Commit 9b389a5e by Jan Hubicka Committed by Jan Hubicka

re PR tree-optimization/45453 (ICE: verify_cgraph_node failed: inlined_to…

re PR tree-optimization/45453 (ICE: verify_cgraph_node failed: inlined_to pointer set for noninline callers with -O2 -fno-early-inlining)


	PR tree-optimization/45453
	* cgraphunit.c (cgraph_finalize_function): Consider comdat & external
	virtual functions are reachable.
	* ipa-inline.c (cgraph_clone_inlined_nodes): Likewise.
	* ipa.c (cgraph_remove_unreachable_nodes): Likewise.
	* ipa-prop.c (ipa_modify_formal_parameters): Clear DECL_VIRTUAL_P
	when modifying function.

	* g++.dg/tree-ssa/pr45453.C: New testcase.

From-SVN: r164405
parent 1151446c
2010-09-18 Jan Hubicka <jh@suse.cz>
PR tree-optimization/45453
* cgraphunit.c (cgraph_finalize_function): Consider comdat & external
virtual functions are reachable.
* ipa-inline.c (cgraph_clone_inlined_nodes): Likewise.
* ipa.c (cgraph_remove_unreachable_nodes): Likewise.
* ipa-prop.c (ipa_modify_formal_parameters): Clear DECL_VIRTUAL_P
when modifying function.
2010-09-18 Jan Hubicka <jh@suse.cz>
PR tree-optimization/45605
* cgraphunit.c (cgraph_analyze_functions): Allocate bitmap obstack.
* gimple-fold.c (static_object_in_other_unit_p): New function.
......
......@@ -363,7 +363,13 @@ cgraph_finalize_function (tree decl, bool nested)
there. */
if ((TREE_PUBLIC (decl) && !DECL_COMDAT (decl) && !DECL_EXTERNAL (decl))
|| DECL_STATIC_CONSTRUCTOR (decl)
|| DECL_STATIC_DESTRUCTOR (decl))
|| DECL_STATIC_DESTRUCTOR (decl)
/* COMDAT virtual functions may be referenced by vtable from
other compilatoin unit. Still we want to devirtualize calls
to those so we need to analyze them.
FIXME: We should introduce may edges for this purpose and update
their handling in unreachable function removal and inliner too. */
|| (DECL_VIRTUAL_P (decl) && (DECL_COMDAT (decl) || DECL_EXTERNAL (decl))))
cgraph_mark_reachable_node (node);
/* If we've not yet emitted decl, tell the debug info about it. */
......
......@@ -251,6 +251,12 @@ cgraph_clone_inlined_nodes (struct cgraph_edge *e, bool duplicate,
In that case just go ahead and re-use it. */
if (!e->callee->callers->next_caller
&& cgraph_can_remove_if_no_direct_calls_p (e->callee)
/* Inlining might enable more devirtualizing, so we want to remove
those only after all devirtualizable virtual calls are processed.
Lacking may edges in callgraph we just preserve them post
inlining. */
&& (!DECL_VIRTUAL_P (e->callee->decl)
|| (!DECL_COMDAT (e->callee->decl) && !DECL_EXTERNAL (e->callee->decl)))
/* Don't reuse if more than one function shares a comdat group.
If the other function(s) are needed, we need to emit even
this function out of line. */
......
......@@ -2120,6 +2120,7 @@ ipa_modify_formal_parameters (tree fndecl, ipa_parm_adjustment_vec adjustments,
}
TREE_TYPE (fndecl) = new_type;
DECL_VIRTUAL_P (fndecl) = 0;
if (otypes)
VEC_free (tree, heap, otypes);
VEC_free (tree, heap, oparms);
......
......@@ -238,7 +238,12 @@ cgraph_remove_unreachable_nodes (bool before_inlining_p, FILE *file)
#endif
varpool_reset_queue ();
for (node = cgraph_nodes; node; node = node->next)
if (!cgraph_can_remove_if_no_direct_calls_and_refs_p (node)
if ((!cgraph_can_remove_if_no_direct_calls_and_refs_p (node)
/* Keep around virtual functions for possible devirtualization. */
|| (!before_inlining_p
&& !node->global.inlined_to
&& DECL_VIRTUAL_P (node->decl)
&& (DECL_COMDAT (node->decl) || DECL_EXTERNAL (node->decl))))
&& ((!DECL_EXTERNAL (node->decl))
|| before_inlining_p))
{
......
2010-09-18 Jan Hubicka <jh@suse.cz>
PR tree-optimization/45453
* g++.dg/tree-ssa/pr45453.C: New testcase.
2010-09-18 Jason Merrill <jason@redhat.com>
* g++.dg/cpp0x/initlist44.C: New.
......
/* { dg-do compile } */
/* { dg-options "-O2 -fdump-tree-optimized" } */
struct S
{
S();
virtual inline void foo ()
{
foo();
}
};
void
B ()
{
S().foo ();
}
/* We should inline foo and devirtualize call to foo in the inlined version. */
// { dg-final { scan-tree-dump-times "OBJ_TYPE_REF" 1 "optimized" } }
// { dg-final { cleanup-tree-dump "optimized" } }
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment