diff --git a/winsup/cygwin/dll_init.cc b/winsup/cygwin/dll_init.cc
index f94c6698d..2204533c6 100644
--- a/winsup/cygwin/dll_init.cc
+++ b/winsup/cygwin/dll_init.cc
@@ -306,8 +306,9 @@ dll_list::alloc (HINSTANCE h, per_process *p, dll_type type)
   guard (true);
   /* Already loaded?  For linked DLLs, only compare the basenames.  Linked
      DLLs are loaded using just the basename and the default DLL search path.
-     The Windows loader picks up the first one it finds.  */
-  dll *d = (type == DLL_LINK) ? dlls.find_by_modname (modname) : dlls[ntname];
+     The Windows loader picks up the first one it finds.
+     This also applies to cygwin1.dll and the main-executable (DLL_SELF).  */
+  dll *d = (type != DLL_LOAD) ? dlls.find_by_modname (modname) : dlls[ntname];
   if (d)
     {
       /* We only get here in the forkee. */
@@ -339,7 +340,8 @@ dll_list::alloc (HINSTANCE h, per_process *p, dll_type type)
       d->modname = d->ntname + (modname - ntname);
       d->handle = h;
       d->count = 0;	/* Reference counting performed in dlopen/dlclose. */
-      d->has_dtors = true;
+      /* DLL_SELF dtors (main-executable, cygwin1.dll) are run elsewhere */
+      d->has_dtors = type != DLL_SELF;
       d->p = p;
       d->ndeps = 0;
       d->deps = NULL;
@@ -526,7 +528,7 @@ dll_list::find (void *retaddr)
 
   dll *d = &start;
   while ((d = d->next))
-    if (d->handle == h)
+    if (d->type != DLL_SELF && d->handle == h)
       break;
   return d;
 }
@@ -566,11 +568,22 @@ dll_list::detach (void *retaddr)
 void
 dll_list::init ()
 {
+  track_self ();
+
   /* Walk the dll chain, initializing each dll */
   dll *d = &start;
   dll_global_dtors_recorded = d->next != NULL;
   while ((d = d->next))
-    d->init ();
+    if (d->type != DLL_SELF) /* linked and early loaded dlls */
+      d->init ();
+}
+
+void
+dll_list::track_self ()
+{
+  /* for cygwin1.dll and main-executable: maintain hardlinks only */
+  alloc (cygwin_hmodule, user_data, DLL_SELF);
+  main_executable = alloc (GetModuleHandle (NULL), user_data, DLL_SELF);
 }
 
 #define A64K (64 * 1024)
@@ -637,7 +650,7 @@ dll_list::reserve_space ()
 
 /* Reload DLLs after a fork.  Iterates over the list of dynamically loaded
    DLLs and attempts to load them in the same place as they were loaded in the
-   parent. */
+   parent.  Updates main-executable and cygwin1.dll tracking. */
 void
 dll_list::load_after_fork (HANDLE parent)
 {
@@ -647,6 +660,7 @@ dll_list::load_after_fork (HANDLE parent)
   in_load_after_fork = true;
   if (reload_on_fork)
     load_after_fork_impl (parent, dlls.istart (DLL_LOAD), 0);
+  track_self ();
   in_load_after_fork = false;
 }
 
diff --git a/winsup/cygwin/dll_init.h b/winsup/cygwin/dll_init.h
index 4897c420f..369fc5427 100644
--- a/winsup/cygwin/dll_init.h
+++ b/winsup/cygwin/dll_init.h
@@ -40,6 +40,7 @@ struct per_module
 typedef enum
 {
   DLL_NONE,
+  DLL_SELF, /* main-program.exe, cygwin1.dll */
   DLL_LINK,
   DLL_LOAD,
   DLL_ANY
@@ -75,6 +76,8 @@ struct dll
 
 class dll_list
 {
+  void track_self ();
+
   dll *end;
   dll *hold;
   dll_type hold_type;
@@ -94,6 +97,7 @@ public:
     return nt_max_path_buffer;
   }
 
+  dll *main_executable;
   dll start;
   int loaded_dlls;
   int reload_on_fork;
diff --git a/winsup/cygwin/fork.cc b/winsup/cygwin/fork.cc
index c78e5cf3b..adcd1d7ad 100644
--- a/winsup/cygwin/fork.cc
+++ b/winsup/cygwin/fork.cc
@@ -175,7 +175,7 @@ frok::child (volatile char * volatile here)
   if (fixup_shms_after_fork ())
     api_fatal ("recreate_shm areas after fork failed");
 
-  /* load dynamic dlls, if any */
+  /* load dynamic dlls, if any, re-track main-executable and cygwin1.dll */
   dlls.load_after_fork (hParent);
 
   cygheap->fdtab.fixup_after_fork (hParent);
@@ -310,11 +310,20 @@ frok::parent (volatile char * volatile stack_here)
 
   while (1)
     {
+      PCWCHAR forking_progname = NULL;
+      if (dlls.main_executable)
+        forking_progname = dll_list::buffered_shortname
+			   (dlls.main_executable->ntname);
+      if (!forking_progname || !*forking_progname)
+	forking_progname = myself->progname;
+
       syscall_printf ("CreateProcessW (%W, %W, 0, 0, 1, %y, 0, 0, %p, %p)",
-		      myself->progname, myself->progname, c_flags, &si, &pi);
+		      forking_progname, myself->progname, c_flags, &si, &pi);
 
       hchild = NULL;
-      rc = CreateProcessW (myself->progname,	/* image to run */
+      /* cygwin1.dll may reuse the forking_progname buffer, even
+	 in case of failure: don't reuse forking_progname later */
+      rc = CreateProcessW (forking_progname,	/* image to run */
 			   GetCommandLineW (),	/* Take same space for command
 						   line as in parent to make
 						   sure child stack is allocated