Avoid applying inline plan for all functions ahead of late compilation

[Jan Hubicka <hubicka at ucw dot cz>]

Hi,
late in GCC 4.9 development we broke the feature that ltrans stages do not read all
functions in ahead.  This is because of late IPA passes that do not like to see functions
without IPA transformations applied.  I was originally OK with the solution based
on fact that we have only IPA-PTA as late IPA pass that is disabled by default and
eventually probably should become part of WPA in some form.
SIMD streaming was however added and this causes us to stream in all function bodies
and apply all inlining decisions at very beggining of optimization queue.

Fixed by this patch.  get_body is now responsible for applying transformations
on demand and late IPA passes needs to call get_body on functions that they
are interested in + are advised to not be interested in every single function in
the program.

The patch also hits a bug in i386's ix86_set_current_function. It is responsible
for initializing backend and it does so lazily remembering the previous options
backend was initialized for. Pragma parsing however clears the cache that leads
to wrong settings being used for subsetquent functions.

Bootstrapped/regtested x86_64-linux, will commit it tomorrow after bit of more testing.

Index: gcc/cgraphclones.c
===================================================================
--- gcc/cgraphclones.c	(revision 217612)
+++ gcc/cgraphclones.c	(working copy)
@@ -307,7 +307,7 @@ duplicate_thunk_for_node (cgraph_node *t
     node = duplicate_thunk_for_node (thunk_of, node);
 
   if (!DECL_ARGUMENTS (thunk->decl))
-    thunk->get_body ();
+    thunk->get_untransformed_body ();
 
   cgraph_edge *cs;
   for (cs = node->callers; cs; cs = cs->next_caller)
@@ -1067,7 +1067,7 @@ symbol_table::materialize_all_clones (vo
 	      && !gimple_has_body_p (node->decl))
 	    {
 	      if (!node->clone_of->clone_of)
-		node->clone_of->get_body ();
+		node->clone_of->get_untransformed_body ();
 	      if (gimple_has_body_p (node->clone_of->decl))
 	        {
 		  if (symtab->dump_file)
Index: gcc/ipa-icf.c
===================================================================
--- gcc/ipa-icf.c	(revision 217612)
+++ gcc/ipa-icf.c	(working copy)
@@ -706,7 +706,7 @@ void
 sem_function::init (void)
 {
   if (in_lto_p)
-    get_node ()->get_body ();
+    get_node ()->get_untransformed_body ();
 
   tree fndecl = node->decl;
   function *func = DECL_STRUCT_FUNCTION (fndecl);
Index: gcc/passes.c
===================================================================
--- gcc/passes.c	(revision 217612)
+++ gcc/passes.c	(working copy)
@@ -2214,36 +2214,6 @@ execute_one_pass (opt_pass *pass)
      executed.  */
   invoke_plugin_callbacks (PLUGIN_PASS_EXECUTION, pass);
 
-  /* SIPLE IPA passes do not handle callgraphs with IPA transforms in it.
-     Apply all trnasforms first.  */
-  if (pass->type == SIMPLE_IPA_PASS)
-    {
-      struct cgraph_node *node;
-      bool applied = false;
-      FOR_EACH_DEFINED_FUNCTION (node)
-	if (node->analyzed
-	    && node->has_gimple_body_p ()
-	    && (!node->clone_of || node->decl != node->clone_of->decl))
-	  {
-	    if (!node->global.inlined_to
-		&& node->ipa_transforms_to_apply.exists ())
-	      {
-		node->get_body ();
-		push_cfun (DECL_STRUCT_FUNCTION (node->decl));
-		execute_all_ipa_transforms ();
-		cgraph_edge::rebuild_edges ();
-		free_dominance_info (CDI_DOMINATORS);
-		free_dominance_info (CDI_POST_DOMINATORS);
-		pop_cfun ();
-		applied = true;
-	      }
-	  }
-      if (applied)
-	symtab->remove_unreachable_nodes (false, dump_file);
-      /* Restore current_pass.  */
-      current_pass = pass;
-    }
-
   if (!quiet_flag && !cfun)
     fprintf (stderr, " <%s>", pass->name ? pass->name : "");
 
Index: gcc/cgraphunit.c
===================================================================
--- gcc/cgraphunit.c	(revision 217612)
+++ gcc/cgraphunit.c	(working copy)
@@ -197,7 +197,6 @@ along with GCC; see the file COPYING3.
 #include "target.h"
 #include "diagnostic.h"
 #include "params.h"
-#include "fibheap.h"
 #include "intl.h"
 #include "hash-map.h"
 #include "plugin-api.h"
@@ -1469,7 +1468,7 @@ cgraph_node::expand_thunk (bool output_a
 	}
 
       if (in_lto_p)
-	get_body ();
+	get_untransformed_body ();
       a = DECL_ARGUMENTS (thunk_fndecl);
       
       current_function_decl = thunk_fndecl;
@@ -1522,7 +1521,7 @@ cgraph_node::expand_thunk (bool output_a
       gimple ret;
 
       if (in_lto_p)
-	get_body ();
+	get_untransformed_body ();
       a = DECL_ARGUMENTS (thunk_fndecl);
 
       current_function_decl = thunk_fndecl;
@@ -1744,7 +1743,7 @@ cgraph_node::expand (void)
   announce_function (decl);
   process = 0;
   gcc_assert (lowered);
-  get_body ();
+  get_untransformed_body ();
 
   /* Generate RTL for the body of DECL.  */
 
Index: gcc/cgraph.c
===================================================================
--- gcc/cgraph.c	(revision 217612)
+++ gcc/cgraph.c	(working copy)
@@ -1664,29 +1664,33 @@ release_function_body (tree decl)
 {
   if (DECL_STRUCT_FUNCTION (decl))
     {
-      push_cfun (DECL_STRUCT_FUNCTION (decl));
-      if (cfun->cfg
-	  && current_loops)
-	{
-	  cfun->curr_properties &= ~PROP_loops;
-	  loop_optimizer_finalize ();
-	}
-      if (cfun->gimple_df)
+      if (DECL_STRUCT_FUNCTION (decl)->cfg
+	  || DECL_STRUCT_FUNCTION (decl)->gimple_df)
 	{
-	  delete_tree_ssa ();
-	  delete_tree_cfg_annotations ();
-	  cfun->eh = NULL;
-	}
-      if (cfun->cfg)
-	{
-	  gcc_assert (!dom_info_available_p (CDI_DOMINATORS));
-	  gcc_assert (!dom_info_available_p (CDI_POST_DOMINATORS));
-	  clear_edges ();
-	  cfun->cfg = NULL;
+	  push_cfun (DECL_STRUCT_FUNCTION (decl));
+	  if (cfun->cfg
+	      && current_loops)
+	    {
+	      cfun->curr_properties &= ~PROP_loops;
+	      loop_optimizer_finalize ();
+	    }
+	  if (cfun->gimple_df)
+	    {
+	      delete_tree_ssa ();
+	      delete_tree_cfg_annotations ();
+	      cfun->eh = NULL;
+	    }
+	  if (cfun->cfg)
+	    {
+	      gcc_assert (!dom_info_available_p (CDI_DOMINATORS));
+	      gcc_assert (!dom_info_available_p (CDI_POST_DOMINATORS));
+	      clear_edges ();
+	      cfun->cfg = NULL;
+	    }
+	  if (cfun->value_histograms)
+	    free_histograms ();
+	  pop_cfun ();
 	}
-      if (cfun->value_histograms)
-	free_histograms ();
-      pop_cfun ();
       gimple_set_body (decl, NULL);
       /* Struct function hangs a lot of data that would leak if we didn't
          removed all pointers to it.   */
@@ -3138,7 +3142,7 @@ cgraph_node::function_symbol (enum avail
    present.  */
 
 bool
-cgraph_node::get_body (void)
+cgraph_node::get_untransformed_body (void)
 {
   lto_file_decl_data *file_data;
   const char *data, *name;
@@ -3178,6 +3182,44 @@ cgraph_node::get_body (void)
   return true;
 }
 
+/* Prepare function body.  When doing LTO, read cgraph_node's body from disk 
+   if it is not already present.  When some IPA transformations are scheduled,
+   apply them.  */
+
+bool
+cgraph_node::get_body (void)
+{
+  bool updated;
+
+  updated = get_untransformed_body ();
+
+  /* Getting transformed body makes no sense for inline clones;
+     we should never use this on real clones becuase they are materialized
+     early.
+     TODO: Materializing clones here will likely lead to smaller LTRANS
+     footprint. */
+  gcc_assert (!global.inlined_to && !clone_of);
+  if (ipa_transforms_to_apply.exists ())
+    {
+      opt_pass *saved_current_pass = current_pass;
+      FILE *saved_dump_file = dump_file;
+      int saved_dump_flags = dump_flags;
+
+      push_cfun (DECL_STRUCT_FUNCTION (decl));
+      execute_all_ipa_transforms ();
+      cgraph_edge::rebuild_edges ();
+      free_dominance_info (CDI_DOMINATORS);
+      free_dominance_info (CDI_POST_DOMINATORS);
+      pop_cfun ();
+      updated = true;
+
+      current_pass = saved_current_pass;
+      dump_file = saved_dump_file;
+      dump_flags = saved_dump_flags;
+    }
+  return updated;
+}
+
 /* Return the DECL_STRUCT_FUNCTION of the function.  */
 
 struct function *
Index: gcc/cgraph.h
===================================================================
--- gcc/cgraph.h	(revision 217612)
+++ gcc/cgraph.h	(working copy)
@@ -933,6 +933,11 @@ public:
 
   /* When doing LTO, read cgraph_node's body from disk if it is not already
      present.  */
+  bool get_untransformed_body (void);
+
+  /* Prepare function body.  When doing LTO, read cgraph_node's body from disk 
+     if it is not already present.  When some IPA transformations are scheduled,
+     apply them.  */
   bool get_body (void);
 
   /* Release memory used to represent body of function.
Index: gcc/config/i386/i386.c
===================================================================
--- gcc/config/i386/i386.c	(revision 217612)
+++ gcc/config/i386/i386.c	(working copy)
@@ -5029,10 +5029,35 @@ ix86_can_inline_p (tree caller, tree cal
 /* Remember the last target of ix86_set_current_function.  */
 static GTY(()) tree ix86_previous_fndecl;
 
+/* Set target globals to default.  */
+
+static void
+ix86_reset_to_default_globals (void)
+{
+  tree old_tree = (ix86_previous_fndecl
+		   ? DECL_FUNCTION_SPECIFIC_TARGET (ix86_previous_fndecl)
+		   : NULL_TREE);
+
+  if (old_tree)
+    {
+      tree new_tree = target_option_current_node;
+      cl_target_option_restore (&global_options,
+				TREE_TARGET_OPTION (new_tree));
+      if (TREE_TARGET_GLOBALS (new_tree))
+	restore_target_globals (TREE_TARGET_GLOBALS (new_tree));
+      else if (new_tree == target_option_default_node)
+	restore_target_globals (&default_target_globals);
+      else
+	TREE_TARGET_GLOBALS (new_tree)
+	  = save_target_globals_default_opts ();
+    }
+}
+
 /* Invalidate ix86_previous_fndecl cache.  */
 void
 ix86_reset_previous_fndecl (void)
 {
+  ix86_reset_to_default_globals ();
   ix86_previous_fndecl = NULL_TREE;
 }
 
@@ -5071,18 +5096,7 @@ ix86_set_current_function (tree fndecl)
 	}
 
       else if (old_tree)
-	{
-	  new_tree = target_option_current_node;
-	  cl_target_option_restore (&global_options,
-				    TREE_TARGET_OPTION (new_tree));
-	  if (TREE_TARGET_GLOBALS (new_tree))
-	    restore_target_globals (TREE_TARGET_GLOBALS (new_tree));
-	  else if (new_tree == target_option_default_node)
-	    restore_target_globals (&default_target_globals);
-	  else
-	    TREE_TARGET_GLOBALS (new_tree)
-	      = save_target_globals_default_opts ();
-	}
+	ix86_reset_to_default_globals ();
     }
 }
 
@@ -50972,7 +50986,7 @@ ix86_simd_clone_adjust (struct cgraph_no
   bool ok = ix86_valid_target_attribute_p (node->decl, NULL, args, 0);
   gcc_assert (ok);
   pop_cfun ();
-  ix86_previous_fndecl = NULL_TREE;
+  ix86_reset_previous_fndecl ();
   ix86_set_current_function (node->decl);
 }
 
Index: gcc/tree-inline.c
===================================================================
--- gcc/tree-inline.c	(revision 217612)
+++ gcc/tree-inline.c	(working copy)
@@ -4338,7 +4338,7 @@ expand_call_inline (basic_block bb, gimp
       goto egress;
     }
   fn = cg_edge->callee->decl;
-  cg_edge->callee->get_body ();
+  cg_edge->callee->get_untransformed_body ();
 
 #ifdef ENABLE_CHECKING
   if (cg_edge->callee->decl != id->dst_node->decl)
Index: gcc/tree-ssa-structalias.c
===================================================================
--- gcc/tree-ssa-structalias.c	(revision 217612)
+++ gcc/tree-ssa-structalias.c	(working copy)
@@ -7086,7 +7086,7 @@ ipa_pta_execute (void)
       /* Nodes without a body are not interesting.  Especially do not
          visit clones at this point for now - we get duplicate decls
 	 there for inline clones at least.  */
-      if (!node->has_gimple_body_p () || node->clone_of)
+      if (!node->has_gimple_body_p () || node->global.inlined_to)
 	continue;
       node->get_body ();