add locale framework

this commit adds non-stub implementations of setlocale, duplocale,
newlocale, and uselocale, along with the data structures and minimal
code needed for representing the active locale on a per-thread basis
and optimizing the common case where thread-local locale settings are
not in use.

at this point, the data structures only contain what is necessary to
represent LC_CTYPE (a single flag) and LC_MESSAGES (a name for use in
finding message translation files). representation for the other
categories will be added later; the expectation is that a single
pointer will suffice for each.

for LC_CTYPE, the strings "C" and "POSIX" are treated as special; any
other string is accepted and treated as "C.UTF-8". for other
categories, any string is accepted after being truncated to a maximum
supported length (currently 15 bytes). for LC_MESSAGES, the name is
kept regardless of whether libc itself can use such a message
translation locale, since applications using catgets or gettext should
be able to use message locales libc is not aware of. for other
categories, names which are not successfully loaded as locales (which,
at present, means all names) are treated as aliases for "C". setlocale
never fails.

locale settings are not yet used anywhere, so this commit should have
no visible effects except for the contents of the string returned by
setlocale.

src/env/__init_tls.c

@@ -16,6 +16,7 @@ int __init_tp(void *p)
 	if (!r) libc.can_do_threads = 1;
 	libc.has_thread_pointer = 1;
 	td->tid = td->pid = __syscall(SYS_set_tid_address, &td->tid);
+	td->locale = &libc.global_locale;
 	return 0;
 }
 

src/internal/libc.h

@@ -5,6 +5,11 @@
 #include <stdio.h>
 #include <limits.h>
 
+struct __locale_struct {
+	int ctype_utf8;
+	char *messages_name;
+};
+
 struct __libc {
 	int has_thread_pointer;
 	int can_do_threads;
@@ -16,6 +21,9 @@ struct __libc {
 	int ofl_lock[2];
 	size_t tls_size;
 	size_t page_size;
+	volatile int uselocale_cnt;
+	volatile int bytelocale_cnt_minus_1;
+	struct __locale_struct global_locale;
 };
 
 extern size_t __hwcap;

src/internal/locale_impl.h

@@ -1,5 +1,17 @@
 #include <locale.h>
+#include <stdlib.h>
+#include "libc.h"
+#include "pthread_impl.h"
 
-struct __locale_struct {
-	int dummy;
-};
+#define LOCALE_NAME_MAX 15
+
+int __setlocalecat(locale_t, int, const char *);
+
+#define CURRENT_LOCALE \
+	(libc.uselocale_cnt ? __pthread_self()->locale : &libc.global_locale)
+
+#define CURRENT_UTF8 \
+	(libc.bytelocale_cnt_minus_1<0 || __pthread_self()->locale->ctype_utf8)
+
+#undef MB_CUR_MAX
+#define MB_CUR_MAX (CURRENT_UTF8 ? 4 : 1)

src/locale/__setlocalecat.c

@@ -0,0 +1,46 @@
+#include <locale.h>
+#include <string.h>
+#include "locale_impl.h"
+#include "libc.h"
+#include "atomic.h"
+
+static const char envvars[][12] = {
+	"LC_CTYPE",
+	"LC_NUMERIC",
+	"LC_TIME",
+	"LC_COLLATE",
+	"LC_MONETARY",
+	"LC_MESSAGES",
+};
+
+int __setlocalecat(locale_t loc, int cat, const char *val)
+{
+	if (!*val) {
+		(val = getenv("LC_ALL")) ||
+		(val = getenv(envvars[cat])) ||
+		(val = getenv("LANG")) ||
+		(val = "C.UTF-8");
+	}
+
+	size_t n = strnlen(val, LOCALE_NAME_MAX);
+	int builtin = (val[0]=='C' && !val[1])
+		|| !strcmp(val, "C.UTF-8")
+		|| !strcmp(val, "POSIX");
+
+	switch (cat) {
+	case LC_CTYPE:
+		a_store(&loc->ctype_utf8, !builtin || val[1]=='.');
+		break;
+	case LC_MESSAGES:
+		if (builtin) {
+			loc->messages_name[0] = 0;
+		} else {
+			memcpy(loc->messages_name, val, n);
+			loc->messages_name[n] = 0;
+		}
+		/* fall through */
+	default:
+		break;
+	}
+	return 0;
+}

src/locale/duplocale.c

@@ -3,12 +3,19 @@
 #include "locale_impl.h"
 #include "libc.h"
 
-locale_t duplocale(locale_t old)
+locale_t __duplocale(locale_t old)
 {
-	locale_t new;
-	new = calloc(1, sizeof *new);
+	locale_t new = calloc(1, sizeof *new + LOCALE_NAME_MAX + 1);
+	if (!new) return 0;
+	new->messages_name = (void *)(new+1);
+
+	if (old == LC_GLOBAL_LOCALE) old = &libc.global_locale;
+	new->ctype_utf8 = old->ctype_utf8;
+	if (old->messages_name)
+		strcpy(new->messages_name, old->messages_name);
+
 	if (new && old != LC_GLOBAL_LOCALE) memcpy(new, old, sizeof *new);
 	return new;
 }
 
-weak_alias(duplocale, __duplocale);
+weak_alias(__duplocale, duplocale);

src/locale/newlocale.c

@@ -3,12 +3,24 @@
 #include "locale_impl.h"
 #include "libc.h"
 
-locale_t newlocale(int mask, const char *name, locale_t base)
+locale_t __newlocale(int mask, const char *name, locale_t loc)
 {
-	if (*name && strcmp(name, "C") && strcmp(name, "POSIX"))
-		return 0;
-	if (!base) base = calloc(1, sizeof *base);
-	return base;
+	int i;
+
+	if (!loc) {
+		loc = calloc(1, sizeof *loc + LOCALE_NAME_MAX + 1);
+		if (!loc) return 0;
+		loc->messages_name = (void *)(loc+1);
+		for (i=0; i<LC_ALL; i++)
+			if (!(mask & (1<<i)))
+				__setlocalecat(loc, i, "");
+	}
+
+	for (i=0; i<LC_ALL; i++)
+		if (mask & (1<<i))
+			__setlocalecat(loc, i, name);
+
+	return loc;
 }
 
-weak_alias(newlocale, __newlocale);
+weak_alias(__newlocale, newlocale);

src/locale/setlocale.c

@@ -1,9 +1,67 @@
 #include <locale.h>
+#include <stdlib.h>
+#include <string.h>
+#include "locale_impl.h"
+#include "libc.h"
+#include "atomic.h"
 
-char *setlocale(int category, const char *locale)
+static char buf[2+4*(LOCALE_NAME_MAX+1)];
+
+char *setlocale(int cat, const char *name)
 {
-	/* Note: plain "C" would be better, but puts some broken
-	 * software into legacy 8-bit-codepage mode, ignoring
-	 * the standard library's multibyte encoding */
-	return "C.UTF-8";
+	if (!libc.global_locale.messages_name) {
+		libc.global_locale.messages_name =
+			buf + 2 + 3*(LOCALE_NAME_MAX+1);
+	}
+
+	if ((unsigned)cat > LC_ALL) return 0;
+
+	/* For LC_ALL, setlocale is required to return a string which
+	 * encodes the current setting for all categories. The format of
+	 * this string is unspecified, and only the following code, which
+	 * performs both the serialization and deserialization, depends
+	 * on the format, so it can easily be changed if needed. */
+	if (cat == LC_ALL) {
+		if (name) {
+			char part[LOCALE_NAME_MAX+1];
+			int i, j;
+			if (name[0] && name[1]==';'
+			    && strlen(name) > 2 + 3*(LOCALE_NAME_MAX+1)) {
+				part[0] = name[0];
+				part[1] = 0;
+				setlocale(LC_CTYPE, part);
+				part[LOCALE_NAME_MAX] = 0;
+				for (i=LC_TIME; i<LC_MESSAGES; i++) {
+					memcpy(part, name + 2 + (i-2)*(LOCALE_NAME_MAX+1), LOCALE_NAME_MAX);
+					for (j=LOCALE_NAME_MAX-1; j && part[j]==';'; j--)
+						part[j] = 0;
+					setlocale(i, part);
+				}
+				setlocale(LC_MESSAGES, name + 2 + 3*(LOCALE_NAME_MAX+1));
+			} else {
+				for (i=0; i<LC_ALL; i++)
+					setlocale(i, name);
+			}
+		}
+		memset(buf, ';', 2 + 3*(LOCALE_NAME_MAX+1));
+		buf[0] = libc.global_locale.ctype_utf8 ? 'U' : 'C';
+		return buf;
+	}
+
+	if (name) {
+		int adj = libc.global_locale.ctype_utf8;
+		__setlocalecat(&libc.global_locale, cat, name);
+		adj -= libc.global_locale.ctype_utf8;
+		if (adj) a_fetch_add(&libc.bytelocale_cnt_minus_1, adj);
+	}
+
+	switch (cat) {
+	case LC_CTYPE:
+		return libc.global_locale.ctype_utf8 ? "C.UTF-8" : "C";
+	case LC_MESSAGES:
+		return libc.global_locale.messages_name[0]
+			? libc.global_locale.messages_name : "C";
+	default:
+		return "C";
+	}
 }

src/locale/uselocale.c

@@ -2,12 +2,25 @@
 #include "pthread_impl.h"
 #include "libc.h"
 
-locale_t uselocale(locale_t l)
+locale_t __uselocale(locale_t new)
 {
 	pthread_t self = __pthread_self();
 	locale_t old = self->locale;
-	if (l) self->locale = l;
-	return old;
+	locale_t global = &libc.global_locale;
+
+	if (new == LC_GLOBAL_LOCALE) new = global;
+
+	if (new && new != old) {
+		int adj = 0;
+		if (new == global) a_dec(&libc.uselocale_cnt);
+		else if (!new->ctype_utf8) adj++;
+		if (old == global) a_inc(&libc.uselocale_cnt);
+		else if (!old->ctype_utf8) adj--;
+		a_fetch_add(&libc.bytelocale_cnt_minus_1, adj);
+		self->locale = new;
+	}
+
+	return old == global ? LC_GLOBAL_LOCALE : old;
 }
 
-weak_alias(uselocale, __uselocale);
+weak_alias(__uselocale, uselocale);

src/thread/pthread_create.c

@@ -57,6 +57,12 @@ _Noreturn void pthread_exit(void *result)
 		exit(0);
 	}
 
+	if (self->locale != &libc.global_locale) {
+		a_dec(&libc.uselocale_cnt);
+		if (self->locale->ctype_utf8)
+			a_dec(&libc.bytelocale_cnt_minus_1);
+	}
+
 	if (self->detached && self->map_base) {
 		/* Detached threads must avoid the kernel clear_child_tid
 		 * feature, since the virtual address will have been
@@ -205,6 +211,7 @@ int pthread_create(pthread_t *restrict res, const pthread_attr_t *restrict attrp
 	new->start_arg = arg;
 	new->self = new;
 	new->tsd = (void *)tsd;
+	new->locale = &libc.global_locale;
 	if (attr._a_detach) {
 		new->detached = 1;
 		flags -= CLONE_CHILD_CLEARTID;