signal sig_handler_t mingw_signal(int sig, sig_handler_t handler) { + sig_handler_t old = timer_fn; if (sig != SIGALRM) return signal(sig, handler); - sig_handler_t old = timer_fn; timer_fn = handler; return old; } @@ -1002,6 +1342,116 @@ static const char *make_backslash_path(const char *path) void mingw_open_html(const char *unixpath) { const char *htmlpath = make_backslash_path(unixpath); + typedef HINSTANCE (WINAPI *T)(HWND, const char *, + const char *, const char *, const char *, INT); + T ShellExecute; + HMODULE shell32; + + shell32 = LoadLibrary("shell32.dll"); + if (!shell32) + die("cannot load shell32.dll"); + ShellExecute = (T)GetProcAddress(shell32, "ShellExecuteA"); + if (!ShellExecute) + die("cannot run browser"); + printf("Launching default browser to display HTML ...\n"); ShellExecute(NULL, "open", htmlpath, NULL, "\\", 0); + + FreeLibrary(shell32); +} + +int link(const char *oldpath, const char *newpath) +{ + typedef BOOL (WINAPI *T)(const char*, const char*, LPSECURITY_ATTRIBUTES); + static T create_hard_link = NULL; + if (!create_hard_link) { + create_hard_link = (T) GetProcAddress( + GetModuleHandle("kernel32.dll"), "CreateHardLinkA"); + if (!create_hard_link) + create_hard_link = (T)-1; + } + if (create_hard_link == (T)-1) { + errno = ENOSYS; + return -1; + } + if (!create_hard_link(newpath, oldpath, NULL)) { + errno = err_win_to_posix(GetLastError()); + return -1; + } + return 0; +} + +char *getpass(const char *prompt) +{ + struct strbuf buf = STRBUF_INIT; + + fputs(prompt, stderr); + for (;;) { + char c = _getch(); + if (c == '\r' || c == '\n') + break; + strbuf_addch(&buf, c); + } + fputs("\n", stderr); + return strbuf_detach(&buf, NULL); +} + +#ifndef NO_MINGW_REPLACE_READDIR +/* MinGW readdir implementation to avoid extra lstats for Git */ +struct mingw_DIR +{ + struct _finddata_t dd_dta; /* disk transfer area for this dir */ + struct mingw_dirent dd_dir; /* Our own implementation, including d_type */ + long dd_handle; /* _findnext handle */ + int dd_stat; /* 0 = next entry to read is first entry, -1 = off the end, positive = 0 based index of next entry */ + char dd_name[1]; /* given path for dir with search pattern (struct is extended) */ +}; + +struct dirent *mingw_readdir(DIR *dir) +{ + WIN32_FIND_DATAA buf; + HANDLE handle; + struct mingw_DIR *mdir = (struct mingw_DIR*)dir; + + if (!dir->dd_handle) { + errno = EBADF; /* No set_errno for mingw */ + return NULL; + } + + if (dir->dd_handle == (long)INVALID_HANDLE_VALUE && dir->dd_stat == 0) + { + DWORD lasterr; + handle = FindFirstFileA(dir->dd_name, &buf); + lasterr = GetLastError(); + dir->dd_handle = (long)handle; + if (handle == INVALID_HANDLE_VALUE && (lasterr != ERROR_NO_MORE_FILES)) { + errno = err_win_to_posix(lasterr); + return NULL; + } + } else if (dir->dd_handle == (long)INVALID_HANDLE_VALUE) { + return NULL; + } else if (!FindNextFileA((HANDLE)dir->dd_handle, &buf)) { + DWORD lasterr = GetLastError(); + FindClose((HANDLE)dir->dd_handle); + dir->dd_handle = (long)INVALID_HANDLE_VALUE; + /* POSIX says you shouldn't set errno when readdir can't + find any more files; so, if another error we leave it set. */ + if (lasterr != ERROR_NO_MORE_FILES) + errno = err_win_to_posix(lasterr); + return NULL; + } + + /* We get here if `buf' contains valid data. */ + strcpy(dir->dd_dir.d_name, buf.cFileName); + ++dir->dd_stat; + + /* Set file type, based on WIN32_FIND_DATA */ + mdir->dd_dir.d_type = 0; + if (buf.dwFileAttributes & FILE_ATTRIBUTE_DIRECTORY) + mdir->dd_dir.d_type |= DT_DIR; + else + mdir->dd_dir.d_type |= DT_REG; + + return (struct dirent*)&dir->dd_dir; } +#endif // !NO_MINGW_REPLACE_READDIR diff --git a/compat/mingw.h b/compat/mingw.h index 6e24686442..e81e752ed2 100644 --- a/compat/mingw.h +++ b/compat/mingw.h @@ -1,4 +1,5 @@ #include <winsock2.h> +#include <ws2tcpip.h> /* * things that are not available in header files @@ -17,9 +18,10 @@ typedef int pid_t; #define S_IROTH 0 #define S_IXOTH 0 -#define WIFEXITED(x) ((unsigned)(x) < 259) /* STILL_ACTIVE */ +#define WIFEXITED(x) 1 +#define WIFSIGNALED(x) 0 #define WEXITSTATUS(x) ((x) & 0xff) -#define WIFSIGNALED(x) ((unsigned)(x) > 259) +#define WTERMSIG(x) SIGTERM #define SIGHUP 1 #define SIGQUIT 3 @@ -38,6 +40,9 @@ struct passwd { char *pw_dir; }; +extern char *getpass(const char *prompt); + +#ifndef POLLIN struct pollfd { int fd; /* file descriptor */ short events; /* requested events */ @@ -45,6 +50,7 @@ struct pollfd { }; #define POLLIN 1 #define POLLHUP 2 +#endif typedef void (__cdecl *sig_handler_t)(int); struct sigaction { @@ -67,8 +73,6 @@ static inline int readlink(const char *path, char *buf, size_t bufsiz) { errno = ENOSYS; return -1; } static inline int symlink(const char *oldpath, const char *newpath) { errno = ENOSYS; return -1; } -static inline int link(const char *oldpath, const char *newpath) -{ errno = ENOSYS; return -1; } static inline int fchmod(int fildes, mode_t mode) { errno = ENOSYS; return -1; } static inline int fork(void) @@ -92,6 +96,8 @@ static inline int fcntl(int fd, int cmd, long arg) errno = EINVAL; return -1; } +/* bash cannot reliably detect negative return codes as failure */ +#define exit(code) exit((code) & 0xff) /* * simple adaptors @@ -111,7 +117,7 @@ static inline int mingw_unlink(const char *pathname) } #define unlink mingw_unlink -static inline int waitpid(pid_t pid, unsigned *status, unsigned options) +static inline int waitpid(pid_t pid, int *status, unsigned options) { if (options == 0) return _cwait(status, pid, 0); @@ -119,6 +125,27 @@ static inline int waitpid(pid_t pid, unsigned *status, unsigned options) return -1; } +#ifndef NO_OPENSSL +#include <openssl/ssl.h> +static inline int mingw_SSL_set_fd(SSL *ssl, int fd) +{ + return SSL_set_fd(ssl, _get_osfhandle(fd)); +} +#define SSL_set_fd mingw_SSL_set_fd + +static inline int mingw_SSL_set_rfd(SSL *ssl, int fd) +{ + return SSL_set_rfd(ssl, _get_osfhandle(fd)); +} +#define SSL_set_rfd mingw_SSL_set_rfd + +static inline int mingw_SSL_set_wfd(SSL *ssl, int fd) +{ + return SSL_set_wfd(ssl, _get_osfhandle(fd)); +} +#define SSL_set_wfd mingw_SSL_set_wfd +#endif + /* * implementations of missing functions */ @@ -134,6 +161,7 @@ int getpagesize(void); /* defined in MinGW's libgcc.a */ struct passwd *getpwuid(int uid); int setitimer(int type, struct itimerval *in, struct itimerval *out); int sigaction(int sig, struct sigaction *in, struct sigaction *out); +int link(const char *oldpath, const char *newpath); /* * replacements of existing functions @@ -142,6 +170,12 @@ int sigaction(int sig, struct sigaction *in, struct sigaction *out); int mingw_open (const char *filename, int oflags, ...); #define open mingw_open +FILE *mingw_fopen (const char *filename, const char *otype); +#define fopen mingw_fopen + +FILE *mingw_freopen (const char *filename, const char *otype, FILE *stream); +#define freopen mingw_freopen + char *mingw_getcwd(char *pointer, int len); #define getcwd mingw_getcwd @@ -151,6 +185,18 @@ char *mingw_getenv(const char *name); struct hostent *mingw_gethostbyname(const char *host); #define gethostbyname mingw_gethostbyname +void mingw_freeaddrinfo(struct addrinfo *res); +#define freeaddrinfo mingw_freeaddrinfo + +int mingw_getaddrinfo(const char *node, const char *service, + const struct addrinfo *hints, struct addrinfo **res); +#define getaddrinfo mingw_getaddrinfo + +int mingw_getnameinfo(const struct sockaddr *sa, socklen_t salen, + char *host, DWORD hostlen, char *serv, DWORD servlen, + int flags); +#define getnameinfo mingw_getnameinfo + int mingw_socket(int domain, int type, int protocol); #define socket mingw_socket @@ -160,22 +206,30 @@ int mingw_connect(int sockfd, struct sockaddr *sa, size_t sz); int mingw_rename(const char*, const char*); #define rename mingw_rename +#if defined(USE_WIN32_MMAP) || defined(_MSC_VER) +int mingw_getpagesize(void); +#define getpagesize mingw_getpagesize +#endif + /* Use mingw_lstat() instead of lstat()/stat() and * mingw_fstat() instead of fstat() on Windows. */ #define off_t off64_t -#define stat _stati64 #define lseek _lseeki64 +#ifndef ALREADY_DECLARED_STAT_FUNCS +#define stat _stati64 int mingw_lstat(const char *file_name, struct stat *buf); int mingw_fstat(int fd, struct stat *buf); #define fstat mingw_fstat #define lstat mingw_lstat #define _stati64(x,y) mingw_lstat(x,y) +#endif int mingw_utime(const char *file_name, const struct utimbuf *times); #define utime mingw_utime -pid_t mingw_spawnvpe(const char *cmd, const char **argv, char **env); +pid_t mingw_spawnvpe(const char *cmd, const char **argv, char **env, + int fhin, int fhout, int fherr); void mingw_execvp(const char *cmd, char *const *argv); #define execvp mingw_execvp @@ -213,19 +267,57 @@ void mingw_open_html(const char *path); * helpers */ -char **copy_environ(void); +char **make_augmented_environ(const char *const *vars); void free_environ(char **env); -char **env_setenv(char **env, const char *name); /* * A replacement of main() that ensures that argv[0] has a path + * and that default fmode and std(in|out|err) are in binary mode */ #define main(c,v) dummy_decl_mingw_main(); \ static int mingw_main(); \ int main(int argc, const char **argv) \ { \ + _fmode = _O_BINARY; \ + _setmode(_fileno(stdin), _O_BINARY); \ + _setmode(_fileno(stdout), _O_BINARY); \ + _setmode(_fileno(stderr), _O_BINARY); \ argv[0] = xstrdup(_pgmptr); \ return mingw_main(argc, argv); \ } \ static int mingw_main(c,v) + +#ifndef NO_MINGW_REPLACE_READDIR +/* + * A replacement of readdir, to ensure that it reads the file type at + * the same time. This avoid extra unneeded lstats in git on MinGW + */ +#undef DT_UNKNOWN +#undef DT_DIR +#undef DT_REG +#undef DT_LNK +#define DT_UNKNOWN 0 +#define DT_DIR 1 +#define DT_REG 2 +#define DT_LNK 3 + +struct mingw_dirent +{ + long d_ino; /* Always zero. */ + union { + unsigned short d_reclen; /* Always zero. */ + unsigned char d_type; /* Reimplementation adds this */ + }; + unsigned short d_namlen; /* Length of name in d_name. */ + char d_name[FILENAME_MAX]; /* File name. */ +}; +#define dirent mingw_dirent +#define readdir(x) mingw_readdir(x) +struct dirent *mingw_readdir(DIR *dir); +#endif // !NO_MINGW_REPLACE_READDIR + +/* + * Used by Pthread API implementation for Windows + */ +extern int err_win_to_posix(DWORD winerr); diff --git a/compat/msvc.c b/compat/msvc.c new file mode 100644 index 0000000000..ac04a4ccbd --- /dev/null +++ b/compat/msvc.c @@ -0,0 +1,35 @@ +#include "../git-compat-util.h" +#include "win32.h" +#include <conio.h> +#include "../strbuf.h" + +DIR *opendir(const char *name) +{ + int len; + DIR *p; + p = (DIR*)malloc(sizeof(DIR)); + memset(p, 0, sizeof(DIR)); + strncpy(p->dd_name, name, PATH_MAX); + len = strlen(p->dd_name); + p->dd_name[len] = '/'; + p->dd_name[len+1] = '*'; + + if (p == NULL) + return NULL; + + p->dd_handle = _findfirst(p->dd_name, &p->dd_dta); + + if (p->dd_handle == -1) { + free(p); + return NULL; + } + return p; +} +int closedir(DIR *dir) +{ + _findclose(dir->dd_handle); + free(dir); + return 0; +} + +#include "mingw.c" diff --git a/compat/msvc.h b/compat/msvc.h new file mode 100644 index 0000000000..023aba0238 --- /dev/null +++ b/compat/msvc.h @@ -0,0 +1,42 @@ +#ifndef __MSVC__HEAD +#define __MSVC__HEAD + +#include <direct.h> +#include <process.h> +#include <malloc.h> + +/* porting function */ +#define inline __inline +#define __inline__ __inline +#define __attribute__(x) +#define va_copy(dst, src) ((dst) = (src)) +#define strncasecmp _strnicmp +#define ftruncate _chsize + +static __inline int strcasecmp (const char *s1, const char *s2) +{ + int size1 = strlen(s1); + int sisz2 = strlen(s2); + return _strnicmp(s1, s2, sisz2 > size1 ? sisz2 : size1); +} + +#undef ERROR + +/* Use mingw_lstat() instead of lstat()/stat() and mingw_fstat() instead + * of fstat(). We add the declaration of these functions here, suppressing + * the corresponding declarations in mingw.h, so that we can use the + * appropriate structure type (and function) names from the msvc headers. + */ +#define stat _stat64 +int mingw_lstat(const char *file_name, struct stat *buf); +int mingw_fstat(int fd, struct stat *buf); +#define fstat mingw_fstat +#define lstat mingw_lstat +#define _stat64(x,y) mingw_lstat(x,y) +#define ALREADY_DECLARED_STAT_FUNCS + +#include "compat/mingw.h" + +#undef ALREADY_DECLARED_STAT_FUNCS + +#endif diff --git a/compat/nedmalloc/License.txt b/compat/nedmalloc/License.txt new file mode 100644 index 0000000000..36b7cd93cd --- /dev/null +++ b/compat/nedmalloc/License.txt @@ -0,0 +1,23 @@ +Boost Software License - Version 1.0 - August 17th, 2003 + +Permission is hereby granted, free of charge, to any person or organization +obtaining a copy of the software and accompanying documentation covered by +this license (the "Software") to use, reproduce, display, distribute, +execute, and transmit the Software, and to prepare derivative works of the +Software, and to permit third-parties to whom the Software is furnished to +do so, all subject to the following: + +The copyright notices in the Software and this entire statement, including +the above license grant, this restriction and the following disclaimer, +must be included in all copies of the Software, in whole or in part, and +all derivative works of the Software, unless such copies or derivative +works are solely in the form of machine-executable object code generated by +a source language processor. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT +SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE +FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE, +ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER +DEALINGS IN THE SOFTWARE. diff --git a/compat/nedmalloc/Readme.txt b/compat/nedmalloc/Readme.txt new file mode 100644 index 0000000000..876365646e --- /dev/null +++ b/compat/nedmalloc/Readme.txt @@ -0,0 +1,136 @@ +nedalloc v1.05 15th June 2008: +-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= + +by Niall Douglas (http://www.nedprod.com/programs/portable/nedmalloc/) + +Enclosed is nedalloc, an alternative malloc implementation for multiple +threads without lock contention based on dlmalloc v2.8.4. It is more +or less a newer implementation of ptmalloc2, the standard allocator in +Linux (which is based on dlmalloc v2.7.0) but also contains a per-thread +cache for maximum CPU scalability. + +It is licensed under the Boost Software License which basically means +you can do anything you like with it. This does not apply to the malloc.c.h +file which remains copyright to others. + +It has been tested on win32 (x86), win64 (x64), Linux (x64), FreeBSD (x64) +and Apple MacOS X (x86). It works very well on all of these and is very +significantly faster than the system allocator on all of these platforms. + +By literally dropping in this allocator as a replacement for your system +allocator, you can see real world improvements of up to three times in normal +code! + +To use: +-=-=-=- +Drop in nedmalloc.h, nedmalloc.c and malloc.c.h into your project. +Configure using the instructions in nedmalloc.h. Run and enjoy. + +To test, compile test.c. It will run a comparison between your system +allocator and nedalloc and tell you how much faster nedalloc is. It also +serves as an example of usage. + +Notes: +-=-=-= +If you want the very latest version of this allocator, get it from the +TnFOX SVN repository at svn://svn.berlios.de/viewcvs/tnfox/trunk/src/nedmalloc + +Because of how nedalloc allocates an mspace per thread, it can cause +severe bloating of memory usage under certain allocation patterns. +You can substantially reduce this wastage by setting MAXTHREADSINPOOL +or the threads parameter to nedcreatepool() to a fraction of the number of +threads which would normally be in a pool at once. This will reduce +bloating at the cost of an increase in lock contention. If allocated size +is less than THREADCACHEMAX, locking is avoided 90-99% of the time and +if most of your allocations are below this value, you can safely set +MAXTHREADSINPOOL to one. + +You will suffer memory leakage unless you call neddisablethreadcache() +per pool for every thread which exits. This is because nedalloc cannot +portably know when a thread exits and thus when its thread cache can +be returned for use by other code. Don't forget pool zero, the system pool. + +For C++ type allocation patterns (where the same sizes of memory are +regularly allocated and deallocated as objects are created and destroyed), +the threadcache always benefits performance. If however your allocation +patterns are different, searching the threadcache may significantly slow +down your code - as a rule of thumb, if cache utilisation is below 80% +(see the source for neddisablethreadcache() for how to enable debug +printing in release mode) then you should disable the thread cache for +that thread. You can compile out the threadcache code by setting +THREADCACHEMAX to zero. + +Speed comparisons: +-=-=-=-=-=-=-=-=-= +See Benchmarks.xls for details. + +The enclosed test.c can do two things: it can be a torture test or a speed +test. The speed test is designed to be a representative synthetic +memory allocator test. It works by randomly mixing allocations with frees +with half of the allocation sizes being a two power multiple less than +512 bytes (to mimic C++ stack instantiated objects) and the other half +being a simple random value less than 16Kb. + +The real world code results are from Tn's TestIO benchmark. This is a +heavily multithreaded and memory intensive benchmark with a lot of branching +and other stuff modern processors don't like so much. As you'll note, the +test doesn't show the benefits of the threadcache mostly due to the saturation +of the memory bus being the limiting factor. + +ChangeLog: +-=-=-=-=-= +v1.05 15th June 2008: + * { 1042 } Added error check for TLSSET() and TLSFREE() macros. Thanks to +Markus Elfring for reporting this. + * { 1043 } Fixed a segfault when freeing memory allocated using +nedindependent_comalloc(). Thanks to Pavel Vozenilek for reporting this. + +v1.04 14th July 2007: + * Fixed a bug with the new optimised implementation that failed to lock +on a realloc under certain conditions. + * Fixed lack of thread synchronisation in InitPool() causing pool corruption + * Fixed a memory leak of thread cache contents on disabling. Thanks to Earl +Chew for reporting this. + * Added a sanity check for freed blocks being valid. + * Reworked test.c into being a torture test. + * Fixed GCC assembler optimisation misspecification + +v1.04alpha_svn915 7th October 2006: + * Fixed failure to unlock thread cache list if allocating a new list failed. +Thanks to Dmitry Chichkov for reporting this. Futher thanks to Aleksey Sanin. + * Fixed realloc(0, <size>) segfaulting. Thanks to Dmitry Chichkov for +reporting this. + * Made config defines #ifndef so they can be overriden by the build system. +Thanks to Aleksey Sanin for suggesting this. + * Fixed deadlock in nedprealloc() due to unnecessary locking of preferred +thread mspace when mspace_realloc() always uses the original block's mspace +anyway. Thanks to Aleksey Sanin for reporting this. + * Made some speed improvements by hacking mspace_malloc() to no longer lock +its mspace, thus allowing the recursive mutex implementation to be removed +with an associated speed increase. Thanks to Aleksey Sanin for suggesting this. + * Fixed a bug where allocating mspaces overran its max limit. Thanks to +Aleksey Sanin for reporting this. + +v1.03 10th July 2006: + * Fixed memory corruption bug in threadcache code which only appeared with >4 +threads and in heavy use of the threadcache. + +v1.02 15th May 2006: + * Integrated dlmalloc v2.8.4, fixing the win32 memory release problem and +improving performance still further. Speed is now up to twice the speed of v1.01 +(average is 67% faster). + * Fixed win32 critical section implementation. Thanks to Pavel Kuznetsov +for reporting this. + * Wasn't locking mspace if all mspaces were locked. Thanks to Pavel Kuznetsov +for reporting this. + * Added Apple Mac OS X support. + +v1.01 24th February 2006: + * Fixed multiprocessor scaling problems by removing sources of cache sloshing + * Earl Chew <earl_chew <at> agilent <dot> com> sent patches for the following: + 1. size2binidx() wasn't working for default code path (non x86) + 2. Fixed failure to release mspace lock under certain circumstances which + caused a deadlock + +v1.00 1st January 2006: + * First release diff --git a/compat/nedmalloc/malloc.c.h b/compat/nedmalloc/malloc.c.h new file mode 100644 index 0000000000..74c42e3162 --- /dev/null +++ b/compat/nedmalloc/malloc.c.h @@ -0,0 +1,5752 @@ +/* + This is a version (aka dlmalloc) of malloc/free/realloc written by + Doug Lea and released to the public domain, as explained at + http://creativecommons.org/licenses/publicdomain. Send questions, + comments, complaints, performance data, etc to dl@cs.oswego.edu + +* Version pre-2.8.4 Mon Nov 27 11:22:37 2006 (dl at gee) + + Note: There may be an updated version of this malloc obtainable at + ftp://gee.cs.oswego.edu/pub/misc/malloc.c + Check before installing! + +* Quickstart + + This library is all in one file to simplify the most common usage: + ftp it, compile it (-O3), and link it into another program. All of + the compile-time options default to reasonable values for use on + most platforms. You might later want to step through various + compile-time and dynamic tuning options. + + For convenience, an include file for code using this malloc is at: + ftp://gee.cs.oswego.edu/pub/misc/malloc-2.8.4.h + You don't really need this .h file unless you call functions not + defined in your system include files. The .h file contains only the + excerpts from this file needed for using this malloc on ANSI C/C++ + systems, so long as you haven't changed compile-time options about + naming and tuning parameters. If you do, then you can create your + own malloc.h that does include all settings by cutting at the point + indicated below. Note that you may already by default be using a C + library containing a malloc that is based on some version of this + malloc (for example in linux). You might still want to use the one + in this file to customize settings or to avoid overheads associated + with library versions. + +* Vital statistics: + + Supported pointer/size_t representation: 4 or 8 bytes + size_t MUST be an unsigned type of the same width as + pointers. (If you are using an ancient system that declares + size_t as a signed type, or need it to be a different width + than pointers, you can use a previous release of this malloc + (e.g. 2.7.2) supporting these.) + + Alignment: 8 bytes (default) + This suffices for nearly all current machines and C compilers. + However, you can define MALLOC_ALIGNMENT to be wider than this + if necessary (up to 128bytes), at the expense of using more space. + + Minimum overhead per allocated chunk: 4 or 8 bytes (if 4byte sizes) + 8 or 16 bytes (if 8byte sizes) + Each malloced chunk has a hidden word of overhead holding size + and status information, and additional cross-check word + if FOOTERS is defined. + + Minimum allocated size: 4-byte ptrs: 16 bytes (including overhead) + 8-byte ptrs: 32 bytes (including overhead) + + Even a request for zero bytes (i.e., malloc(0)) returns a + pointer to something of the minimum allocatable size. + The maximum overhead wastage (i.e., number of extra bytes + allocated than were requested in malloc) is less than or equal + to the minimum size, except for requests >= mmap_threshold that + are serviced via mmap(), where the worst case wastage is about + 32 bytes plus the remainder from a system page (the minimal + mmap unit); typically 4096 or 8192 bytes. + + Security: static-safe; optionally more or less + The "security" of malloc refers to the ability of malicious + code to accentuate the effects of errors (for example, freeing + space that is not currently malloc'ed or overwriting past the + ends of chunks) in code that calls malloc. This malloc + guarantees not to modify any memory locations below the base of + heap, i.e., static variables, even in the presence of usage + errors. The routines additionally detect most improper frees + and reallocs. All this holds as long as the static bookkeeping + for malloc itself is not corrupted by some other means. This + is only one aspect of security -- these checks do not, and + cannot, detect all possible programming errors. + + If FOOTERS is defined nonzero, then each allocated chunk + carries an additional check word to verify that it was malloced + from its space. These check words are the same within each + execution of a program using malloc, but differ across + executions, so externally crafted fake chunks cannot be + freed. This improves security by rejecting frees/reallocs that + could corrupt heap memory, in addition to the checks preventing + writes to statics that are always on. This may further improve + security at the expense of time and space overhead. (Note that + FOOTERS may also be worth using with MSPACES.) + + By default detected errors cause the program to abort (calling + "abort()"). You can override this to instead proceed past + errors by defining PROCEED_ON_ERROR. In this case, a bad free + has no effect, and a malloc that encounters a bad address + caused by user overwrites will ignore the bad address by + dropping pointers and indices to all known memory. This may + be appropriate for programs that should continue if at all + possible in the face of programming errors, although they may + run out of memory because dropped memory is never reclaimed. + + If you don't like either of these options, you can define + CORRUPTION_ERROR_ACTION and USAGE_ERROR_ACTION to do anything + else. And if if you are sure that your program using malloc has + no errors or vulnerabilities, you can define INSECURE to 1, + which might (or might not) provide a small performance improvement. + + Thread-safety: NOT thread-safe unless USE_LOCKS defined + When USE_LOCKS is defined, each public call to malloc, free, + etc is surrounded with either a pthread mutex or a win32 + spinlock (depending on WIN32). This is not especially fast, and + can be a major bottleneck. It is designed only to provide + minimal protection in concurrent environments, and to provide a + basis for extensions. If you are using malloc in a concurrent + program, consider instead using nedmalloc + (http://www.nedprod.com/programs/portable/nedmalloc/) or + ptmalloc (See http://www.malloc.de), which are derived + from versions of this malloc. + + System requirements: Any combination of MORECORE and/or MMAP/MUNMAP + This malloc can use unix sbrk or any emulation (invoked using + the CALL_MORECORE macro) and/or mmap/munmap or any emulation + (invoked using CALL_MMAP/CALL_MUNMAP) to get and release system + memory. On most unix systems, it tends to work best if both + MORECORE and MMAP are enabled. On Win32, it uses emulations + based on VirtualAlloc. It also uses common C library functions + like memset. + + Compliance: I believe it is compliant with the Single Unix Specification + (See http://www.unix.org). Also SVID/XPG, ANSI C, and probably + others as well. + +* Overview of algorithms + + This is not the fastest, most space-conserving, most portable, or + most tunable malloc ever written. However it is among the fastest + while also being among the most space-conserving, portable and + tunable. Consistent balance across these factors results in a good + general-purpose allocator for malloc-intensive programs. + + In most ways, this malloc is a best-fit allocator. Generally, it + chooses the best-fitting existing chunk for a request, with ties + broken in approximately least-recently-used order. (This strategy + normally maintains low fragmentation.) However, for requests less + than 256bytes, it deviates from best-fit when there is not an + exactly fitting available chunk by preferring to use space adjacent + to that used for the previous small request, as well as by breaking + ties in approximately most-recently-used order. (These enhance + locality of series of small allocations.) And for very large requests + (>= 256Kb by default), it relies on system memory mapping + facilities, if supported. (This helps avoid carrying around and + possibly fragmenting memory used only for large chunks.) + + All operations (except malloc_stats and mallinfo) have execution + times that are bounded by a constant factor of the number of bits in + a size_t, not counting any clearing in calloc or copying in realloc, + or actions surrounding MORECORE and MMAP that have times + proportional to the number of non-contiguous regions returned by + system allocation routines, which is often just 1. In real-time + applications, you can optionally suppress segment traversals using + NO_SEGMENT_TRAVERSAL, which assures bounded execution even when + system allocators return non-contiguous spaces, at the typical + expense of carrying around more memory and increased fragmentation. + + The implementation is not very modular and seriously overuses + macros. Perhaps someday all C compilers will do as good a job + inlining modular code as can now be done by brute-force expansion, + but now, enough of them seem not to. + + Some compilers issue a lot of warnings about code that is + dead/unreachable only on some platforms, and also about intentional + uses of negation on unsigned types. All known cases of each can be + ignored. + + For a longer but out of date high-level description, see + http://gee.cs.oswego.edu/dl/html/malloc.html + +* MSPACES + If MSPACES is defined, then in addition to malloc, free, etc., + this file also defines mspace_malloc, mspace_free, etc. These + are versions of malloc routines that take an "mspace" argument + obtained using create_mspace, to control all internal bookkeeping. + If ONLY_MSPACES is defined, only these versions are compiled. + So if you would like to use this allocator for only some allocations, + and your system malloc for others, you can compile with + ONLY_MSPACES and then do something like... + static mspace mymspace = create_mspace(0,0); // for example + #define mymalloc(bytes) mspace_malloc(mymspace, bytes) + + (Note: If you only need one instance of an mspace, you can instead + use "USE_DL_PREFIX" to relabel the global malloc.) + + You can similarly create thread-local allocators by storing + mspaces as thread-locals. For example: + static __thread mspace tlms = 0; + void* tlmalloc(size_t bytes) { + if (tlms == 0) tlms = create_mspace(0, 0); + return mspace_malloc(tlms, bytes); + } + void tlfree(void* mem) { mspace_free(tlms, mem); } + + Unless FOOTERS is defined, each mspace is completely independent. + You cannot allocate from one and free to another (although + conformance is only weakly checked, so usage errors are not always + caught). If FOOTERS is defined, then each chunk carries around a tag + indicating its originating mspace, and frees are directed to their + originating spaces. + + ------------------------- Compile-time options --------------------------- + +Be careful in setting #define values for numerical constants of type +size_t. On some systems, literal values are not automatically extended +to size_t precision unless they are explicitly casted. You can also +use the symbolic values MAX_SIZE_T, SIZE_T_ONE, etc below. + +WIN32 default: defined if _WIN32 defined + Defining WIN32 sets up defaults for MS environment and compilers. + Otherwise defaults are for unix. Beware that there seem to be some + cases where this malloc might not be a pure drop-in replacement for + Win32 malloc: Random-looking failures from Win32 GDI API's (eg; + SetDIBits()) may be due to bugs in some video driver implementations + when pixel buffers are malloc()ed, and the region spans more than + one VirtualAlloc()ed region. Because dlmalloc uses a small (64Kb) + default granularity, pixel buffers may straddle virtual allocation + regions more often than when using the Microsoft allocator. You can + avoid this by using VirtualAlloc() and VirtualFree() for all pixel + buffers rather than using malloc(). If this is not possible, + recompile this malloc with a larger DEFAULT_GRANULARITY. + +MALLOC_ALIGNMENT default: (size_t)8 + Controls the minimum alignment for malloc'ed chunks. It must be a + power of two and at least 8, even on machines for which smaller + alignments would suffice. It may be defined as larger than this + though. Note however that code and data structures are optimized for + the case of 8-byte alignment. + +MSPACES default: 0 (false) + If true, compile in support for independent allocation spaces. + This is only supported if HAVE_MMAP is true. + +ONLY_MSPACES default: 0 (false) + If true, only compile in mspace versions, not regular versions. + +USE_LOCKS default: 0 (false) + Causes each call to each public routine to be surrounded with + pthread or WIN32 mutex lock/unlock. (If set true, this can be + overridden on a per-mspace basis for mspace versions.) If set to a + non-zero value other than 1, locks are used, but their + implementation is left out, so lock functions must be supplied manually. + +USE_SPIN_LOCKS default: 1 iff USE_LOCKS and on x86 using gcc or MSC + If true, uses custom spin locks for locking. This is currently + supported only for x86 platforms using gcc or recent MS compilers. + Otherwise, posix locks or win32 critical sections are used. + +FOOTERS default: 0 + If true, provide extra checking and dispatching by placing + information in the footers of allocated chunks. This adds + space and time overhead. + +INSECURE default: 0 + If true, omit checks for usage errors and heap space overwrites. + +USE_DL_PREFIX default: NOT defined + Causes compiler to prefix all public routines with the string 'dl'. + This can be useful when you only want to use this malloc in one part + of a program, using your regular system malloc elsewhere. + +ABORT default: defined as abort() + Defines how to abort on failed checks. On most systems, a failed + check cannot die with an "assert" or even print an informative + message, because the underlying print routines in turn call malloc, + which will fail again. Generally, the best policy is to simply call + abort(). It's not very useful to do more than this because many + errors due to overwriting will show up as address faults (null, odd + addresses etc) rather than malloc-triggered checks, so will also + abort. Also, most compilers know that abort() does not return, so + can better optimize code conditionally calling it. + +PROCEED_ON_ERROR default: defined as 0 (false) + Controls whether detected bad addresses cause them to bypassed + rather than aborting. If set, detected bad arguments to free and + realloc are ignored. And all bookkeeping information is zeroed out + upon a detected overwrite of freed heap space, thus losing the + ability to ever return it from malloc again, but enabling the + application to proceed. If PROCEED_ON_ERROR is defined, the + static variable malloc_corruption_error_count is compiled in + and can be examined to see if errors have occurred. This option + generates slower code than the default abort policy. + +DEBUG default: NOT defined + The DEBUG setting is mainly intended for people trying to modify + this code or diagnose problems when porting to new platforms. + However, it may also be able to better isolate user errors than just + using runtime checks. The assertions in the check routines spell + out in more detail the assumptions and invariants underlying the + algorithms. The checking is fairly extensive, and will slow down + execution noticeably. Calling malloc_stats or mallinfo with DEBUG + set will attempt to check every non-mmapped allocated and free chunk + in the course of computing the summaries. + +ABORT_ON_ASSERT_FAILURE default: defined as 1 (true) + Debugging assertion failures can be nearly impossible if your + version of the assert macro causes malloc to be called, which will + lead to a cascade of further failures, blowing the runtime stack. + ABORT_ON_ASSERT_FAILURE cause assertions failures to call abort(), + which will usually make debugging easier. + +MALLOC_FAILURE_ACTION default: sets errno to ENOMEM, or no-op on win32 + The action to take before "return 0" when malloc fails to be able to + return memory because there is none available. + +HAVE_MORECORE default: 1 (true) unless win32 or ONLY_MSPACES + True if this system supports sbrk or an emulation of it. + +MORECORE default: sbrk + The name of the sbrk-style system routine to call to obtain more + memory. See below for guidance on writing custom MORECORE + functions. The type of the argument to sbrk/MORECORE varies across + systems. It cannot be size_t, because it supports negative + arguments, so it is normally the signed type of the same width as + size_t (sometimes declared as "intptr_t"). It doesn't much matter + though. Internally, we only call it with arguments less than half + the max value of a size_t, which should work across all reasonable + possibilities, although sometimes generating compiler warnings. + +MORECORE_CONTIGUOUS default: 1 (true) if HAVE_MORECORE + If true, take advantage of fact that consecutive calls to MORECORE + with positive arguments always return contiguous increasing + addresses. This is true of unix sbrk. It does not hurt too much to + set it true anyway, since malloc copes with non-contiguities. + Setting it false when definitely non-contiguous saves time + and possibly wasted space it would take to discover this though. + +MORECORE_CANNOT_TRIM default: NOT defined + True if MORECORE cannot release space back to the system when given + negative arguments. This is generally necessary only if you are + using a hand-crafted MORECORE function that cannot handle negative + arguments. + +NO_SEGMENT_TRAVERSAL default: 0 + If non-zero, suppresses traversals of memory segments + returned by either MORECORE or CALL_MMAP. This disables + merging of segments that are contiguous, and selectively + releasing them to the OS if unused, but bounds execution times. + +HAVE_MMAP default: 1 (true) + True if this system supports mmap or an emulation of it. If so, and + HAVE_MORECORE is not true, MMAP is used for all system + allocation. If set and HAVE_MORECORE is true as well, MMAP is + primarily used to directly allocate very large blocks. It is also + used as a backup strategy in cases where MORECORE fails to provide + space from system. Note: A single call to MUNMAP is assumed to be + able to unmap memory that may have be allocated using multiple calls + to MMAP, so long as they are adjacent. + +HAVE_MREMAP default: 1 on linux, else 0 + If true realloc() uses mremap() to re-allocate large blocks and + extend or shrink allocation spaces. + +MMAP_CLEARS default: 1 except on WINCE. + True if mmap clears memory so calloc doesn't need to. This is true + for standard unix mmap using /dev/zero and on WIN32 except for WINCE. + +USE_BUILTIN_FFS default: 0 (i.e., not used) + Causes malloc to use the builtin ffs() function to compute indices. + Some compilers may recognize and intrinsify ffs to be faster than the + supplied C version. Also, the case of x86 using gcc is special-cased + to an asm instruction, so is already as fast as it can be, and so + this setting has no effect. Similarly for Win32 under recent MS compilers. + (On most x86s, the asm version is only slightly faster than the C version.) + +malloc_getpagesize default: derive from system includes, or 4096. + The system page size. To the extent possible, this malloc manages + memory from the system in page-size units. This may be (and + usually is) a function rather than a constant. This is ignored + if WIN32, where page size is determined using getSystemInfo during + initialization. + +USE_DEV_RANDOM default: 0 (i.e., not used) + Causes malloc to use /dev/random to initialize secure magic seed for + stamping footers. Otherwise, the current time is used. + +NO_MALLINFO default: 0 + If defined, don't compile "mallinfo". This can be a simple way + of dealing with mismatches between system declarations and + those in this file. + +MALLINFO_FIELD_TYPE default: size_t + The type of the fields in the mallinfo struct. This was originally + defined as "int" in SVID etc, but is more usefully defined as + size_t. The value is used only if HAVE_USR_INCLUDE_MALLOC_H is not set + +REALLOC_ZERO_BYTES_FREES default: not defined + This should be set if a call to realloc with zero bytes should + be the same as a call to free. Some people think it should. Otherwise, + since this malloc returns a unique pointer for malloc(0), so does + realloc(p, 0). + +LACKS_UNISTD_H, LACKS_FCNTL_H, LACKS_SYS_PARAM_H, LACKS_SYS_MMAN_H +LACKS_STRINGS_H, LACKS_STRING_H, LACKS_SYS_TYPES_H, LACKS_ERRNO_H +LACKS_STDLIB_H default: NOT defined unless on WIN32 + Define these if your system does not have these header files. + You might need to manually insert some of the declarations they provide. + +DEFAULT_GRANULARITY default: page size if MORECORE_CONTIGUOUS, + system_info.dwAllocationGranularity in WIN32, + otherwise 64K. + Also settable using mallopt(M_GRANULARITY, x) + The unit for allocating and deallocating memory from the system. On + most systems with contiguous MORECORE, there is no reason to + make this more than a page. However, systems with MMAP tend to + either require or encourage larger granularities. You can increase + this value to prevent system allocation functions to be called so + often, especially if they are slow. The value must be at least one + page and must be a power of two. Setting to 0 causes initialization + to either page size or win32 region size. (Note: In previous + versions of malloc, the equivalent of this option was called + "TOP_PAD") + +DEFAULT_TRIM_THRESHOLD default: 2MB + Also settable using mallopt(M_TRIM_THRESHOLD, x) + The maximum amount of unused top-most memory to keep before + releasing via malloc_trim in free(). Automatic trimming is mainly + useful in long-lived programs using contiguous MORECORE. Because + trimming via sbrk can be slow on some systems, and can sometimes be + wasteful (in cases where programs immediately afterward allocate + more large chunks) the value should be high enough so that your + overall system performance would improve by releasing this much + memory. As a rough guide, you might set to a value close to the + average size of a process (program) running on your system. + Releasing this much memory would allow such a process to run in + memory. Generally, it is worth tuning trim thresholds when a + program undergoes phases where several large chunks are allocated + and released in ways that can reuse each other's storage, perhaps + mixed with phases where there are no such chunks at all. The trim + value must be greater than page size to have any useful effect. To + disable trimming completely, you can set to MAX_SIZE_T. Note that the trick + some people use of mallocing a huge space and then freeing it at + program startup, in an attempt to reserve system memory, doesn't + have the intended effect under automatic trimming, since that memory + will immediately be returned to the system. + +DEFAULT_MMAP_THRESHOLD default: 256K + Also settable using mallopt(M_MMAP_THRESHOLD, x) + The request size threshold for using MMAP to directly service a + request. Requests of at least this size that cannot be allocated + using already-existing space will be serviced via mmap. (If enough + normal freed space already exists it is used instead.) Using mmap + segregates relatively large chunks of memory so that they can be + individually obtained and released from the host system. A request + serviced through mmap is never reused by any other request (at least + not directly; the system may just so happen to remap successive + requests to the same locations). Segregating space in this way has + the benefits that: Mmapped space can always be individually released + back to the system, which helps keep the system level memory demands + of a long-lived program low. Also, mapped memory doesn't become + `locked' between other chunks, as can happen with normally allocated + chunks, which means that even trimming via malloc_trim would not + release them. However, it has the disadvantage that the space + cannot be reclaimed, consolidated, and then used to service later + requests, as happens with normal chunks. The advantages of mmap + nearly always outweigh disadvantages for "large" chunks, but the + value of "large" may vary across systems. The default is an + empirically derived value that works well in most systems. You can + disable mmap by setting to MAX_SIZE_T. + +MAX_RELEASE_CHECK_RATE default: 4095 unless not HAVE_MMAP + The number of consolidated frees between checks to release + unused segments when freeing. When using non-contiguous segments, + especially with multiple mspaces, checking only for topmost space + doesn't always suffice to trigger trimming. To compensate for this, + free() will, with a period of MAX_RELEASE_CHECK_RATE (or the + current number of segments, if greater) try to release unused + segments to the OS when freeing chunks that result in + consolidation. The best value for this parameter is a compromise + between slowing down frees with relatively costly checks that + rarely trigger versus holding on to unused memory. To effectively + disable, set to MAX_SIZE_T. This may lead to a very slight speed + improvement at the expense of carrying around more memory. +*/ + +/* Version identifier to allow people to support multiple versions */ +#ifndef DLMALLOC_VERSION +#define DLMALLOC_VERSION 20804 +#endif /* DLMALLOC_VERSION */ + +#ifndef WIN32 +#ifdef _WIN32 +#define WIN32 1 +#endif /* _WIN32 */ +#ifdef _WIN32_WCE +#define LACKS_FCNTL_H +#define WIN32 1 +#endif /* _WIN32_WCE */ +#endif /* WIN32 */ +#ifdef WIN32 +#define WIN32_LEAN_AND_MEAN +#define _WIN32_WINNT 0x403 +#include <windows.h> +#define HAVE_MMAP 1 +#define HAVE_MORECORE 0 +#define LACKS_UNISTD_H +#define LACKS_SYS_PARAM_H +#define LACKS_SYS_MMAN_H +#define LACKS_STRING_H +#define LACKS_STRINGS_H +#define LACKS_SYS_TYPES_H +#define LACKS_ERRNO_H +#ifndef MALLOC_FAILURE_ACTION +#define MALLOC_FAILURE_ACTION +#endif /* MALLOC_FAILURE_ACTION */ +#ifdef _WIN32_WCE /* WINCE reportedly does not clear */ +#define MMAP_CLEARS 0 +#else +#define MMAP_CLEARS 1 +#endif /* _WIN32_WCE */ +#endif /* WIN32 */ + +#if defined(DARWIN) || defined(_DARWIN) +/* Mac OSX docs advise not to use sbrk; it seems better to use mmap */ +#ifndef HAVE_MORECORE +#define HAVE_MORECORE 0 +#define HAVE_MMAP 1 +/* OSX allocators provide 16 byte alignment */ +#ifndef MALLOC_ALIGNMENT +#define MALLOC_ALIGNMENT ((size_t)16U) +#endif +#endif /* HAVE_MORECORE */ +#endif /* DARWIN */ + +#ifndef LACKS_SYS_TYPES_H +#include <sys/types.h> /* For size_t */ +#endif /* LACKS_SYS_TYPES_H */ + +/* The maximum possible size_t value has all bits set */ +#define MAX_SIZE_T (~(size_t)0) + +#ifndef ONLY_MSPACES +#define ONLY_MSPACES 0 /* define to a value */ +#else +#define ONLY_MSPACES 1 +#endif /* ONLY_MSPACES */ +#ifndef MSPACES +#if ONLY_MSPACES +#define MSPACES 1 +#else /* ONLY_MSPACES */ +#define MSPACES 0 +#endif /* ONLY_MSPACES */ +#endif /* MSPACES */ +#ifndef MALLOC_ALIGNMENT +#define MALLOC_ALIGNMENT ((size_t)8U) +#endif /* MALLOC_ALIGNMENT */ +#ifndef FOOTERS +#define FOOTERS 0 +#endif /* FOOTERS */ +#ifndef ABORT +#define ABORT abort() +#endif /* ABORT */ +#ifndef ABORT_ON_ASSERT_FAILURE +#define ABORT_ON_ASSERT_FAILURE 1 +#endif /* ABORT_ON_ASSERT_FAILURE */ +#ifndef PROCEED_ON_ERROR +#define PROCEED_ON_ERROR 0 +#endif /* PROCEED_ON_ERROR */ +#ifndef USE_LOCKS +#define USE_LOCKS 0 +#endif /* USE_LOCKS */ +#ifndef USE_SPIN_LOCKS +#if USE_LOCKS && (defined(__GNUC__) && ((defined(__i386__) || defined(__x86_64__)))) || (defined(_MSC_VER) && _MSC_VER>=1310) +#define USE_SPIN_LOCKS 1 +#else +#define USE_SPIN_LOCKS 0 +#endif /* USE_LOCKS && ... */ +#endif /* USE_SPIN_LOCKS */ +#ifndef INSECURE +#define INSECURE 0 +#endif /* INSECURE */ +#ifndef HAVE_MMAP +#define HAVE_MMAP 1 +#endif /* HAVE_MMAP */ +#ifndef MMAP_CLEARS +#define MMAP_CLEARS 1 +#endif /* MMAP_CLEARS */ +#ifndef HAVE_MREMAP +#ifdef linux +#define HAVE_MREMAP 1 +#else /* linux */ +#define HAVE_MREMAP 0 +#endif /* linux */ +#endif /* HAVE_MREMAP */ +#ifndef MALLOC_FAILURE_ACTION +#define MALLOC_FAILURE_ACTION errno = ENOMEM; +#endif /* MALLOC_FAILURE_ACTION */ +#ifndef HAVE_MORECORE +#if ONLY_MSPACES +#define HAVE_MORECORE 0 +#else /* ONLY_MSPACES */ +#define HAVE_MORECORE 1 +#endif /* ONLY_MSPACES */ +#endif /* HAVE_MORECORE */ +#if !HAVE_MORECORE +#define MORECORE_CONTIGUOUS 0 +#else /* !HAVE_MORECORE */ +#define MORECORE_DEFAULT sbrk +#ifndef MORECORE_CONTIGUOUS +#define MORECORE_CONTIGUOUS 1 +#endif /* MORECORE_CONTIGUOUS */ +#endif /* HAVE_MORECORE */ +#ifndef DEFAULT_GRANULARITY +#if (MORECORE_CONTIGUOUS || defined(WIN32)) +#define DEFAULT_GRANULARITY (0) /* 0 means to compute in init_mparams */ +#else /* MORECORE_CONTIGUOUS */ +#define DEFAULT_GRANULARITY ((size_t)64U * (size_t)1024U) +#endif /* MORECORE_CONTIGUOUS */ +#endif /* DEFAULT_GRANULARITY */ +#ifndef DEFAULT_TRIM_THRESHOLD +#ifndef MORECORE_CANNOT_TRIM +#define DEFAULT_TRIM_THRESHOLD ((size_t)2U * (size_t)1024U * (size_t)1024U) +#else /* MORECORE_CANNOT_TRIM */ +#define DEFAULT_TRIM_THRESHOLD MAX_SIZE_T +#endif /* MORECORE_CANNOT_TRIM */ +#endif /* DEFAULT_TRIM_THRESHOLD */ +#ifndef DEFAULT_MMAP_THRESHOLD +#if HAVE_MMAP +#define DEFAULT_MMAP_THRESHOLD ((size_t)256U * (size_t)1024U) +#else /* HAVE_MMAP */ +#define DEFAULT_MMAP_THRESHOLD MAX_SIZE_T +#endif /* HAVE_MMAP */ +#endif /* DEFAULT_MMAP_THRESHOLD */ +#ifndef MAX_RELEASE_CHECK_RATE +#if HAVE_MMAP +#define MAX_RELEASE_CHECK_RATE 4095 +#else +#define MAX_RELEASE_CHECK_RATE MAX_SIZE_T +#endif /* HAVE_MMAP */ +#endif /* MAX_RELEASE_CHECK_RATE */ +#ifndef USE_BUILTIN_FFS +#define USE_BUILTIN_FFS 0 +#endif /* USE_BUILTIN_FFS */ +#ifndef USE_DEV_RANDOM +#define USE_DEV_RANDOM 0 +#endif /* USE_DEV_RANDOM */ +#ifndef NO_MALLINFO +#define NO_MALLINFO 0 +#endif /* NO_MALLINFO */ +#ifndef MALLINFO_FIELD_TYPE +#define MALLINFO_FIELD_TYPE size_t +#endif /* MALLINFO_FIELD_TYPE */ +#ifndef NO_SEGMENT_TRAVERSAL +#define NO_SEGMENT_TRAVERSAL 0 +#endif /* NO_SEGMENT_TRAVERSAL */ + +/* + mallopt tuning options. SVID/XPG defines four standard parameter + numbers for mallopt, normally defined in malloc.h. None of these + are used in this malloc, so setting them has no effect. But this + malloc does support the following options. +*/ + +#define M_TRIM_THRESHOLD (-1) +#define M_GRANULARITY (-2) +#define M_MMAP_THRESHOLD (-3) + +/* ------------------------ Mallinfo declarations ------------------------ */ + +#if !NO_MALLINFO +/* + This version of malloc supports the standard SVID/XPG mallinfo + routine that returns a struct containing usage properties and + statistics. It should work on any system that has a + /usr/include/malloc.h defining struct mallinfo. The main + declaration needed is the mallinfo struct that is returned (by-copy) + by mallinfo(). The malloinfo struct contains a bunch of fields that + are not even meaningful in this version of malloc. These fields are + are instead filled by mallinfo() with other numbers that might be of + interest. + + HAVE_USR_INCLUDE_MALLOC_H should be set if you have a + /usr/include/malloc.h file that includes a declaration of struct + mallinfo. If so, it is included; else a compliant version is + declared below. These must be precisely the same for mallinfo() to + work. The original SVID version of this struct, defined on most + systems with mallinfo, declares all fields as ints. But some others + define as unsigned long. If your system defines the fields using a + type of different width than listed here, you MUST #include your + system version and #define HAVE_USR_INCLUDE_MALLOC_H. +*/ + +/* #define HAVE_USR_INCLUDE_MALLOC_H */ + +#ifdef HAVE_USR_INCLUDE_MALLOC_H +#include "/usr/include/malloc.h" +#else /* HAVE_USR_INCLUDE_MALLOC_H */ +#ifndef STRUCT_MALLINFO_DECLARED +#define STRUCT_MALLINFO_DECLARED 1 +struct mallinfo { + MALLINFO_FIELD_TYPE arena; /* non-mmapped space allocated from system */ + MALLINFO_FIELD_TYPE ordblks; /* number of free chunks */ + MALLINFO_FIELD_TYPE smblks; /* always 0 */ + MALLINFO_FIELD_TYPE hblks; /* always 0 */ + MALLINFO_FIELD_TYPE hblkhd; /* space in mmapped regions */ + MALLINFO_FIELD_TYPE usmblks; /* maximum total allocated space */ + MALLINFO_FIELD_TYPE fsmblks; /* always 0 */ + MALLINFO_FIELD_TYPE uordblks; /* total allocated space */ + MALLINFO_FIELD_TYPE fordblks; /* total free space */ + MALLINFO_FIELD_TYPE keepcost; /* releasable (via malloc_trim) space */ +}; +#endif /* STRUCT_MALLINFO_DECLARED */ +#endif /* HAVE_USR_INCLUDE_MALLOC_H */ +#endif /* NO_MALLINFO */ + +/* + Try to persuade compilers to inline. The most critical functions for + inlining are defined as macros, so these aren't used for them. +*/ + +#ifndef FORCEINLINE + #if defined(__GNUC__) +#define FORCEINLINE __inline __attribute__ ((always_inline)) + #elif defined(_MSC_VER) + #define FORCEINLINE __forceinline + #endif +#endif +#ifndef NOINLINE + #if defined(__GNUC__) + #define NOINLINE __attribute__ ((noinline)) + #elif defined(_MSC_VER) + #define NOINLINE __declspec(noinline) + #else + #define NOINLINE + #endif +#endif + +#ifdef __cplusplus +extern "C" { +#ifndef FORCEINLINE + #define FORCEINLINE inline +#endif +#endif /* __cplusplus */ +#ifndef FORCEINLINE + #define FORCEINLINE +#endif + +#if !ONLY_MSPACES + +/* ------------------- Declarations of public routines ------------------- */ + +#ifndef USE_DL_PREFIX +#define dlcalloc calloc +#define dlfree free +#define dlmalloc malloc +#define dlmemalign memalign +#define dlrealloc realloc +#define dlvalloc valloc +#define dlpvalloc pvalloc +#define dlmallinfo mallinfo +#define dlmallopt mallopt +#define dlmalloc_trim malloc_trim +#define dlmalloc_stats malloc_stats +#define dlmalloc_usable_size malloc_usable_size +#define dlmalloc_footprint malloc_footprint +#define dlmalloc_max_footprint malloc_max_footprint +#define dlindependent_calloc independent_calloc +#define dlindependent_comalloc independent_comalloc +#endif /* USE_DL_PREFIX */ + + +/* + malloc(size_t n) + Returns a pointer to a newly allocated chunk of at least n bytes, or + null if no space is available, in which case errno is set to ENOMEM + on ANSI C systems. + + If n is zero, malloc returns a minimum-sized chunk. (The minimum + size is 16 bytes on most 32bit systems, and 32 bytes on 64bit + systems.) Note that size_t is an unsigned type, so calls with + arguments that would be negative if signed are interpreted as + requests for huge amounts of space, which will often fail. The + maximum supported value of n differs across systems, but is in all + cases less than the maximum representable value of a size_t. +*/ +void* dlmalloc(size_t); + +/* + free(void* p) + Releases the chunk of memory pointed to by p, that had been previously + allocated using malloc or a related routine such as realloc. + It has no effect if p is null. If p was not malloced or already + freed, free(p) will by default cause the current program to abort. +*/ +void dlfree(void*); + +/* + calloc(size_t n_elements, size_t element_size); + Returns a pointer to n_elements * element_size bytes, with all locations + set to zero. +*/ +void* dlcalloc(size_t, size_t); + +/* + realloc(void* p, size_t n) + Returns a pointer to a chunk of size n that contains the same data + as does chunk p up to the minimum of (n, p's size) bytes, or null + if no space is available. + + The returned pointer may or may not be the same as p. The algorithm + prefers extending p in most cases when possible, otherwise it + employs the equivalent of a malloc-copy-free sequence. + + If p is null, realloc is equivalent to malloc. + + If space is not available, realloc returns null, errno is set (if on + ANSI) and p is NOT freed. + + if n is for fewer bytes than already held by p, the newly unused + space is lopped off and freed if possible. realloc with a size + argument of zero (re)allocates a minimum-sized chunk. + + The old unix realloc convention of allowing the last-free'd chunk + to be used as an argument to realloc is not supported. +*/ + +void* dlrealloc(void*, size_t); + +/* + memalign(size_t alignment, size_t n); + Returns a pointer to a newly allocated chunk of n bytes, aligned + in accord with the alignment argument. + + The alignment argument should be a power of two. If the argument is + not a power of two, the nearest greater power is used. + 8-byte alignment is guaranteed by normal malloc calls, so don't + bother calling memalign with an argument of 8 or less. + + Overreliance on memalign is a sure way to fragment space. +*/ +void* dlmemalign(size_t, size_t); + +/* + valloc(size_t n); + Equivalent to memalign(pagesize, n), where pagesize is the page + size of the system. If the pagesize is unknown, 4096 is used. +*/ +void* dlvalloc(size_t); + +/* + mallopt(int parameter_number, int parameter_value) + Sets tunable parameters The format is to provide a + (parameter-number, parameter-value) pair. mallopt then sets the + corresponding parameter to the argument value if it can (i.e., so + long as the value is meaningful), and returns 1 if successful else + 0. To workaround the fact that mallopt is specified to use int, + not size_t parameters, the value -1 is specially treated as the + maximum unsigned size_t value. + + SVID/XPG/ANSI defines four standard param numbers for mallopt, + normally defined in malloc.h. None of these are use in this malloc, + so setting them has no effect. But this malloc also supports other + options in mallopt. See below for details. Briefly, supported + parameters are as follows (listed defaults are for "typical" + configurations). + + Symbol param # default allowed param values + M_TRIM_THRESHOLD -1 2*1024*1024 any (-1 disables) + M_GRANULARITY -2 page size any power of 2 >= page size + M_MMAP_THRESHOLD -3 256*1024 any (or 0 if no MMAP support) +*/ +int dlmallopt(int, int); + +/* + malloc_footprint(); + Returns the number of bytes obtained from the system. The total + number of bytes allocated by malloc, realloc etc., is less than this + value. Unlike mallinfo, this function returns only a precomputed + result, so can be called frequently to monitor memory consumption. + Even if locks are otherwise defined, this function does not use them, + so results might not be up to date. +*/ +size_t dlmalloc_footprint(void); + +/* + malloc_max_footprint(); + Returns the maximum number of bytes obtained from the system. This + value will be greater than current footprint if deallocated space + has been reclaimed by the system. The peak number of bytes allocated + by malloc, realloc etc., is less than this value. Unlike mallinfo, + this function returns only a precomputed result, so can be called + frequently to monitor memory consumption. Even if locks are + otherwise defined, this function does not use them, so results might + not be up to date. +*/ +size_t dlmalloc_max_footprint(void); + +#if !NO_MALLINFO +/* + mallinfo() + Returns (by copy) a struct containing various summary statistics: + + arena: current total non-mmapped bytes allocated from system + ordblks: the number of free chunks + smblks: always zero. + hblks: current number of mmapped regions + hblkhd: total bytes held in mmapped regions + usmblks: the maximum total allocated space. This will be greater + than current total if trimming has occurred. + fsmblks: always zero + uordblks: current total allocated space (normal or mmapped) + fordblks: total free space + keepcost: the maximum number of bytes that could ideally be released + back to system via malloc_trim. ("ideally" means that + it ignores page restrictions etc.) + + Because these fields are ints, but internal bookkeeping may + be kept as longs, the reported values may wrap around zero and + thus be inaccurate. +*/ +struct mallinfo dlmallinfo(void); +#endif /* NO_MALLINFO */ + +/* + independent_calloc(size_t n_elements, size_t element_size, void* chunks[]); + + independent_calloc is similar to calloc, but instead of returning a + single cleared space, it returns an array of pointers to n_elements + independent elements that can hold contents of size elem_size, each + of which starts out cleared, and can be independently freed, + realloc'ed etc. The elements are guaranteed to be adjacently + allocated (this is not guaranteed to occur with multiple callocs or + mallocs), which may also improve cache locality in some + applications. + + The "chunks" argument is optional (i.e., may be null, which is + probably the most typical usage). If it is null, the returned array + is itself dynamically allocated and should also be freed when it is + no longer needed. Otherwise, the chunks array must be of at least + n_elements in length. It is filled in with the pointers to the + chunks. + + In either case, independent_calloc returns this pointer array, or + null if the allocation failed. If n_elements is zero and "chunks" + is null, it returns a chunk representing an array with zero elements + (which should be freed if not wanted). + + Each element must be individually freed when it is no longer + needed. If you'd like to instead be able to free all at once, you + should instead use regular calloc and assign pointers into this + space to represent elements. (In this case though, you cannot + independently free elements.) + + independent_calloc simplifies and speeds up implementations of many + kinds of pools. It may also be useful when constructing large data + structures that initially have a fixed number of fixed-sized nodes, + but the number is not known at compile time, and some of the nodes + may later need to be freed. For example: + + struct Node { int item; struct Node* next; }; + + struct Node* build_list() { + struct Node** pool; + int n = read_number_of_nodes_needed(); + if (n <= 0) return 0; + pool = (struct Node**)(independent_calloc(n, sizeof(struct Node), 0); + if (pool == 0) die(); + // organize into a linked list... + struct Node* first = pool[0]; + for (i = 0; i < n-1; ++i) + pool[i]->next = pool[i+1]; + free(pool); // Can now free the array (or not, if it is needed later) + return first; + } +*/ +void** dlindependent_calloc(size_t, size_t, void**); + +/* + independent_comalloc(size_t n_elements, size_t sizes[], void* chunks[]); + + independent_comalloc allocates, all at once, a set of n_elements + chunks with sizes indicated in the "sizes" array. It returns + an array of pointers to these elements, each of which can be + independently freed, realloc'ed etc. The elements are guaranteed to + be adjacently allocated (this is not guaranteed to occur with + multiple callocs or mallocs), which may also improve cache locality + in some applications. + + The "chunks" argument is optional (i.e., may be null). If it is null + the returned array is itself dynamically allocated and should also + be freed when it is no longer needed. Otherwise, the chunks array + must be of at least n_elements in length. It is filled in with the + pointers to the chunks. + + In either case, independent_comalloc returns this pointer array, or + null if the allocation failed. If n_elements is zero and chunks is + null, it returns a chunk representing an array with zero elements + (which should be freed if not wanted). + + Each element must be individually freed when it is no longer + needed. If you'd like to instead be able to free all at once, you + should instead use a single regular malloc, and assign pointers at + particular offsets in the aggregate space. (In this case though, you + cannot independently free elements.) + + independent_comallac differs from independent_calloc in that each + element may have a different size, and also that it does not + automatically clear elements. + + independent_comalloc can be used to speed up allocation in cases + where several structs or objects must always be allocated at the + same time. For example: + + struct Head { ... } + struct Foot { ... } + + void send_message(char* msg) { + int msglen = strlen(msg); + size_t sizes[3] = { sizeof(struct Head), msglen, sizeof(struct Foot) }; + void* chunks[3]; + if (independent_comalloc(3, sizes, chunks) == 0) + die(); + struct Head* head = (struct Head*)(chunks[0]); + char* body = (char*)(chunks[1]); + struct Foot* foot = (struct Foot*)(chunks[2]); + // ... + } + + In general though, independent_comalloc is worth using only for + larger values of n_elements. For small values, you probably won't + detect enough difference from series of malloc calls to bother. + + Overuse of independent_comalloc can increase overall memory usage, + since it cannot reuse existing noncontiguous small chunks that + might be available for some of the elements. +*/ +void** dlindependent_comalloc(size_t, size_t*, void**); + + +/* + pvalloc(size_t n); + Equivalent to valloc(minimum-page-that-holds(n)), that is, + round up n to nearest pagesize. + */ +void* dlpvalloc(size_t); + +/* + malloc_trim(size_t pad); + + If possible, gives memory back to the system (via negative arguments + to sbrk) if there is unused memory at the `high' end of the malloc + pool or in unused MMAP segments. You can call this after freeing + large blocks of memory to potentially reduce the system-level memory + requirements of a program. However, it cannot guarantee to reduce + memory. Under some allocation patterns, some large free blocks of + memory will be locked between two used chunks, so they cannot be + given back to the system. + + The `pad' argument to malloc_trim represents the amount of free + trailing space to leave untrimmed. If this argument is zero, only + the minimum amount of memory to maintain internal data structures + will be left. Non-zero arguments can be supplied to maintain enough + trailing space to service future expected allocations without having + to re-obtain memory from the system. + + Malloc_trim returns 1 if it actually released any memory, else 0. +*/ +int dlmalloc_trim(size_t); + +/* + malloc_stats(); + Prints on stderr the amount of space obtained from the system (both + via sbrk and mmap), the maximum amount (which may be more than + current if malloc_trim and/or munmap got called), and the current + number of bytes allocated via malloc (or realloc, etc) but not yet + freed. Note that this is the number of bytes allocated, not the + number requested. It will be larger than the number requested + because of alignment and bookkeeping overhead. Because it includes + alignment wastage as being in use, this figure may be greater than + zero even when no user-level chunks are allocated. + + The reported current and maximum system memory can be inaccurate if + a program makes other calls to system memory allocation functions + (normally sbrk) outside of malloc. + + malloc_stats prints only the most commonly interesting statistics. + More information can be obtained by calling mallinfo. +*/ +void dlmalloc_stats(void); + +#endif /* ONLY_MSPACES */ + +/* + malloc_usable_size(void* p); + + Returns the number of bytes you can actually use in + an allocated chunk, which may be more than you requested (although + often not) due to alignment and minimum size constraints. + You can use this many bytes without worrying about + overwriting other allocated objects. This is not a particularly great + programming practice. malloc_usable_size can be more useful in + debugging and assertions, for example: + + p = malloc(n); + assert(malloc_usable_size(p) >= 256); +*/ +size_t dlmalloc_usable_size(void*); + + +#if MSPACES + +/* + mspace is an opaque type representing an independent + region of space that supports mspace_malloc, etc. +*/ +typedef void* mspace; + +/* + create_mspace creates and returns a new independent space with the + given initial capacity, or, if 0, the default granularity size. It + returns null if there is no system memory available to create the + space. If argument locked is non-zero, the space uses a separate + lock to control access. The capacity of the space will grow + dynamically as needed to service mspace_malloc requests. You can + control the sizes of incremental increases of this space by + compiling with a different DEFAULT_GRANULARITY or dynamically + setting with mallopt(M_GRANULARITY, value). +*/ +mspace create_mspace(size_t capacity, int locked); + +/* + destroy_mspace destroys the given space, and attempts to return all + of its memory back to the system, returning the total number of + bytes freed. After destruction, the results of access to all memory + used by the space become undefined. +*/ +size_t destroy_mspace(mspace msp); + +/* + create_mspace_with_base uses the memory supplied as the initial base + of a new mspace. Part (less than 128*sizeof(size_t) bytes) of this + space is used for bookkeeping, so the capacity must be at least this + large. (Otherwise 0 is returned.) When this initial space is + exhausted, additional memory will be obtained from the system. + Destroying this space will deallocate all additionally allocated + space (if possible) but not the initial base. +*/ +mspace create_mspace_with_base(void* base, size_t capacity, int locked); + +/* + mspace_mmap_large_chunks controls whether requests for large chunks + are allocated in their own mmapped regions, separate from others in + this mspace. By default this is enabled, which reduces + fragmentation. However, such chunks are not necessarily released to + the system upon destroy_mspace. Disabling by setting to false may + increase fragmentation, but avoids leakage when relying on + destroy_mspace to release all memory allocated using this space. +*/ +int mspace_mmap_large_chunks(mspace msp, int enable); + + +/* + mspace_malloc behaves as malloc, but operates within + the given space. +*/ +void* mspace_malloc(mspace msp, size_t bytes); + +/* + mspace_free behaves as free, but operates within + the given space. + + If compiled with FOOTERS==1, mspace_free is not actually needed. + free may be called instead of mspace_free because freed chunks from + any space are handled by their originating spaces. +*/ +void mspace_free(mspace msp, void* mem); + +/* + mspace_realloc behaves as realloc, but operates within + the given space. + + If compiled with FOOTERS==1, mspace_realloc is not actually + needed. realloc may be called instead of mspace_realloc because + realloced chunks from any space are handled by their originating + spaces. +*/ +void* mspace_realloc(mspace msp, void* mem, size_t newsize); + +/* + mspace_calloc behaves as calloc, but operates within + the given space. +*/ +void* mspace_calloc(mspace msp, size_t n_elements, size_t elem_size); + +/* + mspace_memalign behaves as memalign, but operates within + the given space. +*/ +void* mspace_memalign(mspace msp, size_t alignment, size_t bytes); + +/* + mspace_independent_calloc behaves as independent_calloc, but + operates within the given space. +*/ +void** mspace_independent_calloc(mspace msp, size_t n_elements, + size_t elem_size, void* chunks[]); + +/* + mspace_independent_comalloc behaves as independent_comalloc, but + operates within the given space. +*/ +void** mspace_independent_comalloc(mspace msp, size_t n_elements, + size_t sizes[], void* chunks[]); + +/* + mspace_footprint() returns the number of bytes obtained from the + system for this space. +*/ +size_t mspace_footprint(mspace msp); + +/* + mspace_max_footprint() returns the peak number of bytes obtained from the + system for this space. +*/ +size_t mspace_max_footprint(mspace msp); + + +#if !NO_MALLINFO +/* + mspace_mallinfo behaves as mallinfo, but reports properties of + the given space. +*/ +struct mallinfo mspace_mallinfo(mspace msp); +#endif /* NO_MALLINFO */ + +/* + malloc_usable_size(void* p) behaves the same as malloc_usable_size; +*/ + size_t mspace_usable_size(void* mem); + +/* + mspace_malloc_stats behaves as malloc_stats, but reports + properties of the given space. +*/ +void mspace_malloc_stats(mspace msp); + +/* + mspace_trim behaves as malloc_trim, but + operates within the given space. +*/ +int mspace_trim(mspace msp, size_t pad); + +/* + An alias for mallopt. +*/ +int mspace_mallopt(int, int); + +#endif /* MSPACES */ + +#ifdef __cplusplus +}; /* end of extern "C" */ +#endif /* __cplusplus */ + +/* + ======================================================================== + To make a fully customizable malloc.h header file, cut everything + above this line, put into file malloc.h, edit to suit, and #include it + on the next line, as well as in programs that use this malloc. + ======================================================================== +*/ + +/* #include "malloc.h" */ + +/*------------------------------ internal #includes ---------------------- */ + +#ifdef WIN32 +#ifndef __GNUC__ +#pragma warning( disable : 4146 ) /* no "unsigned" warnings */ +#endif +#endif /* WIN32 */ + +#include <stdio.h> /* for printing in malloc_stats */ + +#ifndef LACKS_ERRNO_H +#include <errno.h> /* for MALLOC_FAILURE_ACTION */ +#endif /* LACKS_ERRNO_H */ +#if FOOTERS +#include <time.h> /* for magic initialization */ +#endif /* FOOTERS */ +#ifndef LACKS_STDLIB_H +#include <stdlib.h> /* for abort() */ +#endif /* LACKS_STDLIB_H */ +#ifdef DEBUG +#if ABORT_ON_ASSERT_FAILURE +#define assert(x) if(!(x)) ABORT +#else /* ABORT_ON_ASSERT_FAILURE */ +#include <assert.h> +#endif /* ABORT_ON_ASSERT_FAILURE */ +#else /* DEBUG */ +#ifndef assert +#define assert(x) +#endif +#define DEBUG 0 +#endif /* DEBUG */ +#ifndef LACKS_STRING_H +#include <string.h> /* for memset etc */ +#endif /* LACKS_STRING_H */ +#if USE_BUILTIN_FFS +#ifndef LACKS_STRINGS_H +#include <strings.h> /* for ffs */ +#endif /* LACKS_STRINGS_H */ +#endif /* USE_BUILTIN_FFS */ +#if HAVE_MMAP +#ifndef LACKS_SYS_MMAN_H +#include <sys/mman.h> /* for mmap */ +#endif /* LACKS_SYS_MMAN_H */ +#ifndef LACKS_FCNTL_H +#include <fcntl.h> +#endif /* LACKS_FCNTL_H */ +#endif /* HAVE_MMAP */ +#ifndef LACKS_UNISTD_H +#include <unistd.h> /* for sbrk, sysconf */ +#else /* LACKS_UNISTD_H */ +#if !defined(__FreeBSD__) && !defined(__OpenBSD__) && !defined(__NetBSD__) +extern void* sbrk(ptrdiff_t); +#endif /* FreeBSD etc */ +#endif /* LACKS_UNISTD_H */ + +/* Declarations for locking */ +#if USE_LOCKS +#ifndef WIN32 +#include <pthread.h> +#if defined (__SVR4) && defined (__sun) /* solaris */ +#include <thread.h> +#endif /* solaris */ +#else +#ifndef _M_AMD64 +/* These are already defined on AMD64 builds */ +#ifdef __cplusplus +extern "C" { +#endif /* __cplusplus */ +#ifndef __MINGW32__ +LONG __cdecl _InterlockedCompareExchange(LONG volatile *Dest, LONG Exchange, LONG Comp); +LONG __cdecl _InterlockedExchange(LONG volatile *Target, LONG Value); +#endif +#ifdef __cplusplus +} +#endif /* __cplusplus */ +#endif /* _M_AMD64 */ +#ifndef __MINGW32__ +#pragma intrinsic (_InterlockedCompareExchange) +#pragma intrinsic (_InterlockedExchange) +#else + /* --[ start GCC compatibility ]---------------------------------------------- + * Compatibility <intrin_x86.h> header for GCC -- GCC equivalents of intrinsic + * Microsoft Visual C++ functions. Originally developed for the ReactOS + * (<http://www.reactos.org/>) and TinyKrnl (<http://www.tinykrnl.org/>) + * projects. + * + * Copyright (c) 2006 KJK::Hyperion <hackbunny@reactos.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + */ + + /*** Atomic operations ***/ + #if (__GNUC__ * 10000 + __GNUC_MINOR__ * 100 + __GNUC_PATCHLEVEL__) > 40100 + #define _ReadWriteBarrier() __sync_synchronize() + #else + static __inline__ __attribute__((always_inline)) long __sync_lock_test_and_set(volatile long * const Target, const long Value) + { + long res; + __asm__ __volatile__("xchg%z0 %2, %0" : "=g" (*(Target)), "=r" (res) : "1" (Value)); + return res; + } + static void __inline__ __attribute__((always_inline)) _MemoryBarrier(void) + { + __asm__ __volatile__("" : : : "memory"); + } + #define _ReadWriteBarrier() _MemoryBarrier() + #endif + /* BUGBUG: GCC only supports full barriers */ + static __inline__ __attribute__((always_inline)) long _InterlockedExchange(volatile long * const Target, const long Value) + { + /* NOTE: __sync_lock_test_and_set would be an acquire barrier, so we force a full barrier */ + _ReadWriteBarrier(); + return __sync_lock_test_and_set(Target, Value); + } + /* --[ end GCC compatibility ]---------------------------------------------- */ +#endif +#define interlockedcompareexchange _InterlockedCompareExchange +#define interlockedexchange _InterlockedExchange +#endif /* Win32 */ +#endif /* USE_LOCKS */ + +/* Declarations for bit scanning on win32 */ +#if defined(_MSC_VER) && _MSC_VER>=1300 +#ifndef BitScanForward /* Try to avoid pulling in WinNT.h */ +#ifdef __cplusplus +extern "C" { +#endif /* __cplusplus */ +unsigned char _BitScanForward(unsigned long *index, unsigned long mask); +unsigned char _BitScanReverse(unsigned long *index, unsigned long mask); +#ifdef __cplusplus +} +#endif /* __cplusplus */ + +#define BitScanForward _BitScanForward +#define BitScanReverse _BitScanReverse +#pragma intrinsic(_BitScanForward) +#pragma intrinsic(_BitScanReverse) +#endif /* BitScanForward */ +#endif /* defined(_MSC_VER) && _MSC_VER>=1300 */ + +#ifndef WIN32 +#ifndef malloc_getpagesize +# ifdef _SC_PAGESIZE /* some SVR4 systems omit an underscore */ +# ifndef _SC_PAGE_SIZE +# define _SC_PAGE_SIZE _SC_PAGESIZE +# endif +# endif +# ifdef _SC_PAGE_SIZE +# define malloc_getpagesize sysconf(_SC_PAGE_SIZE) +# else +# if defined(BSD) || defined(DGUX) || defined(HAVE_GETPAGESIZE) + extern size_t getpagesize(); +# define malloc_getpagesize getpagesize() +# else +# ifdef WIN32 /* use supplied emulation of getpagesize */ +# define malloc_getpagesize getpagesize() +# else +# ifndef LACKS_SYS_PARAM_H +# include <sys/param.h> +# endif +# ifdef EXEC_PAGESIZE +# define malloc_getpagesize EXEC_PAGESIZE +# else +# ifdef NBPG +# ifndef CLSIZE +# define malloc_getpagesize NBPG +# else +# define malloc_getpagesize (NBPG * CLSIZE) +# endif +# else +# ifdef NBPC +# define malloc_getpagesize NBPC +# else +# ifdef PAGESIZE +# define malloc_getpagesize PAGESIZE +# else /* just guess */ +# define malloc_getpagesize ((size_t)4096U) +# endif +# endif +# endif +# endif +# endif +# endif +# endif +#endif +#endif + + + +/* ------------------- size_t and alignment properties -------------------- */ + +/* The byte and bit size of a size_t */ +#define SIZE_T_SIZE (sizeof(size_t)) +#define SIZE_T_BITSIZE (sizeof(size_t) << 3) + +/* Some constants coerced to size_t */ +/* Annoying but necessary to avoid errors on some platforms */ +#define SIZE_T_ZERO ((size_t)0) +#define SIZE_T_ONE ((size_t)1) +#define SIZE_T_TWO ((size_t)2) +#define SIZE_T_FOUR ((size_t)4) +#define TWO_SIZE_T_SIZES (SIZE_T_SIZE<<1) +#define FOUR_SIZE_T_SIZES (SIZE_T_SIZE<<2) +#define SIX_SIZE_T_SIZES (FOUR_SIZE_T_SIZES+TWO_SIZE_T_SIZES) +#define HALF_MAX_SIZE_T (MAX_SIZE_T / 2U) + +/* The bit mask value corresponding to MALLOC_ALIGNMENT */ +#define CHUNK_ALIGN_MASK (MALLOC_ALIGNMENT - SIZE_T_ONE) + +/* True if address a has acceptable alignment */ +#define is_aligned(A) (((size_t)((A)) & (CHUNK_ALIGN_MASK)) == 0) + +/* the number of bytes to offset an address to align it */ +#define align_offset(A)\ + ((((size_t)(A) & CHUNK_ALIGN_MASK) == 0)? 0 :\ + ((MALLOC_ALIGNMENT - ((size_t)(A) & CHUNK_ALIGN_MASK)) & CHUNK_ALIGN_MASK)) + +/* -------------------------- MMAP preliminaries ------------------------- */ + +/* + If HAVE_MORECORE or HAVE_MMAP are false, we just define calls and + checks to fail so compiler optimizer can delete code rather than + using so many "#if"s. +*/ + + +/* MORECORE and MMAP must return MFAIL on failure */ +#define MFAIL ((void*)(MAX_SIZE_T)) +#define CMFAIL ((char*)(MFAIL)) /* defined for convenience */ + +#if HAVE_MMAP + +#ifndef WIN32 +#define MUNMAP_DEFAULT(a, s) munmap((a), (s)) +#define MMAP_PROT (PROT_READ|PROT_WRITE) +#if !defined(MAP_ANONYMOUS) && defined(MAP_ANON) +#define MAP_ANONYMOUS MAP_ANON +#endif /* MAP_ANON */ +#ifdef MAP_ANONYMOUS +#define MMAP_FLAGS (MAP_PRIVATE|MAP_ANONYMOUS) +#define MMAP_DEFAULT(s) mmap(0, (s), MMAP_PROT, MMAP_FLAGS, -1, 0) +#else /* MAP_ANONYMOUS */ +/* + Nearly all versions of mmap support MAP_ANONYMOUS, so the following + is unlikely to be needed, but is supplied just in case. +*/ +#define MMAP_FLAGS (MAP_PRIVATE) +static int dev_zero_fd = -1; /* Cached file descriptor for /dev/zero. */ +#define MMAP_DEFAULT(s) ((dev_zero_fd < 0) ? \ + (dev_zero_fd = open("/dev/zero", O_RDWR), \ + mmap(0, (s), MMAP_PROT, MMAP_FLAGS, dev_zero_fd, 0)) : \ + mmap(0, (s), MMAP_PROT, MMAP_FLAGS, dev_zero_fd, 0)) +#endif /* MAP_ANONYMOUS */ + +#define DIRECT_MMAP_DEFAULT(s) MMAP_DEFAULT(s) + +#else /* WIN32 */ + +/* Win32 MMAP via VirtualAlloc */ +static FORCEINLINE void* win32mmap(size_t size) { + void* ptr = VirtualAlloc(0, size, MEM_RESERVE|MEM_COMMIT, PAGE_READWRITE); + return (ptr != 0)? ptr: MFAIL; +} + +/* For direct MMAP, use MEM_TOP_DOWN to minimize interference */ +static FORCEINLINE void* win32direct_mmap(size_t size) { + void* ptr = VirtualAlloc(0, size, MEM_RESERVE|MEM_COMMIT|MEM_TOP_DOWN, + PAGE_READWRITE); + return (ptr != 0)? ptr: MFAIL; +} + +/* This function supports releasing coalesed segments */ +static FORCEINLINE int win32munmap(void* ptr, size_t size) { + MEMORY_BASIC_INFORMATION minfo; + char* cptr = (char*)ptr; + while (size) { + if (VirtualQuery(cptr, &minfo, sizeof(minfo)) == 0) + return -1; + if (minfo.BaseAddress != cptr || minfo.AllocationBase != cptr || + minfo.State != MEM_COMMIT || minfo.RegionSize > size) + return -1; + if (VirtualFree(cptr, 0, MEM_RELEASE) == 0) + return -1; + cptr += minfo.RegionSize; + size -= minfo.RegionSize; + } + return 0; +} + +#define MMAP_DEFAULT(s) win32mmap(s) +#define MUNMAP_DEFAULT(a, s) win32munmap((a), (s)) +#define DIRECT_MMAP_DEFAULT(s) win32direct_mmap(s) +#endif /* WIN32 */ +#endif /* HAVE_MMAP */ + +#if HAVE_MREMAP +#ifndef WIN32 +#define MREMAP_DEFAULT(addr, osz, nsz, mv) mremap((addr), (osz), (nsz), (mv)) +#endif /* WIN32 */ +#endif /* HAVE_MREMAP */ + + +/** + * Define CALL_MORECORE + */ +#if HAVE_MORECORE + #ifdef MORECORE + #define CALL_MORECORE(S) MORECORE(S) + #else /* MORECORE */ + #define CALL_MORECORE(S) MORECORE_DEFAULT(S) + #endif /* MORECORE */ +#else /* HAVE_MORECORE */ + #define CALL_MORECORE(S) MFAIL +#endif /* HAVE_MORECORE */ + +/** + * Define CALL_MMAP/CALL_MUNMAP/CALL_DIRECT_MMAP + */ +#if HAVE_MMAP + #define IS_MMAPPED_BIT (SIZE_T_ONE) + #define USE_MMAP_BIT (SIZE_T_ONE) + + #ifdef MMAP + #define CALL_MMAP(s) MMAP(s) + #else /* MMAP */ + #define CALL_MMAP(s) MMAP_DEFAULT(s) + #endif /* MMAP */ + #ifdef MUNMAP + #define CALL_MUNMAP(a, s) MUNMAP((a), (s)) + #else /* MUNMAP */ + #define CALL_MUNMAP(a, s) MUNMAP_DEFAULT((a), (s)) + #endif /* MUNMAP */ + #ifdef DIRECT_MMAP + #define CALL_DIRECT_MMAP(s) DIRECT_MMAP(s) + #else /* DIRECT_MMAP */ + #define CALL_DIRECT_MMAP(s) DIRECT_MMAP_DEFAULT(s) + #endif /* DIRECT_MMAP */ +#else /* HAVE_MMAP */ + #define IS_MMAPPED_BIT (SIZE_T_ZERO) + #define USE_MMAP_BIT (SIZE_T_ZERO) + + #define MMAP(s) MFAIL + #define MUNMAP(a, s) (-1) + #define DIRECT_MMAP(s) MFAIL + #define CALL_DIRECT_MMAP(s) DIRECT_MMAP(s) + #define CALL_MMAP(s) MMAP(s) + #define CALL_MUNMAP(a, s) MUNMAP((a), (s)) +#endif /* HAVE_MMAP */ + +/** + * Define CALL_MREMAP + */ +#if HAVE_MMAP && HAVE_MREMAP + #ifdef MREMAP + #define CALL_MREMAP(addr, osz, nsz, mv) MREMAP((addr), (osz), (nsz), (mv)) + #else /* MREMAP */ + #define CALL_MREMAP(addr, osz, nsz, mv) MREMAP_DEFAULT((addr), (osz), (nsz), (mv)) + #endif /* MREMAP */ +#else /* HAVE_MMAP && HAVE_MREMAP */ + #define CALL_MREMAP(addr, osz, nsz, mv) MFAIL +#endif /* HAVE_MMAP && HAVE_MREMAP */ + +/* mstate bit set if continguous morecore disabled or failed */ +#define USE_NONCONTIGUOUS_BIT (4U) + +/* segment bit set in create_mspace_with_base */ +#define EXTERN_BIT (8U) + + +/* --------------------------- Lock preliminaries ------------------------ */ + +/* + When locks are defined, there is one global lock, plus + one per-mspace lock. + + The global lock_ensures that mparams.magic and other unique + mparams values are initialized only once. It also protects + sequences of calls to MORECORE. In many cases sys_alloc requires + two calls, that should not be interleaved with calls by other + threads. This does not protect against direct calls to MORECORE + by other threads not using this lock, so there is still code to + cope the best we can on interference. + + Per-mspace locks surround calls to malloc, free, etc. To enable use + in layered extensions, per-mspace locks are reentrant. + + Because lock-protected regions generally have bounded times, it is + OK to use the supplied simple spinlocks in the custom versions for + x86. + + If USE_LOCKS is > 1, the definitions of lock routines here are + bypassed, in which case you will need to define at least + INITIAL_LOCK, ACQUIRE_LOCK, RELEASE_LOCK and possibly TRY_LOCK + (which is not used in this malloc, but commonly needed in + extensions.) +*/ + +#if USE_LOCKS == 1 + +#if USE_SPIN_LOCKS +#ifndef WIN32 + +/* Custom pthread-style spin locks on x86 and x64 for gcc */ +struct pthread_mlock_t { + volatile unsigned int l; + volatile unsigned int c; + volatile pthread_t threadid; +}; +#define MLOCK_T struct pthread_mlock_t +#define CURRENT_THREAD pthread_self() +#define INITIAL_LOCK(sl) (memset(sl, 0, sizeof(MLOCK_T)), 0) +#define ACQUIRE_LOCK(sl) pthread_acquire_lock(sl) +#define RELEASE_LOCK(sl) pthread_release_lock(sl) +#define TRY_LOCK(sl) pthread_try_lock(sl) +#define SPINS_PER_YIELD 63 + +static MLOCK_T malloc_global_mutex = { 0, 0, 0}; + +static FORCEINLINE int pthread_acquire_lock (MLOCK_T *sl) { + int spins = 0; + volatile unsigned int* lp = &sl->l; + for (;;) { + if (*lp != 0) { + if (sl->threadid == CURRENT_THREAD) { + ++sl->c; + return 0; + } + } + else { + /* place args to cmpxchgl in locals to evade oddities in some gccs */ + int cmp = 0; + int val = 1; + int ret; + __asm__ __volatile__ ("lock; cmpxchgl %1, %2" + : "=a" (ret) + : "r" (val), "m" (*(lp)), "0"(cmp) + : "memory", "cc"); + if (!ret) { + assert(!sl->threadid); + sl->c = 1; + sl->threadid = CURRENT_THREAD; + return 0; + } + if ((++spins & SPINS_PER_YIELD) == 0) { +#if defined (__SVR4) && defined (__sun) /* solaris */ + thr_yield(); +#else +#if defined(__linux__) || defined(__FreeBSD__) || defined(__APPLE__) + sched_yield(); +#else /* no-op yield on unknown systems */ + ; +#endif /* __linux__ || __FreeBSD__ || __APPLE__ */ +#endif /* solaris */ + } + } + } +} + +static FORCEINLINE void pthread_release_lock (MLOCK_T *sl) { + assert(sl->l != 0); + assert(sl->threadid == CURRENT_THREAD); + if (--sl->c == 0) { + sl->threadid = 0; + volatile unsigned int* lp = &sl->l; + int prev = 0; + int ret; + __asm__ __volatile__ ("lock; xchgl %0, %1" + : "=r" (ret) + : "m" (*(lp)), "0"(prev) + : "memory"); + } +} + +static FORCEINLINE int pthread_try_lock (MLOCK_T *sl) { + volatile unsigned int* lp = &sl->l; + if (*lp != 0) { + if (sl->threadid == CURRENT_THREAD) { + ++sl->c; + return 1; + } + } + else { + int cmp = 0; + int val = 1; + int ret; + __asm__ __volatile__ ("lock; cmpxchgl %1, %2" + : "=a" (ret) + : "r" (val), "m" (*(lp)), "0"(cmp) + : "memory", "cc"); + if (!ret) { + assert(!sl->threadid); + sl->c = 1; + sl->threadid = CURRENT_THREAD; + return 1; + } + } + return 0; +} + + +#else /* WIN32 */ +/* Custom win32-style spin locks on x86 and x64 for MSC */ +struct win32_mlock_t +{ + volatile long l; + volatile unsigned int c; + volatile long threadid; +}; + +#define MLOCK_T struct win32_mlock_t +#define CURRENT_THREAD win32_getcurrentthreadid() +#define INITIAL_LOCK(sl) (memset(sl, 0, sizeof(MLOCK_T)), 0) +#define ACQUIRE_LOCK(sl) win32_acquire_lock(sl) +#define RELEASE_LOCK(sl) win32_release_lock(sl) +#define TRY_LOCK(sl) win32_try_lock(sl) +#define SPINS_PER_YIELD 63 + +static MLOCK_T malloc_global_mutex = { 0, 0, 0}; + +static FORCEINLINE long win32_getcurrentthreadid() { +#ifdef _MSC_VER +#if defined(_M_IX86) + long *threadstruct=(long *)__readfsdword(0x18); + long threadid=threadstruct[0x24/sizeof(long)]; + return threadid; +#elif defined(_M_X64) + /* todo */ + return GetCurrentThreadId(); +#else + return GetCurrentThreadId(); +#endif +#else + return GetCurrentThreadId(); +#endif +} + +static FORCEINLINE int win32_acquire_lock (MLOCK_T *sl) { + int spins = 0; + for (;;) { + if (sl->l != 0) { + if (sl->threadid == CURRENT_THREAD) { + ++sl->c; + return 0; + } + } + else { + if (!interlockedexchange(&sl->l, 1)) { + assert(!sl->threadid); + sl->c=CURRENT_THREAD; + sl->threadid = CURRENT_THREAD; + sl->c = 1; + return 0; + } + } + if ((++spins & SPINS_PER_YIELD) == 0) + SleepEx(0, FALSE); + } +} + +static FORCEINLINE void win32_release_lock (MLOCK_T *sl) { + assert(sl->threadid == CURRENT_THREAD); + assert(sl->l != 0); + if (--sl->c == 0) { + sl->threadid = 0; + interlockedexchange (&sl->l, 0); + } +} + +static FORCEINLINE int win32_try_lock (MLOCK_T *sl) { + if(sl->l != 0) { + if (sl->threadid == CURRENT_THREAD) { + ++sl->c; + return 1; + } + } + else { + if (!interlockedexchange(&sl->l, 1)){ + assert(!sl->threadid); + sl->threadid = CURRENT_THREAD; + sl->c = 1; + return 1; + } + } + return 0; +} + +#endif /* WIN32 */ +#else /* USE_SPIN_LOCKS */ + +#ifndef WIN32 +/* pthreads-based locks */ + +#define MLOCK_T pthread_mutex_t +#define CURRENT_THREAD pthread_self() +#define INITIAL_LOCK(sl) pthread_init_lock(sl) +#define ACQUIRE_LOCK(sl) pthread_mutex_lock(sl) +#define RELEASE_LOCK(sl) pthread_mutex_unlock(sl) +#define TRY_LOCK(sl) (!pthread_mutex_trylock(sl)) + +static MLOCK_T malloc_global_mutex = PTHREAD_MUTEX_INITIALIZER; + +/* Cope with old-style linux recursive lock initialization by adding */ +/* skipped internal declaration from pthread.h */ +#ifdef linux +#ifndef PTHREAD_MUTEX_RECURSIVE +extern int pthread_mutexattr_setkind_np __P ((pthread_mutexattr_t *__attr, + int __kind)); +#define PTHREAD_MUTEX_RECURSIVE PTHREAD_MUTEX_RECURSIVE_NP +#define pthread_mutexattr_settype(x,y) pthread_mutexattr_setkind_np(x,y) +#endif +#endif + +static int pthread_init_lock (MLOCK_T *sl) { + pthread_mutexattr_t attr; + if (pthread_mutexattr_init(&attr)) return 1; + if (pthread_mutexattr_settype(&attr, PTHREAD_MUTEX_RECURSIVE)) return 1; + if (pthread_mutex_init(sl, &attr)) return 1; + if (pthread_mutexattr_destroy(&attr)) return 1; + return 0; +} + +#else /* WIN32 */ +/* Win32 critical sections */ +#define MLOCK_T CRITICAL_SECTION +#define CURRENT_THREAD GetCurrentThreadId() +#define INITIAL_LOCK(s) (!InitializeCriticalSectionAndSpinCount((s), 0x80000000|4000)) +#define ACQUIRE_LOCK(s) (EnterCriticalSection(s), 0) +#define RELEASE_LOCK(s) LeaveCriticalSection(s) +#define TRY_LOCK(s) TryEnterCriticalSection(s) +#define NEED_GLOBAL_LOCK_INIT + +static MLOCK_T malloc_global_mutex; +static volatile long malloc_global_mutex_status; + +/* Use spin loop to initialize global lock */ +static void init_malloc_global_mutex() { + for (;;) { + long stat = malloc_global_mutex_status; + if (stat > 0) + return; + /* transition to < 0 while initializing, then to > 0) */ + if (stat == 0 && + interlockedcompareexchange(&malloc_global_mutex_status, -1, 0) == 0) { + InitializeCriticalSection(&malloc_global_mutex); + interlockedexchange(&malloc_global_mutex_status,1); + return; + } + SleepEx(0, FALSE); + } +} + +#endif /* WIN32 */ +#endif /* USE_SPIN_LOCKS */ +#endif /* USE_LOCKS == 1 */ + +/* ----------------------- User-defined locks ------------------------ */ + +#if USE_LOCKS > 1 +/* Define your own lock implementation here */ +/* #define INITIAL_LOCK(sl) ... */ +/* #define ACQUIRE_LOCK(sl) ... */ +/* #define RELEASE_LOCK(sl) ... */ +/* #define TRY_LOCK(sl) ... */ +/* static MLOCK_T malloc_global_mutex = ... */ +#endif /* USE_LOCKS > 1 */ + +/* ----------------------- Lock-based state ------------------------ */ + +#if USE_LOCKS +#define USE_LOCK_BIT (2U) +#else /* USE_LOCKS */ +#define USE_LOCK_BIT (0U) +#define INITIAL_LOCK(l) +#endif /* USE_LOCKS */ + +#if USE_LOCKS +#define ACQUIRE_MALLOC_GLOBAL_LOCK() ACQUIRE_LOCK(&malloc_global_mutex); +#define RELEASE_MALLOC_GLOBAL_LOCK() RELEASE_LOCK(&malloc_global_mutex); +#else /* USE_LOCKS */ +#define ACQUIRE_MALLOC_GLOBAL_LOCK() +#define RELEASE_MALLOC_GLOBAL_LOCK() +#endif /* USE_LOCKS */ + + +/* ----------------------- Chunk representations ------------------------ */ + +/* + (The following includes lightly edited explanations by Colin Plumb.) + + The malloc_chunk declaration below is misleading (but accurate and + necessary). It declares a "view" into memory allowing access to + necessary fields at known offsets from a given base. + + Chunks of memory are maintained using a `boundary tag' method as + originally described by Knuth. (See the paper by Paul Wilson + ftp://ftp.cs.utexas.edu/pub/garbage/allocsrv.ps for a survey of such + techniques.) Sizes of free chunks are stored both in the front of + each chunk and at the end. This makes consolidating fragmented + chunks into bigger chunks fast. The head fields also hold bits + representing whether chunks are free or in use. + + Here are some pictures to make it clearer. They are "exploded" to + show that the state of a chunk can be thought of as extending from + the high 31 bits of the head field of its header through the + prev_foot and PINUSE_BIT bit of the following chunk header. + + A chunk that's in use looks like: + + chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Size of previous chunk (if P = 0) | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |P| + | Size of this chunk 1| +-+ + mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | | + +- -+ + | | + +- -+ + | : + +- size - sizeof(size_t) available payload bytes -+ + : | + chunk-> +- -+ + | | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |1| + | Size of next chunk (may or may not be in use) | +-+ + mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + + And if it's free, it looks like this: + + chunk-> +- -+ + | User payload (must be in use, or we would have merged!) | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |P| + | Size of this chunk 0| +-+ + mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Next pointer | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Prev pointer | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | : + +- size - sizeof(struct chunk) unused bytes -+ + : | + chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Size of this chunk | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |0| + | Size of next chunk (must be in use, or we would have merged)| +-+ + mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | : + +- User payload -+ + : | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + |0| + +-+ + Note that since we always merge adjacent free chunks, the chunks + adjacent to a free chunk must be in use. + + Given a pointer to a chunk (which can be derived trivially from the + payload pointer) we can, in O(1) time, find out whether the adjacent + chunks are free, and if so, unlink them from the lists that they + are on and merge them with the current chunk. + + Chunks always begin on even word boundaries, so the mem portion + (which is returned to the user) is also on an even word boundary, and + thus at least double-word aligned. + + The P (PINUSE_BIT) bit, stored in the unused low-order bit of the + chunk size (which is always a multiple of two words), is an in-use + bit for the *previous* chunk. If that bit is *clear*, then the + word before the current chunk size contains the previous chunk + size, and can be used to find the front of the previous chunk. + The very first chunk allocated always has this bit set, preventing + access to non-existent (or non-owned) memory. If pinuse is set for + any given chunk, then you CANNOT determine the size of the + previous chunk, and might even get a memory addressing fault when + trying to do so. + + The C (CINUSE_BIT) bit, stored in the unused second-lowest bit of + the chunk size redundantly records whether the current chunk is + inuse. This redundancy enables usage checks within free and realloc, + and reduces indirection when freeing and consolidating chunks. + + Each freshly allocated chunk must have both cinuse and pinuse set. + That is, each allocated chunk borders either a previously allocated + and still in-use chunk, or the base of its memory arena. This is + ensured by making all allocations from the the `lowest' part of any + found chunk. Further, no free chunk physically borders another one, + so each free chunk is known to be preceded and followed by either + inuse chunks or the ends of memory. + + Note that the `foot' of the current chunk is actually represented + as the prev_foot of the NEXT chunk. This makes it easier to + deal with alignments etc but can be very confusing when trying + to extend or adapt this code. + + The exceptions to all this are + + 1. The special chunk `top' is the top-most available chunk (i.e., + the one bordering the end of available memory). It is treated + specially. Top is never included in any bin, is used only if + no other chunk is available, and is released back to the + system if it is very large (see M_TRIM_THRESHOLD). In effect, + the top chunk is treated as larger (and thus less well + fitting) than any other available chunk. The top chunk + doesn't update its trailing size field since there is no next + contiguous chunk that would have to index off it. However, + space is still allocated for it (TOP_FOOT_SIZE) to enable + separation or merging when space is extended. + + 3. Chunks allocated via mmap, which have the lowest-order bit + (IS_MMAPPED_BIT) set in their prev_foot fields, and do not set + PINUSE_BIT in their head fields. Because they are allocated + one-by-one, each must carry its own prev_foot field, which is + also used to hold the offset this chunk has within its mmapped + region, which is needed to preserve alignment. Each mmapped + chunk is trailed by the first two fields of a fake next-chunk + for sake of usage checks. + +*/ + +struct malloc_chunk { + size_t prev_foot; /* Size of previous chunk (if free). */ + size_t head; /* Size and inuse bits. */ + struct malloc_chunk* fd; /* double links -- used only if free. */ + struct malloc_chunk* bk; +}; + +typedef struct malloc_chunk mchunk; +typedef struct malloc_chunk* mchunkptr; +typedef struct malloc_chunk* sbinptr; /* The type of bins of chunks */ +typedef unsigned int bindex_t; /* Described below */ +typedef unsigned int binmap_t; /* Described below */ +typedef unsigned int flag_t; /* The type of various bit flag sets */ + +/* ------------------- Chunks sizes and alignments ----------------------- */ + +#define MCHUNK_SIZE (sizeof(mchunk)) + +#if FOOTERS +#define CHUNK_OVERHEAD (TWO_SIZE_T_SIZES) +#else /* FOOTERS */ +#define CHUNK_OVERHEAD (SIZE_T_SIZE) +#endif /* FOOTERS */ + +/* MMapped chunks need a second word of overhead ... */ +#define MMAP_CHUNK_OVERHEAD (TWO_SIZE_T_SIZES) +/* ... and additional padding for fake next-chunk at foot */ +#define MMAP_FOOT_PAD (FOUR_SIZE_T_SIZES) + +/* The smallest size we can malloc is an aligned minimal chunk */ +#define MIN_CHUNK_SIZE\ + ((MCHUNK_SIZE + CHUNK_ALIGN_MASK) & ~CHUNK_ALIGN_MASK) + +/* conversion from malloc headers to user pointers, and back */ +#define chunk2mem(p) ((void*)((char*)(p) + TWO_SIZE_T_SIZES)) +#define mem2chunk(mem) ((mchunkptr)((char*)(mem) - TWO_SIZE_T_SIZES)) +/* chunk associated with aligned address A */ +#define align_as_chunk(A) (mchunkptr)((A) + align_offset(chunk2mem(A))) + +/* Bounds on request (not chunk) sizes. */ +#define MAX_REQUEST ((-MIN_CHUNK_SIZE) << 2) +#define MIN_REQUEST (MIN_CHUNK_SIZE - CHUNK_OVERHEAD - SIZE_T_ONE) + +/* pad request bytes into a usable size */ +#define pad_request(req) \ + (((req) + CHUNK_OVERHEAD + CHUNK_ALIGN_MASK) & ~CHUNK_ALIGN_MASK) + +/* pad request, checking for minimum (but not maximum) */ +#define request2size(req) \ + (((req) < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(req)) + + +/* ------------------ Operations on head and foot fields ----------------- */ + +/* + The head field of a chunk is or'ed with PINUSE_BIT when previous + adjacent chunk in use, and or'ed with CINUSE_BIT if this chunk is in + use. If the chunk was obtained with mmap, the prev_foot field has + IS_MMAPPED_BIT set, otherwise holding the offset of the base of the + mmapped region to the base of the chunk. + + FLAG4_BIT is not used by this malloc, but might be useful in extensions. +*/ + +#define PINUSE_BIT (SIZE_T_ONE) +#define CINUSE_BIT (SIZE_T_TWO) +#define FLAG4_BIT (SIZE_T_FOUR) +#define INUSE_BITS (PINUSE_BIT|CINUSE_BIT) +#define FLAG_BITS (PINUSE_BIT|CINUSE_BIT|FLAG4_BIT) + +/* Head value for fenceposts */ +#define FENCEPOST_HEAD (INUSE_BITS|SIZE_T_SIZE) + +/* extraction of fields from head words */ +#define cinuse(p) ((p)->head & CINUSE_BIT) +#define pinuse(p) ((p)->head & PINUSE_BIT) +#define chunksize(p) ((p)->head & ~(FLAG_BITS)) + +#define clear_pinuse(p) ((p)->head &= ~PINUSE_BIT) +#define clear_cinuse(p) ((p)->head &= ~CINUSE_BIT) + +/* Treat space at ptr +/- offset as a chunk */ +#define chunk_plus_offset(p, s) ((mchunkptr)(((char*)(p)) + (s))) +#define chunk_minus_offset(p, s) ((mchunkptr)(((char*)(p)) - (s))) + +/* Ptr to next or previous physical malloc_chunk. */ +#define next_chunk(p) ((mchunkptr)( ((char*)(p)) + ((p)->head & ~FLAG_BITS))) +#define prev_chunk(p) ((mchunkptr)( ((char*)(p)) - ((p)->prev_foot) )) + +/* extract next chunk's pinuse bit */ +#define next_pinuse(p) ((next_chunk(p)->head) & PINUSE_BIT) + +/* Get/set size at footer */ +#define get_foot(p, s) (((mchunkptr)((char*)(p) + (s)))->prev_foot) +#define set_foot(p, s) (((mchunkptr)((char*)(p) + (s)))->prev_foot = (s)) + +/* Set size, pinuse bit, and foot */ +#define set_size_and_pinuse_of_free_chunk(p, s)\ + ((p)->head = (s|PINUSE_BIT), set_foot(p, s)) + +/* Set size, pinuse bit, foot, and clear next pinuse */ +#define set_free_with_pinuse(p, s, n)\ + (clear_pinuse(n), set_size_and_pinuse_of_free_chunk(p, s)) + +#define is_mmapped(p)\ + (!((p)->head & PINUSE_BIT) && ((p)->prev_foot & IS_MMAPPED_BIT)) + +/* Get the internal overhead associated with chunk p */ +#define overhead_for(p)\ + (is_mmapped(p)? MMAP_CHUNK_OVERHEAD : CHUNK_OVERHEAD) + +/* Return true if malloced space is not necessarily cleared */ +#if MMAP_CLEARS +#define calloc_must_clear(p) (!is_mmapped(p)) +#else /* MMAP_CLEARS */ +#define calloc_must_clear(p) (1) +#endif /* MMAP_CLEARS */ + +/* ---------------------- Overlaid data structures ----------------------- */ + +/* + When chunks are not in use, they are treated as nodes of either + lists or trees. + + "Small" chunks are stored in circular doubly-linked lists, and look + like this: + + chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Size of previous chunk | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + `head:' | Size of chunk, in bytes |P| + mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Forward pointer to next chunk in list | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Back pointer to previous chunk in list | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Unused space (may be 0 bytes long) . + . . + . | +nextchunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + `foot:' | Size of chunk, in bytes | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + + Larger chunks are kept in a form of bitwise digital trees (aka + tries) keyed on chunksizes. Because malloc_tree_chunks are only for + free chunks greater than 256 bytes, their size doesn't impose any + constraints on user chunk sizes. Each node looks like: + + chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Size of previous chunk | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + `head:' | Size of chunk, in bytes |P| + mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Forward pointer to next chunk of same size | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Back pointer to previous chunk of same size | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Pointer to left child (child[0]) | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Pointer to right child (child[1]) | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Pointer to parent | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | bin index of this chunk | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Unused space . + . | +nextchunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + `foot:' | Size of chunk, in bytes | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + + Each tree holding treenodes is a tree of unique chunk sizes. Chunks + of the same size are arranged in a circularly-linked list, with only + the oldest chunk (the next to be used, in our FIFO ordering) + actually in the tree. (Tree members are distinguished by a non-null + parent pointer.) If a chunk with the same size an an existing node + is inserted, it is linked off the existing node using pointers that + work in the same way as fd/bk pointers of small chunks. + + Each tree contains a power of 2 sized range of chunk sizes (the + smallest is 0x100 <= x < 0x180), which is is divided in half at each + tree level, with the chunks in the smaller half of the range (0x100 + <= x < 0x140 for the top nose) in the left subtree and the larger + half (0x140 <= x < 0x180) in the right subtree. This is, of course, + done by inspecting individual bits. + + Using these rules, each node's left subtree contains all smaller + sizes than its right subtree. However, the node at the root of each + subtree has no particular ordering relationship to either. (The + dividing line between the subtree sizes is based on trie relation.) + If we remove the last chunk of a given size from the interior of the + tree, we need to replace it with a leaf node. The tree ordering + rules permit a node to be replaced by any leaf below it. + + The smallest chunk in a tree (a common operation in a best-fit + allocator) can be found by walking a path to the leftmost leaf in + the tree. Unlike a usual binary tree, where we follow left child + pointers until we reach a null, here we follow the right child + pointer any time the left one is null, until we reach a leaf with + both child pointers null. The smallest chunk in the tree will be + somewhere along that path. + + The worst case number of steps to add, find, or remove a node is + bounded by the number of bits differentiating chunks within + bins. Under current bin calculations, this ranges from 6 up to 21 + (for 32 bit sizes) or up to 53 (for 64 bit sizes). The typical case + is of course much better. +*/ + +struct malloc_tree_chunk { + /* The first four fields must be compatible with malloc_chunk */ + size_t prev_foot; + size_t head; + struct malloc_tree_chunk* fd; + struct malloc_tree_chunk* bk; + + struct malloc_tree_chunk* child[2]; + struct malloc_tree_chunk* parent; + bindex_t index; +}; + +typedef struct malloc_tree_chunk tchunk; +typedef struct malloc_tree_chunk* tchunkptr; +typedef struct malloc_tree_chunk* tbinptr; /* The type of bins of trees */ + +/* A little helper macro for trees */ +#define leftmost_child(t) ((t)->child[0] != 0? (t)->child[0] : (t)->child[1]) + +/* ----------------------------- Segments -------------------------------- */ + +/* + Each malloc space may include non-contiguous segments, held in a + list headed by an embedded malloc_segment record representing the + top-most space. Segments also include flags holding properties of + the space. Large chunks that are directly allocated by mmap are not + included in this list. They are instead independently created and + destroyed without otherwise keeping track of them. + + Segment management mainly comes into play for spaces allocated by + MMAP. Any call to MMAP might or might not return memory that is + adjacent to an existing segment. MORECORE normally contiguously + extends the current space, so this space is almost always adjacent, + which is simpler and faster to deal with. (This is why MORECORE is + used preferentially to MMAP when both are available -- see + sys_alloc.) When allocating using MMAP, we don't use any of the + hinting mechanisms (inconsistently) supported in various + implementations of unix mmap, or distinguish reserving from + committing memory. Instead, we just ask for space, and exploit + contiguity when we get it. It is probably possible to do + better than this on some systems, but no general scheme seems + to be significantly better. + + Management entails a simpler variant of the consolidation scheme + used for chunks to reduce fragmentation -- new adjacent memory is + normally prepended or appended to an existing segment. However, + there are limitations compared to chunk consolidation that mostly + reflect the fact that segment processing is relatively infrequent + (occurring only when getting memory from system) and that we + don't expect to have huge numbers of segments: + + * Segments are not indexed, so traversal requires linear scans. (It + would be possible to index these, but is not worth the extra + overhead and complexity for most programs on most platforms.) + * New segments are only appended to old ones when holding top-most + memory; if they cannot be prepended to others, they are held in + different segments. + + Except for the top-most segment of an mstate, each segment record + is kept at the tail of its segment. Segments are added by pushing + segment records onto the list headed by &mstate.seg for the + containing mstate. + + Segment flags control allocation/merge/deallocation policies: + * If EXTERN_BIT set, then we did not allocate this segment, + and so should not try to deallocate or merge with others. + (This currently holds only for the initial segment passed + into create_mspace_with_base.) + * If IS_MMAPPED_BIT set, the segment may be merged with + other surrounding mmapped segments and trimmed/de-allocated + using munmap. + * If neither bit is set, then the segment was obtained using + MORECORE so can be merged with surrounding MORECORE'd segments + and deallocated/trimmed using MORECORE with negative arguments. +*/ + +struct malloc_segment { + char* base; /* base address */ + size_t size; /* allocated size */ + struct malloc_segment* next; /* ptr to next segment */ + flag_t sflags; /* mmap and extern flag */ +}; + +#define is_mmapped_segment(S) ((S)->sflags & IS_MMAPPED_BIT) +#define is_extern_segment(S) ((S)->sflags & EXTERN_BIT) + +typedef struct malloc_segment msegment; +typedef struct malloc_segment* msegmentptr; + +/* ---------------------------- malloc_state ----------------------------- */ + +/* + A malloc_state holds all of the bookkeeping for a space. + The main fields are: + + Top + The topmost chunk of the currently active segment. Its size is + cached in topsize. The actual size of topmost space is + topsize+TOP_FOOT_SIZE, which includes space reserved for adding + fenceposts and segment records if necessary when getting more + space from the system. The size at which to autotrim top is + cached from mparams in trim_check, except that it is disabled if + an autotrim fails. + + Designated victim (dv) + This is the preferred chunk for servicing small requests that + don't have exact fits. It is normally the chunk split off most + recently to service another small request. Its size is cached in + dvsize. The link fields of this chunk are not maintained since it + is not kept in a bin. + + SmallBins + An array of bin headers for free chunks. These bins hold chunks + with sizes less than MIN_LARGE_SIZE bytes. Each bin contains + chunks of all the same size, spaced 8 bytes apart. To simplify + use in double-linked lists, each bin header acts as a malloc_chunk + pointing to the real first node, if it exists (else pointing to + itself). This avoids special-casing for headers. But to avoid + waste, we allocate only the fd/bk pointers of bins, and then use + repositioning tricks to treat these as the fields of a chunk. + + TreeBins + Treebins are pointers to the roots of trees holding a range of + sizes. There are 2 equally spaced treebins for each power of two + from TREE_SHIFT to TREE_SHIFT+16. The last bin holds anything + larger. + + Bin maps + There is one bit map for small bins ("smallmap") and one for + treebins ("treemap). Each bin sets its bit when non-empty, and + clears the bit when empty. Bit operations are then used to avoid + bin-by-bin searching -- nearly all "search" is done without ever + looking at bins that won't be selected. The bit maps + conservatively use 32 bits per map word, even if on 64bit system. + For a good description of some of the bit-based techniques used + here, see Henry S. Warren Jr's book "Hacker's Delight" (and + supplement at http://hackersdelight.org/). Many of these are + intended to reduce the branchiness of paths through malloc etc, as + well as to reduce the number of memory locations read or written. + + Segments + A list of segments headed by an embedded malloc_segment record + representing the initial space. + + Address check support + The least_addr field is the least address ever obtained from + MORECORE or MMAP. Attempted frees and reallocs of any address less + than this are trapped (unless INSECURE is defined). + + Magic tag + A cross-check field that should always hold same value as mparams.magic. + + Flags + Bits recording whether to use MMAP, locks, or contiguous MORECORE + + Statistics + Each space keeps track of current and maximum system memory + obtained via MORECORE or MMAP. + + Trim support + Fields holding the amount of unused topmost memory that should trigger + timming, and a counter to force periodic scanning to release unused + non-topmost segments. + + Locking + If USE_LOCKS is defined, the "mutex" lock is acquired and released + around every public call using this mspace. + + Extension support + A void* pointer and a size_t field that can be used to help implement + extensions to this malloc. +*/ + +/* Bin types, widths and sizes */ +#define NSMALLBINS (32U) +#define NTREEBINS (32U) +#define SMALLBIN_SHIFT (3U) +#define SMALLBIN_WIDTH (SIZE_T_ONE << SMALLBIN_SHIFT) +#define TREEBIN_SHIFT (8U) +#define MIN_LARGE_SIZE (SIZE_T_ONE << TREEBIN_SHIFT) +#define MAX_SMALL_SIZE (MIN_LARGE_SIZE - SIZE_T_ONE) +#define MAX_SMALL_REQUEST (MAX_SMALL_SIZE - CHUNK_ALIGN_MASK - CHUNK_OVERHEAD) + +struct malloc_state { + binmap_t smallmap; + binmap_t treemap; + size_t dvsize; + size_t topsize; + char* least_addr; + mchunkptr dv; + mchunkptr top; + size_t trim_check; + size_t release_checks; + size_t magic; + mchunkptr smallbins[(NSMALLBINS+1)*2]; + tbinptr treebins[NTREEBINS]; + size_t footprint; + size_t max_footprint; + flag_t mflags; +#if USE_LOCKS + MLOCK_T mutex; /* locate lock among fields that rarely change */ +#endif /* USE_LOCKS */ + msegment seg; + void* extp; /* Unused but available for extensions */ + size_t exts; +}; + +typedef struct malloc_state* mstate; + +/* ------------- Global malloc_state and malloc_params ------------------- */ + +/* + malloc_params holds global properties, including those that can be + dynamically set using mallopt. There is a single instance, mparams, + initialized in init_mparams. Note that the non-zeroness of "magic" + also serves as an initialization flag. +*/ + +struct malloc_params { + volatile size_t magic; + size_t page_size; + size_t granularity; + size_t mmap_threshold; + size_t trim_threshold; + flag_t default_mflags; +}; + +static struct malloc_params mparams; + +/* Ensure mparams initialized */ +#define ensure_initialization() ((void)(mparams.magic != 0 || init_mparams())) + +#if !ONLY_MSPACES + +/* The global malloc_state used for all non-"mspace" calls */ +static struct malloc_state _gm_; +#define gm (&_gm_) +#define is_global(M) ((M) == &_gm_) + +#endif /* !ONLY_MSPACES */ + +#define is_initialized(M) ((M)->top != 0) + +/* -------------------------- system alloc setup ------------------------- */ + +/* Operations on mflags */ + +#define use_lock(M) ((M)->mflags & USE_LOCK_BIT) +#define enable_lock(M) ((M)->mflags |= USE_LOCK_BIT) +#define disable_lock(M) ((M)->mflags &= ~USE_LOCK_BIT) + +#define use_mmap(M) ((M)->mflags & USE_MMAP_BIT) +#define enable_mmap(M) ((M)->mflags |= USE_MMAP_BIT) +#define disable_mmap(M) ((M)->mflags &= ~USE_MMAP_BIT) + +#define use_noncontiguous(M) ((M)->mflags & USE_NONCONTIGUOUS_BIT) +#define disable_contiguous(M) ((M)->mflags |= USE_NONCONTIGUOUS_BIT) + +#define set_lock(M,L)\ + ((M)->mflags = (L)?\ + ((M)->mflags | USE_LOCK_BIT) :\ + ((M)->mflags & ~USE_LOCK_BIT)) + +/* page-align a size */ +#define page_align(S)\ + (((S) + (mparams.page_size - SIZE_T_ONE)) & ~(mparams.page_size - SIZE_T_ONE)) + +/* granularity-align a size */ +#define granularity_align(S)\ + (((S) + (mparams.granularity - SIZE_T_ONE))\ + & ~(mparams.granularity - SIZE_T_ONE)) + + +/* For mmap, use granularity alignment on windows, else page-align */ +#ifdef WIN32 +#define mmap_align(S) granularity_align(S) +#else +#define mmap_align(S) page_align(S) +#endif + +/* For sys_alloc, enough padding to ensure can malloc request on success */ +#define SYS_ALLOC_PADDING (TOP_FOOT_SIZE + MALLOC_ALIGNMENT) + +#define is_page_aligned(S)\ + (((size_t)(S) & (mparams.page_size - SIZE_T_ONE)) == 0) +#define is_granularity_aligned(S)\ + (((size_t)(S) & (mparams.granularity - SIZE_T_ONE)) == 0) + +/* True if segment S holds address A */ +#define segment_holds(S, A)\ + ((char*)(A) >= S->base && (char*)(A) < S->base + S->size) + +/* Return segment holding given address */ +static msegmentptr segment_holding(mstate m, char* addr) { + msegmentptr sp = &m->seg; + for (;;) { + if (addr >= sp->base && addr < sp->base + sp->size) + return sp; + if ((sp = sp->next) == 0) + return 0; + } +} + +/* Return true if segment contains a segment link */ +static int has_segment_link(mstate m, msegmentptr ss) { + msegmentptr sp = &m->seg; + for (;;) { + if ((char*)sp >= ss->base && (char*)sp < ss->base + ss->size) + return 1; + if ((sp = sp->next) == 0) + return 0; + } +} + +#ifndef MORECORE_CANNOT_TRIM +#define should_trim(M,s) ((s) > (M)->trim_check) +#else /* MORECORE_CANNOT_TRIM */ +#define should_trim(M,s) (0) +#endif /* MORECORE_CANNOT_TRIM */ + +/* + TOP_FOOT_SIZE is padding at the end of a segment, including space + that may be needed to place segment records and fenceposts when new + noncontiguous segments are added. +*/ +#define TOP_FOOT_SIZE\ + (align_offset(chunk2mem(0))+pad_request(sizeof(struct malloc_segment))+MIN_CHUNK_SIZE) + + +/* ------------------------------- Hooks -------------------------------- */ + +/* + PREACTION should be defined to return 0 on success, and nonzero on + failure. If you are not using locking, you can redefine these to do + anything you like. +*/ + +#if USE_LOCKS + +#define PREACTION(M) ((use_lock(M))? ACQUIRE_LOCK(&(M)->mutex) : 0) +#define POSTACTION(M) { if (use_lock(M)) RELEASE_LOCK(&(M)->mutex); } +#else /* USE_LOCKS */ + +#ifndef PREACTION +#define PREACTION(M) (0) +#endif /* PREACTION */ + +#ifndef POSTACTION +#define POSTACTION(M) +#endif /* POSTACTION */ + +#endif /* USE_LOCKS */ + +/* + CORRUPTION_ERROR_ACTION is triggered upon detected bad addresses. + USAGE_ERROR_ACTION is triggered on detected bad frees and + reallocs. The argument p is an address that might have triggered the + fault. It is ignored by the two predefined actions, but might be + useful in custom actions that try to help diagnose errors. +*/ + +#if PROCEED_ON_ERROR + +/* A count of the number of corruption errors causing resets */ +int malloc_corruption_error_count; + +/* default corruption action */ +static void reset_on_error(mstate m); + +#define CORRUPTION_ERROR_ACTION(m) reset_on_error(m) +#define USAGE_ERROR_ACTION(m, p) + +#else /* PROCEED_ON_ERROR */ + +#ifndef CORRUPTION_ERROR_ACTION +#define CORRUPTION_ERROR_ACTION(m) ABORT +#endif /* CORRUPTION_ERROR_ACTION */ + +#ifndef USAGE_ERROR_ACTION +#define USAGE_ERROR_ACTION(m,p) ABORT +#endif /* USAGE_ERROR_ACTION */ + +#endif /* PROCEED_ON_ERROR */ + +/* -------------------------- Debugging setup ---------------------------- */ + +#if ! DEBUG + +#define check_free_chunk(M,P) +#define check_inuse_chunk(M,P) +#define check_malloced_chunk(M,P,N) +#define check_mmapped_chunk(M,P) +#define check_malloc_state(M) +#define check_top_chunk(M,P) + +#else /* DEBUG */ +#define check_free_chunk(M,P) do_check_free_chunk(M,P) +#define check_inuse_chunk(M,P) do_check_inuse_chunk(M,P) +#define check_top_chunk(M,P) do_check_top_chunk(M,P) +#define check_malloced_chunk(M,P,N) do_check_malloced_chunk(M,P,N) +#define check_mmapped_chunk(M,P) do_check_mmapped_chunk(M,P) +#define check_malloc_state(M) do_check_malloc_state(M) + +static void do_check_any_chunk(mstate m, mchunkptr p); +static void do_check_top_chunk(mstate m, mchunkptr p); +static void do_check_mmapped_chunk(mstate m, mchunkptr p); +static void do_check_inuse_chunk(mstate m, mchunkptr p); +static void do_check_free_chunk(mstate m, mchunkptr p); +static void do_check_malloced_chunk(mstate m, void* mem, size_t s); +static void do_check_tree(mstate m, tchunkptr t); +static void do_check_treebin(mstate m, bindex_t i); +static void do_check_smallbin(mstate m, bindex_t i); +static void do_check_malloc_state(mstate m); +static int bin_find(mstate m, mchunkptr x); +static size_t traverse_and_check(mstate m); +#endif /* DEBUG */ + +/* ---------------------------- Indexing Bins ---------------------------- */ + +#define is_small(s) (((s) >> SMALLBIN_SHIFT) < NSMALLBINS) +#define small_index(s) ((s) >> SMALLBIN_SHIFT) +#define small_index2size(i) ((i) << SMALLBIN_SHIFT) +#define MIN_SMALL_INDEX (small_index(MIN_CHUNK_SIZE)) + +/* addressing by index. See above about smallbin repositioning */ +#define smallbin_at(M, i) ((sbinptr)((char*)&((M)->smallbins[(i)<<1]))) +#define treebin_at(M,i) (&((M)->treebins[i])) + +/* assign tree index for size S to variable I. Use x86 asm if possible */ +#if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__)) +#define compute_tree_index(S, I)\ +{\ + unsigned int X = S >> TREEBIN_SHIFT;\ + if (X == 0)\ + I = 0;\ + else if (X > 0xFFFF)\ + I = NTREEBINS-1;\ + else {\ + unsigned int K;\ + __asm__("bsrl\t%1, %0\n\t" : "=r" (K) : "rm" (X));\ + I = (bindex_t)((K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1)));\ + }\ +} + +#elif defined (__INTEL_COMPILER) +#define compute_tree_index(S, I)\ +{\ + size_t X = S >> TREEBIN_SHIFT;\ + if (X == 0)\ + I = 0;\ + else if (X > 0xFFFF)\ + I = NTREEBINS-1;\ + else {\ + unsigned int K = _bit_scan_reverse (X); \ + I = (bindex_t)((K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1)));\ + }\ +} + +#elif defined(_MSC_VER) && _MSC_VER>=1300 +#define compute_tree_index(S, I)\ +{\ + size_t X = S >> TREEBIN_SHIFT;\ + if (X == 0)\ + I = 0;\ + else if (X > 0xFFFF)\ + I = NTREEBINS-1;\ + else {\ + unsigned int K;\ + _BitScanReverse((DWORD *) &K, X);\ + I = (bindex_t)((K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1)));\ + }\ +} + +#else /* GNUC */ +#define compute_tree_index(S, I)\ +{\ + size_t X = S >> TREEBIN_SHIFT;\ + if (X == 0)\ + I = 0;\ + else if (X > 0xFFFF)\ + I = NTREEBINS-1;\ + else {\ + unsigned int Y = (unsigned int)X;\ + unsigned int N = ((Y - 0x100) >> 16) & 8;\ + unsigned int K = (((Y <<= N) - 0x1000) >> 16) & 4;\ + N += K;\ + N += K = (((Y <<= K) - 0x4000) >> 16) & 2;\ + K = 14 - N + ((Y <<= K) >> 15);\ + I = (K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1));\ + }\ +} +#endif /* GNUC */ + +/* Bit representing maximum resolved size in a treebin at i */ +#define bit_for_tree_index(i) \ + (i == NTREEBINS-1)? (SIZE_T_BITSIZE-1) : (((i) >> 1) + TREEBIN_SHIFT - 2) + +/* Shift placing maximum resolved bit in a treebin at i as sign bit */ +#define leftshift_for_tree_index(i) \ + ((i == NTREEBINS-1)? 0 : \ + ((SIZE_T_BITSIZE-SIZE_T_ONE) - (((i) >> 1) + TREEBIN_SHIFT - 2))) + +/* The size of the smallest chunk held in bin with index i */ +#define minsize_for_tree_index(i) \ + ((SIZE_T_ONE << (((i) >> 1) + TREEBIN_SHIFT)) | \ + (((size_t)((i) & SIZE_T_ONE)) << (((i) >> 1) + TREEBIN_SHIFT - 1))) + + +/* ------------------------ Operations on bin maps ----------------------- */ + +/* bit corresponding to given index */ +#define idx2bit(i) ((binmap_t)(1) << (i)) + +/* Mark/Clear bits with given index */ +#define mark_smallmap(M,i) ((M)->smallmap |= idx2bit(i)) +#define clear_smallmap(M,i) ((M)->smallmap &= ~idx2bit(i)) +#define smallmap_is_marked(M,i) ((M)->smallmap & idx2bit(i)) + +#define mark_treemap(M,i) ((M)->treemap |= idx2bit(i)) +#define clear_treemap(M,i) ((M)->treemap &= ~idx2bit(i)) +#define treemap_is_marked(M,i) ((M)->treemap & idx2bit(i)) + +/* isolate the least set bit of a bitmap */ +#define least_bit(x) ((x) & -(x)) + +/* mask with all bits to left of least bit of x on */ +#define left_bits(x) ((x<<1) | -(x<<1)) + +/* mask with all bits to left of or equal to least bit of x on */ +#define same_or_left_bits(x) ((x) | -(x)) + +/* index corresponding to given bit. Use x86 asm if possible */ + +#if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__)) +#define compute_bit2idx(X, I)\ +{\ + unsigned int J;\ + __asm__("bsfl\t%1, %0\n\t" : "=r" (J) : "rm" (X));\ + I = (bindex_t)J;\ +} + +#elif defined (__INTEL_COMPILER) +#define compute_bit2idx(X, I)\ +{\ + unsigned int J;\ + J = _bit_scan_forward (X); \ + I = (bindex_t)J;\ +} + +#elif defined(_MSC_VER) && _MSC_VER>=1300 +#define compute_bit2idx(X, I)\ +{\ + unsigned int J;\ + _BitScanForward((DWORD *) &J, X);\ + I = (bindex_t)J;\ +} + +#elif USE_BUILTIN_FFS +#define compute_bit2idx(X, I) I = ffs(X)-1 + +#else +#define compute_bit2idx(X, I)\ +{\ + unsigned int Y = X - 1;\ + unsigned int K = Y >> (16-4) & 16;\ + unsigned int N = K; Y >>= K;\ + N += K = Y >> (8-3) & 8; Y >>= K;\ + N += K = Y >> (4-2) & 4; Y >>= K;\ + N += K = Y >> (2-1) & 2; Y >>= K;\ + N += K = Y >> (1-0) & 1; Y >>= K;\ + I = (bindex_t)(N + Y);\ +} +#endif /* GNUC */ + + +/* ----------------------- Runtime Check Support ------------------------- */ + +/* + For security, the main invariant is that malloc/free/etc never + writes to a static address other than malloc_state, unless static + malloc_state itself has been corrupted, which cannot occur via + malloc (because of these checks). In essence this means that we + believe all pointers, sizes, maps etc held in malloc_state, but + check all of those linked or offsetted from other embedded data + structures. These checks are interspersed with main code in a way + that tends to minimize their run-time cost. + + When FOOTERS is defined, in addition to range checking, we also + verify footer fields of inuse chunks, which can be used guarantee + that the mstate controlling malloc/free is intact. This is a + streamlined version of the approach described by William Robertson + et al in "Run-time Detection of Heap-based Overflows" LISA'03 + http://www.usenix.org/events/lisa03/tech/robertson.html The footer + of an inuse chunk holds the xor of its mstate and a random seed, + that is checked upon calls to free() and realloc(). This is + (probablistically) unguessable from outside the program, but can be + computed by any code successfully malloc'ing any chunk, so does not + itself provide protection against code that has already broken + security through some other means. Unlike Robertson et al, we + always dynamically check addresses of all offset chunks (previous, + next, etc). This turns out to be cheaper than relying on hashes. +*/ + +#if !INSECURE +/* Check if address a is at least as high as any from MORECORE or MMAP */ +#define ok_address(M, a) ((char*)(a) >= (M)->least_addr) +/* Check if address of next chunk n is higher than base chunk p */ +#define ok_next(p, n) ((char*)(p) < (char*)(n)) +/* Check if p has its cinuse bit on */ +#define ok_cinuse(p) cinuse(p) +/* Check if p has its pinuse bit on */ +#define ok_pinuse(p) pinuse(p) + +#else /* !INSECURE */ +#define ok_address(M, a) (1) +#define ok_next(b, n) (1) +#define ok_cinuse(p) (1) +#define ok_pinuse(p) (1) +#endif /* !INSECURE */ + +#if (FOOTERS && !INSECURE) +/* Check if (alleged) mstate m has expected magic field */ +#define ok_magic(M) ((M)->magic == mparams.magic) +#else /* (FOOTERS && !INSECURE) */ +#define ok_magic(M) (1) +#endif /* (FOOTERS && !INSECURE) */ + + +/* In gcc, use __builtin_expect to minimize impact of checks */ +#if !INSECURE +#if defined(__GNUC__) && __GNUC__ >= 3 +#define RTCHECK(e) __builtin_expect(e, 1) +#else /* GNUC */ +#define RTCHECK(e) (e) +#endif /* GNUC */ +#else /* !INSECURE */ +#define RTCHECK(e) (1) +#endif /* !INSECURE */ + +/* macros to set up inuse chunks with or without footers */ + +#if !FOOTERS + +#define mark_inuse_foot(M,p,s) + +/* Set cinuse bit and pinuse bit of next chunk */ +#define set_inuse(M,p,s)\ + ((p)->head = (((p)->head & PINUSE_BIT)|s|CINUSE_BIT),\ + ((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT) + +/* Set cinuse and pinuse of this chunk and pinuse of next chunk */ +#define set_inuse_and_pinuse(M,p,s)\ + ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\ + ((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT) + +/* Set size, cinuse and pinuse bit of this chunk */ +#define set_size_and_pinuse_of_inuse_chunk(M, p, s)\ + ((p)->head = (s|PINUSE_BIT|CINUSE_BIT)) + +#else /* FOOTERS */ + +/* Set foot of inuse chunk to be xor of mstate and seed */ +#define mark_inuse_foot(M,p,s)\ + (((mchunkptr)((char*)(p) + (s)))->prev_foot = ((size_t)(M) ^ mparams.magic)) + +#define get_mstate_for(p)\ + ((mstate)(((mchunkptr)((char*)(p) +\ + (chunksize(p))))->prev_foot ^ mparams.magic)) + +#define set_inuse(M,p,s)\ + ((p)->head = (((p)->head & PINUSE_BIT)|s|CINUSE_BIT),\ + (((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT), \ + mark_inuse_foot(M,p,s)) + +#define set_inuse_and_pinuse(M,p,s)\ + ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\ + (((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT),\ + mark_inuse_foot(M,p,s)) + +#define set_size_and_pinuse_of_inuse_chunk(M, p, s)\ + ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\ + mark_inuse_foot(M, p, s)) + +#endif /* !FOOTERS */ + +/* ---------------------------- setting mparams -------------------------- */ + +/* Initialize mparams */ +static int init_mparams(void) { +#ifdef NEED_GLOBAL_LOCK_INIT + if (malloc_global_mutex_status <= 0) + init_malloc_global_mutex(); +#endif + + ACQUIRE_MALLOC_GLOBAL_LOCK(); + if (mparams.magic == 0) { + size_t magic; + size_t psize; + size_t gsize; + +#ifndef WIN32 + psize = malloc_getpagesize; + gsize = ((DEFAULT_GRANULARITY != 0)? DEFAULT_GRANULARITY : psize); +#else /* WIN32 */ + { + SYSTEM_INFO system_info; + GetSystemInfo(&system_info); + psize = system_info.dwPageSize; + gsize = ((DEFAULT_GRANULARITY != 0)? + DEFAULT_GRANULARITY : system_info.dwAllocationGranularity); + } +#endif /* WIN32 */ + + /* Sanity-check configuration: + size_t must be unsigned and as wide as pointer type. + ints must be at least 4 bytes. + alignment must be at least 8. + Alignment, min chunk size, and page size must all be powers of 2. + */ + if ((sizeof(size_t) != sizeof(char*)) || + (MAX_SIZE_T < MIN_CHUNK_SIZE) || + (sizeof(int) < 4) || + (MALLOC_ALIGNMENT < (size_t)8U) || + ((MALLOC_ALIGNMENT & (MALLOC_ALIGNMENT-SIZE_T_ONE)) != 0) || + ((MCHUNK_SIZE & (MCHUNK_SIZE-SIZE_T_ONE)) != 0) || + ((gsize & (gsize-SIZE_T_ONE)) != 0) || + ((psize & (psize-SIZE_T_ONE)) != 0)) + ABORT; + + mparams.granularity = gsize; + mparams.page_size = psize; + mparams.mmap_threshold = DEFAULT_MMAP_THRESHOLD; + mparams.trim_threshold = DEFAULT_TRIM_THRESHOLD; +#if MORECORE_CONTIGUOUS + mparams.default_mflags = USE_LOCK_BIT|USE_MMAP_BIT; +#else /* MORECORE_CONTIGUOUS */ + mparams.default_mflags = USE_LOCK_BIT|USE_MMAP_BIT|USE_NONCONTIGUOUS_BIT; +#endif /* MORECORE_CONTIGUOUS */ + +#if !ONLY_MSPACES + /* Set up lock for main malloc area */ + gm->mflags = mparams.default_mflags; + INITIAL_LOCK(&gm->mutex); +#endif + +#if (FOOTERS && !INSECURE) + { +#if USE_DEV_RANDOM + int fd; + unsigned char buf[sizeof(size_t)]; + /* Try to use /dev/urandom, else fall back on using time */ + if ((fd = open("/dev/urandom", O_RDONLY)) >= 0 && + read(fd, buf, sizeof(buf)) == sizeof(buf)) { + magic = *((size_t *) buf); + close(fd); + } + else +#endif /* USE_DEV_RANDOM */ +#ifdef WIN32 + magic = (size_t)(GetTickCount() ^ (size_t)0x55555555U); +#else + magic = (size_t)(time(0) ^ (size_t)0x55555555U); +#endif + magic |= (size_t)8U; /* ensure nonzero */ + magic &= ~(size_t)7U; /* improve chances of fault for bad values */ + } +#else /* (FOOTERS && !INSECURE) */ + magic = (size_t)0x58585858U; +#endif /* (FOOTERS && !INSECURE) */ + + mparams.magic = magic; + } + + RELEASE_MALLOC_GLOBAL_LOCK(); + return 1; +} + +/* support for mallopt */ +static int change_mparam(int param_number, int value) { + size_t val = (value == -1)? MAX_SIZE_T : (size_t)value; + ensure_initialization(); + switch(param_number) { + case M_TRIM_THRESHOLD: + mparams.trim_threshold = val; + return 1; + case M_GRANULARITY: + if (val >= mparams.page_size && ((val & (val-1)) == 0)) { + mparams.granularity = val; + return 1; + } + else + return 0; + case M_MMAP_THRESHOLD: + mparams.mmap_threshold = val; + return 1; + default: + return 0; + } +} + +#if DEBUG +/* ------------------------- Debugging Support --------------------------- */ + +/* Check properties of any chunk, whether free, inuse, mmapped etc */ +static void do_check_any_chunk(mstate m, mchunkptr p) { + assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD)); + assert(ok_address(m, p)); +} + +/* Check properties of top chunk */ +static void do_check_top_chunk(mstate m, mchunkptr p) { + msegmentptr sp = segment_holding(m, (char*)p); + size_t sz = p->head & ~INUSE_BITS; /* third-lowest bit can be set! */ + assert(sp != 0); + assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD)); + assert(ok_address(m, p)); + assert(sz == m->topsize); + assert(sz > 0); + assert(sz == ((sp->base + sp->size) - (char*)p) - TOP_FOOT_SIZE); + assert(pinuse(p)); + assert(!pinuse(chunk_plus_offset(p, sz))); +} + +/* Check properties of (inuse) mmapped chunks */ +static void do_check_mmapped_chunk(mstate m, mchunkptr p) { + size_t sz = chunksize(p); + size_t len = (sz + (p->prev_foot & ~IS_MMAPPED_BIT) + MMAP_FOOT_PAD); + assert(is_mmapped(p)); + assert(use_mmap(m)); + assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD)); + assert(ok_address(m, p)); + assert(!is_small(sz)); + assert((len & (mparams.page_size-SIZE_T_ONE)) == 0); + assert(chunk_plus_offset(p, sz)->head == FENCEPOST_HEAD); + assert(chunk_plus_offset(p, sz+SIZE_T_SIZE)->head == 0); +} + +/* Check properties of inuse chunks */ +static void do_check_inuse_chunk(mstate m, mchunkptr p) { + do_check_any_chunk(m, p); + assert(cinuse(p)); + assert(next_pinuse(p)); + /* If not pinuse and not mmapped, previous chunk has OK offset */ + assert(is_mmapped(p) || pinuse(p) || next_chunk(prev_chunk(p)) == p); + if (is_mmapped(p)) + do_check_mmapped_chunk(m, p); +} + +/* Check properties of free chunks */ +static void do_check_free_chunk(mstate m, mchunkptr p) { + size_t sz = chunksize(p); + mchunkptr next = chunk_plus_offset(p, sz); + do_check_any_chunk(m, p); + assert(!cinuse(p)); + assert(!next_pinuse(p)); + assert (!is_mmapped(p)); + if (p != m->dv && p != m->top) { + if (sz >= MIN_CHUNK_SIZE) { + assert((sz & CHUNK_ALIGN_MASK) == 0); + assert(is_aligned(chunk2mem(p))); + assert(next->prev_foot == sz); + assert(pinuse(p)); + assert (next == m->top || cinuse(next)); + assert(p->fd->bk == p); + assert(p->bk->fd == p); + } + else /* markers are always of size SIZE_T_SIZE */ + assert(sz == SIZE_T_SIZE); + } +} + +/* Check properties of malloced chunks at the point they are malloced */ +static void do_check_malloced_chunk(mstate m, void* mem, size_t s) { + if (mem != 0) { + mchunkptr p = mem2chunk(mem); + size_t sz = p->head & ~(PINUSE_BIT|CINUSE_BIT); + do_check_inuse_chunk(m, p); + assert((sz & CHUNK_ALIGN_MASK) == 0); + assert(sz >= MIN_CHUNK_SIZE); + assert(sz >= s); + /* unless mmapped, size is less than MIN_CHUNK_SIZE more than request */ + assert(is_mmapped(p) || sz < (s + MIN_CHUNK_SIZE)); + } +} + +/* Check a tree and its subtrees. */ +static void do_check_tree(mstate m, tchunkptr t) { + tchunkptr head = 0; + tchunkptr u = t; + bindex_t tindex = t->index; + size_t tsize = chunksize(t); + bindex_t idx; + compute_tree_index(tsize, idx); + assert(tindex == idx); + assert(tsize >= MIN_LARGE_SIZE); + assert(tsize >= minsize_for_tree_index(idx)); + assert((idx == NTREEBINS-1) || (tsize < minsize_for_tree_index((idx+1)))); + + do { /* traverse through chain of same-sized nodes */ + do_check_any_chunk(m, ((mchunkptr)u)); + assert(u->index == tindex); + assert(chunksize(u) == tsize); + assert(!cinuse(u)); + assert(!next_pinuse(u)); + assert(u->fd->bk == u); + assert(u->bk->fd == u); + if (u->parent == 0) { + assert(u->child[0] == 0); + assert(u->child[1] == 0); + } + else { + assert(head == 0); /* only one node on chain has parent */ + head = u; + assert(u->parent != u); + assert (u->parent->child[0] == u || + u->parent->child[1] == u || + *((tbinptr*)(u->parent)) == u); + if (u->child[0] != 0) { + assert(u->child[0]->parent == u); + assert(u->child[0] != u); + do_check_tree(m, u->child[0]); + } + if (u->child[1] != 0) { + assert(u->child[1]->parent == u); + assert(u->child[1] != u); + do_check_tree(m, u->child[1]); + } + if (u->child[0] != 0 && u->child[1] != 0) { + assert(chunksize(u->child[0]) < chunksize(u->child[1])); + } + } + u = u->fd; + } while (u != t); + assert(head != 0); +} + +/* Check all the chunks in a treebin. */ +static void do_check_treebin(mstate m, bindex_t i) { + tbinptr* tb = treebin_at(m, i); + tchunkptr t = *tb; + int empty = (m->treemap & (1U << i)) == 0; + if (t == 0) + assert(empty); + if (!empty) + do_check_tree(m, t); +} + +/* Check all the chunks in a smallbin. */ +static void do_check_smallbin(mstate m, bindex_t i) { + sbinptr b = smallbin_at(m, i); + mchunkptr p = b->bk; + unsigned int empty = (m->smallmap & (1U << i)) == 0; + if (p == b) + assert(empty); + if (!empty) { + for (; p != b; p = p->bk) { + size_t size = chunksize(p); + mchunkptr q; + /* each chunk claims to be free */ + do_check_free_chunk(m, p); + /* chunk belongs in bin */ + assert(small_index(size) == i); + assert(p->bk == b || chunksize(p->bk) == chunksize(p)); + /* chunk is followed by an inuse chunk */ + q = next_chunk(p); + if (q->head != FENCEPOST_HEAD) + do_check_inuse_chunk(m, q); + } + } +} + +/* Find x in a bin. Used in other check functions. */ +static int bin_find(mstate m, mchunkptr x) { + size_t size = chunksize(x); + if (is_small(size)) { + bindex_t sidx = small_index(size); + sbinptr b = smallbin_at(m, sidx); + if (smallmap_is_marked(m, sidx)) { + mchunkptr p = b; + do { + if (p == x) + return 1; + } while ((p = p->fd) != b); + } + } + else { + bindex_t tidx; + compute_tree_index(size, tidx); + if (treemap_is_marked(m, tidx)) { + tchunkptr t = *treebin_at(m, tidx); + size_t sizebits = size << leftshift_for_tree_index(tidx); + while (t != 0 && chunksize(t) != size) { + t = t->child[(sizebits >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1]; + sizebits <<= 1; + } + if (t != 0) { + tchunkptr u = t; + do { + if (u == (tchunkptr)x) + return 1; + } while ((u = u->fd) != t); + } + } + } + return 0; +} + +/* Traverse each chunk and check it; return total */ +static size_t traverse_and_check(mstate m) { + size_t sum = 0; + if (is_initialized(m)) { + msegmentptr s = &m->seg; + sum += m->topsize + TOP_FOOT_SIZE; + while (s != 0) { + mchunkptr q = align_as_chunk(s->base); + mchunkptr lastq = 0; + assert(pinuse(q)); + while (segment_holds(s, q) && + q != m->top && q->head != FENCEPOST_HEAD) { + sum += chunksize(q); + if (cinuse(q)) { + assert(!bin_find(m, q)); + do_check_inuse_chunk(m, q); + } + else { + assert(q == m->dv || bin_find(m, q)); + assert(lastq == 0 || cinuse(lastq)); /* Not 2 consecutive free */ + do_check_free_chunk(m, q); + } + lastq = q; + q = next_chunk(q); + } + s = s->next; + } + } + return sum; +} + +/* Check all properties of malloc_state. */ +static void do_check_malloc_state(mstate m) { + bindex_t i; + size_t total; + /* check bins */ + for (i = 0; i < NSMALLBINS; ++i) + do_check_smallbin(m, i); + for (i = 0; i < NTREEBINS; ++i) + do_check_treebin(m, i); + + if (m->dvsize != 0) { /* check dv chunk */ + do_check_any_chunk(m, m->dv); + assert(m->dvsize == chunksize(m->dv)); + assert(m->dvsize >= MIN_CHUNK_SIZE); + assert(bin_find(m, m->dv) == 0); + } + + if (m->top != 0) { /* check top chunk */ + do_check_top_chunk(m, m->top); + /*assert(m->topsize == chunksize(m->top)); redundant */ + assert(m->topsize > 0); + assert(bin_find(m, m->top) == 0); + } + + total = traverse_and_check(m); + assert(total <= m->footprint); + assert(m->footprint <= m->max_footprint); +} +#endif /* DEBUG */ + +/* ----------------------------- statistics ------------------------------ */ + +#if !NO_MALLINFO +static struct mallinfo internal_mallinfo(mstate m) { + struct mallinfo nm = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }; + ensure_initialization(); + if (!PREACTION(m)) { + check_malloc_state(m); + if (is_initialized(m)) { + size_t nfree = SIZE_T_ONE; /* top always free */ + size_t mfree = m->topsize + TOP_FOOT_SIZE; + size_t sum = mfree; + msegmentptr s = &m->seg; + while (s != 0) { + mchunkptr q = align_as_chunk(s->base); + while (segment_holds(s, q) && + q != m->top && q->head != FENCEPOST_HEAD) { + size_t sz = chunksize(q); + sum += sz; + if (!cinuse(q)) { + mfree += sz; + ++nfree; + } + q = next_chunk(q); + } + s = s->next; + } + + nm.arena = sum; + nm.ordblks = nfree; + nm.hblkhd = m->footprint - sum; + nm.usmblks = m->max_footprint; + nm.uordblks = m->footprint - mfree; + nm.fordblks = mfree; + nm.keepcost = m->topsize; + } + + POSTACTION(m); + } + return nm; +} +#endif /* !NO_MALLINFO */ + +static void internal_malloc_stats(mstate m) { + ensure_initialization(); + if (!PREACTION(m)) { + size_t maxfp = 0; + size_t fp = 0; + size_t used = 0; + check_malloc_state(m); + if (is_initialized(m)) { + msegmentptr s = &m->seg; + maxfp = m->max_footprint; + fp = m->footprint; + used = fp - (m->topsize + TOP_FOOT_SIZE); + + while (s != 0) { + mchunkptr q = align_as_chunk(s->base); + while (segment_holds(s, q) && + q != m->top && q->head != FENCEPOST_HEAD) { + if (!cinuse(q)) + used -= chunksize(q); + q = next_chunk(q); + } + s = s->next; + } + } + + fprintf(stderr, "max system bytes = %10lu\n", (unsigned long)(maxfp)); + fprintf(stderr, "system bytes = %10lu\n", (unsigned long)(fp)); + fprintf(stderr, "in use bytes = %10lu\n", (unsigned long)(used)); + + POSTACTION(m); + } +} + +/* ----------------------- Operations on smallbins ----------------------- */ + +/* + Various forms of linking and unlinking are defined as macros. Even + the ones for trees, which are very long but have very short typical + paths. This is ugly but reduces reliance on inlining support of + compilers. +*/ + +/* Link a free chunk into a smallbin */ +#define insert_small_chunk(M, P, S) {\ + bindex_t I = small_index(S);\ + mchunkptr B = smallbin_at(M, I);\ + mchunkptr F = B;\ + assert(S >= MIN_CHUNK_SIZE);\ + if (!smallmap_is_marked(M, I))\ + mark_smallmap(M, I);\ + else if (RTCHECK(ok_address(M, B->fd)))\ + F = B->fd;\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + }\ + B->fd = P;\ + F->bk = P;\ + P->fd = F;\ + P->bk = B;\ +} + +/* Unlink a chunk from a smallbin */ +#define unlink_small_chunk(M, P, S) {\ + mchunkptr F = P->fd;\ + mchunkptr B = P->bk;\ + bindex_t I = small_index(S);\ + assert(P != B);\ + assert(P != F);\ + assert(chunksize(P) == small_index2size(I));\ + if (F == B)\ + clear_smallmap(M, I);\ + else if (RTCHECK((F == smallbin_at(M,I) || ok_address(M, F)) &&\ + (B == smallbin_at(M,I) || ok_address(M, B)))) {\ + F->bk = B;\ + B->fd = F;\ + }\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + }\ +} + +/* Unlink the first chunk from a smallbin */ +#define unlink_first_small_chunk(M, B, P, I) {\ + mchunkptr F = P->fd;\ + assert(P != B);\ + assert(P != F);\ + assert(chunksize(P) == small_index2size(I));\ + if (B == F)\ + clear_smallmap(M, I);\ + else if (RTCHECK(ok_address(M, F))) {\ + B->fd = F;\ + F->bk = B;\ + }\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + }\ +} + + + +/* Replace dv node, binning the old one */ +/* Used only when dvsize known to be small */ +#define replace_dv(M, P, S) {\ + size_t DVS = M->dvsize;\ + if (DVS != 0) {\ + mchunkptr DV = M->dv;\ + assert(is_small(DVS));\ + insert_small_chunk(M, DV, DVS);\ + }\ + M->dvsize = S;\ + M->dv = P;\ +} + +/* ------------------------- Operations on trees ------------------------- */ + +/* Insert chunk into tree */ +#define insert_large_chunk(M, X, S) {\ + tbinptr* H;\ + bindex_t I;\ + compute_tree_index(S, I);\ + H = treebin_at(M, I);\ + X->index = I;\ + X->child[0] = X->child[1] = 0;\ + if (!treemap_is_marked(M, I)) {\ + mark_treemap(M, I);\ + *H = X;\ + X->parent = (tchunkptr)H;\ + X->fd = X->bk = X;\ + }\ + else {\ + tchunkptr T = *H;\ + size_t K = S << leftshift_for_tree_index(I);\ + for (;;) {\ + if (chunksize(T) != S) {\ + tchunkptr* C = &(T->child[(K >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1]);\ + K <<= 1;\ + if (*C != 0)\ + T = *C;\ + else if (RTCHECK(ok_address(M, C))) {\ + *C = X;\ + X->parent = T;\ + X->fd = X->bk = X;\ + break;\ + }\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + break;\ + }\ + }\ + else {\ + tchunkptr F = T->fd;\ + if (RTCHECK(ok_address(M, T) && ok_address(M, F))) {\ + T->fd = F->bk = X;\ + X->fd = F;\ + X->bk = T;\ + X->parent = 0;\ + break;\ + }\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + break;\ + }\ + }\ + }\ + }\ +} + +/* + Unlink steps: + + 1. If x is a chained node, unlink it from its same-sized fd/bk links + and choose its bk node as its replacement. + 2. If x was the last node of its size, but not a leaf node, it must + be replaced with a leaf node (not merely one with an open left or + right), to make sure that lefts and rights of descendents + correspond properly to bit masks. We use the rightmost descendent + of x. We could use any other leaf, but this is easy to locate and + tends to counteract removal of leftmosts elsewhere, and so keeps + paths shorter than minimally guaranteed. This doesn't loop much + because on average a node in a tree is near the bottom. + 3. If x is the base of a chain (i.e., has parent links) relink + x's parent and children to x's replacement (or null if none). +*/ + +#define unlink_large_chunk(M, X) {\ + tchunkptr XP = X->parent;\ + tchunkptr R;\ + if (X->bk != X) {\ + tchunkptr F = X->fd;\ + R = X->bk;\ + if (RTCHECK(ok_address(M, F))) {\ + F->bk = R;\ + R->fd = F;\ + }\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + }\ + }\ + else {\ + tchunkptr* RP;\ + if (((R = *(RP = &(X->child[1]))) != 0) ||\ + ((R = *(RP = &(X->child[0]))) != 0)) {\ + tchunkptr* CP;\ + while ((*(CP = &(R->child[1])) != 0) ||\ + (*(CP = &(R->child[0])) != 0)) {\ + R = *(RP = CP);\ + }\ + if (RTCHECK(ok_address(M, RP)))\ + *RP = 0;\ + else {\ + CORRUPTION_ERROR_ACTION(M);\ + }\ + }\ + }\ + if (XP != 0) {\ + tbinptr* H = treebin_at(M, X->index);\ + if (X == *H) {\ + if ((*H = R) == 0) \ + clear_treemap(M, X->index);\ + }\ + else if (RTCHECK(ok_address(M, XP))) {\ + if (XP->child[0] == X) \ + XP->child[0] = R;\ + else \ + XP->child[1] = R;\ + }\ + else\ + CORRUPTION_ERROR_ACTION(M);\ + if (R != 0) {\ + if (RTCHECK(ok_address(M, R))) {\ + tchunkptr C0, C1;\ + R->parent = XP;\ + if ((C0 = X->child[0]) != 0) {\ + if (RTCHECK(ok_address(M, C0))) {\ + R->child[0] = C0;\ + C0->parent = R;\ + }\ + else\ + CORRUPTION_ERROR_ACTION(M);\ + }\ + if ((C1 = X->child[1]) != 0) {\ + if (RTCHECK(ok_address(M, C1))) {\ + R->child[1] = C1;\ + C1->parent = R;\ + }\ + else\ + CORRUPTION_ERROR_ACTION(M);\ + }\ + }\ + else\ + CORRUPTION_ERROR_ACTION(M);\ + }\ + }\ +} + +/* Relays to large vs small bin operations */ + +#define insert_chunk(M, P, S)\ + if (is_small(S)) insert_small_chunk(M, P, S)\ + else { tchunkptr TP = (tchunkptr)(P); insert_large_chunk(M, TP, S); } + +#define unlink_chunk(M, P, S)\ + if (is_small(S)) unlink_small_chunk(M, P, S)\ + else { tchunkptr TP = (tchunkptr)(P); unlink_large_chunk(M, TP); } + + +/* Relays to internal calls to malloc/free from realloc, memalign etc */ + +#if ONLY_MSPACES +#define internal_malloc(m, b) mspace_malloc(m, b) +#define internal_free(m, mem) mspace_free(m,mem); +#else /* ONLY_MSPACES */ +#if MSPACES +#define internal_malloc(m, b)\ + (m == gm)? dlmalloc(b) : mspace_malloc(m, b) +#define internal_free(m, mem)\ + if (m == gm) dlfree(mem); else mspace_free(m,mem); +#else /* MSPACES */ +#define internal_malloc(m, b) dlmalloc(b) +#define internal_free(m, mem) dlfree(mem) +#endif /* MSPACES */ +#endif /* ONLY_MSPACES */ + +/* ----------------------- Direct-mmapping chunks ----------------------- */ + +/* + Directly mmapped chunks are set up with an offset to the start of + the mmapped region stored in the prev_foot field of the chunk. This + allows reconstruction of the required argument to MUNMAP when freed, + and also allows adjustment of the returned chunk to meet alignment + requirements (especially in memalign). There is also enough space + allocated to hold a fake next chunk of size SIZE_T_SIZE to maintain + the PINUSE bit so frees can be checked. +*/ + +/* Malloc using mmap */ +static void* mmap_alloc(mstate m, size_t nb) { + size_t mmsize = mmap_align(nb + SIX_SIZE_T_SIZES + CHUNK_ALIGN_MASK); + if (mmsize > nb) { /* Check for wrap around 0 */ + char* mm = (char*)(CALL_DIRECT_MMAP(mmsize)); + if (mm != CMFAIL) { + size_t offset = align_offset(chunk2mem(mm)); + size_t psize = mmsize - offset - MMAP_FOOT_PAD; + mchunkptr p = (mchunkptr)(mm + offset); + p->prev_foot = offset | IS_MMAPPED_BIT; + (p)->head = (psize|CINUSE_BIT); + mark_inuse_foot(m, p, psize); + chunk_plus_offset(p, psize)->head = FENCEPOST_HEAD; + chunk_plus_offset(p, psize+SIZE_T_SIZE)->head = 0; + + if (mm < m->least_addr) + m->least_addr = mm; + if ((m->footprint += mmsize) > m->max_footprint) + m->max_footprint = m->footprint; + assert(is_aligned(chunk2mem(p))); + check_mmapped_chunk(m, p); + return chunk2mem(p); + } + } + return 0; +} + +/* Realloc using mmap */ +static mchunkptr mmap_resize(mstate m, mchunkptr oldp, size_t nb) { + size_t oldsize = chunksize(oldp); + if (is_small(nb)) /* Can't shrink mmap regions below small size */ + return 0; + /* Keep old chunk if big enough but not too big */ + if (oldsize >= nb + SIZE_T_SIZE && + (oldsize - nb) <= (mparams.granularity << 1)) + return oldp; + else { + size_t offset = oldp->prev_foot & ~IS_MMAPPED_BIT; + size_t oldmmsize = oldsize + offset + MMAP_FOOT_PAD; + size_t newmmsize = mmap_align(nb + SIX_SIZE_T_SIZES + CHUNK_ALIGN_MASK); + char* cp = (char*)CALL_MREMAP((char*)oldp - offset, + oldmmsize, newmmsize, 1); + if (cp != CMFAIL) { + mchunkptr newp = (mchunkptr)(cp + offset); + size_t psize = newmmsize - offset - MMAP_FOOT_PAD; + newp->head = (psize|CINUSE_BIT); + mark_inuse_foot(m, newp, psize); + chunk_plus_offset(newp, psize)->head = FENCEPOST_HEAD; + chunk_plus_offset(newp, psize+SIZE_T_SIZE)->head = 0; + + if (cp < m->least_addr) + m->least_addr = cp; + if ((m->footprint += newmmsize - oldmmsize) > m->max_footprint) + m->max_footprint = m->footprint; + check_mmapped_chunk(m, newp); + return newp; + } + } + return 0; +} + +/* -------------------------- mspace management -------------------------- */ + +/* Initialize top chunk and its size */ +static void init_top(mstate m, mchunkptr p, size_t psize) { + /* Ensure alignment */ + size_t offset = align_offset(chunk2mem(p)); + p = (mchunkptr)((char*)p + offset); + psize -= offset; + + m->top = p; + m->topsize = psize; + p->head = psize | PINUSE_BIT; + /* set size of fake trailing chunk holding overhead space only once */ + chunk_plus_offset(p, psize)->head = TOP_FOOT_SIZE; + m->trim_check = mparams.trim_threshold; /* reset on each update */ +} + +/* Initialize bins for a new mstate that is otherwise zeroed out */ +static void init_bins(mstate m) { + /* Establish circular links for smallbins */ + bindex_t i; + for (i = 0; i < NSMALLBINS; ++i) { + sbinptr bin = smallbin_at(m,i); + bin->fd = bin->bk = bin; + } +} + +#if PROCEED_ON_ERROR + +/* default corruption action */ +static void reset_on_error(mstate m) { + int i; + ++malloc_corruption_error_count; + /* Reinitialize fields to forget about all memory */ + m->smallbins = m->treebins = 0; + m->dvsize = m->topsize = 0; + m->seg.base = 0; + m->seg.size = 0; + m->seg.next = 0; + m->top = m->dv = 0; + for (i = 0; i < NTREEBINS; ++i) + *treebin_at(m, i) = 0; + init_bins(m); +} +#endif /* PROCEED_ON_ERROR */ + +/* Allocate chunk and prepend remainder with chunk in successor base. */ +static void* prepend_alloc(mstate m, char* newbase, char* oldbase, + size_t nb) { + mchunkptr p = align_as_chunk(newbase); + mchunkptr oldfirst = align_as_chunk(oldbase); + size_t psize = (char*)oldfirst - (char*)p; + mchunkptr q = chunk_plus_offset(p, nb); + size_t qsize = psize - nb; + set_size_and_pinuse_of_inuse_chunk(m, p, nb); + + assert((char*)oldfirst > (char*)q); + assert(pinuse(oldfirst)); + assert(qsize >= MIN_CHUNK_SIZE); + + /* consolidate remainder with first chunk of old base */ + if (oldfirst == m->top) { + size_t tsize = m->topsize += qsize; + m->top = q; + q->head = tsize | PINUSE_BIT; + check_top_chunk(m, q); + } + else if (oldfirst == m->dv) { + size_t dsize = m->dvsize += qsize; + m->dv = q; + set_size_and_pinuse_of_free_chunk(q, dsize); + } + else { + if (!cinuse(oldfirst)) { + size_t nsize = chunksize(oldfirst); + unlink_chunk(m, oldfirst, nsize); + oldfirst = chunk_plus_offset(oldfirst, nsize); + qsize += nsize; + } + set_free_with_pinuse(q, qsize, oldfirst); + insert_chunk(m, q, qsize); + check_free_chunk(m, q); + } + + check_malloced_chunk(m, chunk2mem(p), nb); + return chunk2mem(p); +} + +/* Add a segment to hold a new noncontiguous region */ +static void add_segment(mstate m, char* tbase, size_t tsize, flag_t mmapped) { + /* Determine locations and sizes of segment, fenceposts, old top */ + char* old_top = (char*)m->top; + msegmentptr oldsp = segment_holding(m, old_top); + char* old_end = oldsp->base + oldsp->size; + size_t ssize = pad_request(sizeof(struct malloc_segment)); + char* rawsp = old_end - (ssize + FOUR_SIZE_T_SIZES + CHUNK_ALIGN_MASK); + size_t offset = align_offset(chunk2mem(rawsp)); + char* asp = rawsp + offset; + char* csp = (asp < (old_top + MIN_CHUNK_SIZE))? old_top : asp; + mchunkptr sp = (mchunkptr)csp; + msegmentptr ss = (msegmentptr)(chunk2mem(sp)); + mchunkptr tnext = chunk_plus_offset(sp, ssize); + mchunkptr p = tnext; + int nfences = 0; + + /* reset top to new space */ + init_top(m, (mchunkptr)tbase, tsize - TOP_FOOT_SIZE); + + /* Set up segment record */ + assert(is_aligned(ss)); + set_size_and_pinuse_of_inuse_chunk(m, sp, ssize); + *ss = m->seg; /* Push current record */ + m->seg.base = tbase; + m->seg.size = tsize; + m->seg.sflags = mmapped; + m->seg.next = ss; + + /* Insert trailing fenceposts */ + for (;;) { + mchunkptr nextp = chunk_plus_offset(p, SIZE_T_SIZE); + p->head = FENCEPOST_HEAD; + ++nfences; + if ((char*)(&(nextp->head)) < old_end) + p = nextp; + else + break; + } + assert(nfences >= 2); + + /* Insert the rest of old top into a bin as an ordinary free chunk */ + if (csp != old_top) { + mchunkptr q = (mchunkptr)old_top; + size_t psize = csp - old_top; + mchunkptr tn = chunk_plus_offset(q, psize); + set_free_with_pinuse(q, psize, tn); + insert_chunk(m, q, psize); + } + + check_top_chunk(m, m->top); +} + +/* -------------------------- System allocation -------------------------- */ + +/* Get memory from system using MORECORE or MMAP */ +static void* sys_alloc(mstate m, size_t nb) { + char* tbase = CMFAIL; + size_t tsize = 0; + flag_t mmap_flag = 0; + + ensure_initialization(); + + /* Directly map large chunks */ + if (use_mmap(m) && nb >= mparams.mmap_threshold) { + void* mem = mmap_alloc(m, nb); + if (mem != 0) + return mem; + } + + /* + Try getting memory in any of three ways (in most-preferred to + least-preferred order): + 1. A call to MORECORE that can normally contiguously extend memory. + (disabled if not MORECORE_CONTIGUOUS or not HAVE_MORECORE or + or main space is mmapped or a previous contiguous call failed) + 2. A call to MMAP new space (disabled if not HAVE_MMAP). + Note that under the default settings, if MORECORE is unable to + fulfill a request, and HAVE_MMAP is true, then mmap is + used as a noncontiguous system allocator. This is a useful backup + strategy for systems with holes in address spaces -- in this case + sbrk cannot contiguously expand the heap, but mmap may be able to + find space. + 3. A call to MORECORE that cannot usually contiguously extend memory. + (disabled if not HAVE_MORECORE) + + In all cases, we need to request enough bytes from system to ensure + we can malloc nb bytes upon success, so pad with enough space for + top_foot, plus alignment-pad to make sure we don't lose bytes if + not on boundary, and round this up to a granularity unit. + */ + + if (MORECORE_CONTIGUOUS && !use_noncontiguous(m)) { + char* br = CMFAIL; + msegmentptr ss = (m->top == 0)? 0 : segment_holding(m, (char*)m->top); + size_t asize = 0; + ACQUIRE_MALLOC_GLOBAL_LOCK(); + + if (ss == 0) { /* First time through or recovery */ + char* base = (char*)CALL_MORECORE(0); + if (base != CMFAIL) { + asize = granularity_align(nb + SYS_ALLOC_PADDING); + /* Adjust to end on a page boundary */ + if (!is_page_aligned(base)) + asize += (page_align((size_t)base) - (size_t)base); + /* Can't call MORECORE if size is negative when treated as signed */ + if (asize < HALF_MAX_SIZE_T && + (br = (char*)(CALL_MORECORE(asize))) == base) { + tbase = base; + tsize = asize; + } + } + } + else { + /* Subtract out existing available top space from MORECORE request. */ + asize = granularity_align(nb - m->topsize + SYS_ALLOC_PADDING); + /* Use mem here only if it did continuously extend old space */ + if (asize < HALF_MAX_SIZE_T && + (br = (char*)(CALL_MORECORE(asize))) == ss->base+ss->size) { + tbase = br; + tsize = asize; + } + } + + if (tbase == CMFAIL) { /* Cope with partial failure */ + if (br != CMFAIL) { /* Try to use/extend the space we did get */ + if (asize < HALF_MAX_SIZE_T && + asize < nb + SYS_ALLOC_PADDING) { + size_t esize = granularity_align(nb + SYS_ALLOC_PADDING - asize); + if (esize < HALF_MAX_SIZE_T) { + char* end = (char*)CALL_MORECORE(esize); + if (end != CMFAIL) + asize += esize; + else { /* Can't use; try to release */ + (void) CALL_MORECORE(-asize); + br = CMFAIL; + } + } + } + } + if (br != CMFAIL) { /* Use the space we did get */ + tbase = br; + tsize = asize; + } + else + disable_contiguous(m); /* Don't try contiguous path in the future */ + } + + RELEASE_MALLOC_GLOBAL_LOCK(); + } + + if (HAVE_MMAP && tbase == CMFAIL) { /* Try MMAP */ + size_t rsize = granularity_align(nb + SYS_ALLOC_PADDING); + if (rsize > nb) { /* Fail if wraps around zero */ + char* mp = (char*)(CALL_MMAP(rsize)); + if (mp != CMFAIL) { + tbase = mp; + tsize = rsize; + mmap_flag = IS_MMAPPED_BIT; + } + } + } + + if (HAVE_MORECORE && tbase == CMFAIL) { /* Try noncontiguous MORECORE */ + size_t asize = granularity_align(nb + SYS_ALLOC_PADDING); + if (asize < HALF_MAX_SIZE_T) { + char* br = CMFAIL; + char* end = CMFAIL; + ACQUIRE_MALLOC_GLOBAL_LOCK(); + br = (char*)(CALL_MORECORE(asize)); + end = (char*)(CALL_MORECORE(0)); + RELEASE_MALLOC_GLOBAL_LOCK(); + if (br != CMFAIL && end != CMFAIL && br < end) { + size_t ssize = end - br; + if (ssize > nb + TOP_FOOT_SIZE) { + tbase = br; + tsize = ssize; + } + } + } + } + + if (tbase != CMFAIL) { + + if ((m->footprint += tsize) > m->max_footprint) + m->max_footprint = m->footprint; + + if (!is_initialized(m)) { /* first-time initialization */ + m->seg.base = m->least_addr = tbase; + m->seg.size = tsize; + m->seg.sflags = mmap_flag; + m->magic = mparams.magic; + m->release_checks = MAX_RELEASE_CHECK_RATE; + init_bins(m); +#if !ONLY_MSPACES + if (is_global(m)) + init_top(m, (mchunkptr)tbase, tsize - TOP_FOOT_SIZE); + else +#endif + { + /* Offset top by embedded malloc_state */ + mchunkptr mn = next_chunk(mem2chunk(m)); + init_top(m, mn, (size_t)((tbase + tsize) - (char*)mn) -TOP_FOOT_SIZE); + } + } + + else { + /* Try to merge with an existing segment */ + msegmentptr sp = &m->seg; + /* Only consider most recent segment if traversal suppressed */ + while (sp != 0 && tbase != sp->base + sp->size) + sp = (NO_SEGMENT_TRAVERSAL) ? 0 : sp->next; + if (sp != 0 && + !is_extern_segment(sp) && + (sp->sflags & IS_MMAPPED_BIT) == mmap_flag && + segment_holds(sp, m->top)) { /* append */ + sp->size += tsize; + init_top(m, m->top, m->topsize + tsize); + } + else { + if (tbase < m->least_addr) + m->least_addr = tbase; + sp = &m->seg; + while (sp != 0 && sp->base != tbase + tsize) + sp = (NO_SEGMENT_TRAVERSAL) ? 0 : sp->next; + if (sp != 0 && + !is_extern_segment(sp) && + (sp->sflags & IS_MMAPPED_BIT) == mmap_flag) { + char* oldbase = sp->base; + sp->base = tbase; + sp->size += tsize; + return prepend_alloc(m, tbase, oldbase, nb); + } + else + add_segment(m, tbase, tsize, mmap_flag); + } + } + + if (nb < m->topsize) { /* Allocate from new or extended top space */ + size_t rsize = m->topsize -= nb; + mchunkptr p = m->top; + mchunkptr r = m->top = chunk_plus_offset(p, nb); + r->head = rsize | PINUSE_BIT; + set_size_and_pinuse_of_inuse_chunk(m, p, nb); + check_top_chunk(m, m->top); + check_malloced_chunk(m, chunk2mem(p), nb); + return chunk2mem(p); + } + } + + MALLOC_FAILURE_ACTION; + return 0; +} + +/* ----------------------- system deallocation -------------------------- */ + +/* Unmap and unlink any mmapped segments that don't contain used chunks */ +static size_t release_unused_segments(mstate m) { + size_t released = 0; + int nsegs = 0; + msegmentptr pred = &m->seg; + msegmentptr sp = pred->next; + while (sp != 0) { + char* base = sp->base; + size_t size = sp->size; + msegmentptr next = sp->next; + ++nsegs; + if (is_mmapped_segment(sp) && !is_extern_segment(sp)) { + mchunkptr p = align_as_chunk(base); + size_t psize = chunksize(p); + /* Can unmap if first chunk holds entire segment and not pinned */ + if (!cinuse(p) && (char*)p + psize >= base + size - TOP_FOOT_SIZE) { + tchunkptr tp = (tchunkptr)p; + assert(segment_holds(sp, (char*)sp)); + if (p == m->dv) { + m->dv = 0; + m->dvsize = 0; + } + else { + unlink_large_chunk(m, tp); + } + if (CALL_MUNMAP(base, size) == 0) { + released += size; + m->footprint -= size; + /* unlink obsoleted record */ + sp = pred; + sp->next = next; + } + else { /* back out if cannot unmap */ + insert_large_chunk(m, tp, psize); + } + } + } + if (NO_SEGMENT_TRAVERSAL) /* scan only first segment */ + break; + pred = sp; + sp = next; + } + /* Reset check counter */ + m->release_checks = ((nsegs > MAX_RELEASE_CHECK_RATE)? + nsegs : MAX_RELEASE_CHECK_RATE); + return released; +} + +static int sys_trim(mstate m, size_t pad) { + size_t released = 0; + ensure_initialization(); + if (pad < MAX_REQUEST && is_initialized(m)) { + pad += TOP_FOOT_SIZE; /* ensure enough room for segment overhead */ + + if (m->topsize > pad) { + /* Shrink top space in granularity-size units, keeping at least one */ + size_t unit = mparams.granularity; + size_t extra = ((m->topsize - pad + (unit - SIZE_T_ONE)) / unit - + SIZE_T_ONE) * unit; + msegmentptr sp = segment_holding(m, (char*)m->top); + + if (!is_extern_segment(sp)) { + if (is_mmapped_segment(sp)) { + if (HAVE_MMAP && + sp->size >= extra && + !has_segment_link(m, sp)) { /* can't shrink if pinned */ + size_t newsize = sp->size - extra; + /* Prefer mremap, fall back to munmap */ + if ((CALL_MREMAP(sp->base, sp->size, newsize, 0) != MFAIL) || + (CALL_MUNMAP(sp->base + newsize, extra) == 0)) { + released = extra; + } + } + } + else if (HAVE_MORECORE) { + if (extra >= HALF_MAX_SIZE_T) /* Avoid wrapping negative */ + extra = (HALF_MAX_SIZE_T) + SIZE_T_ONE - unit; + ACQUIRE_MALLOC_GLOBAL_LOCK(); + { + /* Make sure end of memory is where we last set it. */ + char* old_br = (char*)(CALL_MORECORE(0)); + if (old_br == sp->base + sp->size) { + char* rel_br = (char*)(CALL_MORECORE(-extra)); + char* new_br = (char*)(CALL_MORECORE(0)); + if (rel_br != CMFAIL && new_br < old_br) + released = old_br - new_br; + } + } + RELEASE_MALLOC_GLOBAL_LOCK(); + } + } + + if (released != 0) { + sp->size -= released; + m->footprint -= released; + init_top(m, m->top, m->topsize - released); + check_top_chunk(m, m->top); + } + } + + /* Unmap any unused mmapped segments */ + if (HAVE_MMAP) + released += release_unused_segments(m); + + /* On failure, disable autotrim to avoid repeated failed future calls */ + if (released == 0 && m->topsize > m->trim_check) + m->trim_check = MAX_SIZE_T; + } + + return (released != 0)? 1 : 0; +} + + +/* ---------------------------- malloc support --------------------------- */ + +/* allocate a large request from the best fitting chunk in a treebin */ +static void* tmalloc_large(mstate m, size_t nb) { + tchunkptr v = 0; + size_t rsize = -nb; /* Unsigned negation */ + tchunkptr t; + bindex_t idx; + compute_tree_index(nb, idx); + if ((t = *treebin_at(m, idx)) != 0) { + /* Traverse tree for this bin looking for node with size == nb */ + size_t sizebits = nb << leftshift_for_tree_index(idx); + tchunkptr rst = 0; /* The deepest untaken right subtree */ + for (;;) { + tchunkptr rt; + size_t trem = chunksize(t) - nb; + if (trem < rsize) { + v = t; + if ((rsize = trem) == 0) + break; + } + rt = t->child[1]; + t = t->child[(sizebits >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1]; + if (rt != 0 && rt != t) + rst = rt; + if (t == 0) { + t = rst; /* set t to least subtree holding sizes > nb */ + break; + } + sizebits <<= 1; + } + } + if (t == 0 && v == 0) { /* set t to root of next non-empty treebin */ + binmap_t leftbits = left_bits(idx2bit(idx)) & m->treemap; + if (leftbits != 0) { + bindex_t i; + binmap_t leastbit = least_bit(leftbits); + compute_bit2idx(leastbit, i); + t = *treebin_at(m, i); + } + } + + while (t != 0) { /* find smallest of tree or subtree */ + size_t trem = chunksize(t) - nb; + if (trem < rsize) { + rsize = trem; + v = t; + } + t = leftmost_child(t); + } + + /* If dv is a better fit, return 0 so malloc will use it */ + if (v != 0 && rsize < (size_t)(m->dvsize - nb)) { + if (RTCHECK(ok_address(m, v))) { /* split */ + mchunkptr r = chunk_plus_offset(v, nb); + assert(chunksize(v) == rsize + nb); + if (RTCHECK(ok_next(v, r))) { + unlink_large_chunk(m, v); + if (rsize < MIN_CHUNK_SIZE) + set_inuse_and_pinuse(m, v, (rsize + nb)); + else { + set_size_and_pinuse_of_inuse_chunk(m, v, nb); + set_size_and_pinuse_of_free_chunk(r, rsize); + insert_chunk(m, r, rsize); + } + return chunk2mem(v); + } + } + CORRUPTION_ERROR_ACTION(m); + } + return 0; +} + +/* allocate a small request from the best fitting chunk in a treebin */ +static void* tmalloc_small(mstate m, size_t nb) { + tchunkptr t, v; + size_t rsize; + bindex_t i; + binmap_t leastbit = least_bit(m->treemap); + compute_bit2idx(leastbit, i); + v = t = *treebin_at(m, i); + rsize = chunksize(t) - nb; + + while ((t = leftmost_child(t)) != 0) { + size_t trem = chunksize(t) - nb; + if (trem < rsize) { + rsize = trem; + v = t; + } + } + + if (RTCHECK(ok_address(m, v))) { + mchunkptr r = chunk_plus_offset(v, nb); + assert(chunksize(v) == rsize + nb); + if (RTCHECK(ok_next(v, r))) { + unlink_large_chunk(m, v); + if (rsize < MIN_CHUNK_SIZE) + set_inuse_and_pinuse(m, v, (rsize + nb)); + else { + set_size_and_pinuse_of_inuse_chunk(m, v, nb); + set_size_and_pinuse_of_free_chunk(r, rsize); + replace_dv(m, r, rsize); + } + return chunk2mem(v); + } + } + + CORRUPTION_ERROR_ACTION(m); + return 0; +} + +/* --------------------------- realloc support --------------------------- */ + +static void* internal_realloc(mstate m, void* oldmem, size_t bytes) { + if (bytes >= MAX_REQUEST) { + MALLOC_FAILURE_ACTION; + return 0; + } + if (!PREACTION(m)) { + mchunkptr oldp = mem2chunk(oldmem); + size_t oldsize = chunksize(oldp); + mchunkptr next = chunk_plus_offset(oldp, oldsize); + mchunkptr newp = 0; + void* extra = 0; + + /* Try to either shrink or extend into top. Else malloc-copy-free */ + + if (RTCHECK(ok_address(m, oldp) && ok_cinuse(oldp) && + ok_next(oldp, next) && ok_pinuse(next))) { + size_t nb = request2size(bytes); + if (is_mmapped(oldp)) + newp = mmap_resize(m, oldp, nb); + else if (oldsize >= nb) { /* already big enough */ + size_t rsize = oldsize - nb; + newp = oldp; + if (rsize >= MIN_CHUNK_SIZE) { + mchunkptr remainder = chunk_plus_offset(newp, nb); + set_inuse(m, newp, nb); + set_inuse(m, remainder, rsize); + extra = chunk2mem(remainder); + } + } + else if (next == m->top && oldsize + m->topsize > nb) { + /* Expand into top */ + size_t newsize = oldsize + m->topsize; + size_t newtopsize = newsize - nb; + mchunkptr newtop = chunk_plus_offset(oldp, nb); + set_inuse(m, oldp, nb); + newtop->head = newtopsize |PINUSE_BIT; + m->top = newtop; + m->topsize = newtopsize; + newp = oldp; + } + } + else { + USAGE_ERROR_ACTION(m, oldmem); + POSTACTION(m); + return 0; + } + + POSTACTION(m); + + if (newp != 0) { + if (extra != 0) { + internal_free(m, extra); + } + check_inuse_chunk(m, newp); + return chunk2mem(newp); + } + else { + void* newmem = internal_malloc(m, bytes); + if (newmem != 0) { + size_t oc = oldsize - overhead_for(oldp); + memcpy(newmem, oldmem, (oc < bytes)? oc : bytes); + internal_free(m, oldmem); + } + return newmem; + } + } + return 0; +} + +/* --------------------------- memalign support -------------------------- */ + +static void* internal_memalign(mstate m, size_t alignment, size_t bytes) { + if (alignment <= MALLOC_ALIGNMENT) /* Can just use malloc */ + return internal_malloc(m, bytes); + if (alignment < MIN_CHUNK_SIZE) /* must be at least a minimum chunk size */ + alignment = MIN_CHUNK_SIZE; + if ((alignment & (alignment-SIZE_T_ONE)) != 0) {/* Ensure a power of 2 */ + size_t a = MALLOC_ALIGNMENT << 1; + while (a < alignment) a <<= 1; + alignment = a; + } + + if (bytes >= MAX_REQUEST - alignment) { + if (m != 0) { /* Test isn't needed but avoids compiler warning */ + MALLOC_FAILURE_ACTION; + } + } + else { + size_t nb = request2size(bytes); + size_t req = nb + alignment + MIN_CHUNK_SIZE - CHUNK_OVERHEAD; + char* mem = (char*)internal_malloc(m, req); + if (mem != 0) { + void* leader = 0; + void* trailer = 0; + mchunkptr p = mem2chunk(mem); + + if (PREACTION(m)) return 0; + if ((((size_t)(mem)) % alignment) != 0) { /* misaligned */ + /* + Find an aligned spot inside chunk. Since we need to give + back leading space in a chunk of at least MIN_CHUNK_SIZE, if + the first calculation places us at a spot with less than + MIN_CHUNK_SIZE leader, we can move to the next aligned spot. + We've allocated enough total room so that this is always + possible. + */ + char* br = (char*)mem2chunk((size_t)(((size_t)(mem + + alignment - + SIZE_T_ONE)) & + -alignment)); + char* pos = ((size_t)(br - (char*)(p)) >= MIN_CHUNK_SIZE)? + br : br+alignment; + mchunkptr newp = (mchunkptr)pos; + size_t leadsize = pos - (char*)(p); + size_t newsize = chunksize(p) - leadsize; + + if (is_mmapped(p)) { /* For mmapped chunks, just adjust offset */ + newp->prev_foot = p->prev_foot + leadsize; + newp->head = (newsize|CINUSE_BIT); + } + else { /* Otherwise, give back leader, use the rest */ + set_inuse(m, newp, newsize); + set_inuse(m, p, leadsize); + leader = chunk2mem(p); + } + p = newp; + } + + /* Give back spare room at the end */ + if (!is_mmapped(p)) { + size_t size = chunksize(p); + if (size > nb + MIN_CHUNK_SIZE) { + size_t remainder_size = size - nb; + mchunkptr remainder = chunk_plus_offset(p, nb); + set_inuse(m, p, nb); + set_inuse(m, remainder, remainder_size); + trailer = chunk2mem(remainder); + } + } + + assert (chunksize(p) >= nb); + assert((((size_t)(chunk2mem(p))) % alignment) == 0); + check_inuse_chunk(m, p); + POSTACTION(m); + if (leader != 0) { + internal_free(m, leader); + } + if (trailer != 0) { + internal_free(m, trailer); + } + return chunk2mem(p); + } + } + return 0; +} + +/* ------------------------ comalloc/coalloc support --------------------- */ + +static void** ialloc(mstate m, + size_t n_elements, + size_t* sizes, + int opts, + void* chunks[]) { + /* + This provides common support for independent_X routines, handling + all of the combinations that can result. + + The opts arg has: + bit 0 set if all elements are same size (using sizes[0]) + bit 1 set if elements should be zeroed + */ + + size_t element_size; /* chunksize of each element, if all same */ + size_t contents_size; /* total size of elements */ + size_t array_size; /* request size of pointer array */ + void* mem; /* malloced aggregate space */ + mchunkptr p; /* corresponding chunk */ + size_t remainder_size; /* remaining bytes while splitting */ + void** marray; /* either "chunks" or malloced ptr array */ + mchunkptr array_chunk; /* chunk for malloced ptr array */ + flag_t was_enabled; /* to disable mmap */ + size_t size; + size_t i; + + ensure_initialization(); + /* compute array length, if needed */ + if (chunks != 0) { + if (n_elements == 0) + return chunks; /* nothing to do */ + marray = chunks; + array_size = 0; + } + else { + /* if empty req, must still return chunk representing empty array */ + if (n_elements == 0) + return (void**)internal_malloc(m, 0); + marray = 0; + array_size = request2size(n_elements * (sizeof(void*))); + } + + /* compute total element size */ + if (opts & 0x1) { /* all-same-size */ + element_size = request2size(*sizes); + contents_size = n_elements * element_size; + } + else { /* add up all the sizes */ + element_size = 0; + contents_size = 0; + for (i = 0; i != n_elements; ++i) + contents_size += request2size(sizes[i]); + } + + size = contents_size + array_size; + + /* + Allocate the aggregate chunk. First disable direct-mmapping so + malloc won't use it, since we would not be able to later + free/realloc space internal to a segregated mmap region. + */ + was_enabled = use_mmap(m); + disable_mmap(m); + mem = internal_malloc(m, size - CHUNK_OVERHEAD); + if (was_enabled) + enable_mmap(m); + if (mem == 0) + return 0; + + if (PREACTION(m)) return 0; + p = mem2chunk(mem); + remainder_size = chunksize(p); + + assert(!is_mmapped(p)); + + if (opts & 0x2) { /* optionally clear the elements */ + memset((size_t*)mem, 0, remainder_size - SIZE_T_SIZE - array_size); + } + + /* If not provided, allocate the pointer array as final part of chunk */ + if (marray == 0) { + size_t array_chunk_size; + array_chunk = chunk_plus_offset(p, contents_size); + array_chunk_size = remainder_size - contents_size; + marray = (void**) (chunk2mem(array_chunk)); + set_size_and_pinuse_of_inuse_chunk(m, array_chunk, array_chunk_size); + remainder_size = contents_size; + } + + /* split out elements */ + for (i = 0; ; ++i) { + marray[i] = chunk2mem(p); + if (i != n_elements-1) { + if (element_size != 0) + size = element_size; + else + size = request2size(sizes[i]); + remainder_size -= size; + set_size_and_pinuse_of_inuse_chunk(m, p, size); + p = chunk_plus_offset(p, size); + } + else { /* the final element absorbs any overallocation slop */ + set_size_and_pinuse_of_inuse_chunk(m, p, remainder_size); + break; + } + } + +#if DEBUG + if (marray != chunks) { + /* final element must have exactly exhausted chunk */ + if (element_size != 0) { + assert(remainder_size == element_size); + } + else { + assert(remainder_size == request2size(sizes[i])); + } + check_inuse_chunk(m, mem2chunk(marray)); + } + for (i = 0; i != n_elements; ++i) + check_inuse_chunk(m, mem2chunk(marray[i])); + +#endif /* DEBUG */ + + POSTACTION(m); + return marray; +} + + +/* -------------------------- public routines ---------------------------- */ + +#if !ONLY_MSPACES + +void* dlmalloc(size_t bytes) { + /* + Basic algorithm: + If a small request (< 256 bytes minus per-chunk overhead): + 1. If one exists, use a remainderless chunk in associated smallbin. + (Remainderless means that there are too few excess bytes to + represent as a chunk.) + 2. If it is big enough, use the dv chunk, which is normally the + chunk adjacent to the one used for the most recent small request. + 3. If one exists, split the smallest available chunk in a bin, + saving remainder in dv. + 4. If it is big enough, use the top chunk. + 5. If available, get memory from system and use it + Otherwise, for a large request: + 1. Find the smallest available binned chunk that fits, and use it + if it is better fitting than dv chunk, splitting if necessary. + 2. If better fitting than any binned chunk, use the dv chunk. + 3. If it is big enough, use the top chunk. + 4. If request size >= mmap threshold, try to directly mmap this chunk. + 5. If available, get memory from system and use it + + The ugly goto's here ensure that postaction occurs along all paths. + */ + +#if USE_LOCKS + ensure_initialization(); /* initialize in sys_alloc if not using locks */ +#endif + + if (!PREACTION(gm)) { + void* mem; + size_t nb; + if (bytes <= MAX_SMALL_REQUEST) { + bindex_t idx; + binmap_t smallbits; + nb = (bytes < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(bytes); + idx = small_index(nb); + smallbits = gm->smallmap >> idx; + + if ((smallbits & 0x3U) != 0) { /* Remainderless fit to a smallbin. */ + mchunkptr b, p; + idx += ~smallbits & 1; /* Uses next bin if idx empty */ + b = smallbin_at(gm, idx); + p = b->fd; + assert(chunksize(p) == small_index2size(idx)); + unlink_first_small_chunk(gm, b, p, idx); + set_inuse_and_pinuse(gm, p, small_index2size(idx)); + mem = chunk2mem(p); + check_malloced_chunk(gm, mem, nb); + goto postaction; + } + + else if (nb > gm->dvsize) { + if (smallbits != 0) { /* Use chunk in next nonempty smallbin */ + mchunkptr b, p, r; + size_t rsize; + bindex_t i; + binmap_t leftbits = (smallbits << idx) & left_bits(idx2bit(idx)); + binmap_t leastbit = least_bit(leftbits); + compute_bit2idx(leastbit, i); + b = smallbin_at(gm, i); + p = b->fd; + assert(chunksize(p) == small_index2size(i)); + unlink_first_small_chunk(gm, b, p, i); + rsize = small_index2size(i) - nb; + /* Fit here cannot be remainderless if 4byte sizes */ + if (SIZE_T_SIZE != 4 && rsize < MIN_CHUNK_SIZE) + set_inuse_and_pinuse(gm, p, small_index2size(i)); + else { + set_size_and_pinuse_of_inuse_chunk(gm, p, nb); + r = chunk_plus_offset(p, nb); + set_size_and_pinuse_of_free_chunk(r, rsize); + replace_dv(gm, r, rsize); + } + mem = chunk2mem(p); + check_malloced_chunk(gm, mem, nb); + goto postaction; + } + + else if (gm->treemap != 0 && (mem = tmalloc_small(gm, nb)) != 0) { + check_malloced_chunk(gm, mem, nb); + goto postaction; + } + } + } + else if (bytes >= MAX_REQUEST) + nb = MAX_SIZE_T; /* Too big to allocate. Force failure (in sys alloc) */ + else { + nb = pad_request(bytes); + if (gm->treemap != 0 && (mem = tmalloc_large(gm, nb)) != 0) { + check_malloced_chunk(gm, mem, nb); + goto postaction; + } + } + + if (nb <= gm->dvsize) { + size_t rsize = gm->dvsize - nb; + mchunkptr p = gm->dv; + if (rsize >= MIN_CHUNK_SIZE) { /* split dv */ + mchunkptr r = gm->dv = chunk_plus_offset(p, nb); + gm->dvsize = rsize; + set_size_and_pinuse_of_free_chunk(r, rsize); + set_size_and_pinuse_of_inuse_chunk(gm, p, nb); + } + else { /* exhaust dv */ + size_t dvs = gm->dvsize; + gm->dvsize = 0; + gm->dv = 0; + set_inuse_and_pinuse(gm, p, dvs); + } + mem = chunk2mem(p); + check_malloced_chunk(gm, mem, nb); + goto postaction; + } + + else if (nb < gm->topsize) { /* Split top */ + size_t rsize = gm->topsize -= nb; + mchunkptr p = gm->top; + mchunkptr r = gm->top = chunk_plus_offset(p, nb); + r->head = rsize | PINUSE_BIT; + set_size_and_pinuse_of_inuse_chunk(gm, p, nb); + mem = chunk2mem(p); + check_top_chunk(gm, gm->top); + check_malloced_chunk(gm, mem, nb); + goto postaction; + } + + mem = sys_alloc(gm, nb); + + postaction: + POSTACTION(gm); + return mem; + } + + return 0; +} + +void dlfree(void* mem) { + /* + Consolidate freed chunks with preceeding or succeeding bordering + free chunks, if they exist, and then place in a bin. Intermixed + with special cases for top, dv, mmapped chunks, and usage errors. + */ + + if (mem != 0) { + mchunkptr p = mem2chunk(mem); +#if FOOTERS + mstate fm = get_mstate_for(p); + if (!ok_magic(fm)) { + USAGE_ERROR_ACTION(fm, p); + return; + } +#else /* FOOTERS */ +#define fm gm +#endif /* FOOTERS */ + if (!PREACTION(fm)) { + check_inuse_chunk(fm, p); + if (RTCHECK(ok_address(fm, p) && ok_cinuse(p))) { + size_t psize = chunksize(p); + mchunkptr next = chunk_plus_offset(p, psize); + if (!pinuse(p)) { + size_t prevsize = p->prev_foot; + if ((prevsize & IS_MMAPPED_BIT) != 0) { + prevsize &= ~IS_MMAPPED_BIT; + psize += prevsize + MMAP_FOOT_PAD; + if (CALL_MUNMAP((char*)p - prevsize, psize) == 0) + fm->footprint -= psize; + goto postaction; + } + else { + mchunkptr prev = chunk_minus_offset(p, prevsize); + psize += prevsize; + p = prev; + if (RTCHECK(ok_address(fm, prev))) { /* consolidate backward */ + if (p != fm->dv) { + unlink_chunk(fm, p, prevsize); + } + else if ((next->head & INUSE_BITS) == INUSE_BITS) { + fm->dvsize = psize; + set_free_with_pinuse(p, psize, next); + goto postaction; + } + } + else + goto erroraction; + } + } + + if (RTCHECK(ok_next(p, next) && ok_pinuse(next))) { + if (!cinuse(next)) { /* consolidate forward */ + if (next == fm->top) { + size_t tsize = fm->topsize += psize; + fm->top = p; + p->head = tsize | PINUSE_BIT; + if (p == fm->dv) { + fm->dv = 0; + fm->dvsize = 0; + } + if (should_trim(fm, tsize)) + sys_trim(fm, 0); + goto postaction; + } + else if (next == fm->dv) { + size_t dsize = fm->dvsize += psize; + fm->dv = p; + set_size_and_pinuse_of_free_chunk(p, dsize); + goto postaction; + } + else { + size_t nsize = chunksize(next); + psize += nsize; + unlink_chunk(fm, next, nsize); + set_size_and_pinuse_of_free_chunk(p, psize); + if (p == fm->dv) { + fm->dvsize = psize; + goto postaction; + } + } + } + else + set_free_with_pinuse(p, psize, next); + + if (is_small(psize)) { + insert_small_chunk(fm, p, psize); + check_free_chunk(fm, p); + } + else { + tchunkptr tp = (tchunkptr)p; + insert_large_chunk(fm, tp, psize); + check_free_chunk(fm, p); + if (--fm->release_checks == 0) + release_unused_segments(fm); + } + goto postaction; + } + } + erroraction: + USAGE_ERROR_ACTION(fm, p); + postaction: + POSTACTION(fm); + } + } +#if !FOOTERS +#undef fm +#endif /* FOOTERS */ +} + +void* dlcalloc(size_t n_elements, size_t elem_size) { + void* mem; + size_t req = 0; + if (n_elements != 0) { + req = n_elements * elem_size; + if (((n_elements | elem_size) & ~(size_t)0xffff) && + (req / n_elements != elem_size)) + req = MAX_SIZE_T; /* force downstream failure on overflow */ + } + mem = dlmalloc(req); + if (mem != 0 && calloc_must_clear(mem2chunk(mem))) + memset(mem, 0, req); + return mem; +} + +void* dlrealloc(void* oldmem, size_t bytes) { + if (oldmem == 0) + return dlmalloc(bytes); +#ifdef REALLOC_ZERO_BYTES_FREES + if (bytes == 0) { + dlfree(oldmem); + return 0; + } +#endif /* REALLOC_ZERO_BYTES_FREES */ + else { +#if ! FOOTERS + mstate m = gm; +#else /* FOOTERS */ + mstate m = get_mstate_for(mem2chunk(oldmem)); + if (!ok_magic(m)) { + USAGE_ERROR_ACTION(m, oldmem); + return 0; + } +#endif /* FOOTERS */ + return internal_realloc(m, oldmem, bytes); + } +} + +void* dlmemalign(size_t alignment, size_t bytes) { + return internal_memalign(gm, alignment, bytes); +} + +void** dlindependent_calloc(size_t n_elements, size_t elem_size, + void* chunks[]) { + size_t sz = elem_size; /* serves as 1-element array */ + return ialloc(gm, n_elements, &sz, 3, chunks); +} + +void** dlindependent_comalloc(size_t n_elements, size_t sizes[], + void* chunks[]) { + return ialloc(gm, n_elements, sizes, 0, chunks); +} + +void* dlvalloc(size_t bytes) { + size_t pagesz; + ensure_initialization(); + pagesz = mparams.page_size; + return dlmemalign(pagesz, bytes); +} + +void* dlpvalloc(size_t bytes) { + size_t pagesz; + ensure_initialization(); + pagesz = mparams.page_size; + return dlmemalign(pagesz, (bytes + pagesz - SIZE_T_ONE) & ~(pagesz - SIZE_T_ONE)); +} + +int dlmalloc_trim(size_t pad) { + ensure_initialization(); + int result = 0; + if (!PREACTION(gm)) { + result = sys_trim(gm, pad); + POSTACTION(gm); + } + return result; +} + +size_t dlmalloc_footprint(void) { + return gm->footprint; +} + +size_t dlmalloc_max_footprint(void) { + return gm->max_footprint; +} + +#if !NO_MALLINFO +struct mallinfo dlmallinfo(void) { + return internal_mallinfo(gm); +} +#endif /* NO_MALLINFO */ + +void dlmalloc_stats() { + internal_malloc_stats(gm); +} + +int dlmallopt(int param_number, int value) { + return change_mparam(param_number, value); +} + +#endif /* !ONLY_MSPACES */ + +size_t dlmalloc_usable_size(void* mem) { + if (mem != 0) { + mchunkptr p = mem2chunk(mem); + if (cinuse(p)) + return chunksize(p) - overhead_for(p); + } + return 0; +} + +/* ----------------------------- user mspaces ---------------------------- */ + +#if MSPACES + +static mstate init_user_mstate(char* tbase, size_t tsize) { + size_t msize = pad_request(sizeof(struct malloc_state)); + mchunkptr mn; + mchunkptr msp = align_as_chunk(tbase); + mstate m = (mstate)(chunk2mem(msp)); + memset(m, 0, msize); + INITIAL_LOCK(&m->mutex); + msp->head = (msize|PINUSE_BIT|CINUSE_BIT); + m->seg.base = m->least_addr = tbase; + m->seg.size = m->footprint = m->max_footprint = tsize; + m->magic = mparams.magic; + m->release_checks = MAX_RELEASE_CHECK_RATE; + m->mflags = mparams.default_mflags; + m->extp = 0; + m->exts = 0; + disable_contiguous(m); + init_bins(m); + mn = next_chunk(mem2chunk(m)); + init_top(m, mn, (size_t)((tbase + tsize) - (char*)mn) - TOP_FOOT_SIZE); + check_top_chunk(m, m->top); + return m; +} + +mspace create_mspace(size_t capacity, int locked) { + mstate m = 0; + size_t msize; + ensure_initialization(); + msize = pad_request(sizeof(struct malloc_state)); + if (capacity < (size_t) -(msize + TOP_FOOT_SIZE + mparams.page_size)) { + size_t rs = ((capacity == 0)? mparams.granularity : + (capacity + TOP_FOOT_SIZE + msize)); + size_t tsize = granularity_align(rs); + char* tbase = (char*)(CALL_MMAP(tsize)); + if (tbase != CMFAIL) { + m = init_user_mstate(tbase, tsize); + m->seg.sflags = IS_MMAPPED_BIT; + set_lock(m, locked); + } + } + return (mspace)m; +} + +mspace create_mspace_with_base(void* base, size_t capacity, int locked) { + mstate m = 0; + size_t msize; + ensure_initialization(); + msize = pad_request(sizeof(struct malloc_state)); + if (capacity > msize + TOP_FOOT_SIZE && + capacity < (size_t) -(msize + TOP_FOOT_SIZE + mparams.page_size)) { + m = init_user_mstate((char*)base, capacity); + m->seg.sflags = EXTERN_BIT; + set_lock(m, locked); + } + return (mspace)m; +} + +int mspace_mmap_large_chunks(mspace msp, int enable) { + int ret = 0; + mstate ms = (mstate)msp; + if (!PREACTION(ms)) { + if (use_mmap(ms)) + ret = 1; + if (enable) + enable_mmap(ms); + else + disable_mmap(ms); + POSTACTION(ms); + } + return ret; +} + +size_t destroy_mspace(mspace msp) { + size_t freed = 0; + mstate ms = (mstate)msp; + if (ok_magic(ms)) { + msegmentptr sp = &ms->seg; + while (sp != 0) { + char* base = sp->base; + size_t size = sp->size; + flag_t flag = sp->sflags; + sp = sp->next; + if ((flag & IS_MMAPPED_BIT) && !(flag & EXTERN_BIT) && + CALL_MUNMAP(base, size) == 0) + freed += size; + } + } + else { + USAGE_ERROR_ACTION(ms,ms); + } + return freed; +} + +/* + mspace versions of routines are near-clones of the global + versions. This is not so nice but better than the alternatives. +*/ + + +void* mspace_malloc(mspace msp, size_t bytes) { + mstate ms = (mstate)msp; + if (!ok_magic(ms)) { + USAGE_ERROR_ACTION(ms,ms); + return 0; + } + if (!PREACTION(ms)) { + void* mem; + size_t nb; + if (bytes <= MAX_SMALL_REQUEST) { + bindex_t idx; + binmap_t smallbits; + nb = (bytes < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(bytes); + idx = small_index(nb); + smallbits = ms->smallmap >> idx; + + if ((smallbits & 0x3U) != 0) { /* Remainderless fit to a smallbin. */ + mchunkptr b, p; + idx += ~smallbits & 1; /* Uses next bin if idx empty */ + b = smallbin_at(ms, idx); + p = b->fd; + assert(chunksize(p) == small_index2size(idx)); + unlink_first_small_chunk(ms, b, p, idx); + set_inuse_and_pinuse(ms, p, small_index2size(idx)); + mem = chunk2mem(p); + check_malloced_chunk(ms, mem, nb); + goto postaction; + } + + else if (nb > ms->dvsize) { + if (smallbits != 0) { /* Use chunk in next nonempty smallbin */ + mchunkptr b, p, r; + size_t rsize; + bindex_t i; + binmap_t leftbits = (smallbits << idx) & left_bits(idx2bit(idx)); + binmap_t leastbit = least_bit(leftbits); + compute_bit2idx(leastbit, i); + b = smallbin_at(ms, i); + p = b->fd; + assert(chunksize(p) == small_index2size(i)); + unlink_first_small_chunk(ms, b, p, i); + rsize = small_index2size(i) - nb; + /* Fit here cannot be remainderless if 4byte sizes */ + if (SIZE_T_SIZE != 4 && rsize < MIN_CHUNK_SIZE) + set_inuse_and_pinuse(ms, p, small_index2size(i)); + else { + set_size_and_pinuse_of_inuse_chunk(ms, p, nb); + r = chunk_plus_offset(p, nb); + set_size_and_pinuse_of_free_chunk(r, rsize); + replace_dv(ms, r, rsize); + } + mem = chunk2mem(p); + check_malloced_chunk(ms, mem, nb); + goto postaction; + } + + else if (ms->treemap != 0 && (mem = tmalloc_small(ms, nb)) != 0) { + check_malloced_chunk(ms, mem, nb); + goto postaction; + } + } + } + else if (bytes >= MAX_REQUEST) + nb = MAX_SIZE_T; /* Too big to allocate. Force failure (in sys alloc) */ + else { + nb = pad_request(bytes); + if (ms->treemap != 0 && (mem = tmalloc_large(ms, nb)) != 0) { + check_malloced_chunk(ms, mem, nb); + goto postaction; + } + } + + if (nb <= ms->dvsize) { + size_t rsize = ms->dvsize - nb; + mchunkptr p = ms->dv; + if (rsize >= MIN_CHUNK_SIZE) { /* split dv */ + mchunkptr r = ms->dv = chunk_plus_offset(p, nb); + ms->dvsize = rsize; + set_size_and_pinuse_of_free_chunk(r, rsize); + set_size_and_pinuse_of_inuse_chunk(ms, p, nb); + } + else { /* exhaust dv */ + size_t dvs = ms->dvsize; + ms->dvsize = 0; + ms->dv = 0; + set_inuse_and_pinuse(ms, p, dvs); + } + mem = chunk2mem(p); + check_malloced_chunk(ms, mem, nb); + goto postaction; + } + + else if (nb < ms->topsize) { /* Split top */ + size_t rsize = ms->topsize -= nb; + mchunkptr p = ms->top; + mchunkptr r = ms->top = chunk_plus_offset(p, nb); + r->head = rsize | PINUSE_BIT; + set_size_and_pinuse_of_inuse_chunk(ms, p, nb); + mem = chunk2mem(p); + check_top_chunk(ms, ms->top); + check_malloced_chunk(ms, mem, nb); + goto postaction; + } + + mem = sys_alloc(ms, nb); + + postaction: + POSTACTION(ms); + return mem; + } + + return 0; +} + +void mspace_free(mspace msp, void* mem) { + if (mem != 0) { + mchunkptr p = mem2chunk(mem); +#if FOOTERS + mstate fm = get_mstate_for(p); +#else /* FOOTERS */ + mstate fm = (mstate)msp; +#endif /* FOOTERS */ + if (!ok_magic(fm)) { + USAGE_ERROR_ACTION(fm, p); + return; + } + if (!PREACTION(fm)) { + check_inuse_chunk(fm, p); + if (RTCHECK(ok_address(fm, p) && ok_cinuse(p))) { + size_t psize = chunksize(p); + mchunkptr next = chunk_plus_offset(p, psize); + if (!pinuse(p)) { + size_t prevsize = p->prev_foot; + if ((prevsize & IS_MMAPPED_BIT) != 0) { + prevsize &= ~IS_MMAPPED_BIT; + psize += prevsize + MMAP_FOOT_PAD; + if (CALL_MUNMAP((char*)p - prevsize, psize) == 0) + fm->footprint -= psize; + goto postaction; + } + else { + mchunkptr prev = chunk_minus_offset(p, prevsize); + psize += prevsize; + p = prev; + if (RTCHECK(ok_address(fm, prev))) { /* consolidate backward */ + if (p != fm->dv) { + unlink_chunk(fm, p, prevsize); + } + else if ((next->head & INUSE_BITS) == INUSE_BITS) { + fm->dvsize = psize; + set_free_with_pinuse(p, psize, next); + goto postaction; + } + } + else + goto erroraction; + } + } + + if (RTCHECK(ok_next(p, next) && ok_pinuse(next))) { + if (!cinuse(next)) { /* consolidate forward */ + if (next == fm->top) { + size_t tsize = fm->topsize += psize; + fm->top = p; + p->head = tsize | PINUSE_BIT; + if (p == fm->dv) { + fm->dv = 0; + fm->dvsize = 0; + } + if (should_trim(fm, tsize)) + sys_trim(fm, 0); + goto postaction; + } + else if (next == fm->dv) { + size_t dsize = fm->dvsize += psize; + fm->dv = p; + set_size_and_pinuse_of_free_chunk(p, dsize); + goto postaction; + } + else { + size_t nsize = chunksize(next); + psize += nsize; + unlink_chunk(fm, next, nsize); + set_size_and_pinuse_of_free_chunk(p, psize); + if (p == fm->dv) { + fm->dvsize = psize; + goto postaction; + } + } + } + else + set_free_with_pinuse(p, psize, next); + + if (is_small(psize)) { + insert_small_chunk(fm, p, psize); + check_free_chunk(fm, p); + } + else { + tchunkptr tp = (tchunkptr)p; + insert_large_chunk(fm, tp, psize); + check_free_chunk(fm, p); + if (--fm->release_checks == 0) + release_unused_segments(fm); + } + goto postaction; + } + } + erroraction: + USAGE_ERROR_ACTION(fm, p); + postaction: + POSTACTION(fm); + } + } +} + +void* mspace_calloc(mspace msp, size_t n_elements, size_t elem_size) { + void* mem; + size_t req = 0; + mstate ms = (mstate)msp; + if (!ok_magic(ms)) { + USAGE_ERROR_ACTION(ms,ms); + return 0; + } + if (n_elements != 0) { + req = n_elements * elem_size; + if (((n_elements | elem_size) & ~(size_t)0xffff) && + (req / n_elements != elem_size)) + req = MAX_SIZE_T; /* force downstream failure on overflow */ + } + mem = internal_malloc(ms, req); + if (mem != 0 && calloc_must_clear(mem2chunk(mem))) + memset(mem, 0, req); + return mem; +} + +void* mspace_realloc(mspace msp, void* oldmem, size_t bytes) { + if (oldmem == 0) + return mspace_malloc(msp, bytes); +#ifdef REALLOC_ZERO_BYTES_FREES + if (bytes == 0) { + mspace_free(msp, oldmem); + return 0; + } +#endif /* REALLOC_ZERO_BYTES_FREES */ + else { +#if FOOTERS + mchunkptr p = mem2chunk(oldmem); + mstate ms = get_mstate_for(p); +#else /* FOOTERS */ + mstate ms = (mstate)msp; +#endif /* FOOTERS */ + if (!ok_magic(ms)) { + USAGE_ERROR_ACTION(ms,ms); + return 0; + } + return internal_realloc(ms, oldmem, bytes); + } +} + +void* mspace_memalign(mspace msp, size_t alignment, size_t bytes) { + mstate ms = (mstate)msp; + if (!ok_magic(ms)) { + USAGE_ERROR_ACTION(ms,ms); + return 0; + } + return internal_memalign(ms, alignment, bytes); +} + +void** mspace_independent_calloc(mspace msp, size_t n_elements, + size_t elem_size, void* chunks[]) { + size_t sz = elem_size; /* serves as 1-element array */ + mstate ms = (mstate)msp; + if (!ok_magic(ms)) { + USAGE_ERROR_ACTION(ms,ms); + return 0; + } + return ialloc(ms, n_elements, &sz, 3, chunks); +} + +void** mspace_independent_comalloc(mspace msp, size_t n_elements, + size_t sizes[], void* chunks[]) { + mstate ms = (mstate)msp; + if (!ok_magic(ms)) { + USAGE_ERROR_ACTION(ms,ms); + return 0; + } + return ialloc(ms, n_elements, sizes, 0, chunks); +} + +int mspace_trim(mspace msp, size_t pad) { + int result = 0; + mstate ms = (mstate)msp; + if (ok_magic(ms)) { + if (!PREACTION(ms)) { + result = sys_trim(ms, pad); + POSTACTION(ms); + } + } + else { + USAGE_ERROR_ACTION(ms,ms); + } + return result; +} + +void mspace_malloc_stats(mspace msp) { + mstate ms = (mstate)msp; + if (ok_magic(ms)) { + internal_malloc_stats(ms); + } + else { + USAGE_ERROR_ACTION(ms,ms); + } +} + +size_t mspace_footprint(mspace msp) { + size_t result = 0; + mstate ms = (mstate)msp; + if (ok_magic(ms)) { + result = ms->footprint; + } + else { + USAGE_ERROR_ACTION(ms,ms); + } + return result; +} + + +size_t mspace_max_footprint(mspace msp) { + size_t result = 0; + mstate ms = (mstate)msp; + if (ok_magic(ms)) { + result = ms->max_footprint; + } + else { + USAGE_ERROR_ACTION(ms,ms); + } + return result; +} + + +#if !NO_MALLINFO +struct mallinfo mspace_mallinfo(mspace msp) { + mstate ms = (mstate)msp; + if (!ok_magic(ms)) { + USAGE_ERROR_ACTION(ms,ms); + } + return internal_mallinfo(ms); +} +#endif /* NO_MALLINFO */ + +size_t mspace_usable_size(void* mem) { + if (mem != 0) { + mchunkptr p = mem2chunk(mem); + if (cinuse(p)) + return chunksize(p) - overhead_for(p); + } + return 0; +} + +int mspace_mallopt(int param_number, int value) { + return change_mparam(param_number, value); +} + +#endif /* MSPACES */ + +/* -------------------- Alternative MORECORE functions ------------------- */ + +/* + Guidelines for creating a custom version of MORECORE: + + * For best performance, MORECORE should allocate in multiples of pagesize. + * MORECORE may allocate more memory than requested. (Or even less, + but this will usually result in a malloc failure.) + * MORECORE must not allocate memory when given argument zero, but + instead return one past the end address of memory from previous + nonzero call. + * For best performance, consecutive calls to MORECORE with positive + arguments should return increasing addresses, indicating that + space has been contiguously extended. + * Even though consecutive calls to MORECORE need not return contiguous + addresses, it must be OK for malloc'ed chunks to span multiple + regions in those cases where they do happen to be contiguous. + * MORECORE need not handle negative arguments -- it may instead + just return MFAIL when given negative arguments. + Negative arguments are always multiples of pagesize. MORECORE + must not misinterpret negative args as large positive unsigned + args. You can suppress all such calls from even occurring by defining + MORECORE_CANNOT_TRIM, + + As an example alternative MORECORE, here is a custom allocator + kindly contributed for pre-OSX macOS. It uses virtually but not + necessarily physically contiguous non-paged memory (locked in, + present and won't get swapped out). You can use it by uncommenting + this section, adding some #includes, and setting up the appropriate + defines above: + + #define MORECORE osMoreCore + + There is also a shutdown routine that should somehow be called for + cleanup upon program exit. + + #define MAX_POOL_ENTRIES 100 + #define MINIMUM_MORECORE_SIZE (64 * 1024U) + static int next_os_pool; + void *our_os_pools[MAX_POOL_ENTRIES]; + + void *osMoreCore(int size) + { + void *ptr = 0; + static void *sbrk_top = 0; + + if (size > 0) + { + if (size < MINIMUM_MORECORE_SIZE) + size = MINIMUM_MORECORE_SIZE; + if (CurrentExecutionLevel() == kTaskLevel) + ptr = PoolAllocateResident(size + RM_PAGE_SIZE, 0); + if (ptr == 0) + { + return (void *) MFAIL; + } + // save ptrs so they can be freed during cleanup + our_os_pools[next_os_pool] = ptr; + next_os_pool++; + ptr = (void *) ((((size_t) ptr) + RM_PAGE_MASK) & ~RM_PAGE_MASK); + sbrk_top = (char *) ptr + size; + return ptr; + } + else if (size < 0) + { + // we don't currently support shrink behavior + return (void *) MFAIL; + } + else + { + return sbrk_top; + } + } + + // cleanup any allocated memory pools + // called as last thing before shutting down driver + + void osCleanupMem(void) + { + void **ptr; + + for (ptr = our_os_pools; ptr < &our_os_pools[MAX_POOL_ENTRIES]; ptr++) + if (*ptr) + { + PoolDeallocate(*ptr); + *ptr = 0; + } + } + +*/ + + +/* ----------------------------------------------------------------------- +History: + V2.8.4 (not yet released) + * Add mspace_mmap_large_chunks; thanks to Jean Brouwers + * Fix insufficient sys_alloc padding when using 16byte alignment + * Fix bad error check in mspace_footprint + * Adaptations for ptmalloc, courtesy of Wolfram Gloger. + * Reentrant spin locks, courtesy of Earl Chew and others + * Win32 improvements, courtesy of Niall Douglas and Earl Chew + * Add NO_SEGMENT_TRAVERSAL and MAX_RELEASE_CHECK_RATE options + * Extension hook in malloc_state + * Various small adjustments to reduce warnings on some compilers + * Various configuration extensions/changes for more platforms. Thanks + to all who contributed these. + + V2.8.3 Thu Sep 22 11:16:32 2005 Doug Lea (dl at gee) + * Add max_footprint functions + * Ensure all appropriate literals are size_t + * Fix conditional compilation problem for some #define settings + * Avoid concatenating segments with the one provided + in create_mspace_with_base + * Rename some variables to avoid compiler shadowing warnings + * Use explicit lock initialization. + * Better handling of sbrk interference. + * Simplify and fix segment insertion, trimming and mspace_destroy + * Reinstate REALLOC_ZERO_BYTES_FREES option from 2.7.x + * Thanks especially to Dennis Flanagan for help on these. + + V2.8.2 Sun Jun 12 16:01:10 2005 Doug Lea (dl at gee) + * Fix memalign brace error. + + V2.8.1 Wed Jun 8 16:11:46 2005 Doug Lea (dl at gee) + * Fix improper #endif nesting in C++ + * Add explicit casts needed for C++ + + V2.8.0 Mon May 30 14:09:02 2005 Doug Lea (dl at gee) + * Use trees for large bins + * Support mspaces + * Use segments to unify sbrk-based and mmap-based system allocation, + removing need for emulation on most platforms without sbrk. + * Default safety checks + * Optional footer checks. Thanks to William Robertson for the idea. + * Internal code refactoring + * Incorporate suggestions and platform-specific changes. + Thanks to Dennis Flanagan, Colin Plumb, Niall Douglas, + Aaron Bachmann, Emery Berger, and others. + * Speed up non-fastbin processing enough to remove fastbins. + * Remove useless cfree() to avoid conflicts with other apps. + * Remove internal memcpy, memset. Compilers handle builtins better. + * Remove some options that no one ever used and rename others. + + V2.7.2 Sat Aug 17 09:07:30 2002 Doug Lea (dl at gee) + * Fix malloc_state bitmap array misdeclaration + + V2.7.1 Thu Jul 25 10:58:03 2002 Doug Lea (dl at gee) + * Allow tuning of FIRST_SORTED_BIN_SIZE + * Use PTR_UINT as type for all ptr->int casts. Thanks to John Belmonte. + * Better detection and support for non-contiguousness of MORECORE. + Thanks to Andreas Mueller, Conal Walsh, and Wolfram Gloger + * Bypass most of malloc if no frees. Thanks To Emery Berger. + * Fix freeing of old top non-contiguous chunk im sysmalloc. + * Raised default trim and map thresholds to 256K. + * Fix mmap-related #defines. Thanks to Lubos Lunak. + * Fix copy macros; added LACKS_FCNTL_H. Thanks to Neal Walfield. + * Branch-free bin calculation + * Default trim and mmap thresholds now 256K. + + V2.7.0 Sun Mar 11 14:14:06 2001 Doug Lea (dl at gee) + * Introduce independent_comalloc and independent_calloc. + Thanks to Michael Pachos for motivation and help. + * Make optional .h file available + * Allow > 2GB requests on 32bit systems. + * new WIN32 sbrk, mmap, munmap, lock code from <Walter@GeNeSys-e.de>. + Thanks also to Andreas Mueller <a.mueller at paradatec.de>, + and Anonymous. + * Allow override of MALLOC_ALIGNMENT (Thanks to Ruud Waij for + helping test this.) + * memalign: check alignment arg + * realloc: don't try to shift chunks backwards, since this + leads to more fragmentation in some programs and doesn't + seem to help in any others. + * Collect all cases in malloc requiring system memory into sysmalloc + * Use mmap as backup to sbrk + * Place all internal state in malloc_state + * Introduce fastbins (although similar to 2.5.1) + * Many minor tunings and cosmetic improvements + * Introduce USE_PUBLIC_MALLOC_WRAPPERS, USE_MALLOC_LOCK + * Introduce MALLOC_FAILURE_ACTION, MORECORE_CONTIGUOUS + Thanks to Tony E. Bennett <tbennett@nvidia.com> and others. + * Include errno.h to support default failure action. + + V2.6.6 Sun Dec 5 07:42:19 1999 Doug Lea (dl at gee) + * return null for negative arguments + * Added Several WIN32 cleanups from Martin C. Fong <mcfong at yahoo.com> + * Add 'LACKS_SYS_PARAM_H' for those systems without 'sys/param.h' + (e.g. WIN32 platforms) + * Cleanup header file inclusion for WIN32 platforms + * Cleanup code to avoid Microsoft Visual C++ compiler complaints + * Add 'USE_DL_PREFIX' to quickly allow co-existence with existing + memory allocation routines + * Set 'malloc_getpagesize' for WIN32 platforms (needs more work) + * Use 'assert' rather than 'ASSERT' in WIN32 code to conform to + usage of 'assert' in non-WIN32 code + * Improve WIN32 'sbrk()' emulation's 'findRegion()' routine to + avoid infinite loop + * Always call 'fREe()' rather than 'free()' + + V2.6.5 Wed Jun 17 15:57:31 1998 Doug Lea (dl at gee) + * Fixed ordering problem with boundary-stamping + + V2.6.3 Sun May 19 08:17:58 1996 Doug Lea (dl at gee) + * Added pvalloc, as recommended by H.J. Liu + * Added 64bit pointer support mainly from Wolfram Gloger + * Added anonymously donated WIN32 sbrk emulation + * Malloc, calloc, getpagesize: add optimizations from Raymond Nijssen + * malloc_extend_top: fix mask error that caused wastage after + foreign sbrks + * Add linux mremap support code from HJ Liu + + V2.6.2 Tue Dec 5 06:52:55 1995 Doug Lea (dl at gee) + * Integrated most documentation with the code. + * Add support for mmap, with help from + Wolfram Gloger (Gloger@lrz.uni-muenchen.de). + * Use last_remainder in more cases. + * Pack bins using idea from colin@nyx10.cs.du.edu + * Use ordered bins instead of best-fit threshhold + * Eliminate block-local decls to simplify tracing and debugging. + * Support another case of realloc via move into top + * Fix error occuring when initial sbrk_base not word-aligned. + * Rely on page size for units instead of SBRK_UNIT to + avoid surprises about sbrk alignment conventions. + * Add mallinfo, mallopt. Thanks to Raymond Nijssen + (raymond@es.ele.tue.nl) for the suggestion. + * Add `pad' argument to malloc_trim and top_pad mallopt parameter. + * More precautions for cases where other routines call sbrk, + courtesy of Wolfram Gloger (Gloger@lrz.uni-muenchen.de). + * Added macros etc., allowing use in linux libc from + H.J. Lu (hjl@gnu.ai.mit.edu) + * Inverted this history list + + V2.6.1 Sat Dec 2 14:10:57 1995 Doug Lea (dl at gee) + * Re-tuned and fixed to behave more nicely with V2.6.0 changes. + * Removed all preallocation code since under current scheme + the work required to undo bad preallocations exceeds + the work saved in good cases for most test programs. + * No longer use return list or unconsolidated bins since + no scheme using them consistently outperforms those that don't + given above changes. + * Use best fit for very large chunks to prevent some worst-cases. + * Added some support for debugging + + V2.6.0 Sat Nov 4 07:05:23 1995 Doug Lea (dl at gee) + * Removed footers when chunks are in use. Thanks to + Paul Wilson (wilson@cs.texas.edu) for the suggestion. + + V2.5.4 Wed Nov 1 07:54:51 1995 Doug Lea (dl at gee) + * Added malloc_trim, with help from Wolfram Gloger + (wmglo@Dent.MED.Uni-Muenchen.DE). + + V2.5.3 Tue Apr 26 10:16:01 1994 Doug Lea (dl at g) + + V2.5.2 Tue Apr 5 16:20:40 1994 Doug Lea (dl at g) + * realloc: try to expand in both directions + * malloc: swap order of clean-bin strategy; + * realloc: only conditionally expand backwards + * Try not to scavenge used bins + * Use bin counts as a guide to preallocation + * Occasionally bin return list chunks in first scan + * Add a few optimizations from colin@nyx10.cs.du.edu + + V2.5.1 Sat Aug 14 15:40:43 1993 Doug Lea (dl at g) + * faster bin computation & slightly different binning + * merged all consolidations to one part of malloc proper + (eliminating old malloc_find_space & malloc_clean_bin) + * Scan 2 returns chunks (not just 1) + * Propagate failure in realloc if malloc returns 0 + * Add stuff to allow compilation on non-ANSI compilers + from kpv@research.att.com + + V2.5 Sat Aug 7 07:41:59 1993 Doug Lea (dl at g.oswego.edu) + * removed potential for odd address access in prev_chunk + * removed dependency on getpagesize.h + * misc cosmetics and a bit more internal documentation + * anticosmetics: mangled names in macros to evade debugger strangeness + * tested on sparc, hp-700, dec-mips, rs6000 + with gcc & native cc (hp, dec only) allowing + Detlefs & Zorn comparison study (in SIGPLAN Notices.) + + Trial version Fri Aug 28 13:14:29 1992 Doug Lea (dl at g.oswego.edu) + * Based loosely on libg++-1.2X malloc. (It retains some of the overall + structure of old version, but most details differ.) + +*/ + + diff --git a/compat/nedmalloc/nedmalloc.c b/compat/nedmalloc/nedmalloc.c new file mode 100644 index 0000000000..d9a17a8057 --- /dev/null +++ b/compat/nedmalloc/nedmalloc.c @@ -0,0 +1,966 @@ +/* Alternative malloc implementation for multiple threads without +lock contention based on dlmalloc. (C) 2005-2006 Niall Douglas + +Boost Software License - Version 1.0 - August 17th, 2003 + +Permission is hereby granted, free of charge, to any person or organization +obtaining a copy of the software and accompanying documentation covered by +this license (the "Software") to use, reproduce, display, distribute, +execute, and transmit the Software, and to prepare derivative works of the +Software, and to permit third-parties to whom the Software is furnished to +do so, all subject to the following: + +The copyright notices in the Software and this entire statement, including +the above license grant, this restriction and the following disclaimer, +must be included in all copies of the Software, in whole or in part, and +all derivative works of the Software, unless such copies or derivative +works are solely in the form of machine-executable object code generated by +a source language processor. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT +SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE +FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE, +ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER +DEALINGS IN THE SOFTWARE. +*/ + +#ifdef _MSC_VER +/* Enable full aliasing on MSVC */ +/*#pragma optimize("a", on)*/ +#endif + +/*#define FULLSANITYCHECKS*/ + +#include "nedmalloc.h" +#if defined(WIN32) + #include <malloc.h> +#endif +#define MSPACES 1 +#define ONLY_MSPACES 1 +#ifndef USE_LOCKS + #define USE_LOCKS 1 +#endif +#define FOOTERS 1 /* Need to enable footers so frees lock the right mspace */ +#undef DEBUG /* dlmalloc wants DEBUG either 0 or 1 */ +#ifdef _DEBUG + #define DEBUG 1 +#else + #define DEBUG 0 +#endif +#ifdef NDEBUG /* Disable assert checking on release builds */ + #undef DEBUG +#endif +/* The default of 64Kb means we spend too much time kernel-side */ +#ifndef DEFAULT_GRANULARITY +#define DEFAULT_GRANULARITY (1*1024*1024) +#endif +/*#define USE_SPIN_LOCKS 0*/ + + +/*#define FORCEINLINE*/ +#include "malloc.c.h" +#ifdef NDEBUG /* Disable assert checking on release builds */ + #undef DEBUG +#endif + +/* The maximum concurrent threads in a pool possible */ +#ifndef MAXTHREADSINPOOL +#define MAXTHREADSINPOOL 16 +#endif +/* The maximum number of threadcaches which can be allocated */ +#ifndef THREADCACHEMAXCACHES +#define THREADCACHEMAXCACHES 256 +#endif +/* The maximum size to be allocated from the thread cache */ +#ifndef THREADCACHEMAX +#define THREADCACHEMAX 8192 +#endif +#if 0 +/* The number of cache entries for finer grained bins. This is (topbitpos(THREADCACHEMAX)-4)*2 */ +#define THREADCACHEMAXBINS ((13-4)*2) +#else +/* The number of cache entries. This is (topbitpos(THREADCACHEMAX)-4) */ +#define THREADCACHEMAXBINS (13-4) +#endif +/* Point at which the free space in a thread cache is garbage collected */ +#ifndef THREADCACHEMAXFREESPACE +#define THREADCACHEMAXFREESPACE (512*1024) +#endif + + +#ifdef WIN32 + #define TLSVAR DWORD + #define TLSALLOC(k) (*(k)=TlsAlloc(), TLS_OUT_OF_INDEXES==*(k)) + #define TLSFREE(k) (!TlsFree(k)) + #define TLSGET(k) TlsGetValue(k) + #define TLSSET(k, a) (!TlsSetValue(k, a)) + #ifdef DEBUG +static LPVOID ChkedTlsGetValue(DWORD idx) +{ + LPVOID ret=TlsGetValue(idx); + assert(S_OK==GetLastError()); + return ret; +} + #undef TLSGET + #define TLSGET(k) ChkedTlsGetValue(k) + #endif +#else + #define TLSVAR pthread_key_t + #define TLSALLOC(k) pthread_key_create(k, 0) + #define TLSFREE(k) pthread_key_delete(k) + #define TLSGET(k) pthread_getspecific(k) + #define TLSSET(k, a) pthread_setspecific(k, a) +#endif + +#if 0 +/* Only enable if testing with valgrind. Causes misoperation */ +#define mspace_malloc(p, s) malloc(s) +#define mspace_realloc(p, m, s) realloc(m, s) +#define mspace_calloc(p, n, s) calloc(n, s) +#define mspace_free(p, m) free(m) +#endif + + +#if defined(__cplusplus) +#if !defined(NO_NED_NAMESPACE) +namespace nedalloc { +#else +extern "C" { +#endif +#endif + +size_t nedblksize(void *mem) THROWSPEC +{ +#if 0 + /* Only enable if testing with valgrind. Causes misoperation */ + return THREADCACHEMAX; +#else + if(mem) + { + mchunkptr p=mem2chunk(mem); + assert(cinuse(p)); /* If this fails, someone tried to free a block twice */ + if(cinuse(p)) + return chunksize(p)-overhead_for(p); + } + return 0; +#endif +} + +void nedsetvalue(void *v) THROWSPEC { nedpsetvalue(0, v); } +void * nedmalloc(size_t size) THROWSPEC { return nedpmalloc(0, size); } +void * nedcalloc(size_t no, size_t size) THROWSPEC { return nedpcalloc(0, no, size); } +void * nedrealloc(void *mem, size_t size) THROWSPEC { return nedprealloc(0, mem, size); } +void nedfree(void *mem) THROWSPEC { nedpfree(0, mem); } +void * nedmemalign(size_t alignment, size_t bytes) THROWSPEC { return nedpmemalign(0, alignment, bytes); } +#if !NO_MALLINFO +struct mallinfo nedmallinfo(void) THROWSPEC { return nedpmallinfo(0); } +#endif +int nedmallopt(int parno, int value) THROWSPEC { return nedpmallopt(0, parno, value); } +int nedmalloc_trim(size_t pad) THROWSPEC { return nedpmalloc_trim(0, pad); } +void nedmalloc_stats() THROWSPEC { nedpmalloc_stats(0); } +size_t nedmalloc_footprint() THROWSPEC { return nedpmalloc_footprint(0); } +void **nedindependent_calloc(size_t elemsno, size_t elemsize, void **chunks) THROWSPEC { return nedpindependent_calloc(0, elemsno, elemsize, chunks); } +void **nedindependent_comalloc(size_t elems, size_t *sizes, void **chunks) THROWSPEC { return nedpindependent_comalloc(0, elems, sizes, chunks); } + +struct threadcacheblk_t; +typedef struct threadcacheblk_t threadcacheblk; +struct threadcacheblk_t +{ /* Keep less than 16 bytes on 32 bit systems and 32 bytes on 64 bit systems */ +#ifdef FULLSANITYCHECKS + unsigned int magic; +#endif + unsigned int lastUsed, size; + threadcacheblk *next, *prev; +}; +typedef struct threadcache_t +{ +#ifdef FULLSANITYCHECKS + unsigned int magic1; +#endif + int mymspace; /* Last mspace entry this thread used */ + long threadid; + unsigned int mallocs, frees, successes; + size_t freeInCache; /* How much free space is stored in this cache */ + threadcacheblk *bins[(THREADCACHEMAXBINS+1)*2]; +#ifdef FULLSANITYCHECKS + unsigned int magic2; +#endif +} threadcache; +struct nedpool_t +{ + MLOCK_T mutex; + void *uservalue; + int threads; /* Max entries in m to use */ + threadcache *caches[THREADCACHEMAXCACHES]; + TLSVAR mycache; /* Thread cache for this thread. 0 for unset, negative for use mspace-1 directly, otherwise is cache-1 */ + mstate m[MAXTHREADSINPOOL+1]; /* mspace entries for this pool */ +}; +static nedpool syspool; + +static FORCEINLINE unsigned int size2binidx(size_t _size) THROWSPEC +{ /* 8=1000 16=10000 20=10100 24=11000 32=100000 48=110000 4096=1000000000000 */ + unsigned int topbit, size=(unsigned int)(_size>>4); + /* 16=1 20=1 24=1 32=10 48=11 64=100 96=110 128=1000 4096=100000000 */ + +#if defined(__GNUC__) + topbit = sizeof(size)*__CHAR_BIT__ - 1 - __builtin_clz(size); +#elif defined(_MSC_VER) && _MSC_VER>=1300 + { + unsigned long bsrTopBit; + + _BitScanReverse(&bsrTopBit, size); + + topbit = bsrTopBit; + } +#else +#if 0 + union { + unsigned asInt[2]; + double asDouble; + }; + int n; + + asDouble = (double)size + 0.5; + topbit = (asInt[!FOX_BIGENDIAN] >> 20) - 1023; +#else + { + unsigned int x=size; + x = x | (x >> 1); + x = x | (x >> 2); + x = x | (x >> 4); + x = x | (x >> 8); + x = x | (x >>16); + x = ~x; + x = x - ((x >> 1) & 0x55555555); + x = (x & 0x33333333) + ((x >> 2) & 0x33333333); + x = (x + (x >> 4)) & 0x0F0F0F0F; + x = x + (x << 8); + x = x + (x << 16); + topbit=31 - (x >> 24); + } +#endif +#endif + return topbit; +} + + +#ifdef FULLSANITYCHECKS +static void tcsanitycheck(threadcacheblk **ptr) THROWSPEC +{ + assert((ptr[0] && ptr[1]) || (!ptr[0] && !ptr[1])); + if(ptr[0] && ptr[1]) + { + assert(nedblksize(ptr[0])>=sizeof(threadcacheblk)); + assert(nedblksize(ptr[1])>=sizeof(threadcacheblk)); + assert(*(unsigned int *) "NEDN"==ptr[0]->magic); + assert(*(unsigned int *) "NEDN"==ptr[1]->magic); + assert(!ptr[0]->prev); + assert(!ptr[1]->next); + if(ptr[0]==ptr[1]) + { + assert(!ptr[0]->next); + assert(!ptr[1]->prev); + } + } +} +static void tcfullsanitycheck(threadcache *tc) THROWSPEC +{ + threadcacheblk **tcbptr=tc->bins; + int n; + for(n=0; n<=THREADCACHEMAXBINS; n++, tcbptr+=2) + { + threadcacheblk *b, *ob=0; + tcsanitycheck(tcbptr); + for(b=tcbptr[0]; b; ob=b, b=b->next) + { + assert(*(unsigned int *) "NEDN"==b->magic); + assert(!ob || ob->next==b); + assert(!ob || b->prev==ob); + } + } +} +#endif + +static NOINLINE void RemoveCacheEntries(nedpool *p, threadcache *tc, unsigned int age) THROWSPEC +{ +#ifdef FULLSANITYCHECKS + tcfullsanitycheck(tc); +#endif + if(tc->freeInCache) + { + threadcacheblk **tcbptr=tc->bins; + int n; + for(n=0; n<=THREADCACHEMAXBINS; n++, tcbptr+=2) + { + threadcacheblk **tcb=tcbptr+1; /* come from oldest end of list */ + /*tcsanitycheck(tcbptr);*/ + for(; *tcb && tc->frees-(*tcb)->lastUsed>=age; ) + { + threadcacheblk *f=*tcb; + size_t blksize=f->size; /*nedblksize(f);*/ + assert(blksize<=nedblksize(f)); + assert(blksize); +#ifdef FULLSANITYCHECKS + assert(*(unsigned int *) "NEDN"==(*tcb)->magic); +#endif + *tcb=(*tcb)->prev; + if(*tcb) + (*tcb)->next=0; + else + *tcbptr=0; + tc->freeInCache-=blksize; + assert((long) tc->freeInCache>=0); + mspace_free(0, f); + /*tcsanitycheck(tcbptr);*/ + } + } + } +#ifdef FULLSANITYCHECKS + tcfullsanitycheck(tc); +#endif +} +static void DestroyCaches(nedpool *p) THROWSPEC +{ + if(p->caches) + { + threadcache *tc; + int n; + for(n=0; n<THREADCACHEMAXCACHES; n++) + { + if((tc=p->caches[n])) + { + tc->frees++; + RemoveCacheEntries(p, tc, 0); + assert(!tc->freeInCache); + tc->mymspace=-1; + tc->threadid=0; + mspace_free(0, tc); + p->caches[n]=0; + } + } + } +} + +static NOINLINE threadcache *AllocCache(nedpool *p) THROWSPEC +{ + threadcache *tc=0; + int n, end; + ACQUIRE_LOCK(&p->mutex); + for(n=0; n<THREADCACHEMAXCACHES && p->caches[n]; n++); + if(THREADCACHEMAXCACHES==n) + { /* List exhausted, so disable for this thread */ + RELEASE_LOCK(&p->mutex); + return 0; + } + tc=p->caches[n]=(threadcache *) mspace_calloc(p->m[0], 1, sizeof(threadcache)); + if(!tc) + { + RELEASE_LOCK(&p->mutex); + return 0; + } +#ifdef FULLSANITYCHECKS + tc->magic1=*(unsigned int *)"NEDMALC1"; + tc->magic2=*(unsigned int *)"NEDMALC2"; +#endif + tc->threadid=(long)(size_t)CURRENT_THREAD; + for(end=0; p->m[end]; end++); + tc->mymspace=tc->threadid % end; + RELEASE_LOCK(&p->mutex); + if(TLSSET(p->mycache, (void *)(size_t)(n+1))) abort(); + return tc; +} + +static void *threadcache_malloc(nedpool *p, threadcache *tc, size_t *size) THROWSPEC +{ + void *ret=0; + unsigned int bestsize; + unsigned int idx=size2binidx(*size); + size_t blksize=0; + threadcacheblk *blk, **binsptr; +#ifdef FULLSANITYCHECKS + tcfullsanitycheck(tc); +#endif + /* Calculate best fit bin size */ + bestsize=1<<(idx+4); +#if 0 + /* Finer grained bin fit */ + idx<<=1; + if(*size>bestsize) + { + idx++; + bestsize+=bestsize>>1; + } + if(*size>bestsize) + { + idx++; + bestsize=1<<(4+(idx>>1)); + } +#else + if(*size>bestsize) + { + idx++; + bestsize<<=1; + } +#endif + assert(bestsize>=*size); + if(*size<bestsize) *size=bestsize; + assert(*size<=THREADCACHEMAX); + assert(idx<=THREADCACHEMAXBINS); + binsptr=&tc->bins[idx*2]; + /* Try to match close, but move up a bin if necessary */ + blk=*binsptr; + if(!blk || blk->size<*size) + { /* Bump it up a bin */ + if(idx<THREADCACHEMAXBINS) + { + idx++; + binsptr+=2; + blk=*binsptr; + } + } + if(blk) + { + blksize=blk->size; /*nedblksize(blk);*/ + assert(nedblksize(blk)>=blksize); + assert(blksize>=*size); + if(blk->next) + blk->next->prev=0; + *binsptr=blk->next; + if(!*binsptr) + binsptr[1]=0; +#ifdef FULLSANITYCHECKS + blk->magic=0; +#endif + assert(binsptr[0]!=blk && binsptr[1]!=blk); + assert(nedblksize(blk)>=sizeof(threadcacheblk) && nedblksize(blk)<=THREADCACHEMAX+CHUNK_OVERHEAD); + /*printf("malloc: %p, %p, %p, %lu\n", p, tc, blk, (long) size);*/ + ret=(void *) blk; + } + ++tc->mallocs; + if(ret) + { + assert(blksize>=*size); + ++tc->successes; + tc->freeInCache-=blksize; + assert((long) tc->freeInCache>=0); + } +#if defined(DEBUG) && 0 + if(!(tc->mallocs & 0xfff)) + { + printf("*** threadcache=%u, mallocs=%u (%f), free=%u (%f), freeInCache=%u\n", (unsigned int) tc->threadid, tc->mallocs, + (float) tc->successes/tc->mallocs, tc->frees, (float) tc->successes/tc->frees, (unsigned int) tc->freeInCache); + } +#endif +#ifdef FULLSANITYCHECKS + tcfullsanitycheck(tc); +#endif + return ret; +} +static NOINLINE void ReleaseFreeInCache(nedpool *p, threadcache *tc, int mymspace) THROWSPEC +{ + unsigned int age=THREADCACHEMAXFREESPACE/8192; + /*ACQUIRE_LOCK(&p->m[mymspace]->mutex);*/ + while(age && tc->freeInCache>=THREADCACHEMAXFREESPACE) + { + RemoveCacheEntries(p, tc, age); + /*printf("*** Removing cache entries older than %u (%u)\n", age, (unsigned int) tc->freeInCache);*/ + age>>=1; + } + /*RELEASE_LOCK(&p->m[mymspace]->mutex);*/ +} +static void threadcache_free(nedpool *p, threadcache *tc, int mymspace, void *mem, size_t size) THROWSPEC +{ + unsigned int bestsize; + unsigned int idx=size2binidx(size); + threadcacheblk **binsptr, *tck=(threadcacheblk *) mem; + assert(size>=sizeof(threadcacheblk) && size<=THREADCACHEMAX+CHUNK_OVERHEAD); +#ifdef DEBUG + { /* Make sure this is a valid memory block */ + mchunkptr p = mem2chunk(mem); + mstate fm = get_mstate_for(p); + if (!ok_magic(fm)) { + USAGE_ERROR_ACTION(fm, p); + return; + } + } +#endif +#ifdef FULLSANITYCHECKS + tcfullsanitycheck(tc); +#endif + /* Calculate best fit bin size */ + bestsize=1<<(idx+4); +#if 0 + /* Finer grained bin fit */ + idx<<=1; + if(size>bestsize) + { + unsigned int biggerbestsize=bestsize+bestsize<<1; + if(size>=biggerbestsize) + { + idx++; + bestsize=biggerbestsize; + } + } +#endif + if(bestsize!=size) /* dlmalloc can round up, so we round down to preserve indexing */ + size=bestsize; + binsptr=&tc->bins[idx*2]; + assert(idx<=THREADCACHEMAXBINS); + if(tck==*binsptr) + { + fprintf(stderr, "Attempt to free already freed memory block %p - aborting!\n", tck); + abort(); + } +#ifdef FULLSANITYCHECKS + tck->magic=*(unsigned int *) "NEDN"; +#endif + tck->lastUsed=++tc->frees; + tck->size=(unsigned int) size; + tck->next=*binsptr; + tck->prev=0; + if(tck->next) + tck->next->prev=tck; + else + binsptr[1]=tck; + assert(!*binsptr || (*binsptr)->size==tck->size); + *binsptr=tck; + assert(tck==tc->bins[idx*2]); + assert(tc->bins[idx*2+1]==tck || binsptr[0]->next->prev==tck); + /*printf("free: %p, %p, %p, %lu\n", p, tc, mem, (long) size);*/ + tc->freeInCache+=size; +#ifdef FULLSANITYCHECKS + tcfullsanitycheck(tc); +#endif +#if 1 + if(tc->freeInCache>=THREADCACHEMAXFREESPACE) + ReleaseFreeInCache(p, tc, mymspace); +#endif +} + + + + +static NOINLINE int InitPool(nedpool *p, size_t capacity, int threads) THROWSPEC +{ /* threads is -1 for system pool */ + ensure_initialization(); + ACQUIRE_MALLOC_GLOBAL_LOCK(); + if(p->threads) goto done; + if(INITIAL_LOCK(&p->mutex)) goto err; + if(TLSALLOC(&p->mycache)) goto err; + if(!(p->m[0]=(mstate) create_mspace(capacity, 1))) goto err; + p->m[0]->extp=p; + p->threads=(threads<1 || threads>MAXTHREADSINPOOL) ? MAXTHREADSINPOOL : threads; +done: + RELEASE_MALLOC_GLOBAL_LOCK(); + return 1; +err: + if(threads<0) + abort(); /* If you can't allocate for system pool, we're screwed */ + DestroyCaches(p); + if(p->m[0]) + { + destroy_mspace(p->m[0]); + p->m[0]=0; + } + if(p->mycache) + { + if(TLSFREE(p->mycache)) abort(); + p->mycache=0; + } + RELEASE_MALLOC_GLOBAL_LOCK(); + return 0; +} +static NOINLINE mstate FindMSpace(nedpool *p, threadcache *tc, int *lastUsed, size_t size) THROWSPEC +{ /* Gets called when thread's last used mspace is in use. The strategy + is to run through the list of all available mspaces looking for an + unlocked one and if we fail, we create a new one so long as we don't + exceed p->threads */ + int n, end; + for(n=end=*lastUsed+1; p->m[n]; end=++n) + { + if(TRY_LOCK(&p->m[n]->mutex)) goto found; + } + for(n=0; n<*lastUsed && p->m[n]; n++) + { + if(TRY_LOCK(&p->m[n]->mutex)) goto found; + } + if(end<p->threads) + { + mstate temp; + if(!(temp=(mstate) create_mspace(size, 1))) + goto badexit; + /* Now we're ready to modify the lists, we lock */ + ACQUIRE_LOCK(&p->mutex); + while(p->m[end] && end<p->threads) + end++; + if(end>=p->threads) + { /* Drat, must destroy it now */ + RELEASE_LOCK(&p->mutex); + destroy_mspace((mspace) temp); + goto badexit; + } + /* We really want to make sure this goes into memory now but we + have to be careful of breaking aliasing rules, so write it twice */ + *((volatile struct malloc_state **) &p->m[end])=p->m[end]=temp; + ACQUIRE_LOCK(&p->m[end]->mutex); + /*printf("Created mspace idx %d\n", end);*/ + RELEASE_LOCK(&p->mutex); + n=end; + goto found; + } + /* Let it lock on the last one it used */ +badexit: + ACQUIRE_LOCK(&p->m[*lastUsed]->mutex); + return p->m[*lastUsed]; +found: + *lastUsed=n; + if(tc) + tc->mymspace=n; + else + { + if(TLSSET(p->mycache, (void *)(size_t)(-(n+1)))) abort(); + } + return p->m[n]; +} + +nedpool *nedcreatepool(size_t capacity, int threads) THROWSPEC +{ + nedpool *ret; + if(!(ret=(nedpool *) nedpcalloc(0, 1, sizeof(nedpool)))) return 0; + if(!InitPool(ret, capacity, threads)) + { + nedpfree(0, ret); + return 0; + } + return ret; +} +void neddestroypool(nedpool *p) THROWSPEC +{ + int n; + ACQUIRE_LOCK(&p->mutex); + DestroyCaches(p); + for(n=0; p->m[n]; n++) + { + destroy_mspace(p->m[n]); + p->m[n]=0; + } + RELEASE_LOCK(&p->mutex); + if(TLSFREE(p->mycache)) abort(); + nedpfree(0, p); +} + +void nedpsetvalue(nedpool *p, void *v) THROWSPEC +{ + if(!p) { p=&syspool; if(!syspool.threads) InitPool(&syspool, 0, -1); } + p->uservalue=v; +} +void *nedgetvalue(nedpool **p, void *mem) THROWSPEC +{ + nedpool *np=0; + mchunkptr mcp=mem2chunk(mem); + mstate fm; + if(!(is_aligned(chunk2mem(mcp))) && mcp->head != FENCEPOST_HEAD) return 0; + if(!cinuse(mcp)) return 0; + if(!next_pinuse(mcp)) return 0; + if(!is_mmapped(mcp) && !pinuse(mcp)) + { + if(next_chunk(prev_chunk(mcp))!=mcp) return 0; + } + fm=get_mstate_for(mcp); + if(!ok_magic(fm)) return 0; + if(!ok_address(fm, mcp)) return 0; + if(!fm->extp) return 0; + np=(nedpool *) fm->extp; + if(p) *p=np; + return np->uservalue; +} + +void neddisablethreadcache(nedpool *p) THROWSPEC +{ + int mycache; + if(!p) + { + p=&syspool; + if(!syspool.threads) InitPool(&syspool, 0, -1); + } + mycache=(int)(size_t) TLSGET(p->mycache); + if(!mycache) + { /* Set to mspace 0 */ + if(TLSSET(p->mycache, (void *)-1)) abort(); + } + else if(mycache>0) + { /* Set to last used mspace */ + threadcache *tc=p->caches[mycache-1]; +#if defined(DEBUG) + printf("Threadcache utilisation: %lf%% in cache with %lf%% lost to other threads\n", + 100.0*tc->successes/tc->mallocs, 100.0*((double) tc->mallocs-tc->frees)/tc->mallocs); +#endif + if(TLSSET(p->mycache, (void *)(size_t)(-tc->mymspace))) abort(); + tc->frees++; + RemoveCacheEntries(p, tc, 0); + assert(!tc->freeInCache); + tc->mymspace=-1; + tc->threadid=0; + mspace_free(0, p->caches[mycache-1]); + p->caches[mycache-1]=0; + } +} + +#define GETMSPACE(m,p,tc,ms,s,action) \ + do \ + { \ + mstate m = GetMSpace((p),(tc),(ms),(s)); \ + action; \ + RELEASE_LOCK(&m->mutex); \ + } while (0) + +static FORCEINLINE mstate GetMSpace(nedpool *p, threadcache *tc, int mymspace, size_t size) THROWSPEC +{ /* Returns a locked and ready for use mspace */ + mstate m=p->m[mymspace]; + assert(m); + if(!TRY_LOCK(&p->m[mymspace]->mutex)) m=FindMSpace(p, tc, &mymspace, size);\ + /*assert(IS_LOCKED(&p->m[mymspace]->mutex));*/ + return m; +} +static FORCEINLINE void GetThreadCache(nedpool **p, threadcache **tc, int *mymspace, size_t *size) THROWSPEC +{ + int mycache; + if(size && *size<sizeof(threadcacheblk)) *size=sizeof(threadcacheblk); + if(!*p) + { + *p=&syspool; + if(!syspool.threads) InitPool(&syspool, 0, -1); + } + mycache=(int)(size_t) TLSGET((*p)->mycache); + if(mycache>0) + { + *tc=(*p)->caches[mycache-1]; + *mymspace=(*tc)->mymspace; + } + else if(!mycache) + { + *tc=AllocCache(*p); + if(!*tc) + { /* Disable */ + if(TLSSET((*p)->mycache, (void *)-1)) abort(); + *mymspace=0; + } + else + *mymspace=(*tc)->mymspace; + } + else + { + *tc=0; + *mymspace=-mycache-1; + } + assert(*mymspace>=0); + assert((long)(size_t)CURRENT_THREAD==(*tc)->threadid); +#ifdef FULLSANITYCHECKS + if(*tc) + { + if(*(unsigned int *)"NEDMALC1"!=(*tc)->magic1 || *(unsigned int *)"NEDMALC2"!=(*tc)->magic2) + { + abort(); + } + } +#endif +} + +void * nedpmalloc(nedpool *p, size_t size) THROWSPEC +{ + void *ret=0; + threadcache *tc; + int mymspace; + GetThreadCache(&p, &tc, &mymspace, &size); +#if THREADCACHEMAX + if(tc && size<=THREADCACHEMAX) + { /* Use the thread cache */ + ret=threadcache_malloc(p, tc, &size); + } +#endif + if(!ret) + { /* Use this thread's mspace */ + GETMSPACE(m, p, tc, mymspace, size, + ret=mspace_malloc(m, size)); + } + return ret; +} +void * nedpcalloc(nedpool *p, size_t no, size_t size) THROWSPEC +{ + size_t rsize=size*no; + void *ret=0; + threadcache *tc; + int mymspace; + GetThreadCache(&p, &tc, &mymspace, &rsize); +#if THREADCACHEMAX + if(tc && rsize<=THREADCACHEMAX) + { /* Use the thread cache */ + if((ret=threadcache_malloc(p, tc, &rsize))) + memset(ret, 0, rsize); + } +#endif + if(!ret) + { /* Use this thread's mspace */ + GETMSPACE(m, p, tc, mymspace, rsize, + ret=mspace_calloc(m, 1, rsize)); + } + return ret; +} +void * nedprealloc(nedpool *p, void *mem, size_t size) THROWSPEC +{ + void *ret=0; + threadcache *tc; + int mymspace; + if(!mem) return nedpmalloc(p, size); + GetThreadCache(&p, &tc, &mymspace, &size); +#if THREADCACHEMAX + if(tc && size && size<=THREADCACHEMAX) + { /* Use the thread cache */ + size_t memsize=nedblksize(mem); + assert(memsize); + if((ret=threadcache_malloc(p, tc, &size))) + { + memcpy(ret, mem, memsize<size ? memsize : size); + if(memsize<=THREADCACHEMAX) + threadcache_free(p, tc, mymspace, mem, memsize); + else + mspace_free(0, mem); + } + } +#endif + if(!ret) + { /* Reallocs always happen in the mspace they happened in, so skip + locking the preferred mspace for this thread */ + ret=mspace_realloc(0, mem, size); + } + return ret; +} +void nedpfree(nedpool *p, void *mem) THROWSPEC +{ /* Frees always happen in the mspace they happened in, so skip + locking the preferred mspace for this thread */ + threadcache *tc; + int mymspace; + size_t memsize; + assert(mem); + GetThreadCache(&p, &tc, &mymspace, 0); +#if THREADCACHEMAX + memsize=nedblksize(mem); + assert(memsize); + if(mem && tc && memsize<=(THREADCACHEMAX+CHUNK_OVERHEAD)) + threadcache_free(p, tc, mymspace, mem, memsize); + else +#endif + mspace_free(0, mem); +} +void * nedpmemalign(nedpool *p, size_t alignment, size_t bytes) THROWSPEC +{ + void *ret; + threadcache *tc; + int mymspace; + GetThreadCache(&p, &tc, &mymspace, &bytes); + { /* Use this thread's mspace */ + GETMSPACE(m, p, tc, mymspace, bytes, + ret=mspace_memalign(m, alignment, bytes)); + } + return ret; +} +#if !NO_MALLINFO +struct mallinfo nedpmallinfo(nedpool *p) THROWSPEC +{ + int n; + struct mallinfo ret={0}; + if(!p) { p=&syspool; if(!syspool.threads) InitPool(&syspool, 0, -1); } + for(n=0; p->m[n]; n++) + { + struct mallinfo t=mspace_mallinfo(p->m[n]); + ret.arena+=t.arena; + ret.ordblks+=t.ordblks; + ret.hblkhd+=t.hblkhd; + ret.usmblks+=t.usmblks; + ret.uordblks+=t.uordblks; + ret.fordblks+=t.fordblks; + ret.keepcost+=t.keepcost; + } + return ret; +} +#endif +int nedpmallopt(nedpool *p, int parno, int value) THROWSPEC +{ + return mspace_mallopt(parno, value); +} +int nedpmalloc_trim(nedpool *p, size_t pad) THROWSPEC +{ + int n, ret=0; + if(!p) { p=&syspool; if(!syspool.threads) InitPool(&syspool, 0, -1); } + for(n=0; p->m[n]; n++) + { + ret+=mspace_trim(p->m[n], pad); + } + return ret; +} +void nedpmalloc_stats(nedpool *p) THROWSPEC +{ + int n; + if(!p) { p=&syspool; if(!syspool.threads) InitPool(&syspool, 0, -1); } + for(n=0; p->m[n]; n++) + { + mspace_malloc_stats(p->m[n]); + } +} +size_t nedpmalloc_footprint(nedpool *p) THROWSPEC +{ + size_t ret=0; + int n; + if(!p) { p=&syspool; if(!syspool.threads) InitPool(&syspool, 0, -1); } + for(n=0; p->m[n]; n++) + { + ret+=mspace_footprint(p->m[n]); + } + return ret; +} +void **nedpindependent_calloc(nedpool *p, size_t elemsno, size_t elemsize, void **chunks) THROWSPEC +{ + void **ret; + threadcache *tc; + int mymspace; + GetThreadCache(&p, &tc, &mymspace, &elemsize); + GETMSPACE(m, p, tc, mymspace, elemsno*elemsize, + ret=mspace_independent_calloc(m, elemsno, elemsize, chunks)); + return ret; +} +void **nedpindependent_comalloc(nedpool *p, size_t elems, size_t *sizes, void **chunks) THROWSPEC +{ + void **ret; + threadcache *tc; + int mymspace; + size_t i, *adjustedsizes=(size_t *) alloca(elems*sizeof(size_t)); + if(!adjustedsizes) return 0; + for(i=0; i<elems; i++) + adjustedsizes[i]=sizes[i]<sizeof(threadcacheblk) ? sizeof(threadcacheblk) : sizes[i]; + GetThreadCache(&p, &tc, &mymspace, 0); + GETMSPACE(m, p, tc, mymspace, 0, + ret=mspace_independent_comalloc(m, elems, adjustedsizes, chunks)); + return ret; +} + +#ifdef OVERRIDE_STRDUP +/* + * This implementation is purely there to override the libc version, to + * avoid a crash due to allocation and free on different 'heaps'. + */ +char *strdup(const char *s1) +{ + char *s2 = 0; + if (s1) { + s2 = malloc(strlen(s1) + 1); + strcpy(s2, s1); + } + return s2; +} +#endif + +#if defined(__cplusplus) +} +#endif diff --git a/compat/nedmalloc/nedmalloc.h b/compat/nedmalloc/nedmalloc.h new file mode 100644 index 0000000000..f960e66063 --- /dev/null +++ b/compat/nedmalloc/nedmalloc.h @@ -0,0 +1,180 @@ +/* nedalloc, an alternative malloc implementation for multiple threads without +lock contention based on dlmalloc v2.8.3. (C) 2005 Niall Douglas + +Boost Software License - Version 1.0 - August 17th, 2003 + +Permission is hereby granted, free of charge, to any person or organization +obtaining a copy of the software and accompanying documentation covered by +this license (the "Software") to use, reproduce, display, distribute, +execute, and transmit the Software, and to prepare derivative works of the +Software, and to permit third-parties to whom the Software is furnished to +do so, all subject to the following: + +The copyright notices in the Software and this entire statement, including +the above license grant, this restriction and the following disclaimer, +must be included in all copies of the Software, in whole or in part, and +all derivative works of the Software, unless such copies or derivative +works are solely in the form of machine-executable object code generated by +a source language processor. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT +SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE +FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE, +ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER +DEALINGS IN THE SOFTWARE. +*/ + +#ifndef NEDMALLOC_H +#define NEDMALLOC_H + + +/* See malloc.c.h for what each function does. + +REPLACE_SYSTEM_ALLOCATOR causes nedalloc's functions to be called malloc, +free etc. instead of nedmalloc, nedfree etc. You may or may not want this. + +NO_NED_NAMESPACE prevents the functions from being defined in the nedalloc +namespace when in C++ (uses the global namespace instead). + +EXTSPEC can be defined to be __declspec(dllexport) or +__attribute__ ((visibility("default"))) or whatever you like. It defaults +to extern. + +USE_LOCKS can be 2 if you want to define your own MLOCK_T, INITIAL_LOCK, +ACQUIRE_LOCK, RELEASE_LOCK, TRY_LOCK, IS_LOCKED and NULL_LOCK_INITIALIZER. + +*/ + +#include <stddef.h> /* for size_t */ + +#ifndef EXTSPEC + #define EXTSPEC extern +#endif + +#if defined(_MSC_VER) && _MSC_VER>=1400 + #define MALLOCATTR __declspec(restrict) +#endif +#ifdef __GNUC__ + #define MALLOCATTR __attribute__ ((malloc)) +#endif +#ifndef MALLOCATTR + #define MALLOCATTR +#endif + +#ifdef REPLACE_SYSTEM_ALLOCATOR + #define nedmalloc malloc + #define nedcalloc calloc + #define nedrealloc realloc + #define nedfree free + #define nedmemalign memalign + #define nedmallinfo mallinfo + #define nedmallopt mallopt + #define nedmalloc_trim malloc_trim + #define nedmalloc_stats malloc_stats + #define nedmalloc_footprint malloc_footprint + #define nedindependent_calloc independent_calloc + #define nedindependent_comalloc independent_comalloc + #ifdef _MSC_VER + #define nedblksize _msize + #endif +#endif + +#ifndef NO_MALLINFO +#define NO_MALLINFO 0 +#endif + +#if !NO_MALLINFO +struct mallinfo; +#endif + +#if defined(__cplusplus) + #if !defined(NO_NED_NAMESPACE) +namespace nedalloc { + #else +extern "C" { + #endif + #define THROWSPEC throw() +#else + #define THROWSPEC +#endif + +/* These are the global functions */ + +/* Gets the usable size of an allocated block. Note this will always be bigger than what was +asked for due to rounding etc. +*/ +EXTSPEC size_t nedblksize(void *mem) THROWSPEC; + +EXTSPEC void nedsetvalue(void *v) THROWSPEC; + +EXTSPEC MALLOCATTR void * nedmalloc(size_t size) THROWSPEC; +EXTSPEC MALLOCATTR void * nedcalloc(size_t no, size_t size) THROWSPEC; +EXTSPEC MALLOCATTR void * nedrealloc(void *mem, size_t size) THROWSPEC; +EXTSPEC void nedfree(void *mem) THROWSPEC; +EXTSPEC MALLOCATTR void * nedmemalign(size_t alignment, size_t bytes) THROWSPEC; +#if !NO_MALLINFO +EXTSPEC struct mallinfo nedmallinfo(void) THROWSPEC; +#endif +EXTSPEC int nedmallopt(int parno, int value) THROWSPEC; +EXTSPEC int nedmalloc_trim(size_t pad) THROWSPEC; +EXTSPEC void nedmalloc_stats(void) THROWSPEC; +EXTSPEC size_t nedmalloc_footprint(void) THROWSPEC; +EXTSPEC MALLOCATTR void **nedindependent_calloc(size_t elemsno, size_t elemsize, void **chunks) THROWSPEC; +EXTSPEC MALLOCATTR void **nedindependent_comalloc(size_t elems, size_t *sizes, void **chunks) THROWSPEC; + +/* These are the pool functions */ +struct nedpool_t; +typedef struct nedpool_t nedpool; + +/* Creates a memory pool for use with the nedp* functions below. +Capacity is how much to allocate immediately (if you know you'll be allocating a lot +of memory very soon) which you can leave at zero. Threads specifies how many threads +will *normally* be accessing the pool concurrently. Setting this to zero means it +extends on demand, but be careful of this as it can rapidly consume system resources +where bursts of concurrent threads use a pool at once. +*/ +EXTSPEC MALLOCATTR nedpool *nedcreatepool(size_t capacity, int threads) THROWSPEC; + +/* Destroys a memory pool previously created by nedcreatepool(). +*/ +EXTSPEC void neddestroypool(nedpool *p) THROWSPEC; + +/* Sets a value to be associated with a pool. You can retrieve this value by passing +any memory block allocated from that pool. +*/ +EXTSPEC void nedpsetvalue(nedpool *p, void *v) THROWSPEC; +/* Gets a previously set value using nedpsetvalue() or zero if memory is unknown. +Optionally can also retrieve pool. +*/ +EXTSPEC void *nedgetvalue(nedpool **p, void *mem) THROWSPEC; + +/* Disables the thread cache for the calling thread, returning any existing cache +data to the central pool. +*/ +EXTSPEC void neddisablethreadcache(nedpool *p) THROWSPEC; + +EXTSPEC MALLOCATTR void * nedpmalloc(nedpool *p, size_t size) THROWSPEC; +EXTSPEC MALLOCATTR void * nedpcalloc(nedpool *p, size_t no, size_t size) THROWSPEC; +EXTSPEC MALLOCATTR void * nedprealloc(nedpool *p, void *mem, size_t size) THROWSPEC; +EXTSPEC void nedpfree(nedpool *p, void *mem) THROWSPEC; +EXTSPEC MALLOCATTR void * nedpmemalign(nedpool *p, size_t alignment, size_t bytes) THROWSPEC; +#if !NO_MALLINFO +EXTSPEC struct mallinfo nedpmallinfo(nedpool *p) THROWSPEC; +#endif +EXTSPEC int nedpmallopt(nedpool *p, int parno, int value) THROWSPEC; +EXTSPEC int nedpmalloc_trim(nedpool *p, size_t pad) THROWSPEC; +EXTSPEC void nedpmalloc_stats(nedpool *p) THROWSPEC; +EXTSPEC size_t nedpmalloc_footprint(nedpool *p) THROWSPEC; +EXTSPEC MALLOCATTR void **nedpindependent_calloc(nedpool *p, size_t elemsno, size_t elemsize, void **chunks) THROWSPEC; +EXTSPEC MALLOCATTR void **nedpindependent_comalloc(nedpool *p, size_t elems, size_t *sizes, void **chunks) THROWSPEC; + +#if defined(__cplusplus) +} +#endif + +#undef MALLOCATTR +#undef EXTSPEC + +#endif diff --git a/compat/regex/regex.c b/compat/regex/regex.c index 87b33e4669..556d8ab11f 100644 --- a/compat/regex/regex.c +++ b/compat/regex/regex.c @@ -1043,7 +1043,7 @@ regex_compile (pattern, size, syntax, bufp) they can be reliably used as array indices. */ register unsigned char c, c1; - /* A random tempory spot in PATTERN. */ + /* A random temporary spot in PATTERN. */ const char *p1; /* Points to the end of the buffer, where we should append. */ @@ -1796,7 +1796,7 @@ regex_compile (pattern, size, syntax, bufp) we're all done, the pattern will look like: set_number_at <jump count> <upper bound> set_number_at <succeed_n count> <lower bound> - succeed_n <after jump addr> <succed_n count> + succeed_n <after jump addr> <succeed_n count> <body of loop> jump_n <succeed_n addr> <jump count> (The upper bound and `jump_n' are omitted if @@ -2808,7 +2808,7 @@ re_set_registers (bufp, regs, num_regs, starts, ends) { bufp->regs_allocated = REGS_UNALLOCATED; regs->num_regs = 0; - regs->start = regs->end = (regoff_t) 0; + regs->start = regs->end = (regoff_t *) 0; } } @@ -4852,11 +4852,8 @@ regexec (preg, string, nmatch, pmatch, eflags) from either regcomp or regexec. We don't use PREG here. */ size_t -regerror (errcode, preg, errbuf, errbuf_size) - int errcode; - const regex_t *preg; - char *errbuf; - size_t errbuf_size; +regerror(int errcode, const regex_t *preg, + char *errbuf, size_t errbuf_size) { const char *msg; size_t msg_size; diff --git a/compat/snprintf.c b/compat/snprintf.c index 357e733074..e1e0e7543d 100644 --- a/compat/snprintf.c +++ b/compat/snprintf.c @@ -2,12 +2,19 @@ /* * The size parameter specifies the available space, i.e. includes - * the trailing NUL byte; but Windows's vsnprintf expects the - * number of characters to write without the trailing NUL. + * the trailing NUL byte; but Windows's vsnprintf uses the entire + * buffer and avoids the trailing NUL, should the buffer be exactly + * big enough for the result. Defining SNPRINTF_SIZE_CORR to 1 will + * therefore remove 1 byte from the reported buffer size, so we + * always have room for a trailing NUL byte. */ #ifndef SNPRINTF_SIZE_CORR +#if defined(WIN32) && (!defined(__GNUC__) || __GNUC__ < 4) +#define SNPRINTF_SIZE_CORR 1 +#else #define SNPRINTF_SIZE_CORR 0 #endif +#endif #undef vsnprintf int git_vsnprintf(char *str, size_t maxsize, const char *format, va_list ap) diff --git a/compat/vcbuild/README b/compat/vcbuild/README new file mode 100644 index 0000000000..df8a6574c9 --- /dev/null +++ b/compat/vcbuild/README @@ -0,0 +1,50 @@ +The Steps of Build Git with VS2008 + +1. You need the build environment, which contains the Git dependencies + to be able to compile, link and run Git with MSVC. + + You can either use the binary repository: + + WWW: http://repo.or.cz/w/msvcgit.git + Git: git clone git://repo.or.cz/msvcgit.git + Zip: http://repo.or.cz/w/msvcgit.git?a=snapshot;h=master;sf=zip + + and call the setup_32bit_env.cmd batch script before compiling Git, + (see repo/package README for details), or the source repository: + + WWW: http://repo.or.cz/w/gitbuild.git + Git: git clone git://repo.or.cz/gitbuild.git + Zip: (None, as it's a project with submodules) + + and build the support libs as instructed in that repo/package. + +2. Ensure you have the msysgit environment in your path, so you have + GNU Make, bash and perl available. + + WWW: http://repo.or.cz/w/msysgit.git + Git: git clone git://repo.or.cz/msysgit.git + Zip: http://repo.or.cz/w/msysgit.git?a=snapshot;h=master;sf=zip + + This environment is also needed when you use the resulting + executables, since Git might need to run scripts which are part of + the git operations. + +3. Inside Git's directory run the command: + make common-cmds.h + to generate the common-cmds.h file needed to compile git. + +4. Then either build Git with the GNU Make Makefile in the Git projects + root + make MSVC=1 + or generate Visual Studio solution/projects (.sln/.vcproj) with the + command + perl contrib/buildsystems/generate -g Vcproj + and open and build the solution with the IDE + devenv git.sln /useenv + or build with the IDE build engine directly from the command line + devenv git.sln /useenv /build "Release|Win32" + The /useenv option is required, so Visual Studio picks up the + environment variables for the support libraries required to build + Git, which you set up in step 1. + +Done! diff --git a/compat/vcbuild/include/alloca.h b/compat/vcbuild/include/alloca.h new file mode 100644 index 0000000000..c0d7985b7e --- /dev/null +++ b/compat/vcbuild/include/alloca.h @@ -0,0 +1 @@ +#include <malloc.h> diff --git a/compat/vcbuild/include/arpa/inet.h b/compat/vcbuild/include/arpa/inet.h new file mode 100644 index 0000000000..0d8552a2c6 --- /dev/null +++ b/compat/vcbuild/include/arpa/inet.h @@ -0,0 +1 @@ +/* Intentionally empty file to support building git with MSVC */ diff --git a/compat/vcbuild/include/dirent.h b/compat/vcbuild/include/dirent.h new file mode 100644 index 0000000000..440618db0d --- /dev/null +++ b/compat/vcbuild/include/dirent.h @@ -0,0 +1,128 @@ +/* + * DIRENT.H (formerly DIRLIB.H) + * This file has no copyright assigned and is placed in the Public Domain. + * This file is a part of the mingw-runtime package. + * + * The mingw-runtime package and its code is distributed in the hope that it + * will be useful but WITHOUT ANY WARRANTY. ALL WARRANTIES, EXPRESSED OR + * IMPLIED ARE HEREBY DISCLAIMED. This includes but is not limited to + * warranties of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * + * You are free to use this package and its code without limitation. + */ +#ifndef _DIRENT_H_ +#define _DIRENT_H_ +#include <io.h> + +#define PATH_MAX 512 + +#define __MINGW_NOTHROW + +#ifndef RC_INVOKED + +#ifdef __cplusplus +extern "C" { +#endif + +struct dirent +{ + long d_ino; /* Always zero. */ + unsigned short d_reclen; /* Always zero. */ + unsigned short d_namlen; /* Length of name in d_name. */ + char d_name[FILENAME_MAX]; /* File name. */ +}; + +/* + * This is an internal data structure. Good programmers will not use it + * except as an argument to one of the functions below. + * dd_stat field is now int (was short in older versions). + */ +typedef struct +{ + /* disk transfer area for this dir */ + struct _finddata_t dd_dta; + + /* dirent struct to return from dir (NOTE: this makes this thread + * safe as long as only one thread uses a particular DIR struct at + * a time) */ + struct dirent dd_dir; + + /* _findnext handle */ + long dd_handle; + + /* + * Status of search: + * 0 = not started yet (next entry to read is first entry) + * -1 = off the end + * positive = 0 based index of next entry + */ + int dd_stat; + + /* given path for dir with search pattern (struct is extended) */ + char dd_name[PATH_MAX+3]; +} DIR; + +DIR* __cdecl __MINGW_NOTHROW opendir (const char*); +struct dirent* __cdecl __MINGW_NOTHROW readdir (DIR*); +int __cdecl __MINGW_NOTHROW closedir (DIR*); +void __cdecl __MINGW_NOTHROW rewinddir (DIR*); +long __cdecl __MINGW_NOTHROW telldir (DIR*); +void __cdecl __MINGW_NOTHROW seekdir (DIR*, long); + + +/* wide char versions */ + +struct _wdirent +{ + long d_ino; /* Always zero. */ + unsigned short d_reclen; /* Always zero. */ + unsigned short d_namlen; /* Length of name in d_name. */ + wchar_t d_name[FILENAME_MAX]; /* File name. */ +}; + +/* + * This is an internal data structure. Good programmers will not use it + * except as an argument to one of the functions below. + */ +typedef struct +{ + /* disk transfer area for this dir */ + //struct _wfinddata_t dd_dta; + + /* dirent struct to return from dir (NOTE: this makes this thread + * safe as long as only one thread uses a particular DIR struct at + * a time) */ + struct _wdirent dd_dir; + + /* _findnext handle */ + long dd_handle; + + /* + * Status of search: + * 0 = not started yet (next entry to read is first entry) + * -1 = off the end + * positive = 0 based index of next entry + */ + int dd_stat; + + /* given path for dir with search pattern (struct is extended) */ + wchar_t dd_name[1]; +} _WDIR; + + + +_WDIR* __cdecl __MINGW_NOTHROW _wopendir (const wchar_t*); +struct _wdirent* __cdecl __MINGW_NOTHROW _wreaddir (_WDIR*); +int __cdecl __MINGW_NOTHROW _wclosedir (_WDIR*); +void __cdecl __MINGW_NOTHROW _wrewinddir (_WDIR*); +long __cdecl __MINGW_NOTHROW _wtelldir (_WDIR*); +void __cdecl __MINGW_NOTHROW _wseekdir (_WDIR*, long); + + +#ifdef __cplusplus +} +#endif + +#endif /* Not RC_INVOKED */ + +#endif /* Not _DIRENT_H_ */ diff --git a/compat/vcbuild/include/grp.h b/compat/vcbuild/include/grp.h new file mode 100644 index 0000000000..0d8552a2c6 --- /dev/null +++ b/compat/vcbuild/include/grp.h @@ -0,0 +1 @@ +/* Intentionally empty file to support building git with MSVC */ diff --git a/compat/vcbuild/include/inttypes.h b/compat/vcbuild/include/inttypes.h new file mode 100644 index 0000000000..0d8552a2c6 --- /dev/null +++ b/compat/vcbuild/include/inttypes.h @@ -0,0 +1 @@ +/* Intentionally empty file to support building git with MSVC */ diff --git a/compat/vcbuild/include/netdb.h b/compat/vcbuild/include/netdb.h new file mode 100644 index 0000000000..0d8552a2c6 --- /dev/null +++ b/compat/vcbuild/include/netdb.h @@ -0,0 +1 @@ +/* Intentionally empty file to support building git with MSVC */ diff --git a/compat/vcbuild/include/netinet/in.h b/compat/vcbuild/include/netinet/in.h new file mode 100644 index 0000000000..0d8552a2c6 --- /dev/null +++ b/compat/vcbuild/include/netinet/in.h @@ -0,0 +1 @@ +/* Intentionally empty file to support building git with MSVC */ diff --git a/compat/vcbuild/include/netinet/tcp.h b/compat/vcbuild/include/netinet/tcp.h new file mode 100644 index 0000000000..0d8552a2c6 --- /dev/null +++ b/compat/vcbuild/include/netinet/tcp.h @@ -0,0 +1 @@ +/* Intentionally empty file to support building git with MSVC */ diff --git a/compat/vcbuild/include/pwd.h b/compat/vcbuild/include/pwd.h new file mode 100644 index 0000000000..0d8552a2c6 --- /dev/null +++ b/compat/vcbuild/include/pwd.h @@ -0,0 +1 @@ +/* Intentionally empty file to support building git with MSVC */ diff --git a/compat/vcbuild/include/sys/ioctl.h b/compat/vcbuild/include/sys/ioctl.h new file mode 100644 index 0000000000..0d8552a2c6 --- /dev/null +++ b/compat/vcbuild/include/sys/ioctl.h @@ -0,0 +1 @@ +/* Intentionally empty file to support building git with MSVC */ diff --git a/compat/vcbuild/include/sys/param.h b/compat/vcbuild/include/sys/param.h new file mode 100644 index 0000000000..0d8552a2c6 --- /dev/null +++ b/compat/vcbuild/include/sys/param.h @@ -0,0 +1 @@ +/* Intentionally empty file to support building git with MSVC */ diff --git a/compat/vcbuild/include/sys/poll.h b/compat/vcbuild/include/sys/poll.h new file mode 100644 index 0000000000..0d8552a2c6 --- /dev/null +++ b/compat/vcbuild/include/sys/poll.h @@ -0,0 +1 @@ +/* Intentionally empty file to support building git with MSVC */ diff --git a/compat/vcbuild/include/sys/select.h b/compat/vcbuild/include/sys/select.h new file mode 100644 index 0000000000..0d8552a2c6 --- /dev/null +++ b/compat/vcbuild/include/sys/select.h @@ -0,0 +1 @@ +/* Intentionally empty file to support building git with MSVC */ diff --git a/compat/vcbuild/include/sys/socket.h b/compat/vcbuild/include/sys/socket.h new file mode 100644 index 0000000000..0d8552a2c6 --- /dev/null +++ b/compat/vcbuild/include/sys/socket.h @@ -0,0 +1 @@ +/* Intentionally empty file to support building git with MSVC */ diff --git a/compat/vcbuild/include/sys/time.h b/compat/vcbuild/include/sys/time.h new file mode 100644 index 0000000000..0d8552a2c6 --- /dev/null +++ b/compat/vcbuild/include/sys/time.h @@ -0,0 +1 @@ +/* Intentionally empty file to support building git with MSVC */ diff --git a/compat/vcbuild/include/sys/utime.h b/compat/vcbuild/include/sys/utime.h new file mode 100644 index 0000000000..582589c70a --- /dev/null +++ b/compat/vcbuild/include/sys/utime.h @@ -0,0 +1,34 @@ +#ifndef _UTIME_H_ +#define _UTIME_H_ +/* + * UTIME.H + * This file has no copyright assigned and is placed in the Public Domain. + * This file is a part of the mingw-runtime package. + * + * The mingw-runtime package and its code is distributed in the hope that it + * will be useful but WITHOUT ANY WARRANTY. ALL WARRANTIES, EXPRESSED OR + * IMPLIED ARE HEREBY DISCLAIMED. This includes but is not limited to + * warranties of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * + * You are free to use this package and its code without limitation. + */ + +/* + * Structure used by _utime function. + */ +struct _utimbuf +{ + time_t actime; /* Access time */ + time_t modtime; /* Modification time */ +}; + +#ifndef _NO_OLDNAMES +/* NOTE: Must be the same as _utimbuf above. */ +struct utimbuf +{ + time_t actime; + time_t modtime; +}; +#endif /* Not _NO_OLDNAMES */ + +#endif diff --git a/compat/vcbuild/include/sys/wait.h b/compat/vcbuild/include/sys/wait.h new file mode 100644 index 0000000000..0d8552a2c6 --- /dev/null +++ b/compat/vcbuild/include/sys/wait.h @@ -0,0 +1 @@ +/* Intentionally empty file to support building git with MSVC */ diff --git a/compat/vcbuild/include/unistd.h b/compat/vcbuild/include/unistd.h new file mode 100644 index 0000000000..2a4f276869 --- /dev/null +++ b/compat/vcbuild/include/unistd.h @@ -0,0 +1,92 @@ +#ifndef _UNISTD_ +#define _UNISTD_ + +/* Win32 define for porting git*/ + +#ifndef _MODE_T_ +#define _MODE_T_ +typedef unsigned short _mode_t; + +#ifndef _NO_OLDNAMES +typedef _mode_t mode_t; +#endif +#endif /* Not _MODE_T_ */ + +#ifndef _SSIZE_T_ +#define _SSIZE_T_ +typedef long _ssize_t; + +#ifndef _OFF_T_ +#define _OFF_T_ +typedef long _off_t; + +#ifndef _NO_OLDNAMES +typedef _off_t off_t; +#endif +#endif /* Not _OFF_T_ */ + + +#ifndef _NO_OLDNAMES +typedef _ssize_t ssize_t; +#endif +#endif /* Not _SSIZE_T_ */ + +typedef signed char int8_t; +typedef unsigned char uint8_t; +typedef short int16_t; +typedef unsigned short uint16_t; +typedef int int32_t; +typedef unsigned uint32_t; +typedef long long int64_t; +typedef unsigned long long uint64_t; + +typedef long long intmax_t; +typedef unsigned long long uintmax_t; + +typedef int64_t off64_t; + +#define STDOUT_FILENO 1 +#define STDERR_FILENO 2 + +/* Some defines for _access nAccessMode (MS doesn't define them, but + * it doesn't seem to hurt to add them). */ +#define F_OK 0 /* Check for file existence */ +/* Well maybe it does hurt. On newer versions of MSVCRT, an access mode + of 1 causes invalid parameter error. */ +#define X_OK 0 /* MS access() doesn't check for execute permission. */ +#define W_OK 2 /* Check for write permission */ +#define R_OK 4 /* Check for read permission */ + +#define _S_IFIFO 0x1000 /* FIFO */ +#define _S_IFCHR 0x2000 /* Character */ +#define _S_IFBLK 0x3000 /* Block: Is this ever set under w32? */ +#define _S_IFDIR 0x4000 /* Directory */ +#define _S_IFREG 0x8000 /* Regular */ + +#define _S_IFMT 0xF000 /* File type mask */ + +#define _S_IXUSR _S_IEXEC +#define _S_IWUSR _S_IWRITE +#define _S_IRUSR _S_IREAD +#define _S_ISDIR(m) (((m) & _S_IFMT) == _S_IFDIR) + +#define S_IFIFO _S_IFIFO +#define S_IFCHR _S_IFCHR +#define S_IFBLK _S_IFBLK +#define S_IFDIR _S_IFDIR +#define S_IFREG _S_IFREG +#define S_IFMT _S_IFMT +#define S_IEXEC _S_IEXEC +#define S_IWRITE _S_IWRITE +#define S_IREAD _S_IREAD +#define S_IRWXU _S_IRWXU +#define S_IXUSR _S_IXUSR +#define S_IWUSR _S_IWUSR +#define S_IRUSR _S_IRUSR + + +#define S_ISDIR(m) (((m) & S_IFMT) == S_IFDIR) +#define S_ISREG(m) (((m) & S_IFMT) == S_IFREG) +#define S_ISFIFO(m) (((m) & S_IFMT) == S_IFIFO) + +#endif diff --git a/compat/vcbuild/include/utime.h b/compat/vcbuild/include/utime.h new file mode 100644 index 0000000000..8285f38fde --- /dev/null +++ b/compat/vcbuild/include/utime.h @@ -0,0 +1 @@ +#include <sys/utime.h> diff --git a/compat/vcbuild/scripts/clink.pl b/compat/vcbuild/scripts/clink.pl new file mode 100644 index 0000000000..4374771df2 --- /dev/null +++ b/compat/vcbuild/scripts/clink.pl @@ -0,0 +1,52 @@ +#!/usr/bin/perl -w +###################################################################### +# Compiles or links files +# +# This is a wrapper to facilitate the compilation of Git with MSVC +# using GNU Make as the build system. So, instead of manipulating the +# Makefile into something nasty, just to support non-space arguments +# etc, we use this wrapper to fix the command line options +# +# Copyright (C) 2009 Marius Storm-Olsen <mstormo@gmail.com> +###################################################################### +use strict; +my @args = (); +my @cflags = (); +my $is_linking = 0; +while (@ARGV) { + my $arg = shift @ARGV; + if ("$arg" =~ /^-[DIMGO]/) { + push(@cflags, $arg); + } elsif ("$arg" eq "-o") { + my $file_out = shift @ARGV; + if ("$file_out" =~ /exe$/) { + $is_linking = 1; + push(@args, "-OUT:$file_out"); + } else { + push(@args, "-Fo$file_out"); + } + } elsif ("$arg" eq "-lz") { + push(@args, "zlib.lib"); + } elsif ("$arg" eq "-liconv") { + push(@args, "iconv.lib"); + } elsif ("$arg" eq "-lcrypto") { + push(@args, "libeay32.lib"); + } elsif ("$arg" eq "-lssl") { + push(@args, "ssleay32.lib"); + } elsif ("$arg" =~ /^-L/ && "$arg" ne "-LTCG") { + $arg =~ s/^-L/-LIBPATH:/; + push(@args, $arg); + } elsif ("$arg" =~ /^-R/) { + # eat + } else { + push(@args, $arg); + } +} +if ($is_linking) { + unshift(@args, "link.exe"); +} else { + unshift(@args, "cl.exe"); + push(@args, @cflags); +} +#printf("**** @args\n"); +exit (system(@args) != 0); diff --git a/compat/vcbuild/scripts/lib.pl b/compat/vcbuild/scripts/lib.pl new file mode 100644 index 0000000000..d8054e469f --- /dev/null +++ b/compat/vcbuild/scripts/lib.pl @@ -0,0 +1,26 @@ +#!/usr/bin/perl -w +###################################################################### +# Libifies files on Windows +# +# This is a wrapper to facilitate the compilation of Git with MSVC +# using GNU Make as the build system. So, instead of manipulating the +# Makefile into something nasty, just to support non-space arguments +# etc, we use this wrapper to fix the command line options +# +# Copyright (C) 2009 Marius Storm-Olsen <mstormo@gmail.com> +###################################################################### +use strict; +my @args = (); +while (@ARGV) { + my $arg = shift @ARGV; + if ("$arg" eq "rcs") { + # Consume the rcs option + } elsif ("$arg" =~ /\.a$/) { + push(@args, "-OUT:$arg"); + } else { + push(@args, $arg); + } +} +unshift(@args, "lib.exe"); +# printf("**** @args\n"); +exit (system(@args) != 0); diff --git a/compat/win32.h b/compat/win32.h index c26384e595..8ce91048de 100644 --- a/compat/win32.h +++ b/compat/win32.h @@ -1,5 +1,10 @@ +#ifndef WIN32_H +#define WIN32_H + /* common Win32 functions for MinGW and Cygwin */ +#ifndef WIN32 /* Not defined by Cygwin */ #include <windows.h> +#endif static inline int file_attr_to_st_mode (DWORD attr) { @@ -32,3 +37,5 @@ static inline int get_file_attr(const char *fname, WIN32_FILE_ATTRIBUTE_DATA *fd return ENOENT; } } + +#endif diff --git a/compat/win32/pthread.c b/compat/win32/pthread.c new file mode 100644 index 0000000000..0f949fc425 --- /dev/null +++ b/compat/win32/pthread.c @@ -0,0 +1,188 @@ +/* + * Copyright (C) 2009 Andrzej K. Haczewski <ahaczewski@gmail.com> + * + * DISCLAIMER: The implementation is Git-specific, it is subset of original + * Pthreads API, without lots of other features that Git doesn't use. + * Git also makes sure that the passed arguments are valid, so there's + * no need for double-checking. + */ + +#include "../../git-compat-util.h" +#include "pthread.h" + +#include <errno.h> +#include <limits.h> + +static unsigned __stdcall win32_start_routine(void *arg) +{ + pthread_t *thread = arg; + thread->arg = thread->start_routine(thread->arg); + return 0; +} + +int pthread_create(pthread_t *thread, const void *unused, + void *(*start_routine)(void*), void *arg) +{ + thread->arg = arg; + thread->start_routine = start_routine; + thread->handle = (HANDLE) + _beginthreadex(NULL, 0, win32_start_routine, thread, 0, NULL); + + if (!thread->handle) + return errno; + else + return 0; +} + +int win32_pthread_join(pthread_t *thread, void **value_ptr) +{ + DWORD result = WaitForSingleObject(thread->handle, INFINITE); + switch (result) { + case WAIT_OBJECT_0: + if (value_ptr) + *value_ptr = thread->arg; + return 0; + case WAIT_ABANDONED: + return EINVAL; + default: + return err_win_to_posix(GetLastError()); + } +} + +int pthread_cond_init(pthread_cond_t *cond, const void *unused) +{ + cond->waiters = 0; + cond->was_broadcast = 0; + InitializeCriticalSection(&cond->waiters_lock); + + cond->sema = CreateSemaphore(NULL, 0, LONG_MAX, NULL); + if (!cond->sema) + die("CreateSemaphore() failed"); + + cond->continue_broadcast = CreateEvent(NULL, /* security */ + FALSE, /* auto-reset */ + FALSE, /* not signaled */ + NULL); /* name */ + if (!cond->continue_broadcast) + die("CreateEvent() failed"); + + return 0; +} + +int pthread_cond_destroy(pthread_cond_t *cond) +{ + CloseHandle(cond->sema); + CloseHandle(cond->continue_broadcast); + DeleteCriticalSection(&cond->waiters_lock); + return 0; +} + +int pthread_cond_wait(pthread_cond_t *cond, CRITICAL_SECTION *mutex) +{ + int last_waiter; + + EnterCriticalSection(&cond->waiters_lock); + cond->waiters++; + LeaveCriticalSection(&cond->waiters_lock); + + /* + * Unlock external mutex and wait for signal. + * NOTE: we've held mutex locked long enough to increment + * waiters count above, so there's no problem with + * leaving mutex unlocked before we wait on semaphore. + */ + LeaveCriticalSection(mutex); + + /* let's wait - ignore return value */ + WaitForSingleObject(cond->sema, INFINITE); + + /* + * Decrease waiters count. If we are the last waiter, then we must + * notify the broadcasting thread that it can continue. + * But if we continued due to cond_signal, we do not have to do that + * because the signaling thread knows that only one waiter continued. + */ + EnterCriticalSection(&cond->waiters_lock); + cond->waiters--; + last_waiter = cond->was_broadcast && cond->waiters == 0; + LeaveCriticalSection(&cond->waiters_lock); + + if (last_waiter) { + /* + * cond_broadcast was issued while mutex was held. This means + * that all other waiters have continued, but are contending + * for the mutex at the end of this function because the + * broadcasting thread did not leave cond_broadcast, yet. + * (This is so that it can be sure that each waiter has + * consumed exactly one slice of the semaphor.) + * The last waiter must tell the broadcasting thread that it + * can go on. + */ + SetEvent(cond->continue_broadcast); + /* + * Now we go on to contend with all other waiters for + * the mutex. Auf in den Kampf! + */ + } + /* lock external mutex again */ + EnterCriticalSection(mutex); + + return 0; +} + +/* + * IMPORTANT: This implementation requires that pthread_cond_signal + * is called while the mutex is held that is used in the corresponding + * pthread_cond_wait calls! + */ +int pthread_cond_signal(pthread_cond_t *cond) +{ + int have_waiters; + + EnterCriticalSection(&cond->waiters_lock); + have_waiters = cond->waiters > 0; + LeaveCriticalSection(&cond->waiters_lock); + + /* + * Signal only when there are waiters + */ + if (have_waiters) + return ReleaseSemaphore(cond->sema, 1, NULL) ? + 0 : err_win_to_posix(GetLastError()); + else + return 0; +} + +/* + * DOUBLY IMPORTANT: This implementation requires that pthread_cond_broadcast + * is called while the mutex is held that is used in the corresponding + * pthread_cond_wait calls! + */ +int pthread_cond_broadcast(pthread_cond_t *cond) +{ + EnterCriticalSection(&cond->waiters_lock); + + if ((cond->was_broadcast = cond->waiters > 0)) { + /* wake up all waiters */ + ReleaseSemaphore(cond->sema, cond->waiters, NULL); + LeaveCriticalSection(&cond->waiters_lock); + /* + * At this point all waiters continue. Each one takes its + * slice of the semaphor. Now it's our turn to wait: Since + * the external mutex is held, no thread can leave cond_wait, + * yet. For this reason, we can be sure that no thread gets + * a chance to eat *more* than one slice. OTOH, it means + * that the last waiter must send us a wake-up. + */ + WaitForSingleObject(cond->continue_broadcast, INFINITE); + /* + * Since the external mutex is held, no thread can enter + * cond_wait, and, hence, it is safe to reset this flag + * without cond->waiters_lock held. + */ + cond->was_broadcast = 0; + } else { + LeaveCriticalSection(&cond->waiters_lock); + } + return 0; +} diff --git a/compat/win32/pthread.h b/compat/win32/pthread.h new file mode 100644 index 0000000000..c72f100f40 --- /dev/null +++ b/compat/win32/pthread.h @@ -0,0 +1,68 @@ +/* + * Header used to adapt pthread-based POSIX code to Windows API threads. + * + * Copyright (C) 2009 Andrzej K. Haczewski <ahaczewski@gmail.com> + */ + +#ifndef PTHREAD_H +#define PTHREAD_H + +#ifndef WIN32_LEAN_AND_MEAN +#define WIN32_LEAN_AND_MEAN +#endif + +#include <windows.h> + +/* + * Defines that adapt Windows API threads to pthreads API + */ +#define pthread_mutex_t CRITICAL_SECTION + +#define pthread_mutex_init(a,b) InitializeCriticalSection((a)) +#define pthread_mutex_destroy(a) DeleteCriticalSection((a)) +#define pthread_mutex_lock EnterCriticalSection +#define pthread_mutex_unlock LeaveCriticalSection + +/* + * Implement simple condition variable for Windows threads, based on ACE + * implementation. + * + * See original implementation: http://bit.ly/1vkDjo + * ACE homepage: http://www.cse.wustl.edu/~schmidt/ACE.html + * See also: http://www.cse.wustl.edu/~schmidt/win32-cv-1.html + */ +typedef struct { + LONG waiters; + int was_broadcast; + CRITICAL_SECTION waiters_lock; + HANDLE sema; + HANDLE continue_broadcast; +} pthread_cond_t; + +extern int pthread_cond_init(pthread_cond_t *cond, const void *unused); +extern int pthread_cond_destroy(pthread_cond_t *cond); +extern int pthread_cond_wait(pthread_cond_t *cond, CRITICAL_SECTION *mutex); +extern int pthread_cond_signal(pthread_cond_t *cond); +extern int pthread_cond_broadcast(pthread_cond_t *cond); + +/* + * Simple thread creation implementation using pthread API + */ +typedef struct { + HANDLE handle; + void *(*start_routine)(void*); + void *arg; +} pthread_t; + +extern int pthread_create(pthread_t *thread, const void *unused, + void *(*start_routine)(void*), void *arg); + +/* + * To avoid the need of copying a struct, we use small macro wrapper to pass + * pointer to win32_pthread_join instead. + */ +#define pthread_join(a, b) win32_pthread_join(&(a), (b)) + +extern int win32_pthread_join(pthread_t *thread, void **value_ptr); + +#endif /* PTHREAD_H */ diff --git a/compat/win32mmap.c b/compat/win32mmap.c new file mode 100644 index 0000000000..1c5a14922f --- /dev/null +++ b/compat/win32mmap.c @@ -0,0 +1,41 @@ +#include "../git-compat-util.h" + +void *git_mmap(void *start, size_t length, int prot, int flags, int fd, off_t offset) +{ + HANDLE hmap; + void *temp; + size_t len; + struct stat st; + uint64_t o = offset; + uint32_t l = o & 0xFFFFFFFF; + uint32_t h = (o >> 32) & 0xFFFFFFFF; + + if (!fstat(fd, &st)) + len = xsize_t(st.st_size); + else + die("mmap: could not determine filesize"); + + if ((length + offset) > len) + length = len - offset; + + if (!(flags & MAP_PRIVATE)) + die("Invalid usage of mmap when built with USE_WIN32_MMAP"); + + hmap = CreateFileMapping((HANDLE)_get_osfhandle(fd), 0, PAGE_WRITECOPY, + 0, 0, 0); + + if (!hmap) + return MAP_FAILED; + + temp = MapViewOfFileEx(hmap, FILE_MAP_COPY, h, l, length, start); + + if (!CloseHandle(hmap)) + warning("unable to close file mapping handle\n"); + + return temp ? temp : MAP_FAILED; +} + +int git_munmap(void *start, size_t length) +{ + return !UnmapViewOfFile(start); +} diff --git a/compat/winansi.c b/compat/winansi.c index e2d96dfe6f..dedce2104e 100644 --- a/compat/winansi.c +++ b/compat/winansi.c @@ -2,7 +2,6 @@ * Copyright 2008 Peter Harris <git@peter.is-a-geek.org> */ -#include <windows.h> #include "../git-compat-util.h" /* @@ -18,8 +17,6 @@ This file is git-specific. Therefore, this file does not attempt to implement any codes that are not used by git. - - TODO: K */ static HANDLE console; @@ -79,6 +76,21 @@ static void set_console_attr(void) SetConsoleTextAttribute(console, attributes); } +static void erase_in_line(void) +{ + CONSOLE_SCREEN_BUFFER_INFO sbi; + DWORD dummy; /* Needed for Windows 7 (or Vista) regression */ + + if (!console) + return; + + GetConsoleScreenBufferInfo(console, &sbi); + FillConsoleOutputCharacterA(console, ' ', + sbi.dwSize.X - sbi.dwCursorPosition.X, sbi.dwCursorPosition, + &dummy); +} + + static const char *set_attr(const char *str) { const char *func; @@ -218,7 +230,7 @@ static const char *set_attr(const char *str) set_console_attr(); break; case 'K': - /* TODO */ + erase_in_line(); break; default: /* Unsupported code */ |