Index: winsup/cygwin/Makefile.in
===================================================================
RCS file: /cvs/src/src/winsup/cygwin/Makefile.in,v
retrieving revision 1.248
diff -u -p -r1.248 Makefile.in
--- winsup/cygwin/Makefile.in	2 May 2011 19:14:39 -0000	1.248
+++ winsup/cygwin/Makefile.in	19 Aug 2011 21:31:25 -0000
@@ -233,7 +233,7 @@ EXTRALIBS:=libautomode.a libbinmode.a li
 INSTOBJS:=automode.o binmode.o textmode.o textreadmode.o
 TARGET_LIBS:=$(LIB_NAME) $(CYGWIN_START) $(GMON_START) $(LIBGMON_A) $(SUBLIBS) $(INSTOBJS) $(EXTRALIBS)
 
-ifneq "${filter -O%,$(CFLAGS)}" ""
+ifneq "" ""
 cygheap_CFLAGS:=-fomit-frame-pointer
 cygthread_CFLAGS:=-fomit-frame-pointer
 cygtls_CFLAGS:=-fomit-frame-pointer
@@ -286,6 +286,16 @@ syscalls_CFLAGS:=-fomit-frame-pointer
 sysconf_CFLAGS:=-fomit-frame-pointer
 uinfo_CFLAGS:=-fomit-frame-pointer
 endif
+EXTRA_DEPENDENCIES_1=gcrt1.o boundbuffer.o instrument.o gmon.o mcount.o profil.o
+EXTRA_LDFLAGS_1=../w32api/lib/libkernel32.a
+ifeq '$(profile)' '1'
+override CFLAGS=-MMD -DPROFILE ${$(*F)_CFLAGS} ${PROFILE_CFLAGS_${shell echo $(EXTRA_DEPENDENCIES_1:.o=) pthread kernel32 malloc_wrapper pseudo-reloc libstdcxx_wrapper cxx sync|grep -q "$(*F)";ret=$$?;echo $$ret;echo $(*F) $$ret 1>&2}} -fmerge-constants -ftracer \
+  -mno-use-libstdc-wrappers $(CCEXTRA)
+PROFILE_CFLAGS_1=-O4 -g -pg -finstrument-functions
+PROFILE_CFLAGS_0=-O4 -g -fomit-frame-pointer -Wno-error=unused-but-set-variable
+gcrt1.o: $(srcdir)/gcrt0.c
+	$(COMPILE_CC) -o $(@D)/$(*F)$o $<
+endif
 
 fhandler_proc_CFLAGS+=-DUSERNAME="\"$(USER)\"" -DHOSTNAME="\"$(HOSTNAME)\""
 fhandler_proc_CFLAGS+=-DGCC_VERSION="\"`$(CC) -v 2>&1 | tail -n 1`\""
@@ -390,15 +400,13 @@ maintainer-clean realclean: clean
 	@echo "This command is intended for maintainers to use;"
 	@echo "it deletes files that may require special tools to rebuild."
 	-rm -fr configure
-
-
 # Rule to build cygwin.dll
-$(TEST_DLL_NAME): $(LDSCRIPT) dllfixdbg $(DLL_OFILES) $(DLL_IMPORTS) $(LIBSERVER) $(LIBC) $(LIBM) $(API_VER) Makefile winver_stamp
+$(TEST_DLL_NAME): $(LDSCRIPT) dllfixdbg $(EXTRA_DEPENDENCIES_$(profile)) $(DLL_OFILES) $(DLL_IMPORTS) $(LIBSERVER) $(LIBC) $(LIBM) $(API_VER) Makefile winver_stamp
 	$(CXX) $(CXXFLAGS) -Wl,--gc-sections $(nostdlib) -Wl,-T$(firstword $^) \
 	-Wl,--heap=0 -Wl,--out-implib,cygdll.a -shared -o $@ \
-	-e $(DLL_ENTRY) $(DEF_FILE) $(DLL_OFILES) version.o winver.o \
+	-e $(DLL_ENTRY) $(DEF_FILE) $(EXTRA_DEPENDENCIES_$(profile)) $(DLL_OFILES) version.o winver.o \
 	$(MALLOC_OBJ) $(LIBSERVER) $(LIBM) $(LIBC) \
-	-lgcc $(DLL_IMPORTS) -Wl,-Map,cygwin.map
+	-lgcc $(EXTRA_LDFLAGS_$(profile)) $(DLL_IMPORTS) -Wl,-Map,cygwin.map
 	@$(word 2,$^) $(OBJDUMP) $(OBJCOPY) $@ ${patsubst %0.dll,%1.dbg,$@}
 	@ln -f $@ new-$(DLL_NAME)
 
Index: winsup/cygwin/dcrt0.cc
===================================================================
RCS file: /cvs/src/src/winsup/cygwin/dcrt0.cc,v
retrieving revision 1.406
diff -u -p -r1.406 dcrt0.cc
--- winsup/cygwin/dcrt0.cc	18 Aug 2011 15:59:16 -0000	1.406
+++ winsup/cygwin/dcrt0.cc	19 Aug 2011 21:31:25 -0000
@@ -37,7 +37,7 @@ details. */
 #include "cygxdr.h"
 #include "fenv.h"
 #include "ntdll.h"
-
+#include "profil.h"
 #define MAX_AT_FILE_LEVEL 10
 
 #define PREMAIN_LEN (sizeof (user_data->premain) / sizeof (user_data->premain[0]))
@@ -648,12 +648,16 @@ init_windows_system_directory ()
   windows_system_directory[windows_system_directory_length++] = L'\\';
   windows_system_directory[windows_system_directory_length] = L'\0';
 }
-
+extern "C" {
+  void _monstartup (void);
+  void _mcleanup (void);
+}
 void
 dll_crt0_0 ()
 {
   init_windows_system_directory ();
   init_global_security ();
+  _monstartup();
   initial_env ();
 
   SetErrorMode (SEM_FAILCRITICALERRORS | SEM_NOGPFAULTERRORBOX);
@@ -695,6 +699,9 @@ dll_crt0_0 ()
 	    break;
 	}
     }
+#ifdef PROFILE
+  atexit (&_mcleanup);
+#endif
 
   user_data->threadinterface->Init ();
 
Index: winsup/cygwin/exceptions.cc
===================================================================
RCS file: /cvs/src/src/winsup/cygwin/exceptions.cc,v
retrieving revision 1.360
diff -u -p -r1.360 exceptions.cc
--- winsup/cygwin/exceptions.cc	3 Aug 2011 16:40:47 -0000	1.360
+++ winsup/cygwin/exceptions.cc	19 Aug 2011 21:31:25 -0000
@@ -31,7 +31,7 @@ details. */
 #include "child_info.h"
 #include "ntdll.h"
 #include "exception.h"
-
+#include "profil.h"
 #define CALL_HANDLER_RETRY_OUTER 10
 #define CALL_HANDLER_RETRY_INNER 10
 
@@ -937,6 +937,7 @@ ctrl_c_handler (DWORD type)
       if (myself->cygstarted)	/* Was this process created by a cygwin process? */
 	return TRUE;		/* Yes.  Let the parent eventually handle CTRL-C issues. */
       debug_printf ("exiting with status %p", STATUS_CONTROL_C_EXIT);
+      profile_thread_off();
       ExitProcess (STATUS_CONTROL_C_EXIT);
     }
 
Index: winsup/cygwin/external.cc
===================================================================
RCS file: /cvs/src/src/winsup/cygwin/external.cc,v
retrieving revision 1.123
diff -u -p -r1.123 external.cc
--- winsup/cygwin/external.cc	1 Jun 2011 01:20:27 -0000	1.123
+++ winsup/cygwin/external.cc	19 Aug 2011 21:31:25 -0000
@@ -30,7 +30,7 @@ details. */
 #include <stdlib.h>
 #include <wchar.h>
 #include <iptypes.h>
-
+#include "profil.h"
 child_info *get_cygwin_startup_info ();
 static void exit_process (UINT, bool) __attribute__((noreturn));
 
@@ -180,6 +180,7 @@ sync_winenv ()
 static void
 exit_process (UINT status, bool useTerminateProcess)
 {
+  profile_thread_off();
   pid_t pid = getpid ();
   external_pinfo * ep = fillout_pinfo (pid, 1);
   DWORD dwpid = ep ? ep->dwProcessId : pid;
Index: winsup/cygwin/gcrt0.c
===================================================================
RCS file: /cvs/src/src/winsup/cygwin/gcrt0.c,v
retrieving revision 1.5
diff -u -p -r1.5 gcrt0.c
--- winsup/cygwin/gcrt0.c	11 Sep 2001 20:01:00 -0000	1.5
+++ winsup/cygwin/gcrt0.c	19 Aug 2011 21:31:25 -0000
@@ -15,9 +15,9 @@ extern u_char etext asm ("etext");
 extern u_char eprol asm ("__eprol");
 extern void _mcleanup (void);
 extern void monstartup (u_long, u_long);
-
+#ifndef PROFILE
 void _monstartup (void) __attribute__((__constructor__));
-
+#endif
 /* startup initialization for -pg support */
 
 void
@@ -33,7 +33,9 @@ _monstartup (void)
     return;
 
   monstartup ((u_long) &eprol, (u_long) &etext);
+#ifndef PROFILE
   atexit (&_mcleanup);
+#endif
 }
 
 asm (".text");
Index: winsup/cygwin/gmon.c
===================================================================
RCS file: /cvs/src/src/winsup/cygwin/gmon.c,v
retrieving revision 1.7
diff -u -p -r1.7 gmon.c
--- winsup/cygwin/gmon.c	30 Aug 2010 01:57:36 -0000	1.7
+++ winsup/cygwin/gmon.c	19 Aug 2011 21:31:25 -0000
@@ -34,11 +34,12 @@
 #if !defined(lint) && defined(LIBC_SCCS)
 static char rcsid[] = "$OpenBSD: gmon.c,v 1.8 1997/07/23 21:11:27 kstailey Exp $";
 #endif
-
+#include "winsup.h"
 #include "winlean.h"
 #include <fcntl.h>
 #include <stdio.h>
 #include <unistd.h>
+#include <string.h>
 #include <gmon.h>
 #include <stdlib.h>
 
@@ -47,9 +48,9 @@ static char rcsid[] = "$OpenBSD: gmon.c,
 /* XXX needed? */
 //extern char *minbrk __asm ("minbrk");
 
-struct gmonparam _gmonparam = { GMON_PROF_OFF };
+struct gmonparam NO_COPY_INIT _gmonparam = { GMON_PROF_OFF };
 
-static int	s_scale;
+int	NO_COPY_INIT s_scale;
 /* see profil(2) where this is describe (incorrectly) */
 #define		SCALE_1_TO_1	0x10000L
 
@@ -60,7 +61,7 @@ void	moncontrol __P((int));
 static void *
 fake_sbrk(int size)
 {
-    void *rv = malloc(size);
+    void *rv = LocalAlloc(0x40,size);
     if (rv)
       return rv;
     else
@@ -93,7 +94,7 @@ monstartup(lowpc, highpc)
 		p->tolimit = MAXARCS;
 	p->tossize = p->tolimit * sizeof(struct tostruct);
 
-	cp = fake_sbrk(p->kcountsize + p->fromssize + p->tossize);
+	cp = fake_sbrk(5*p->kcountsize + p->fromssize + p->tossize);
 	if (cp == (char *)-1) {
 		ERR("monstartup: out of memory\n");
 		return;
@@ -105,6 +106,8 @@ monstartup(lowpc, highpc)
 	cp += p->tossize;
 	p->kcount = (u_short *)cp;
 	cp += p->kcountsize;
+	p->comm_kcount=(u_int64_t*)cp;
+	cp += 4*p->kcountsize;
 	p->froms = (u_short *)cp;
 
 	/* XXX minbrk needed? */
@@ -136,6 +139,7 @@ monstartup(lowpc, highpc)
 void
 _mcleanup()
 {
+	unsigned i;
 	int fd;
 	int hz;
 	int fromindex;
@@ -204,8 +208,11 @@ _mcleanup()
 	}
 #else
 	{
-	  char gmon_out[] = "gmon.out";
-	  proffile = gmon_out;
+    char gmon_out[1024];
+    char proc_modulename[1024];
+    GetModuleFileNameA( 0, proc_modulename, 1024 );
+    sprintf( gmon_out, "gmon.%s.%d.out", strrchr( proc_modulename, '\\' ) + 1, (int) GetCurrentProcessId() );
+    proffile = gmon_out;
 	}
 #endif
 
@@ -230,6 +237,15 @@ _mcleanup()
 	hdr->ncnt = p->kcountsize + sizeof(gmonhdr);
 	hdr->version = GMONVERSION;
 	hdr->profrate = hz;
+	for ( i = 0; i < p->kcountsize / 2; i++ )
+    {
+    if ( p->comm_kcount[i] < prof.perffreq )
+      continue;
+    else
+      {
+      p->kcount[i] = p->comm_kcount[i] / prof.perffreq;
+      }
+    }
 	write(fd, (char *)hdr, sizeof *hdr);
 	write(fd, p->kcount, p->kcountsize);
 	endfrom = p->fromssize / sizeof(*p->froms);
Index: winsup/cygwin/gmon.h
===================================================================
RCS file: /cvs/src/src/winsup/cygwin/gmon.h,v
retrieving revision 1.2
diff -u -p -r1.2 gmon.h
--- winsup/cygwin/gmon.h	24 Jun 2001 22:26:51 -0000	1.2
+++ winsup/cygwin/gmon.h	19 Aug 2011 21:31:25 -0000
@@ -134,6 +134,7 @@ struct rawarc {
 struct gmonparam {
 	int		state;
 	u_short		*kcount;
+	u_int64_t *comm_kcount;
 	u_long		kcountsize;
 	u_short		*froms;
 	u_long		fromssize;
Index: winsup/cygwin/init.cc
===================================================================
RCS file: /cvs/src/src/winsup/cygwin/init.cc,v
retrieving revision 1.84
diff -u -p -r1.84 init.cc
--- winsup/cygwin/init.cc	18 Aug 2011 15:59:16 -0000	1.84
+++ winsup/cygwin/init.cc	19 Aug 2011 21:31:25 -0000
@@ -13,6 +13,8 @@ details. */
 #include "cygtls.h"
 #include "ntdll.h"
 #include "shared_info.h"
+#include "profil.h"
+#include "instrument.h"
 
 static DWORD _my_oldfunc;
 
@@ -29,7 +31,8 @@ threadfunc_fe (VOID *arg)
   asm volatile ("andl $-16,%%esp" ::: "%esp");
   _cygtls::call ((DWORD (*)  (void *, void *)) TlsGetValue (_my_oldfunc), arg);
 }
-
+extern "C" DWORD __stdcall
+      worker_consumer(void* arg);
 /* If possible, redirect the thread entry point to a cygwin routine which
    adds tls stuff to the stack. */
 static void
@@ -106,6 +109,7 @@ respawn_wow64_process ()
 	api_fatal ("Waiting for process %d failed, %E", pi.dwProcessId);
       GetExitCodeProcess (pi.hProcess, &ret);
       CloseHandle (pi.hProcess);
+      profile_thread_off();
       ExitProcess (ret);
     }
 }
@@ -120,6 +124,8 @@ dll_entry (HANDLE h, DWORD reason, void 
   switch (reason)
     {
     case DLL_PROCESS_ATTACH:
+      __cyg_profile_func_ctor();
+      __cyg_profile_tls_ctor();
       wincap.init ();
       init_console_handler (false);
 
@@ -143,8 +149,11 @@ dll_entry (HANDLE h, DWORD reason, void 
     case DLL_PROCESS_DETACH:
       if (dynamically_loaded)
 	shared_destroy ();
+      __cyg_profile_tls_dtor();
+      __cyg_profile_func_dtor();
       break;
     case DLL_THREAD_ATTACH:
+      __cyg_profile_tls_ctor();
       if (dll_finished_loading)
 	munge_threadfunc ();
       break;
@@ -153,6 +162,7 @@ dll_entry (HANDLE h, DWORD reason, void 
 	  && (PVOID) &_my_tls > (PVOID) &wow64_test_stack_marker
 	  && _my_tls.isinitialized ())
 	_my_tls.remove (0);
+	__cyg_profile_tls_dtor();
       /* Windows 2000 has a bug in NtTerminateThread.  Instead of releasing
 	 the stack at teb->DeallocationStack it uses the value of
 	 teb->Tib.StackLimit to evaluate the stack address.  So we just claim
Index: winsup/cygwin/pinfo.cc
===================================================================
RCS file: /cvs/src/src/winsup/cygwin/pinfo.cc,v
retrieving revision 1.279
diff -u -p -r1.279 pinfo.cc
--- winsup/cygwin/pinfo.cc	13 Aug 2011 10:28:15 -0000	1.279
+++ winsup/cygwin/pinfo.cc	19 Aug 2011 21:31:25 -0000
@@ -29,7 +29,7 @@ details. */
 #include "cygtls.h"
 #include "tls_pbuf.h"
 #include "child_info.h"
-
+#include "profil.h"
 class pinfo_basic: public _pinfo
 {
 public:
@@ -204,6 +204,7 @@ pinfo::exit (DWORD n)
   if (!self->cygstarted)
     exitcode = ((exitcode & 0xff) << 8) | ((exitcode >> 8) & 0xff);
   sigproc_printf ("Calling ExitProcess n %p, exitcode %p", n, exitcode);
+  profile_thread_off();
   ExitProcess (exitcode);
 }
 # undef self
Index: winsup/cygwin/profil.c
===================================================================
RCS file: /cvs/src/src/winsup/cygwin/profil.c,v
retrieving revision 1.8
diff -u -p -r1.8 profil.c
--- winsup/cygwin/profil.c	30 Aug 2010 01:57:36 -0000	1.8
+++ winsup/cygwin/profil.c	19 Aug 2011 21:31:25 -0000
@@ -7,17 +7,18 @@
    This software is a copyrighted work licensed under the terms of the
    Cygwin license.  Please consult the file "CYGWIN_LICENSE" for
    details. */
-
+#include "winsup.h"
 #include "winlean.h"
 #include <sys/types.h>
 #include <errno.h>
-
+#include "gmon.h"
 #include <profil.h>
 
 #define SLEEPTIME (1000 / PROF_HZ)
 
+extern SECURITY_ATTRIBUTES sec_none_nih;
 /* global profinfo for profil() call */
-static struct profinfo prof;
+struct profinfo NO_COPY prof;
 
 /* Get the pc for thread THR */
 
@@ -85,21 +86,44 @@ profile_off (struct profinfo *p)
 {
   if (p->profthr)
     {
-      TerminateThread (p->profthr, 0);
-      CloseHandle (p->profthr);
+      if (prof.queue.worker_enabled)
+        {
+          profile_thread_off();
+          boundbuffer_dtor(&p->queue);
+          while (boundbuffer_empty(&p->queue))
+            {
+              message msg;
+              boundbuffer_dequeue_nolock(&p->queue, &msg);
+              unsigned idx = PROFIDX ((unsigned)msg.pv, p->lowpc, p->scale);
+              if (!msg.ullval)
+                continue;
+              _gmonparam.comm_kcount[idx] += msg.ullval;
+            }
+        }
+      CloseHandle(p->profthr);
+      CloseHandle(prof.operational);
+      p->profthr = 0;
+
     }
+#if 0
   if (p->targthr)
     CloseHandle (p->targthr);
+#endif
   return 0;
 }
-
+static void __stdcall
+apc_spawnthread(unsigned long arg)
+{
+  struct profinfo* p = (struct profinfo*) arg;
+  p->profthr = CreateThread(&sec_none_nih, 0, worker_consumer, (void *) p, 0,
+	  0);
+}
 /* Create a timer thread and pass it a pointer P to the profiling buffer. */
 
 static int
 profile_on (struct profinfo *p)
 {
-  DWORD thrid;
-
+#if 0
   /* get handle for this thread */
   if (!DuplicateHandle (GetCurrentProcess (), GetCurrentThread (),
 			GetCurrentProcess (), &p->targthr, 0, FALSE,
@@ -108,15 +132,12 @@ profile_on (struct profinfo *p)
       errno = ESRCH;
       return -1;
     }
-
-  p->profthr = CreateThread (0, 0, profthr_func, (void *) p, 0, &thrid);
-  if (!p->profthr)
-    {
-      CloseHandle (p->targthr);
-      p->targthr = 0;
-      errno = EAGAIN;
-      return -1;
-    }
+#endif
+  QueryPerformanceFrequency((PLARGE_INTEGER) &prof.perffreq);
+  prof.perffreq /= PROF_HZ;
+  boundbuffer_initial(&prof.queue);
+  prof.operational = CreateSemaphoreA(&sec_none_nih, 0, 1, 0);
+  QueueUserAPC(apc_spawnthread, GetCurrentThread(), p);
   return 0;
 }
 
@@ -170,4 +191,11 @@ profil (char *samples, size_t size, u_lo
 {
   return profile_ctl (&prof, samples, size, offset, scale);
 }
+void
+profile_thread_off()
+{
+  int enabled = __sync_fetch_and_and(&prof.queue.worker_enabled, 0);
+  if (enabled)
+	WaitForSingleObject(prof.profthr, INFINITE);
+}
 
Index: winsup/cygwin/profil.h
===================================================================
RCS file: /cvs/src/src/winsup/cygwin/profil.h,v
retrieving revision 1.4
diff -u -p -r1.4 profil.h
--- winsup/cygwin/profil.h	28 Apr 2003 20:10:53 -0000	1.4
+++ winsup/cygwin/profil.h	19 Aug 2011 21:31:25 -0000
@@ -7,10 +7,14 @@ This file is part of Cygwin.
 This software is a copyrighted work licensed under the terms of the
 Cygwin license.  Please consult the file "CYGWIN_LICENSE" for
 details. */
-
+#ifndef PROFIL_H
+#define PROFIL_H
+#ifdef __cplusplus
+extern "C"{
+#endif
 /* profiling frequency.  (No larger than 1000) */
-#define PROF_HZ			100
-
+#define PROF_HZ			1000UL
+#include "boundbuffer.h"
 /* convert an addr to an index */
 #define PROFIDX(pc, base, scale)	\
   ({									\
@@ -37,8 +41,21 @@ struct profinfo {
     u_short *counter;			/* profiling counters */
     u_long lowpc, highpc;		/* range to be profiled */
     u_int scale;			/* scale value of bins */
+    u_int64_t perffreq;
+    struct boundbuffer queue;
+    _WINHANDLE operational;
 };
-
+extern struct profinfo prof;
 int profile_ctl(struct profinfo *, char *, size_t, u_long, u_int);
 int profil(char *, size_t, u_long, u_int);
-
+extern void profile_thread_off();
+struct clk
+{
+  unsigned idx;
+  void* pc[0x10000];
+  unsigned long long tsc[0x10000];
+};
+#ifdef __cplusplus
+}
+#endif
+#endif