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

1 files changed, 99 insertions, 104 deletions

diff --git a/liboffloadmic/plugin/libgomp-plugin-intelmic.cpp b/liboffloadmic/plugin/libgomp-plugin-intelmic.cpp
index 3e7a958..a2d61b1 100644
--- a/liboffloadmic/plugin/libgomp-plugin-intelmic.cpp
+++ b/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 *image_start = ((void **) target_image)[0];
+  void *image_end   = ((void **) target_image)[1];
 
-  void **target_image_descr = (void **) lib_descrs[lib_num].second;
-  void *image_start = target_image_descr[0];
-  void *image_end   = target_image_descr[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
@@ -279,94 +281,87 @@ 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)
-    {
-      fprintf (stderr, "%s: Can't map target variables\n", __FILE__);
-      exit (1);
-    }
+      int num_funcs = 0;
+      int num_vars = 0;
+      void **table = NULL;
 
-  table = (mapping_table *) realloc (table, (table_size + host_num_funcs
-					     + host_num_vars)
-					    * sizeof (mapping_table));
-  if (table == NULL)
-    {
-      fprintf (stderr, "%s: Can't allocate memory\n", __FILE__);
-      exit (1);
-    }
+      get_target_table (dev, num_funcs, num_vars, table);
 
-  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;
-
-      TRACE ("() lib %d, func %d:\t0x%llx -- 0x%llx",
-	     lib_num, i, t.host_start, t.tgt_start);
-
-      table[table_size++] = t;
-    }
+      AddrVect curr_dev_table;
 
-  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];
+      for (int i = 0; i < num_funcs; i++)
+	{
+	  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);
+	}
 
-      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);
+      for (int i = 0; i < num_vars; i++)
+	{
+	  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);
+	}
 
-      table[table_size++] = t;
+      dev_table.push_back (curr_dev_table);
     }
 
-  delete [] tgt_table;
+  address_table->insert (std::make_pair (target_image, dev_table));
+
+  free (image);
 }
 
 extern "C" int
-GOMP_OFFLOAD_get_table (int device, void *result)
+GOMP_OFFLOAD_load_image (int device, void *target_image, addr_pair **result)
 {
-  TRACE ("(num_libraries = %d)", num_libraries);
+  TRACE ("(device = %d, target_image = %p)", device, target_image);
 
-  mapping_table *table = NULL;
-  int table_size = 0;
+  /* 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);
 
-  for (int i = 0; i < num_libraries; i++)
-    load_lib_and_get_table (device, i, table, table_size);
+  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);
+    }
 
-  *(void **) result = table;
+  std::copy (curr_dev_table->begin (), curr_dev_table->end (), table);
+  *result = table;
   return table_size;
 }
 
+extern "C" void
+GOMP_OFFLOAD_unload_image (int device, void *target_image)
+{
+  TRACE ("(device = %d, target_image = %p)", device, target_image);
+
+  /* TODO: Currently liboffloadmic doesn't support __offload_unregister_image
+     for libraries.  */
+
+  address_table->erase (target_image);
+}
+
 extern "C" void *
 GOMP_OFFLOAD_alloc (int device, size_t size)
 {