OpenMP: requires unified_shared_memory patch, insert USM allocators into libgfortran

(This is a backport of
 https://gcc.gnu.org/pipermail/gcc-patches/2022-September/601059.html)

After the prior libgfortran memory allocator preparation patch, this is the
actual patch that organizes unified_shared_memory allocation into libgfortran.

In the current OpenMP requires implementation, the requires_mask is collected
through offload LTO processing, and presented to libgomp when registering
offload images through GOMP_offload_register_ver() (called by the mkoffload
generated constructor linked into the program binary)

This means that the only reliable place to access omp_requires_mask is in
GOMP_offload_register_ver, however since it is called through an ELF constructor
in the *main program*, this runs later than libgfortran/runtime/main.c:init()
constructor, and because some libgfortran init actions there start allocating
memory, this can cause more deallocation errors later.

Another issue is that CUDA appears to be registering some cleanup actions using
atexit(), which forces libgomp to register gomp_target_fini() using atexit as
well (to properly run before the underlying CUDA stuff disappears). This happens
to us here as well.

In summary we need to: (1) order libgfortran init actions after
omp_requires_mask processing is done, and (2) order libgfortran cleanup actions
before gomp_target_fini, to properly deallocate stuff without crashing.

We implement this by creating callback registering functions exported from
libgomp to libgfortran, basically to register libgfortran init/fini actions
into libgomp to run.

Inside GOMP_offload_register_ver, after omp_requires_mask processing is done,
we call into libgfortran through a new _gfortran_mem_allocators_init function
to insert the omp_free/alloc/etc. based allocators into the Fortran runtime,
when GOMP_REQUIRES_UNIFIED_SHARED_MEMORY is set.

All symbol references between libgfortran/libgomp are defined with weak
symbols. Test of the weak symbols are also used to determine if the other
library exists in this program.

For the final case where we have an OpenMP program that does NOT have
offloading, we cannot passively determine in libgomp/libgfortran whether
offloading exists or not, only the main program itself can, by seeing if the
hidden __OFFLOAD_TABLE__ exists. But those with no offloading will not have
those callback properly run (because of no offload image loading)
Therefore the solution here is a constructor added into the crtoffloadend.o
fragment that does a "null" call of GOMP_offload_register_ver, solely for
triggering the post-offload_register callbacks when __OFFLOAD_TABLE__ is NULL.
(crtoffloadend.o Makefile rule is adjusted to compile with PIC due to this)

libgcc/ChangeLog:
	* Makefile.in (crtoffloadend$(objext)): Add $(PICFLAG) to compile rule.
	* offloadstuff.c (GOMP_offload_register_ver): Add declaration of weak
	symbol.
	(__OFFLOAD_TABLE__): Likewise.
	(init_non_offload): New function.

libgfortran/ChangeLog:
	* gfortran.map (GFORTRAN_13): New namespace.
	(_gfortran_mem_allocators_init): New name inside GFORTRAN_14.
	* libgfortran.h (mem_allocators_init): New exported declaration.
	* runtime/main.c (do_init): Rename from init, add run-once guard code.
	(cleanup): Add run-once guard code.
	(GOMP_post_offload_register_callback): Declare weak symbol.
	(GOMP_pre_gomp_target_fini_callback): Likewise.
	(init): New constructor to register offload callbacks, or call do_init
	when not OpenMP.
	* runtime/memory.c (gfortran_malloc): New pointer variable.
	(gfortran_calloc): Likewise.
	(gfortran_realloc): Likewise.
	(gfortran_free): Likewise.
	(mem_allocators_init): New function.
	(xmalloc): Use gfortran_malloc.
	(xmallocarray): Use gfortran_malloc.
	(xcalloc): Use gfortran_calloc.
	(xrealloc): Use gfortran_realloc.
	(xfree): Use gfortran_free.

libgomp/ChangeLog:
	* libgomp.map (GOMP_5.1.2): New version namespace.
	(GOMP_post_offload_register_callback): New name inside GOMP_5.1.2.
	(GOMP_pre_gomp_target_fini_callback): Likewise.
	(GOMP_DEFINE_CALLBACK_SET): Macro to define callback set.
	(post_offload_register): Define callback set for after offload image
	register.
	(pre_gomp_target_fini): Define callback set for before gomp_target_fini
	is called.
	(libgfortran_malloc_usm): New function.
	(libgfortran_calloc_usm): Likewise
	(libgfortran_realloc_usm): Likewise
	(libgfortran_free_usm): Likewise.
	(_gfortran_mem_allocators_init): Declare weak symbol.
	(gomp_libgfortran_omp_allocators_init): New function.
	(GOMP_offload_register_ver): Add handling of host_table == NULL, calling
	into libgfortran to set unified_shared_memory allocators, and execution
	of post_offload_register callbacks.
	(gomp_target_init): Register all pre_gomp_target_fini callbacks to run
	at end of main using atexit().

	* testsuite/libgomp.fortran/target-unified_shared_memory-1.f90: New test.

libgcc/Makefile.in

@@ -1048,8 +1048,9 @@ crtbeginT$(objext): $(srcdir)/crtstuff.c
 crtoffloadbegin$(objext): $(srcdir)/offloadstuff.c
 	$(crt_compile) $(CRTSTUFF_T_CFLAGS) -c $< -DCRT_BEGIN
 
+# crtoffloadend contains a constructor with calls to libgomp, so build as PIC.
 crtoffloadend$(objext): $(srcdir)/offloadstuff.c
-	$(crt_compile) $(CRTSTUFF_T_CFLAGS) -c $< -DCRT_END
+	$(crt_compile) $(CRTSTUFF_T_CFLAGS) $(PICFLAG) -c $< -DCRT_END
 
 crtoffloadtable$(objext): $(srcdir)/offloadstuff.c
 	$(crt_compile) $(CRTSTUFF_T_CFLAGS) -c $< -DCRT_TABLE

libgcc/offloadstuff.c

@@ -63,6 +63,19 @@ const void *const __offload_vars_end[0]
   __attribute__ ((__used__, visibility ("hidden"),
 		  section (OFFLOAD_VAR_TABLE_SECTION_NAME))) = { };
 
+extern void GOMP_offload_register_ver (unsigned, const void *, int,
+				       const void *);
+extern const void *const __OFFLOAD_TABLE__[0] __attribute__ ((weak));
+static void __attribute__((constructor))
+init_non_offload (void)
+{
+  /* If an OpenMP program has no offloading, post-offload_register callbacks
+     that need to run will require a call to GOMP_offload_register_ver, in
+     order to properly trigger those callbacks during init.  */
+  if (__OFFLOAD_TABLE__ == NULL)
+    GOMP_offload_register_ver (0, NULL, 0, NULL);
+}
+
 #elif defined CRT_TABLE
 
 extern const void *const __offload_func_table[];

libgfortran/gfortran.map

@@ -1765,3 +1765,8 @@ GFORTRAN_13 {
     __ieee_exceptions_MOD_ieee_get_modes;
     __ieee_exceptions_MOD_ieee_set_modes;
 } GFORTRAN_12;
+
+GFORTRAN_14 {
+  global:
+  _gfortran_mem_allocators_init;
+} GFORTRAN_13;

libgfortran/libgfortran.h

@@ -878,6 +878,11 @@ internal_proto(xrealloc);
 extern void xfree (void *);
 internal_proto(xfree);
 
+#if !defined(LIBGFOR_MINIMAL) && defined(__linux__)
+extern void mem_allocators_init (void *, void *, void *, void *);
+export_proto(mem_allocators_init);
+#endif
+
 /* environ.c */
 
 extern void init_variables (void);

libgfortran/runtime/main.c

@@ -61,9 +61,16 @@ get_args (int *argc, char ***argv)
 
 /* Initialize the runtime library.  */
 
-static void __attribute__((constructor))
-init (void)
+static void
+do_init (void)
 {
+#if !defined(LIBGFOR_MINIMAL) && defined(__linux__)
+  static bool do_init_ran = false;
+  if (do_init_ran)
+    return;
+  do_init_ran = true;
+#endif
+
   /* Must be first */
   init_variables ();
 
@@ -82,5 +89,37 @@ init (void)
 static void __attribute__((destructor))
 cleanup (void)
 {
+#if !defined(LIBGFOR_MINIMAL) && defined(__linux__)
+  static bool cleanup_ran = false;
+  if (cleanup_ran)
+    return;
+  cleanup_ran = true;
+#endif
+
   close_units ();
 }
+
+#if !defined(LIBGFOR_MINIMAL) && defined(__linux__)
+extern void __attribute__((weak))
+GOMP_post_offload_register_callback (void (*func)(void));
+
+extern void __attribute__((weak))
+GOMP_pre_gomp_target_fini_callback (void (*func)(void));
+#endif
+
+static void __attribute__((constructor))
+init (void)
+{
+#if !defined(LIBGFOR_MINIMAL) && defined(__linux__)
+  if (GOMP_post_offload_register_callback)
+    {
+      GOMP_post_offload_register_callback (do_init);
+      GOMP_pre_gomp_target_fini_callback (cleanup);
+      return;
+    }
+#endif
+
+  /* If libgomp is not present, then we can go ahead and call do_init
+     directly.  */
+  do_init ();
+}

libgfortran/runtime/memory.c

@@ -26,6 +26,28 @@ see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
 #include "libgfortran.h"
 #include <errno.h>
 
+#if !defined(LIBGFOR_MINIMAL) && defined(__linux__)
+static void * (*gfortran_malloc)(size_t) = malloc;
+static void * (*gfortran_calloc)(size_t, size_t) = calloc;
+static void * (*gfortran_realloc)(void *, size_t) = realloc;
+static void (*gfortran_free)(void *) = free;
+
+void
+mem_allocators_init (void *malloc_ptr, void *calloc_ptr,
+		     void *realloc_ptr, void *free_ptr)
+{
+  gfortran_malloc = malloc_ptr;
+  gfortran_calloc = calloc_ptr;
+  gfortran_realloc = realloc_ptr;
+  gfortran_free = free_ptr;
+}
+
+#else
+#define gfortran_malloc malloc
+#define gfortran_calloc calloc
+#define gfortran_realloc realloc
+#define gfortran_free free
+#endif
 
 void *
 xmalloc (size_t n)
@@ -35,7 +57,7 @@ xmalloc (size_t n)
   if (n == 0)
     n = 1;
 
-  p = malloc (n);
+  p = gfortran_malloc (n);
 
   if (p == NULL)
     os_error ("Memory allocation failed");
@@ -57,7 +79,7 @@ xmallocarray (size_t nmemb, size_t size)
       os_error ("Integer overflow in xmallocarray");
     }
 
-  p = malloc (prod);
+  p = gfortran_malloc (prod);
 
   if (!p)
     os_error ("Memory allocation failed in xmallocarray");
@@ -73,7 +95,7 @@ xcalloc (size_t nmemb, size_t size)
   if (!nmemb || !size)
     nmemb = size = 1;
 
-  void *p = calloc (nmemb, size);
+  void *p = gfortran_calloc (nmemb, size);
   if (!p)
     os_error ("Allocating cleared memory failed");
 
@@ -86,7 +108,7 @@ xrealloc (void *ptr, size_t size)
   if (size == 0)
     size = 1;
 
-  void *newp = realloc (ptr, size);
+  void *newp = gfortran_realloc (ptr, size);
   if (!newp)
     os_error ("Memory allocation failure in xrealloc");
 
@@ -96,5 +118,5 @@ xrealloc (void *ptr, size_t size)
 void
 xfree (void *ptr)
 {
-  free (ptr);
+  gfortran_free (ptr);
 }

libgomp/libgomp.map

@@ -423,6 +423,12 @@ GOMP_5.1.1 {
 	GOMP_taskwait_depend_nowait;
 } GOMP_5.1;
 
+GOMP_5.1.2 {
+  global:
+	GOMP_post_offload_register_callback;
+	GOMP_pre_gomp_target_fini_callback;
+} GOMP_5.1.1;
+
 OACC_2.0 {
   global:
 	acc_get_num_devices;

libgomp/target.c

@@ -3153,6 +3153,70 @@ gomp_requires_to_name (char *buf, size_t size, int requires_mask)
 		   (p == buf ? "" : ", "));
 }
 
+/* Macro to define a callback set with a name, and routine to register
+   a callback function into set.  */
+#define GOMP_DEFINE_CALLBACK_SET(name)				\
+  static unsigned int num_ ## name ## _callbacks = 0;		\
+  static void (*name ## _callbacks[4])(void);			\
+  void GOMP_ ## name ## _callback (void (*fn)(void))		\
+  {								\
+    if (num_ ## name ## _callbacks				\
+	< (sizeof (name ## _callbacks)				\
+	   / sizeof (name ## _callbacks[0])))			\
+      {								\
+	name ## _callbacks[num_ ## name ## _callbacks] = fn;	\
+	num_ ## name ## _callbacks += 1;			\
+      }								\
+  }
+GOMP_DEFINE_CALLBACK_SET(post_offload_register)
+GOMP_DEFINE_CALLBACK_SET(pre_gomp_target_fini)
+#undef GOMP_DEFINE_CALLBACK_SET
+
+/* Routines to insert into libgfortran, under unified_shared_memory.  */
+static void *
+libgfortran_malloc_usm (size_t size)
+{
+  return omp_alloc (size, ompx_unified_shared_mem_alloc);
+}
+
+static void *
+libgfortran_calloc_usm (size_t n, size_t size)
+{
+  return omp_calloc (n, size, ompx_unified_shared_mem_alloc);
+}
+
+static void *
+libgfortran_realloc_usm (void *ptr, size_t size)
+{
+  return omp_realloc (ptr, size, ompx_unified_shared_mem_alloc,
+		      ompx_unified_shared_mem_alloc);
+}
+
+static void
+libgfortran_free_usm (void *ptr)
+{
+  omp_free (ptr, ompx_unified_shared_mem_alloc);
+}
+
+extern void __attribute__((weak))
+_gfortran_mem_allocators_init (void *, void *, void *, void *);
+
+static void
+gomp_libgfortran_omp_allocators_init (int omp_requires_mask)
+{
+  static bool init = false;
+  if (init)
+    return;
+  init = true;
+
+  if ((omp_requires_mask & GOMP_REQUIRES_UNIFIED_SHARED_MEMORY)
+      && _gfortran_mem_allocators_init != NULL)
+    _gfortran_mem_allocators_init (libgfortran_malloc_usm,
+				   libgfortran_calloc_usm,
+				   libgfortran_realloc_usm,
+				   libgfortran_free_usm);
+}
+
 /* This function should be called from every offload image while loading.
    It gets the descriptor of the host func and var tables HOST_TABLE, TYPE of
    the target, and DATA.  */
@@ -3163,6 +3227,9 @@ GOMP_offload_register_ver (unsigned version, const void *host_table,
 {
   int i;
 
+  if (host_table == NULL)
+    goto end;
+
   if (GOMP_VERSION_LIB (version) > GOMP_VERSION)
     gomp_fatal ("Library too old for offload (version %u < %u)",
 		GOMP_VERSION, GOMP_VERSION_LIB (version));
@@ -3229,6 +3296,14 @@ GOMP_offload_register_ver (unsigned version, const void *host_table,
 
   num_offload_images++;
   gomp_mutex_unlock (&register_lock);
+
+  /* Call into libgfortran to initialize OpenMP memory allocators.  */
+  gomp_libgfortran_omp_allocators_init (omp_requires_mask);
+
+ end:
+  for (int i = 0; i < num_post_offload_register_callbacks; i++)
+    post_offload_register_callbacks[i] ();
+  num_post_offload_register_callbacks = 0;
 }
 
 /* Legacy entry point.  */
@@ -3341,7 +3416,7 @@ gomp_unload_device (struct gomp_device_descr *devicep)
   if (devicep->state == GOMP_DEVICE_INITIALIZED)
     {
       unsigned i;
-      
+
       /* Unload from device all images registered at the moment.  */
       for (i = 0; i < num_offload_images; i++)
 	{
@@ -6507,6 +6582,13 @@ gomp_target_init (void)
   devices = devs;
   if (atexit (gomp_target_fini) != 0)
     gomp_fatal ("atexit failed");
+
+  /* Register 'pre_gomp_target_fini' callbacks to run before gomp_target_fini
+     during finalization.  */
+  for (int i = 0; i < num_pre_gomp_target_fini_callbacks; i++)
+    if (atexit (pre_gomp_target_fini_callbacks[i]) != 0)
+      gomp_fatal ("atexit failed");
+  num_pre_gomp_target_fini_callbacks = 0;
 }
 
 #else /* PLUGIN_SUPPORT */

libgomp/testsuite/libgomp.fortran/target-unified_shared_memory-1.f90

@@ -0,0 +1,13 @@
+! { dg-do run }
+
+program requires_unified_shared_memory
+  character(32) :: str
+  !$omp requires unified_shared_memory
+
+  str = trim (str)
+
+  !$omp target
+  block
+  end block
+
+end program requires_unified_shared_memory