libgomp: rework initialization of offloading

gcc/
	* config/i386/intelmic-mkoffload.c (generate_host_descr_file): Call
	GOMP_offload_unregister from the destructor.
libgomp/
	* libgomp-plugin.h (struct mapping_table): Replace with addr_pair.
	* libgomp.h (struct gomp_memory_mapping): Remove.
	(struct target_mem_desc): Change type of mem_map from
	gomp_memory_mapping * to splay_tree_s *.
	(struct gomp_device_descr): Remove register_image_func, get_table_func.
	Add load_image_func, unload_image_func.
	Change type of mem_map from gomp_memory_mapping to splay_tree_s.
	Remove offload_regions_registered.
	(gomp_init_tables): Remove.
	(gomp_free_memmap): Change type of argument from gomp_memory_mapping *
	to splay_tree_s *.
	* libgomp.map (GOMP_4.0.1): Add GOMP_offload_unregister.
	* oacc-host.c (host_dispatch): Do not initialize register_image_func,
	get_table_func, mem_map.is_initialized, mem_map.splay_tree.root,
	offload_regions_registered.
	Initialize load_image_func, unload_image_func, mem_map.root.
	(goacc_host_init): Do not initialize host_dispatch.mem_map.lock.
	* oacc-init.c (lazy_open): Don't call gomp_init_tables.
	(acc_shutdown_1): Use dev's lock and splay_tree instead of mem_map's.
	* oacc-mem.c (lookup_host): Get gomp_device_descr *dev instead of
	gomp_memory_mapping *.  Use dev's lock and splay_tree.
	(lookup_dev): Use dev's lock.
	(acc_deviceptr): Pass dev to lookup_host instead of mem_map.
	(acc_is_present): Likewise.
	(acc_map_data): Likewise.
	(acc_unmap_data): Likewise.  Use dev's lock.
	(present_create_copy): Likewise.
	(delete_copyout): Pass dev to lookup_host instead of mem_map.
	(update_dev_host): Likewise.
	(gomp_acc_remove_pointer): Likewise.  Use dev's lock.
	* oacc-parallel.c (GOACC_parallel): Use dev's lock and splay_tree.
	* plugin/plugin-host.c (GOMP_OFFLOAD_register_image): Remove.
	(GOMP_OFFLOAD_get_table): Remove
	(GOMP_OFFLOAD_load_image): New function.
	(GOMP_OFFLOAD_unload_image): New function.
	* target.c (register_lock): New mutex for offload image registration.
	(num_devices): Do not guard with PLUGIN_SUPPORT.
	(gomp_realloc_unlock): New static function.
	(gomp_map_vars_existing): Add device descriptor argument.  Unlock mutex
	before gomp_fatal.
	(gomp_map_vars): Use dev's lock and splay_tree instead of mem_map's.
	Pass devicep to gomp_map_vars_existing.  Unlock mutex before gomp_fatal.
	(gomp_copy_from_async): Use dev's lock and splay_tree instead of
	mem_map's.
	(gomp_unmap_vars): Likewise.
	(gomp_update): Remove gomp_memory_mapping argument.  Use dev's lock and
	splay_tree instead of mm's.  Unlock mutex before gomp_fatal.
	(gomp_offload_image_to_device): New static function.
	(GOMP_offload_register): Add mutex lock.
	Call gomp_offload_image_to_device for all initialized devices.
	Replace gomp_realloc with gomp_realloc_unlock.
	(GOMP_offload_unregister): New function.
	(gomp_init_tables): Replace with gomp_init_device.  Replace a call to
	get_table_func from the plugin with calls to init_device_func and
	gomp_offload_image_to_device.
	(gomp_free_memmap): Change type of argument from gomp_memory_mapping *
	to splay_tree_s *.
	(GOMP_target): Do not call gomp_init_tables.  Use dev's lock and
	splay_tree instead of mem_map's.  Unlock mutex before gomp_fatal.
	(GOMP_target_data): Do not call gomp_init_tables.
	(GOMP_target_update): Likewise.  Remove argument from gomp_update.
	(gomp_load_plugin_for_device): Replace register_image and get_table
	with load_image and unload_image in DLSYM ().
	(gomp_register_images_for_device): Remove function.
	(gomp_target_init): Do not initialize current_device.mem_map.*,
	current_device.offload_regions_registered.
	Remove call to gomp_register_images_for_device.
	Do not free offload_images and num_offload_images.
liboffloadmic/
	* plugin/libgomp-plugin-intelmic.cpp: Include map.
	(AddrVect, DevAddrVect, ImgDevAddrMap): New typedefs.
	(num_devices, num_images, address_table): New static vars.
	(num_libraries, lib_descrs): Remove static vars.
	(set_mic_lib_path): Rename to ...
	(init): ... this.  Allocate address_table and get num_devices.
	(GOMP_OFFLOAD_get_num_devices): return num_devices.
	(load_lib_and_get_table): Remove static function.
	(offload_image): New static function.
	(GOMP_OFFLOAD_get_table): Remove function.
	(GOMP_OFFLOAD_load_image, GOMP_OFFLOAD_unload_image): New functions.

From-SVN: r221878

gcc/ChangeLog

+2015-04-06  Ilya Verbin  <ilya.verbin@intel.com>
+
+	* config/i386/intelmic-mkoffload.c (generate_host_descr_file): Call
+	GOMP_offload_unregister from the destructor.
+
 2015-04-06  Ilya Enkovich  <ilya.enkovich@intel.com>
 
 	* ipa-chkp.c (chkp_maybe_create_clone): Reset cdtor

gcc/config/i386/intelmic-mkoffload.c

@@ -350,14 +350,27 @@ generate_host_descr_file (const char *host_compiler)
 	   "#ifdef __cplusplus\n"
 	   "extern \"C\"\n"
 	   "#endif\n"
-	   "void GOMP_offload_register (void *, int, void *);\n\n"
+	   "void GOMP_offload_register (void *, int, void *);\n"
+	   "#ifdef __cplusplus\n"
+	   "extern \"C\"\n"
+	   "#endif\n"
+	   "void GOMP_offload_unregister (void *, int, void *);\n\n"
 
 	   "__attribute__((constructor))\n"
 	   "static void\n"
 	   "init (void)\n"
 	   "{\n"
 	   "  GOMP_offload_register (&__OFFLOAD_TABLE__, %d, __offload_target_data);\n"
+	   "}\n\n", GOMP_DEVICE_INTEL_MIC);
+
+  fprintf (src_file,
+	   "__attribute__((destructor))\n"
+	   "static void\n"
+	   "fini (void)\n"
+	   "{\n"
+	   "  GOMP_offload_unregister (&__OFFLOAD_TABLE__, %d, __offload_target_data);\n"
 	   "}\n", GOMP_DEVICE_INTEL_MIC);
+
   fclose (src_file);
 
   unsigned new_argc = 0;

libgomp/ChangeLog

+2015-04-06  Ilya Verbin  <ilya.verbin@intel.com>
+
+	* libgomp-plugin.h (struct mapping_table): Replace with addr_pair.
+	* libgomp.h (struct gomp_memory_mapping): Remove.
+	(struct target_mem_desc): Change type of mem_map from
+	gomp_memory_mapping * to splay_tree_s *.
+	(struct gomp_device_descr): Remove register_image_func, get_table_func.
+	Add load_image_func, unload_image_func.
+	Change type of mem_map from gomp_memory_mapping to splay_tree_s.
+	Remove offload_regions_registered.
+	(gomp_init_tables): Remove.
+	(gomp_free_memmap): Change type of argument from gomp_memory_mapping *
+	to splay_tree_s *.
+	* libgomp.map (GOMP_4.0.1): Add GOMP_offload_unregister.
+	* oacc-host.c (host_dispatch): Do not initialize register_image_func,
+	get_table_func, mem_map.is_initialized, mem_map.splay_tree.root,
+	offload_regions_registered.
+	Initialize load_image_func, unload_image_func, mem_map.root.
+	(goacc_host_init): Do not initialize host_dispatch.mem_map.lock.
+	* oacc-init.c (lazy_open): Don't call gomp_init_tables.
+	(acc_shutdown_1): Use dev's lock and splay_tree instead of mem_map's.
+	* oacc-mem.c (lookup_host): Get gomp_device_descr *dev instead of
+	gomp_memory_mapping *.  Use dev's lock and splay_tree.
+	(lookup_dev): Use dev's lock.
+	(acc_deviceptr): Pass dev to lookup_host instead of mem_map.
+	(acc_is_present): Likewise.
+	(acc_map_data): Likewise.
+	(acc_unmap_data): Likewise.  Use dev's lock.
+	(present_create_copy): Likewise.
+	(delete_copyout): Pass dev to lookup_host instead of mem_map.
+	(update_dev_host): Likewise.
+	(gomp_acc_remove_pointer): Likewise.  Use dev's lock.
+	* oacc-parallel.c (GOACC_parallel): Use dev's lock and splay_tree.
+	* plugin/plugin-host.c (GOMP_OFFLOAD_register_image): Remove.
+	(GOMP_OFFLOAD_get_table): Remove
+	(GOMP_OFFLOAD_load_image): New function.
+	(GOMP_OFFLOAD_unload_image): New function.
+	* target.c (register_lock): New mutex for offload image registration.
+	(num_devices): Do not guard with PLUGIN_SUPPORT.
+	(gomp_realloc_unlock): New static function.
+	(gomp_map_vars_existing): Add device descriptor argument.  Unlock mutex
+	before gomp_fatal.
+	(gomp_map_vars): Use dev's lock and splay_tree instead of mem_map's.
+	Pass devicep to gomp_map_vars_existing.  Unlock mutex before gomp_fatal.
+	(gomp_copy_from_async): Use dev's lock and splay_tree instead of
+	mem_map's.
+	(gomp_unmap_vars): Likewise.
+	(gomp_update): Remove gomp_memory_mapping argument.  Use dev's lock and
+	splay_tree instead of mm's.  Unlock mutex before gomp_fatal.
+	(gomp_offload_image_to_device): New static function.
+	(GOMP_offload_register): Add mutex lock.
+	Call gomp_offload_image_to_device for all initialized devices.
+	Replace gomp_realloc with gomp_realloc_unlock.
+	(GOMP_offload_unregister): New function.
+	(gomp_init_tables): Replace with gomp_init_device.  Replace a call to
+	get_table_func from the plugin with calls to init_device_func and
+	gomp_offload_image_to_device.
+	(gomp_free_memmap): Change type of argument from gomp_memory_mapping *
+	to splay_tree_s *.
+	(GOMP_target): Do not call gomp_init_tables.  Use dev's lock and
+	splay_tree instead of mem_map's.  Unlock mutex before gomp_fatal.
+	(GOMP_target_data): Do not call gomp_init_tables.
+	(GOMP_target_update): Likewise.  Remove argument from gomp_update.
+	(gomp_load_plugin_for_device): Replace register_image and get_table
+	with load_image and unload_image in DLSYM ().
+	(gomp_register_images_for_device): Remove function.
+	(gomp_target_init): Do not initialize current_device.mem_map.*,
+	current_device.offload_regions_registered.
+	Remove call to gomp_register_images_for_device.
+	Do not free offload_images and num_offload_images.
+
 2015-03-30  Jakub Jelinek  <jakub@redhat.com>
 
 	PR fortran/65597

libgomp/libgomp-plugin.h

@@ -51,14 +51,12 @@ enum offload_target_type
   OFFLOAD_TARGET_TYPE_INTEL_MIC = 6
 };
 
-/* Auxiliary struct, used for transferring a host-target address range mapping
-   from plugin to libgomp.  */
-struct mapping_table
+/* Auxiliary struct, used for transferring pairs of addresses from plugin
+   to libgomp.  */
+struct addr_pair
 {
-  uintptr_t host_start;
-  uintptr_t host_end;
-  uintptr_t tgt_start;
-  uintptr_t tgt_end;
+  uintptr_t start;
+  uintptr_t end;
 };
 
 /* Miscellaneous functions.  */

libgomp/libgomp.h

@@ -224,7 +224,6 @@ struct gomp_team_state
 };
 
 struct target_mem_desc;
-struct gomp_memory_mapping;
 
 /* These are the OpenMP 4.0 Internal Control Variables described in
    section 2.3.1.  Those described as having one copy per task are
@@ -657,7 +656,7 @@ struct target_mem_desc {
   struct gomp_device_descr *device_descr;
 
   /* Memory mapping info for the thread that created this descriptor.  */
-  struct gomp_memory_mapping *mem_map;
+  struct splay_tree_s *mem_map;
 
   /* List of splay keys to remove (or decrease refcount)
      at the end of region.  */
@@ -683,20 +682,6 @@ struct splay_tree_key_s {
 
 #include "splay-tree.h"
 
-/* Information about mapped memory regions (per device/context).  */
-
-struct gomp_memory_mapping
-{
-  /* Mutex for operating with the splay tree and other shared structures.  */
-  gomp_mutex_t lock;
-
-  /* True when tables have been added to this memory map.  */
-  bool is_initialized;
-
-  /* Splay tree containing information about mapped memory regions.  */
-  struct splay_tree_s splay_tree;
-};
-
 typedef struct acc_dispatch_t
 {
   /* This is a linked list of data mapped using the
@@ -773,19 +758,18 @@ struct gomp_device_descr
   unsigned int (*get_caps_func) (void);
   int (*get_type_func) (void);
   int (*get_num_devices_func) (void);
-  void (*register_image_func) (void *, void *);
   void (*init_device_func) (int);
   void (*fini_device_func) (int);
-  int (*get_table_func) (int, struct mapping_table **);
+  int (*load_image_func) (int, void *, struct addr_pair **);
+  void (*unload_image_func) (int, void *);
   void *(*alloc_func) (int, size_t);
   void (*free_func) (int, void *);
   void *(*dev2host_func) (int, void *, const void *, size_t);
   void *(*host2dev_func) (int, void *, const void *, size_t);
   void (*run_func) (int, void *, void *);
 
-  /* Memory-mapping info for this device instance.  */
-  /* Uses a separate lock.  */
-  struct gomp_memory_mapping mem_map;
+  /* Splay tree containing information about mapped memory regions.  */
+  struct splay_tree_s mem_map;
 
   /* Mutex for the mutable data.  */
   gomp_mutex_t lock;
@@ -793,9 +777,6 @@ struct gomp_device_descr
   /* Set to true when device is initialized.  */
   bool is_initialized;
 
-  /* True when offload regions have been registered with this device.  */
-  bool offload_regions_registered;
-
   /* OpenACC-specific data and functions.  */
   /* This is mutable because of its mutable data_environ and target_data
      members.  */
@@ -811,9 +792,7 @@ extern struct target_mem_desc *gomp_map_vars (struct gomp_device_descr *,
 extern void gomp_copy_from_async (struct target_mem_desc *);
 extern void gomp_unmap_vars (struct target_mem_desc *, bool);
 extern void gomp_init_device (struct gomp_device_descr *);
-extern void gomp_init_tables (struct gomp_device_descr *,
-			      struct gomp_memory_mapping *);
-extern void gomp_free_memmap (struct gomp_memory_mapping *);
+extern void gomp_free_memmap (struct splay_tree_s *);
 extern void gomp_fini_device (struct gomp_device_descr *);
 
 /* work.c */

libgomp/libgomp.map

@@ -231,6 +231,7 @@ GOMP_4.0 {
 GOMP_4.0.1 {
   global:
 	GOMP_offload_register;
+	GOMP_offload_unregister;
 } GOMP_4.0;
 
 OACC_2.0 {

libgomp/oacc-host.c

@@ -43,20 +43,18 @@ static struct gomp_device_descr host_dispatch =
     .get_caps_func = GOMP_OFFLOAD_get_caps,
     .get_type_func = GOMP_OFFLOAD_get_type,
     .get_num_devices_func = GOMP_OFFLOAD_get_num_devices,
-    .register_image_func = GOMP_OFFLOAD_register_image,
     .init_device_func = GOMP_OFFLOAD_init_device,
     .fini_device_func = GOMP_OFFLOAD_fini_device,
-    .get_table_func = GOMP_OFFLOAD_get_table,
+    .load_image_func = GOMP_OFFLOAD_load_image,
+    .unload_image_func = GOMP_OFFLOAD_unload_image,
     .alloc_func = GOMP_OFFLOAD_alloc,
     .free_func = GOMP_OFFLOAD_free,
     .dev2host_func = GOMP_OFFLOAD_dev2host,
     .host2dev_func = GOMP_OFFLOAD_host2dev,
     .run_func = GOMP_OFFLOAD_run,
 
-    .mem_map.is_initialized = false,
-    .mem_map.splay_tree.root = NULL,
+    .mem_map.root = NULL,
     .is_initialized = false,
-    .offload_regions_registered = false,
 
     .openacc = {
       .open_device_func = GOMP_OFFLOAD_openacc_open_device,
@@ -94,7 +92,6 @@ static struct gomp_device_descr host_dispatch =
 static __attribute__ ((constructor))
 void goacc_host_init (void)
 {
-  gomp_mutex_init (&host_dispatch.mem_map.lock);
   gomp_mutex_init (&host_dispatch.lock);
   goacc_register (&host_dispatch);
 }

libgomp/oacc-init.c

@@ -284,12 +284,6 @@ lazy_open (int ord)
     = acc_dev->openacc.create_thread_data_func (acc_dev->openacc.target_data);
 
   acc_dev->openacc.async_set_async_func (acc_async_sync);
-
-  struct gomp_memory_mapping *mem_map = &acc_dev->mem_map;
-  gomp_mutex_lock (&mem_map->lock);
-  if (!mem_map->is_initialized)
-    gomp_init_tables (acc_dev, mem_map);
-  gomp_mutex_unlock (&mem_map->lock);
 }
 
 /* OpenACC 2.0a (3.2.12, 3.2.13) doesn't specify whether the serialization of
@@ -351,10 +345,9 @@ acc_shutdown_1 (acc_device_t d)
 
 	  walk->dev->openacc.target_data = target_data = NULL;
 
-	  struct gomp_memory_mapping *mem_map = &walk->dev->mem_map;
-	  gomp_mutex_lock (&mem_map->lock);
-	  gomp_free_memmap (mem_map);
-	  gomp_mutex_unlock (&mem_map->lock);
+	  gomp_mutex_lock (&walk->dev->lock);
+	  gomp_free_memmap (&walk->dev->mem_map);
+	  gomp_mutex_unlock (&walk->dev->lock);
 
 	  walk->dev = NULL;
 	}

libgomp/oacc-mem.c

@@ -38,7 +38,7 @@
 /* Return block containing [H->S), or NULL if not contained.  */
 
 static splay_tree_key
-lookup_host (struct gomp_memory_mapping *mem_map, void *h, size_t s)
+lookup_host (struct gomp_device_descr *dev, void *h, size_t s)
 {
   struct splay_tree_key_s node;
   splay_tree_key key;
@@ -46,11 +46,9 @@ lookup_host (struct gomp_memory_mapping *mem_map, void *h, size_t s)
   node.host_start = (uintptr_t) h;
   node.host_end = (uintptr_t) h + s;
 
-  gomp_mutex_lock (&mem_map->lock);
-
-  key = splay_tree_lookup (&mem_map->splay_tree, &node);
-
-  gomp_mutex_unlock (&mem_map->lock);
+  gomp_mutex_lock (&dev->lock);
+  key = splay_tree_lookup (&dev->mem_map, &node);
+  gomp_mutex_unlock (&dev->lock);
 
   return key;
 }
@@ -65,14 +63,11 @@ lookup_dev (struct target_mem_desc *tgt, void *d, size_t s)
 {
   int i;
   struct target_mem_desc *t;
-  struct gomp_memory_mapping *mem_map;
 
   if (!tgt)
     return NULL;
 
-  mem_map = tgt->mem_map;
-
-  gomp_mutex_lock (&mem_map->lock);
+  gomp_mutex_lock (&tgt->device_descr->lock);
 
   for (t = tgt; t != NULL; t = t->prev)
     {
@@ -80,7 +75,7 @@ lookup_dev (struct target_mem_desc *tgt, void *d, size_t s)
         break;
     }
 
-  gomp_mutex_unlock (&mem_map->lock);
+  gomp_mutex_unlock (&tgt->device_descr->lock);
 
   if (!t)
     return NULL;
@@ -176,7 +171,7 @@ acc_deviceptr (void *h)
 
   struct goacc_thread *thr = goacc_thread ();
 
-  n = lookup_host (&thr->dev->mem_map, h, 1);
+  n = lookup_host (thr->dev, h, 1);
 
   if (!n)
     return NULL;
@@ -229,7 +224,7 @@ acc_is_present (void *h, size_t s)
   struct goacc_thread *thr = goacc_thread ();
   struct gomp_device_descr *acc_dev = thr->dev;
 
-  n = lookup_host (&acc_dev->mem_map, h, s);
+  n = lookup_host (acc_dev, h, s);
 
   if (n && ((uintptr_t)h < n->host_start
 	    || (uintptr_t)h + s > n->host_end
@@ -271,7 +266,7 @@ acc_map_data (void *h, void *d, size_t s)
 	gomp_fatal ("[%p,+%d]->[%p,+%d] is a bad map",
                     (void *)h, (int)s, (void *)d, (int)s);
 
-      if (lookup_host (&acc_dev->mem_map, h, s))
+      if (lookup_host (acc_dev, h, s))
 	gomp_fatal ("host address [%p, +%d] is already mapped", (void *)h,
 		    (int)s);
 
@@ -296,7 +291,7 @@ acc_unmap_data (void *h)
   /* No need to call lazy open, as the address must have been mapped.  */
 
   size_t host_size;
-  splay_tree_key n = lookup_host (&acc_dev->mem_map, h, 1);
+  splay_tree_key n = lookup_host (acc_dev, h, 1);
   struct target_mem_desc *t;
 
   if (!n)
@@ -320,7 +315,7 @@ acc_unmap_data (void *h)
       t->tgt_end = 0;
       t->to_free = 0;
 
-      gomp_mutex_lock (&acc_dev->mem_map.lock);
+      gomp_mutex_lock (&acc_dev->lock);
 
       for (tp = NULL, t = acc_dev->openacc.data_environ; t != NULL;
 	   tp = t, t = t->prev)
@@ -334,7 +329,7 @@ acc_unmap_data (void *h)
 	    break;
 	  }
 
-      gomp_mutex_unlock (&acc_dev->mem_map.lock);
+      gomp_mutex_unlock (&acc_dev->lock);
     }
 
   gomp_unmap_vars (t, true);
@@ -358,7 +353,7 @@ present_create_copy (unsigned f, void *h, size_t s)
   struct goacc_thread *thr = goacc_thread ();
   struct gomp_device_descr *acc_dev = thr->dev;
 
-  n = lookup_host (&acc_dev->mem_map, h, s);
+  n = lookup_host (acc_dev, h, s);
   if (n)
     {
       /* Present. */
@@ -389,13 +384,13 @@ present_create_copy (unsigned f, void *h, size_t s)
       tgt = gomp_map_vars (acc_dev, mapnum, &hostaddrs, NULL, &s, &kinds, true,
 			   false);
 
-      gomp_mutex_lock (&acc_dev->mem_map.lock);
+      gomp_mutex_lock (&acc_dev->lock);
 
       d = tgt->to_free;
       tgt->prev = acc_dev->openacc.data_environ;
       acc_dev->openacc.data_environ = tgt;
 
-      gomp_mutex_unlock (&acc_dev->mem_map.lock);
+      gomp_mutex_unlock (&acc_dev->lock);
     }
 
   return d;
@@ -436,7 +431,7 @@ delete_copyout (unsigned f, void *h, size_t s)
   struct goacc_thread *thr = goacc_thread ();
   struct gomp_device_descr *acc_dev = thr->dev;
 
-  n = lookup_host (&acc_dev->mem_map, h, s);
+  n = lookup_host (acc_dev, h, s);
 
   /* No need to call lazy open, as the data must already have been
      mapped.  */
@@ -479,7 +474,7 @@ update_dev_host (int is_dev, void *h, size_t s)
   struct goacc_thread *thr = goacc_thread ();
   struct gomp_device_descr *acc_dev = thr->dev;
 
-  n = lookup_host (&acc_dev->mem_map, h, s);
+  n = lookup_host (acc_dev, h, s);
 
   /* No need to call lazy open, as the data must already have been
      mapped.  */
@@ -532,7 +527,7 @@ gomp_acc_remove_pointer (void *h, bool force_copyfrom, int async, int mapnum)
   struct target_mem_desc *t;
   int minrefs = (mapnum == 1) ? 2 : 3;
 
-  n = lookup_host (&acc_dev->mem_map, h, 1);
+  n = lookup_host (acc_dev, h, 1);
 
   if (!n)
     gomp_fatal ("%p is not a mapped block", (void *)h);
@@ -543,7 +538,7 @@ gomp_acc_remove_pointer (void *h, bool force_copyfrom, int async, int mapnum)
 
   struct target_mem_desc *tp;
 
-  gomp_mutex_lock (&acc_dev->mem_map.lock);
+  gomp_mutex_lock (&acc_dev->lock);
 
   if (t->refcount == minrefs)
     {
@@ -570,7 +565,7 @@ gomp_acc_remove_pointer (void *h, bool force_copyfrom, int async, int mapnum)
   if (force_copyfrom)
     t->list[0]->copy_from = 1;
 
-  gomp_mutex_unlock (&acc_dev->mem_map.lock);
+  gomp_mutex_unlock (&acc_dev->lock);
 
   /* If running synchronously, unmap immediately.  */
   if (async < acc_async_noval)

libgomp/oacc-parallel.c

@@ -144,9 +144,9 @@ GOACC_parallel (int device, void (*fn) (void *),
     {
       k.host_start = (uintptr_t) fn;
       k.host_end = k.host_start + 1;
-      gomp_mutex_lock (&acc_dev->mem_map.lock);
-      tgt_fn_key = splay_tree_lookup (&acc_dev->mem_map.splay_tree, &k);
-      gomp_mutex_unlock (&acc_dev->mem_map.lock);
+      gomp_mutex_lock (&acc_dev->lock);
+      tgt_fn_key = splay_tree_lookup (&acc_dev->mem_map, &k);
+      gomp_mutex_unlock (&acc_dev->lock);
 
       if (tgt_fn_key == NULL)
 	gomp_fatal ("target function wasn't mapped");

libgomp/plugin/plugin-host.c

@@ -95,12 +95,6 @@ GOMP_OFFLOAD_get_num_devices (void)
 }
 
 STATIC void
-GOMP_OFFLOAD_register_image (void *host_table __attribute__ ((unused)),
-			     void *target_data __attribute__ ((unused)))
-{
-}
-
-STATIC void
 GOMP_OFFLOAD_init_device (int n __attribute__ ((unused)))
 {
 }
@@ -111,12 +105,19 @@ GOMP_OFFLOAD_fini_device (int n __attribute__ ((unused)))
 }
 
 STATIC int
-GOMP_OFFLOAD_get_table (int n __attribute__ ((unused)),
-			struct mapping_table **table __attribute__ ((unused)))
+GOMP_OFFLOAD_load_image (int n __attribute__ ((unused)),
+			 void *i __attribute__ ((unused)),
+			 struct addr_pair **r __attribute__ ((unused)))
 {
   return 0;
 }
 
+STATIC void
+GOMP_OFFLOAD_unload_image (int n __attribute__ ((unused)),
+			   void *i __attribute__ ((unused)))
+{
+}
+
 STATIC void *
 GOMP_OFFLOAD_openacc_open_device (int n)
 {

liboffloadmic/ChangeLog

+2015-04-06  Ilya Verbin  <ilya.verbin@intel.com>
+
+	* plugin/libgomp-plugin-intelmic.cpp: Include map.
+	(AddrVect, DevAddrVect, ImgDevAddrMap): New typedefs.
+	(num_devices, num_images, address_table): New static vars.
+	(num_libraries, lib_descrs): Remove static vars.
+	(set_mic_lib_path): Rename to ...
+	(init): ... this.  Allocate address_table and get num_devices.
+	(GOMP_OFFLOAD_get_num_devices): return num_devices.
+	(load_lib_and_get_table): Remove static function.
+	(offload_image): New static function.
+	(GOMP_OFFLOAD_get_table): Remove function.
+	(GOMP_OFFLOAD_load_image, GOMP_OFFLOAD_unload_image): New functions.
+
 2015-01-15  Thomas Schwinge  <thomas@codesourcery.com>
 
 	* plugin/libgomp-plugin-intelmic.cpp (GOMP_OFFLOAD_get_name)

liboffloadmic/plugin/libgomp-plugin-intelmic.cpp

@@ -34,6 +34,7 @@
 #include <string.h>
 #include <utility>
 #include <vector>
+#include <map>
 #include "libgomp-plugin.h"
 #include "compiler_if_host.h"
 #include "main_target_image.h"
@@ -53,6 +54,29 @@ fprintf (stderr, "\n");					    \
 #endif
 
 
+/* Start/end addresses of functions and global variables on a device.  */
+typedef std::vector<addr_pair> AddrVect;
+
+/* Addresses for one image and all devices.  */
+typedef std::vector<AddrVect> DevAddrVect;
+
+/* Addresses for all images and all devices.  */
+typedef std::map<void *, DevAddrVect> ImgDevAddrMap;
+
+
+/* Total number of available devices.  */
+static int num_devices;
+
+/* Total number of shared libraries with offloading to Intel MIC.  */
+static int num_images;
+
+/* Two dimensional array: one key is a pointer to image,
+   second key is number of device.  Contains a vector of pointer pairs.  */
+static ImgDevAddrMap *address_table;
+
+/* Thread-safe registration of the main image.  */
+static pthread_once_t main_image_is_registered = PTHREAD_ONCE_INIT;
+
 static VarDesc vd_host2tgt = {
   { 1, 1 },		      /* dst, src			      */
   { 1, 0 },		      /* in, out			      */
@@ -90,28 +114,17 @@ static VarDesc vd_tgt2host = {
 };
 
 
-/* Total number of shared libraries with offloading to Intel MIC.  */
-static int num_libraries;
-
-/* Pointers to the descriptors, containing pointers to host-side tables and to
-   target images.  */
-static std::vector< std::pair<void *, void *> > lib_descrs;
-
-/* Thread-safe registration of the main image.  */
-static pthread_once_t main_image_is_registered = PTHREAD_ONCE_INIT;
-
-
 /* Add path specified in LD_LIBRARY_PATH to MIC_LD_LIBRARY_PATH, which is
    required by liboffloadmic.  */
 __attribute__((constructor))
 static void
-set_mic_lib_path (void)
+init (void)
 {
   const char *ld_lib_path = getenv (LD_LIBRARY_PATH_ENV);
   const char *mic_lib_path = getenv (MIC_LD_LIBRARY_PATH_ENV);
 
   if (!ld_lib_path)
-    return;
+    goto out;
 
   if (!mic_lib_path)
     setenv (MIC_LD_LIBRARY_PATH_ENV, ld_lib_path, 1);
@@ -133,6 +146,10 @@ set_mic_lib_path (void)
       if (!use_alloca)
 	free (mic_lib_path_new);
     }
+
+out:
+  address_table = new ImgDevAddrMap;
+  num_devices = _Offload_number_of_devices ();
 }
 
 extern "C" const char *
@@ -162,18 +179,8 @@ GOMP_OFFLOAD_get_type (void)
 extern "C" int
 GOMP_OFFLOAD_get_num_devices (void)
 {
-  int res = _Offload_number_of_devices ();
-  TRACE ("(): return %d", res);
-  return res;
-}
-
-/* This should be called from every shared library with offloading.  */
-extern "C" void
-GOMP_OFFLOAD_register_image (void *host_table, void *target_image)
-{
-  TRACE ("(host_table = %p, target_image = %p)", host_table, target_image);
-  lib_descrs.push_back (std::make_pair (host_table, target_image));
-  num_libraries++;
+  TRACE ("(): return %d", num_devices);
+  return num_devices;
 }
 
 static void
@@ -196,7 +203,8 @@ register_main_image ()
   __offload_register_image (&main_target_image);
 }
 
-/* Load offload_target_main on target.  */
+/* liboffloadmic loads and runs offload_target_main on all available devices
+   during a first call to offload ().  */
 extern "C" void
 GOMP_OFFLOAD_init_device (int device)
 {
@@ -243,9 +251,11 @@ get_target_table (int device, int &num_funcs, int &num_vars, void **&table)
     }
 }
 
+/* Offload TARGET_IMAGE to all available devices and fill address_table with
+   corresponding target addresses.  */
+
 static void
-load_lib_and_get_table (int device, int lib_num, mapping_table *&table,
-			int &table_size)
+offload_image (void *target_image)
 {
   struct TargetImage {
     int64_t size;
@@ -254,19 +264,11 @@ load_lib_and_get_table (int device, int lib_num, mapping_table *&table,
     char data[];
   } __attribute__ ((packed));
 
-  void ***host_table_descr = (void ***) lib_descrs[lib_num].first;
-  void **host_func_start = host_table_descr[0];
-  void **host_func_end   = host_table_descr[1];
-  void **host_var_start  = host_table_descr[2];
-  void **host_var_end    = host_table_descr[3];
-
-  void **target_image_descr = (void **) lib_descrs[lib_num].second;
-  void *image_start = target_image_descr[0];
-  void *image_end   = target_image_descr[1];
+  void *image_start = ((void **) target_image)[0];
+  void *image_end   = ((void **) target_image)[1];
 
-  TRACE ("() host_table_descr { %p, %p, %p, %p }", host_func_start,
-	 host_func_end, host_var_start, host_var_end);
-  TRACE ("() target_image_descr { %p, %p }", image_start, image_end);
+  TRACE ("(target_image = %p { %p, %p })",
+	 target_image, image_start, image_end);
 
   int64_t image_size = (uintptr_t) image_end - (uintptr_t) image_start;
   TargetImage *image
@@ -279,92 +281,85 @@ load_lib_and_get_table (int device, int lib_num, mapping_table *&table,
     }
 
   image->size = image_size;
-  sprintf (image->name, "lib%010d.so", lib_num);
+  sprintf (image->name, "lib%010d.so", num_images++);
   memcpy (image->data, image_start, image->size);
 
   TRACE ("() __offload_register_image %s { %p, %d }",
 	 image->name, image_start, image->size);
   __offload_register_image (image);
 
-  int tgt_num_funcs = 0;
-  int tgt_num_vars = 0;
-  void **tgt_table = NULL;
-  get_target_table (device, tgt_num_funcs, tgt_num_vars, tgt_table);
-  free (image);
-
-  /* The func table contains only addresses, the var table contains addresses
-     and corresponding sizes.  */
-  int host_num_funcs = host_func_end - host_func_start;
-  int host_num_vars  = (host_var_end - host_var_start) / 2;
-  TRACE ("() host_num_funcs = %d, tgt_num_funcs = %d",
-	 host_num_funcs, tgt_num_funcs);
-  TRACE ("() host_num_vars = %d, tgt_num_vars = %d",
-	 host_num_vars, tgt_num_vars);
-  if (host_num_funcs != tgt_num_funcs)
+  /* Receive tables for target_image from all devices.  */
+  DevAddrVect dev_table;
+  for (int dev = 0; dev < num_devices; dev++)
     {
-      fprintf (stderr, "%s: Can't map target functions\n", __FILE__);
-      exit (1);
-    }
-  if (host_num_vars != tgt_num_vars)
+      int num_funcs = 0;
+      int num_vars = 0;
+      void **table = NULL;
+
+      get_target_table (dev, num_funcs, num_vars, table);
+
+      AddrVect curr_dev_table;
+
+      for (int i = 0; i < num_funcs; i++)
 	{
-      fprintf (stderr, "%s: Can't map target variables\n", __FILE__);
-      exit (1);
+	  addr_pair tgt_addr;
+	  tgt_addr.start = (uintptr_t) table[i];
+	  tgt_addr.end = tgt_addr.start + 1;
+	  TRACE ("() func %d:\t0x%llx..0x%llx", i,
+		 tgt_addr.start, tgt_addr.end);
+	  curr_dev_table.push_back (tgt_addr);
 	}
 
-  table = (mapping_table *) realloc (table, (table_size + host_num_funcs
-					     + host_num_vars)
-					    * sizeof (mapping_table));
-  if (table == NULL)
+      for (int i = 0; i < num_vars; i++)
 	{
-      fprintf (stderr, "%s: Can't allocate memory\n", __FILE__);
-      exit (1);
+	  addr_pair tgt_addr;
+	  tgt_addr.start = (uintptr_t) table[num_funcs+i*2];
+	  tgt_addr.end = tgt_addr.start + (uintptr_t) table[num_funcs+i*2+1];
+	  TRACE ("() var %d:\t0x%llx..0x%llx", i, tgt_addr.start, tgt_addr.end);
+	  curr_dev_table.push_back (tgt_addr);
 	}
 
-  for (int i = 0; i < host_num_funcs; i++)
-    {
-      mapping_table t;
-      t.host_start = (uintptr_t) host_func_start[i];
-      t.host_end = t.host_start + 1;
-      t.tgt_start = (uintptr_t) tgt_table[i];
-      t.tgt_end = t.tgt_start + 1;
+      dev_table.push_back (curr_dev_table);
+    }
 
-      TRACE ("() lib %d, func %d:\t0x%llx -- 0x%llx",
-	     lib_num, i, t.host_start, t.tgt_start);
+  address_table->insert (std::make_pair (target_image, dev_table));
 
-      table[table_size++] = t;
-    }
+  free (image);
+}
 
-  for (int i = 0; i < host_num_vars * 2; i += 2)
-    {
-      mapping_table t;
-      t.host_start = (uintptr_t) host_var_start[i];
-      t.host_end = t.host_start + (uintptr_t) host_var_start[i+1];
-      t.tgt_start = (uintptr_t) tgt_table[tgt_num_funcs+i];
-      t.tgt_end = t.tgt_start + (uintptr_t) tgt_table[tgt_num_funcs+i+1];
+extern "C" int
+GOMP_OFFLOAD_load_image (int device, void *target_image, addr_pair **result)
+{
+  TRACE ("(device = %d, target_image = %p)", device, target_image);
 
-      TRACE ("() lib %d, var %d:\t0x%llx (%d) -- 0x%llx (%d)", lib_num, i/2,
-	     t.host_start, t.host_end - t.host_start,
-	     t.tgt_start, t.tgt_end - t.tgt_start);
+  /* If target_image is already present in address_table, then there is no need
+     to offload it.  */
+  if (address_table->count (target_image) == 0)
+    offload_image (target_image);
 
-      table[table_size++] = t;
+  AddrVect *curr_dev_table = &(*address_table)[target_image][device];
+  int table_size = curr_dev_table->size ();
+  addr_pair *table = (addr_pair *) malloc (table_size * sizeof (addr_pair));
+  if (table == NULL)
+    {
+      fprintf (stderr, "%s: Can't allocate memory\n", __FILE__);
+      exit (1);
     }
 
-  delete [] tgt_table;
+  std::copy (curr_dev_table->begin (), curr_dev_table->end (), table);
+  *result = table;
+  return table_size;
 }
 
-extern "C" int
-GOMP_OFFLOAD_get_table (int device, void *result)
+extern "C" void
+GOMP_OFFLOAD_unload_image (int device, void *target_image)
 {
-  TRACE ("(num_libraries = %d)", num_libraries);
-
-  mapping_table *table = NULL;
-  int table_size = 0;
+  TRACE ("(device = %d, target_image = %p)", device, target_image);
 
-  for (int i = 0; i < num_libraries; i++)
-    load_lib_and_get_table (device, i, table, table_size);
+  /* TODO: Currently liboffloadmic doesn't support __offload_unregister_image
+     for libraries.  */
 
-  *(void **) result = table;
-  return table_size;
+  address_table->erase (target_image);
 }
 
 extern "C" void *