OpenACC reference count overhaul

	libgomp/
	* libgomp.h (struct splay_tree_key_s): Substitute dynamic_refcount
	field for virtual_refcount.
	(enum gomp_map_vars_kind): Add GOMP_MAP_VARS_OPENACC_ENTER_DATA.
	(gomp_free_memmap): Remove prototype.
	* oacc-init.c (acc_shutdown_1): Iteratively call gomp_remove_var
	instead of calling gomp_free_memmap.
	* oacc-mem.c (acc_map_data): Use virtual_refcount instead of
	dynamic_refcount.
	(acc_unmap_data): Open code instead of forcing target_mem_desc's
	to_free field to NULL then calling gomp_unmap_vars.  Handle
	REFCOUNT_INFINITY on target blocks.
	(goacc_enter_data): Rename to...
	(goacc_enter_datum): ...this.  Remove MAPNUM parameter and special
	handling for mapping groups.  Use virtual_refcount instead of
	dynamic_refcount.  Use GOMP_MAP_VARS_OPENACC_ENTER_DATA for
	map_map_vars_async call.  Re-do lookup for target pointer return value.
	(acc_create, acc_create_async, acc_copyin, acc_copyin_async): Call
	renamed goacc_enter_datum function.
	(goacc_exit_data): Rename to...
	(goacc_exit_datum): ...this.  Update for virtual_refcount semantics.
	(acc_delete, acc_delete_async, acc_delete_finalize,
	acc_delete_finalize_async, acc_copyout, acc_copyout_async,
	acc_copyout_finalize, acc_copyout_finalize_async): Call renamed
	goacc_exit_datum function.
	(gomp_acc_remove_pointer, find_pointer): Remove functions.
	(find_group_last, goacc_enter_data_internal, goacc_exit_data_internal):
	New functions.
	(GOACC_enter_exit_data): Use goacc_enter_data_internal and
	goacc_exit_data_internal helper functions.
	* target.c (gomp_map_vars_internal): Handle
	GOMP_MAP_VARS_OPENACC_ENTER_DATA.  Update for virtual_refcount
	semantics.
	(gomp_unmap_vars_internal): Update for virtual_refcount semantics.
	(gomp_load_image_to_device, omp_target_associate_ptr): Zero-initialise
	virtual_refcount field instead of dynamic_refcount.
	(gomp_free_memmap): Remove function.
	* testsuite/libgomp.oacc-c-c++-common/unmap-infinity-1.c: New test.
	* testsuite/libgomp.c-c++-common/unmap-infinity-2.c: New test.
	* testsuite/libgomp.oacc-c-c++-common/pr92843-1.c: Add XFAIL.

From-SVN: r279621

libgomp/ChangeLog

 2019-12-19  Julian Brown  <julian@codesourcery.com>
+
+	* libgomp.h (struct splay_tree_key_s): Substitute dynamic_refcount
+	field for virtual_refcount.
+	(enum gomp_map_vars_kind): Add GOMP_MAP_VARS_OPENACC_ENTER_DATA.
+	(gomp_free_memmap): Remove prototype.
+	* oacc-init.c (acc_shutdown_1): Iteratively call gomp_remove_var
+	instead of calling gomp_free_memmap.
+	* oacc-mem.c (acc_map_data): Use virtual_refcount instead of
+	dynamic_refcount.
+	(acc_unmap_data): Open code instead of forcing target_mem_desc's
+	to_free field to NULL then calling gomp_unmap_vars.  Handle
+	REFCOUNT_INFINITY on target blocks.
+	(goacc_enter_data): Rename to...
+	(goacc_enter_datum): ...this.  Remove MAPNUM parameter and special
+	handling for mapping groups.  Use virtual_refcount instead of
+	dynamic_refcount.  Use GOMP_MAP_VARS_OPENACC_ENTER_DATA for
+	map_map_vars_async call.  Re-do lookup for target pointer return value.
+	(acc_create, acc_create_async, acc_copyin, acc_copyin_async): Call
+	renamed goacc_enter_datum function.
+	(goacc_exit_data): Rename to...
+	(goacc_exit_datum): ...this.  Update for virtual_refcount semantics.
+	(acc_delete, acc_delete_async, acc_delete_finalize,
+	acc_delete_finalize_async, acc_copyout, acc_copyout_async,
+	acc_copyout_finalize, acc_copyout_finalize_async): Call renamed
+	goacc_exit_datum function.
+	(gomp_acc_remove_pointer, find_pointer): Remove functions.
+	(find_group_last, goacc_enter_data_internal, goacc_exit_data_internal):
+	New functions.
+	(GOACC_enter_exit_data): Use goacc_enter_data_internal and
+	goacc_exit_data_internal helper functions.
+	* target.c (gomp_map_vars_internal): Handle
+	GOMP_MAP_VARS_OPENACC_ENTER_DATA.  Update for virtual_refcount
+	semantics.
+	(gomp_unmap_vars_internal): Update for virtual_refcount semantics.
+	(gomp_load_image_to_device, omp_target_associate_ptr): Zero-initialise
+	virtual_refcount field instead of dynamic_refcount.
+	(gomp_free_memmap): Remove function.
+	* testsuite/libgomp.oacc-c-c++-common/unmap-infinity-1.c: New test.
+	* testsuite/libgomp.c-c++-common/unmap-infinity-2.c: New test.
+	* testsuite/libgomp.oacc-c-c++-common/pr92843-1.c: Add XFAIL.
+
+2019-12-19  Julian Brown  <julian@codesourcery.com>
 	    Thomas Schwinge  <thomas@codesourcery.com>
 
 	* libgomp.h (struct splay_tree_aux): New.

libgomp/libgomp.h

@@ -1007,8 +1007,11 @@ struct splay_tree_key_s {
   uintptr_t tgt_offset;
   /* Reference count.  */
   uintptr_t refcount;
-  /* Dynamic reference count.  */
-  uintptr_t dynamic_refcount;
+  /* Reference counts beyond those that represent genuine references in the
+     linked splay tree key/target memory structures, e.g. for multiple OpenACC
+     "present increment" operations (via "acc enter data") referring to the same
+     host-memory block.  */
+  uintptr_t virtual_refcount;
   struct splay_tree_aux *aux;
 };
 
@@ -1139,6 +1142,7 @@ struct gomp_device_descr
 enum gomp_map_vars_kind
 {
   GOMP_MAP_VARS_OPENACC,
+  GOMP_MAP_VARS_OPENACC_ENTER_DATA,
   GOMP_MAP_VARS_TARGET,
   GOMP_MAP_VARS_DATA,
   GOMP_MAP_VARS_ENTER_DATA
@@ -1168,7 +1172,6 @@ extern void gomp_unmap_vars_async (struct target_mem_desc *, bool,
 				   struct goacc_asyncqueue *);
 extern void gomp_init_device (struct gomp_device_descr *);
 extern bool gomp_fini_device (struct gomp_device_descr *);
-extern void gomp_free_memmap (struct splay_tree_s *);
 extern void gomp_unload_device (struct gomp_device_descr *);
 extern bool gomp_remove_var (struct gomp_device_descr *, splay_tree_key);
 extern void gomp_remove_var_async (struct gomp_device_descr *, splay_tree_key,

libgomp/oacc-init.c

@@ -370,7 +370,15 @@ acc_shutdown_1 (acc_device_t d)
       if (walk->dev)
 	{
 	  gomp_mutex_lock (&walk->dev->lock);
-	  gomp_free_memmap (&walk->dev->mem_map);
+
+	  while (walk->dev->mem_map.root)
+	    {
+	      splay_tree_key k = &walk->dev->mem_map.root->key;
+	      if (k->aux)
+		k->aux->link_key = NULL;
+	      gomp_remove_var (walk->dev, k);
+	    }
+
 	  gomp_mutex_unlock (&walk->dev->lock);
 
 	  walk->dev = NULL;

libgomp/target.c

@@ -537,8 +537,10 @@ gomp_map_vars_internal (struct gomp_device_descr *devicep,
   struct target_mem_desc *tgt
     = gomp_malloc (sizeof (*tgt) + sizeof (tgt->list[0]) * mapnum);
   tgt->list_count = mapnum;
-  tgt->refcount = pragma_kind == GOMP_MAP_VARS_ENTER_DATA ? 0 : 1;
+  tgt->refcount = (pragma_kind == GOMP_MAP_VARS_ENTER_DATA
+		   || pragma_kind == GOMP_MAP_VARS_OPENACC_ENTER_DATA) ? 0 : 1;
   tgt->device_descr = devicep;
+  tgt->prev = NULL;
   struct gomp_coalesce_buf cbuf, *cbufp = NULL;
 
   if (mapnum == 0)
@@ -963,7 +965,7 @@ gomp_map_vars_internal (struct gomp_device_descr *devicep,
 		tgt->list[i].offset = 0;
 		tgt->list[i].length = k->host_end - k->host_start;
 		k->refcount = 1;
-		k->dynamic_refcount = 0;
+		k->virtual_refcount = 0;
 		tgt->refcount++;
 		array->left = NULL;
 		array->right = NULL;
@@ -1101,8 +1103,20 @@ gomp_map_vars_internal (struct gomp_device_descr *devicep,
   /* If the variable from "omp target enter data" map-list was already mapped,
      tgt is not needed.  Otherwise tgt will be freed by gomp_unmap_vars or
      gomp_exit_data.  */
-  if (pragma_kind == GOMP_MAP_VARS_ENTER_DATA && tgt->refcount == 0)
-    {
+  if ((pragma_kind == GOMP_MAP_VARS_ENTER_DATA
+       || pragma_kind == GOMP_MAP_VARS_OPENACC_ENTER_DATA)
+      && tgt->refcount == 0)
+    {
+      /* If we're about to discard a target_mem_desc with no "structural"
+	 references (tgt->refcount == 0), any splay keys linked in the tgt's
+	 list must have their virtual refcount incremented to represent that
+	 "lost" reference in order to implement the semantics of the OpenACC
+	 "present increment" operation properly.  */
+      if (pragma_kind == GOMP_MAP_VARS_OPENACC_ENTER_DATA)
+	for (i = 0; i < tgt->list_count; i++)
+	  if (tgt->list[i].key)
+	    tgt->list[i].key->virtual_refcount++;
+
       free (tgt);
       tgt = NULL;
     }
@@ -1240,7 +1254,14 @@ gomp_unmap_vars_internal (struct target_mem_desc *tgt, bool do_copyfrom,
 	continue;
 
       bool do_unmap = false;
-      if (k->refcount > 1 && k->refcount != REFCOUNT_INFINITY)
+      if (k->tgt == tgt
+	  && k->virtual_refcount > 0
+	  && k->refcount != REFCOUNT_INFINITY)
+	{
+	  k->virtual_refcount--;
+	  k->refcount--;
+	}
+      else if (k->refcount > 1 && k->refcount != REFCOUNT_INFINITY)
 	k->refcount--;
       else if (k->refcount == 1)
 	{
@@ -1405,7 +1426,7 @@ gomp_load_image_to_device (struct gomp_device_descr *devicep, unsigned version,
       k->tgt = tgt;
       k->tgt_offset = target_table[i].start;
       k->refcount = REFCOUNT_INFINITY;
-      k->dynamic_refcount = 0;
+      k->virtual_refcount = 0;
       k->aux = NULL;
       array->left = NULL;
       array->right = NULL;
@@ -1438,7 +1459,7 @@ gomp_load_image_to_device (struct gomp_device_descr *devicep, unsigned version,
       k->tgt = tgt;
       k->tgt_offset = target_var->start;
       k->refcount = target_size & link_bit ? REFCOUNT_LINK : REFCOUNT_INFINITY;
-      k->dynamic_refcount = 0;
+      k->virtual_refcount = 0;
       k->aux = NULL;
       array->left = NULL;
       array->right = NULL;
@@ -1673,22 +1694,6 @@ gomp_unload_device (struct gomp_device_descr *devicep)
     }
 }
 
-/* Free address mapping tables.  MM must be locked on entry, and remains locked
-   on return.  */
-
-attribute_hidden void
-gomp_free_memmap (struct splay_tree_s *mem_map)
-{
-  while (mem_map->root)
-    {
-      struct target_mem_desc *tgt = mem_map->root->key.tgt;
-
-      splay_tree_remove (mem_map, &mem_map->root->key);
-      free (tgt->array);
-      free (tgt);
-    }
-}
-
 /* Host fallback for GOMP_target{,_ext} routines.  */
 
 static void
@@ -2700,7 +2705,7 @@ omp_target_associate_ptr (const void *host_ptr, const void *device_ptr,
       k->tgt = tgt;
       k->tgt_offset = (uintptr_t) device_ptr + device_offset;
       k->refcount = REFCOUNT_INFINITY;
-      k->dynamic_refcount = 0;
+      k->virtual_refcount = 0;
       k->aux = NULL;
       array->left = NULL;
       array->right = NULL;

libgomp/testsuite/libgomp.c-c++-common/unmap-infinity-2.c

+int foo[16];
+#pragma omp declare target (foo)
+
+__attribute__((used)) void bar (void)
+{
+  #pragma omp target parallel for
+  for (int i = 0; i < 16; i++)
+    foo[i] = i;
+}
+
+int
+main (int argc, char *argv[])
+{
+  int *foo_copy = foo;
+  /* Try to trigger the unmapping of a REFCOUNT_INFINITY target block.  This
+     does nothing at the time of writing.  */
+  #pragma omp target exit data map(delete: foo_copy[0:16])
+  return 0;
+}

libgomp/testsuite/libgomp.oacc-c-c++-common/pr92843-1.c

 /* Verify that 'acc_copyout' etc. is a no-op if there's still a structured
    reference count.  */
 
+/* { dg-xfail-run-if "TODO PR92843" { *-*-* } } */
 /* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
 
 #include <assert.h>

libgomp/testsuite/libgomp.oacc-c-c++-common/unmap-infinity-1.c

+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <openacc.h>
+
+int foo[16];
+#pragma acc declare device_resident(foo)
+
+int
+main (int argc, char *argv[])
+{
+  acc_init (acc_device_default);
+  acc_unmap_data ((void *) foo);
+/* { dg-output "libgomp: cannot unmap target block" } */
+  return 0;
+}
+
+/* { dg-shouldfail "" } */