OpenACC 2.6 deep copy: libgomp parts

	include/
	* gomp-constants.h (GOMP_MAP_FLAG_SPECIAL_4, GOMP_MAP_DEEP_COPY):
	Define.
	(gomp_map_kind): Add GOMP_MAP_ATTACH, GOMP_MAP_DETACH,
	GOMP_MAP_FORCE_DETACH.

	libgomp/
	* libgomp.h (struct target_var_desc): Add do_detach flag.
	* oacc-init.c (acc_shutdown_1): Free aux block if present.
	* oacc-mem.c (find_group_last): Add SIZES parameter. Support
	struct components.  Tidy up and add some new checks.
	(goacc_enter_data_internal): Update call to find_group_last.
	(goacc_exit_data_internal): Support detach operations and
	GOMP_MAP_STRUCT.
	(GOACC_enter_exit_data): Handle initial GOMP_MAP_STRUCT or
	GOMP_MAP_FORCE_PRESENT in finalization detection code.  Handle
	attach/detach in enter/exit data detection code.
	* target.c (gomp_map_vars_existing): Initialise do_detach field of
	tgt_var_desc.
	(gomp_map_vars_internal): Support attach.
	(gomp_unmap_vars_internal): Support detach.

From-SVN: r279625

include/ChangeLog

 2019-12-19  Julian Brown  <julian@codesourcery.com>
+
+	* gomp-constants.h (GOMP_MAP_FLAG_SPECIAL_4, GOMP_MAP_DEEP_COPY):
+	Define.
+	(gomp_map_kind): Add GOMP_MAP_ATTACH, GOMP_MAP_DETACH,
+	GOMP_MAP_FORCE_DETACH.
+
+2019-12-19  Julian Brown  <julian@codesourcery.com>
 	    Maciej W. Rozycki  <macro@codesourcery.com>
 	    Tobias Burnus  <tobias@codesourcery.com>
 	    Thomas Schwinge  <thomas@codesourcery.com>

include/gomp-constants.h

@@ -40,8 +40,11 @@
 #define GOMP_MAP_FLAG_SPECIAL_0		(1 << 2)
 #define GOMP_MAP_FLAG_SPECIAL_1		(1 << 3)
 #define GOMP_MAP_FLAG_SPECIAL_2		(1 << 4)
+#define GOMP_MAP_FLAG_SPECIAL_4		(1 << 6)
 #define GOMP_MAP_FLAG_SPECIAL		(GOMP_MAP_FLAG_SPECIAL_1 \
 					 | GOMP_MAP_FLAG_SPECIAL_0)
+#define GOMP_MAP_DEEP_COPY		(GOMP_MAP_FLAG_SPECIAL_4 \
+					 | GOMP_MAP_FLAG_SPECIAL_2)
 /* Flag to force a specific behavior (or else, trigger a run-time error).  */
 #define GOMP_MAP_FLAG_FORCE		(1 << 7)
 
@@ -129,6 +132,13 @@ enum gomp_map_kind
     /* Decrement usage count and deallocate if zero.  */
     GOMP_MAP_RELEASE =			(GOMP_MAP_FLAG_SPECIAL_2
 					 | GOMP_MAP_DELETE),
+    /* In OpenACC, attach a pointer to a mapped struct field.  */
+    GOMP_MAP_ATTACH =			(GOMP_MAP_DEEP_COPY | 0),
+    /* In OpenACC, detach a pointer to a mapped struct field.  */
+    GOMP_MAP_DETACH =			(GOMP_MAP_DEEP_COPY | 1),
+    /* In OpenACC, detach a pointer to a mapped struct field.  */
+    GOMP_MAP_FORCE_DETACH =		(GOMP_MAP_DEEP_COPY
+					 | GOMP_MAP_FLAG_FORCE | 1),
 
     /* Internal to GCC, not used in libgomp.  */
     /* Do not map, but pointer assign a pointer instead.  */

libgomp/ChangeLog

 2019-12-19  Julian Brown  <julian@codesourcery.com>
+
+	* libgomp.h (struct target_var_desc): Add do_detach flag.
+	* oacc-init.c (acc_shutdown_1): Free aux block if present.
+	* oacc-mem.c (find_group_last): Add SIZES parameter. Support
+	struct components.  Tidy up and add some new checks.
+	(goacc_enter_data_internal): Update call to find_group_last.
+	(goacc_exit_data_internal): Support detach operations and
+	GOMP_MAP_STRUCT.
+	(GOACC_enter_exit_data): Handle initial GOMP_MAP_STRUCT or
+	GOMP_MAP_FORCE_PRESENT in finalization detection code.  Handle
+	attach/detach in enter/exit data detection code.
+	* target.c (gomp_map_vars_existing): Initialise do_detach field of
+	tgt_var_desc.
+	(gomp_map_vars_internal): Support attach.
+	(gomp_unmap_vars_internal): Support detach.
+
+2019-12-19  Julian Brown  <julian@codesourcery.com>
 	    Thomas Schwinge  <thomas@codesourcery.com>
 
 	* libgomp.h (struct splay_tree_aux): Add attach_count field.

libgomp/libgomp.h

@@ -948,6 +948,8 @@ struct target_var_desc {
   bool copy_from;
   /* True if data always should be copied from device to host at the end.  */
   bool always_copy_from;
+  /* True if variable should be detached at end of region.  */
+  bool do_detach;
   /* Relative offset against key host_start.  */
   uintptr_t offset;
   /* Actual length.  */

libgomp/oacc-mem.c

@@ -957,33 +957,48 @@ acc_detach_finalize_async (void **hostaddr, int async)
    mappings.  */
 
 static int
-find_group_last (int pos, size_t mapnum, unsigned short *kinds)
+find_group_last (int pos, size_t mapnum, size_t *sizes, unsigned short *kinds)
 {
   unsigned char kind0 = kinds[pos] & 0xff;
-  int first_pos = pos, last_pos = pos;
+  int first_pos = pos;
 
-  if (kind0 == GOMP_MAP_TO_PSET)
+  switch (kind0)
     {
+    case GOMP_MAP_TO_PSET:
       while (pos + 1 < mapnum && (kinds[pos + 1] & 0xff) == GOMP_MAP_POINTER)
-	last_pos = ++pos;
+	pos++;
       /* We expect at least one GOMP_MAP_POINTER after a GOMP_MAP_TO_PSET.  */
-      assert (last_pos > first_pos);
-    }
-  else
-    {
+      assert (pos > first_pos);
+      break;
+
+    case GOMP_MAP_STRUCT:
+      pos += sizes[pos];
+      break;
+
+    case GOMP_MAP_POINTER:
+    case GOMP_MAP_ALWAYS_POINTER:
+      /* These mappings are only expected after some other mapping.  If we
+	 see one by itself, something has gone wrong.  */
+      gomp_fatal ("unexpected mapping");
+      break;
+
+    default:
       /* GOMP_MAP_ALWAYS_POINTER can only appear directly after some other
 	 mapping.  */
-      if (pos + 1 < mapnum
-	  && (kinds[pos + 1] & 0xff) == GOMP_MAP_ALWAYS_POINTER)
-	return pos + 1;
+      if (pos + 1 < mapnum)
+	{
+	  unsigned char kind1 = kinds[pos + 1] & 0xff;
+	  if (kind1 == GOMP_MAP_ALWAYS_POINTER)
+	    return pos + 1;
+	}
 
-      /* We can have one or several GOMP_MAP_POINTER mappings after a to/from
+      /* We can have zero or more GOMP_MAP_POINTER mappings after a to/from
 	 (etc.) mapping.  */
       while (pos + 1 < mapnum && (kinds[pos + 1] & 0xff) == GOMP_MAP_POINTER)
-	last_pos = ++pos;
+	pos++;
     }
 
-  return last_pos;
+  return pos;
 }
 
 /* Map variables for OpenACC "enter data".  We can't just call
@@ -997,7 +1012,7 @@ goacc_enter_data_internal (struct gomp_device_descr *acc_dev, size_t mapnum,
 {
   for (size_t i = 0; i < mapnum; i++)
     {
-      int group_last = find_group_last (i, mapnum, kinds);
+      int group_last = find_group_last (i, mapnum, sizes, kinds);
 
       gomp_map_vars_async (acc_dev, aq,
 			   (group_last - i) + 1,
@@ -1018,6 +1033,37 @@ goacc_exit_data_internal (struct gomp_device_descr *acc_dev, size_t mapnum,
 {
   gomp_mutex_lock (&acc_dev->lock);
 
+  /* Handle "detach" before copyback/deletion of mapped data.  */
+  for (size_t i = 0; i < mapnum; ++i)
+    {
+      unsigned char kind = kinds[i] & 0xff;
+      bool finalize = false;
+      switch (kind)
+	{
+	case GOMP_MAP_FORCE_DETACH:
+	  finalize = true;
+	  /* Fallthrough.  */
+
+	case GOMP_MAP_DETACH:
+	  {
+	    struct splay_tree_key_s cur_node;
+	    uintptr_t hostaddr = (uintptr_t) hostaddrs[i];
+	    cur_node.host_start = hostaddr;
+	    cur_node.host_end = cur_node.host_start + sizeof (void *);
+	    splay_tree_key n
+	      = splay_tree_lookup (&acc_dev->mem_map, &cur_node);
+
+	    if (n == NULL)
+	      gomp_fatal ("struct not mapped for detach operation");
+
+	    gomp_detach_pointer (acc_dev, aq, n, hostaddr, finalize, NULL);
+	  }
+	  break;
+	default:
+	  ;
+	}
+    }
+
   for (size_t i = 0; i < mapnum; ++i)
     {
       unsigned char kind = kinds[i] & 0xff;
@@ -1025,7 +1071,8 @@ goacc_exit_data_internal (struct gomp_device_descr *acc_dev, size_t mapnum,
       bool finalize = false;
 
       if (kind == GOMP_MAP_FORCE_FROM
-	  || kind == GOMP_MAP_DELETE)
+	  || kind == GOMP_MAP_DELETE
+	  || kind == GOMP_MAP_FORCE_DETACH)
 	finalize = true;
 
       switch (kind)
@@ -1040,10 +1087,14 @@ goacc_exit_data_internal (struct gomp_device_descr *acc_dev, size_t mapnum,
 	case GOMP_MAP_POINTER:
 	case GOMP_MAP_DELETE:
 	case GOMP_MAP_RELEASE:
+	case GOMP_MAP_DETACH:
+	case GOMP_MAP_FORCE_DETACH:
 	  {
 	    struct splay_tree_key_s cur_node;
 	    size_t size;
-	    if (kind == GOMP_MAP_POINTER)
+	    if (kind == GOMP_MAP_POINTER
+		|| kind == GOMP_MAP_DETACH
+		|| kind == GOMP_MAP_FORCE_DETACH)
 	      size = sizeof (void *);
 	    else
 	      size = sizes[i];
@@ -1083,6 +1134,42 @@ goacc_exit_data_internal (struct gomp_device_descr *acc_dev, size_t mapnum,
 	      gomp_remove_var_async (acc_dev, n, aq);
 	  }
 	  break;
+
+	case GOMP_MAP_STRUCT:
+	  {
+	    int elems = sizes[i];
+	    for (int j = 1; j <= elems; j++)
+	      {
+		struct splay_tree_key_s k;
+		k.host_start = (uintptr_t) hostaddrs[i + j];
+		k.host_end = k.host_start + sizes[i + j];
+		splay_tree_key str;
+		str = splay_tree_lookup (&acc_dev->mem_map, &k);
+		if (str)
+		  {
+		    if (finalize)
+		      {
+			if (str->refcount != REFCOUNT_INFINITY)
+			  str->refcount -= str->virtual_refcount;
+			str->virtual_refcount = 0;
+		      }
+		    if (str->virtual_refcount > 0)
+		      {
+			if (str->refcount != REFCOUNT_INFINITY)
+			  str->refcount--;
+			str->virtual_refcount--;
+		      }
+		    else if (str->refcount > 0
+			     && str->refcount != REFCOUNT_INFINITY)
+		      str->refcount--;
+		    if (str->refcount == 0)
+		      gomp_remove_var_async (acc_dev, str, aq);
+		  }
+	      }
+	    i += elems;
+	  }
+	  break;
+
 	default:
 	  gomp_fatal (">>>> goacc_exit_data_internal UNHANDLED kind 0x%.2x",
 			  kind);
@@ -1114,11 +1201,14 @@ GOACC_enter_exit_data (int flags_m, size_t mapnum, void **hostaddrs,
     {
       unsigned char kind = kinds[i] & 0xff;
 
-      if (kind == GOMP_MAP_POINTER || kind == GOMP_MAP_TO_PSET)
+      if (kind == GOMP_MAP_POINTER
+	  || kind == GOMP_MAP_TO_PSET
+	  || kind == GOMP_MAP_STRUCT)
 	continue;
 
       if (kind == GOMP_MAP_FORCE_ALLOC
 	  || kind == GOMP_MAP_FORCE_PRESENT
+	  || kind == GOMP_MAP_ATTACH
 	  || kind == GOMP_MAP_FORCE_TO
 	  || kind == GOMP_MAP_TO
 	  || kind == GOMP_MAP_ALLOC)
@@ -1129,6 +1219,8 @@ GOACC_enter_exit_data (int flags_m, size_t mapnum, void **hostaddrs,
 
       if (kind == GOMP_MAP_RELEASE
 	  || kind == GOMP_MAP_DELETE
+	  || kind == GOMP_MAP_DETACH
+	  || kind == GOMP_MAP_FORCE_DETACH
 	  || kind == GOMP_MAP_FROM
 	  || kind == GOMP_MAP_FORCE_FROM)
 	break;

libgomp/target.c

@@ -360,6 +360,7 @@ gomp_map_vars_existing (struct gomp_device_descr *devicep,
   tgt_var->key = oldn;
   tgt_var->copy_from = GOMP_MAP_COPY_FROM_P (kind);
   tgt_var->always_copy_from = GOMP_MAP_ALWAYS_FROM_P (kind);
+  tgt_var->do_detach = kind == GOMP_MAP_ATTACH;
   tgt_var->offset = newn->host_start - oldn->host_start;
   tgt_var->length = newn->host_end - newn->host_start;
 
@@ -798,8 +799,15 @@ gomp_map_vars_internal (struct gomp_device_descr *devicep,
 	  has_firstprivate = true;
 	  continue;
 	}
+      else if ((kind & typemask) == GOMP_MAP_ATTACH)
+	{
+	  tgt->list[i].key = NULL;
+	  has_firstprivate = true;
+	  continue;
+	}
       cur_node.host_start = (uintptr_t) hostaddrs[i];
-      if (!GOMP_MAP_POINTER_P (kind & typemask))
+      if (!GOMP_MAP_POINTER_P (kind & typemask)
+	  && (kind & typemask) != GOMP_MAP_ATTACH)
 	cur_node.host_end = cur_node.host_start + sizes[i];
       else
 	cur_node.host_end = cur_node.host_start + sizeof (void *);
@@ -1046,6 +1054,32 @@ gomp_map_vars_internal (struct gomp_device_descr *devicep,
 			== GOMP_MAP_POINTER))
 		  ++i;
 		continue;
+	      case GOMP_MAP_ATTACH:
+		{
+		  cur_node.host_start = (uintptr_t) hostaddrs[i];
+		  cur_node.host_end = cur_node.host_start + sizeof (void *);
+		  splay_tree_key n = splay_tree_lookup (mem_map, &cur_node);
+		  if (n != NULL)
+		    {
+		      tgt->list[i].key = n;
+		      tgt->list[i].offset = cur_node.host_start - n->host_start;
+		      tgt->list[i].length = n->host_end - n->host_start;
+		      tgt->list[i].copy_from = false;
+		      tgt->list[i].always_copy_from = false;
+		      tgt->list[i].do_detach
+			= (pragma_kind != GOMP_MAP_VARS_OPENACC_ENTER_DATA);
+		      n->refcount++;
+		    }
+		  else
+		    {
+		      gomp_mutex_unlock (&devicep->lock);
+		      gomp_fatal ("outer struct not mapped for attach");
+		    }
+		  gomp_attach_pointer (devicep, aq, mem_map, n,
+				       (uintptr_t) hostaddrs[i], sizes[i],
+				       cbufp);
+		  continue;
+		}
 	      default:
 		break;
 	      }
@@ -1090,10 +1124,12 @@ gomp_map_vars_internal (struct gomp_device_descr *devicep,
 		tgt->list[i].copy_from = GOMP_MAP_COPY_FROM_P (kind & typemask);
 		tgt->list[i].always_copy_from
 		  = GOMP_MAP_ALWAYS_FROM_P (kind & typemask);
+		tgt->list[i].do_detach = false;
 		tgt->list[i].offset = 0;
 		tgt->list[i].length = k->host_end - k->host_start;
 		k->refcount = 1;
 		k->virtual_refcount = 0;
+		k->aux = NULL;
 		tgt->refcount++;
 		array->left = NULL;
 		array->right = NULL;
@@ -1144,6 +1180,7 @@ gomp_map_vars_internal (struct gomp_device_descr *devicep,
 			  tgt->list[j].key = k;
 			  tgt->list[j].copy_from = false;
 			  tgt->list[j].always_copy_from = false;
+			  tgt->list[j].do_detach = false;
 			  if (k->refcount != REFCOUNT_INFINITY)
 			    k->refcount++;
 			  gomp_map_pointer (tgt, aq,
@@ -1377,6 +1414,18 @@ gomp_unmap_vars_internal (struct target_mem_desc *tgt, bool do_copyfrom,
     }
 
   size_t i;
+
+  /* We must perform detachments before any copies back to the host.  */
+  for (i = 0; i < tgt->list_count; i++)
+    {
+      splay_tree_key k = tgt->list[i].key;
+
+      if (k != NULL && tgt->list[i].do_detach)
+	gomp_detach_pointer (devicep, aq, k, tgt->list[i].key->host_start
+					     + tgt->list[i].offset,
+			     k->refcount == 1, NULL);
+    }
+
   for (i = 0; i < tgt->list_count; i++)
     {
       splay_tree_key k = tgt->list[i].key;