MSVC: Windows-native implementation for subset of Pthreads API

This patch implements native to Windows subset of pthreads API used by Git.
It allows to remove Pthreads for Win32 dependency for MSVC, msysgit and
Cygwin.

[J6t: If the MinGW build was built as part of the msysgit build
environment, then threading was already enabled because the
pthreads-win32 package is available in msysgit. With this patch, we can now
enable threaded code unconditionally.]

Signed-off-by: Andrzej K. Haczewski <ahaczewski@gmail.com>
Signed-off-by: Johannes Sixt <j6t@kdbg.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

6 files changed, 217 insertions, 11 deletions

diff --git a/Makefile b/Makefile
index 6933555660..7f5814c7a3 100644
--- a/Makefile
+++ b/Makefile
@@ -478,6 +478,7 @@ LIB_H += commit.h
 LIB_H += compat/bswap.h
 LIB_H += compat/cygwin.h
 LIB_H += compat/mingw.h
+LIB_H += compat/win32/pthread.h
 LIB_H += csum-file.h
 LIB_H += decorate.h
 LIB_H += delta.h
@@ -996,15 +997,15 @@ ifeq ($(uname_S),Windows)
 	NO_REGEX = YesPlease
 	NO_CURL = YesPlease
 	NO_PYTHON = YesPlease
-	NO_PTHREADS = YesPlease
 	BLK_SHA1 = YesPlease
+	THREADED_DELTA_SEARCH = YesPlease
 
 	CC = compat/vcbuild/scripts/clink.pl
 	AR = compat/vcbuild/scripts/lib.pl
 	CFLAGS =
 	BASIC_CFLAGS = -nologo -I. -I../zlib -Icompat/vcbuild -Icompat/vcbuild/include -DWIN32 -D_CONSOLE -DHAVE_STRING_H -D_CRT_SECURE_NO_WARNINGS -D_CRT_NONSTDC_NO_DEPRECATE
-	COMPAT_OBJS = compat/msvc.o compat/fnmatch/fnmatch.o compat/winansi.o
-	COMPAT_CFLAGS = -D__USE_MINGW_ACCESS -DNOGDI -DHAVE_STRING_H -DHAVE_ALLOCA_H -Icompat -Icompat/fnmatch -Icompat/regex -Icompat/fnmatch -DSTRIP_EXTENSION=\".exe\"
+	COMPAT_OBJS = compat/msvc.o compat/fnmatch/fnmatch.o compat/winansi.o compat/win32/pthread.o
+	COMPAT_CFLAGS = -D__USE_MINGW_ACCESS -DNOGDI -DHAVE_STRING_H -DHAVE_ALLOCA_H -Icompat -Icompat/fnmatch -Icompat/regex -Icompat/fnmatch -Icompat/win32 -DSTRIP_EXTENSION=\".exe\"
 	BASIC_LDFLAGS = -IGNORE:4217 -IGNORE:4049 -NOLOGO -SUBSYSTEM:CONSOLE -NODEFAULTLIB:MSVCRT.lib
 	EXTLIBS = advapi32.lib shell32.lib wininet.lib ws2_32.lib
 	lib =
@@ -1048,9 +1049,11 @@ ifneq (,$(findstring MINGW,$(uname_S)))
 	NO_REGEX = YesPlease
 	NO_PYTHON = YesPlease
 	BLK_SHA1 = YesPlease
+	THREADED_DELTA_SEARCH = YesPlease
 	COMPAT_CFLAGS += -D__USE_MINGW_ACCESS -DNOGDI -Icompat -Icompat/fnmatch
 	COMPAT_CFLAGS += -DSTRIP_EXTENSION=\".exe\"
-	COMPAT_OBJS += compat/mingw.o compat/fnmatch/fnmatch.o compat/winansi.o
+	COMPAT_OBJS += compat/mingw.o compat/fnmatch/fnmatch.o compat/winansi.o \
+		compat/win32/pthread.o
 	EXTLIBS += -lws2_32
 	X = .exe
 ifneq (,$(wildcard ../THIS_IS_MSYSGIT))
@@ -1060,10 +1063,8 @@ ifneq (,$(wildcard ../THIS_IS_MSYSGIT))
 	EXTLIBS += /mingw/lib/libz.a
 	NO_R_TO_GCC_LINKER = YesPlease
 	INTERNAL_QSORT = YesPlease
-	THREADED_DELTA_SEARCH = YesPlease
 else
 	NO_CURL = YesPlease
-	NO_PTHREADS = YesPlease
 endif
 endif
 
diff --git a/builtin-pack-objects.c b/builtin-pack-objects.c
index 4429d53a1e..890f45cf20 100644
--- a/builtin-pack-objects.c
+++ b/builtin-pack-objects.c
@@ -1256,15 +1256,15 @@ static int delta_cacheable(unsigned long src_size, unsigned long trg_size,
 
 #ifdef THREADED_DELTA_SEARCH
 
-static pthread_mutex_t read_mutex = PTHREAD_MUTEX_INITIALIZER;
+static pthread_mutex_t read_mutex;
 #define read_lock()		pthread_mutex_lock(&read_mutex)
 #define read_unlock()		pthread_mutex_unlock(&read_mutex)
 
-static pthread_mutex_t cache_mutex = PTHREAD_MUTEX_INITIALIZER;
+static pthread_mutex_t cache_mutex;
 #define cache_lock()		pthread_mutex_lock(&cache_mutex)
 #define cache_unlock()		pthread_mutex_unlock(&cache_mutex)
 
-static pthread_mutex_t progress_mutex = PTHREAD_MUTEX_INITIALIZER;
+static pthread_mutex_t progress_mutex;
 #define progress_lock()		pthread_mutex_lock(&progress_mutex)
 #define progress_unlock()	pthread_mutex_unlock(&progress_mutex)
 
@@ -1591,7 +1591,26 @@ struct thread_params {
 	unsigned *processed;
 };
 
-static pthread_cond_t progress_cond = PTHREAD_COND_INITIALIZER;
+static pthread_cond_t progress_cond;
+
+/*
+ * Mutex and conditional variable can't be statically-initialized on Windows.
+ */
+static void init_threaded_search(void)
+{
+	pthread_mutex_init(&read_mutex, NULL);
+	pthread_mutex_init(&cache_mutex, NULL);
+	pthread_mutex_init(&progress_mutex, NULL);
+	pthread_cond_init(&progress_cond, NULL);
+}
+
+static void cleanup_threaded_search(void)
+{
+	pthread_cond_destroy(&progress_cond);
+	pthread_mutex_destroy(&read_mutex);
+	pthread_mutex_destroy(&cache_mutex);
+	pthread_mutex_destroy(&progress_mutex);
+}
 
 static void *threaded_find_deltas(void *arg)
 {
@@ -1630,10 +1649,13 @@ static void ll_find_deltas(struct object_entry **list, unsigned list_size,
 	struct thread_params *p;
 	int i, ret, active_threads = 0;
 
+	init_threaded_search();
+
 	if (!delta_search_threads)	/* --threads=0 means autodetect */
 		delta_search_threads = online_cpus();
 	if (delta_search_threads <= 1) {
 		find_deltas(list, &list_size, window, depth, processed);
+		cleanup_threaded_search();
 		return;
 	}
 	if (progress > pack_to_stdout)
@@ -1748,6 +1770,7 @@ static void ll_find_deltas(struct object_entry **list, unsigned list_size,
 			active_threads--;
 		}
 	}
+	cleanup_threaded_search();
 	free(p);
 }
 
diff --git a/compat/mingw.c b/compat/mingw.c
index 73762473c5..74ffc1834f 100644
--- a/compat/mingw.c
+++ b/compat/mingw.c
@@ -3,7 +3,7 @@
 #include <conio.h>
 #include "../strbuf.h"
 
-static int err_win_to_posix(DWORD winerr)
+int err_win_to_posix(DWORD winerr)
 {
 	int error = ENOSYS;
 	switch(winerr) {
diff --git a/compat/mingw.h b/compat/mingw.h
index afe12ea554..e254fb4e06 100644
--- a/compat/mingw.h
+++ b/compat/mingw.h
@@ -310,3 +310,8 @@ struct 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/win32/pthread.c b/compat/win32/pthread.c
new file mode 100644
index 0000000000..631c0a46ea
--- /dev/null
+++ b/compat/win32/pthread.c
@@ -0,0 +1,110 @@
+/*
+ * Copyright (C) 2009 Andrzej K. Haczewski <ahaczewski@gmail.com>
+ *
+ * DISCLAMER: 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->sema = CreateSemaphore(NULL, 0, LONG_MAX, NULL);
+	if (!cond->sema)
+		die("CreateSemaphore() failed");
+	return 0;
+}
+
+int pthread_cond_destroy(pthread_cond_t *cond)
+{
+	CloseHandle(cond->sema);
+	cond->sema = NULL;
+
+	return 0;
+}
+
+int pthread_cond_wait(pthread_cond_t *cond, CRITICAL_SECTION *mutex)
+{
+	InterlockedIncrement(&cond->waiters);
+
+	/*
+	 * 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);
+
+	/* we're done waiting, so make sure we decrease waiters count */
+	InterlockedDecrement(&cond->waiters);
+
+	/* lock external mutex again */
+	EnterCriticalSection(mutex);
+
+	return 0;
+}
+
+int pthread_cond_signal(pthread_cond_t *cond)
+{
+	/*
+	 * Access to waiters count is atomic; see "Interlocked Variable Access"
+	 * http://msdn.microsoft.com/en-us/library/ms684122(VS.85).aspx
+	 */
+	int have_waiters = cond->waiters > 0;
+
+	/*
+	 * Signal only when there are waiters
+	 */
+	if (have_waiters)
+		return ReleaseSemaphore(cond->sema, 1, NULL) ?
+			0 : err_win_to_posix(GetLastError());
+	else
+		return 0;
+}
diff --git a/compat/win32/pthread.h b/compat/win32/pthread.h
new file mode 100644
index 0000000000..b8e1bcb046
--- /dev/null
+++ b/compat/win32/pthread.h
@@ -0,0 +1,67 @@
+/*
+ * 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 {
+	volatile LONG waiters;
+	HANDLE sema;
+} 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);
+
+/*
+ * 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 */