analyzer: prevent ICE on isnan (PR 93290)

PR analyzer/93290 reports an ICE on calls to isnan().
The root cause is that an UNORDERED_EXPR is passed
to region_model::eval_condition_without_cm, and there's
a stray gcc_unreachable () in the case where we're comparing
an svalue against itself.

I attempted a more involved patch that properly handled NaN in general
but it seems I've baked the assumption of reflexivity too deeply into
the constraint_manager code.

For now, this patch avoids the ICE and documents the limitation.

gcc/analyzer/ChangeLog:
	PR analyzer/93290
	* region-model.cc (region_model::eval_condition_without_cm): Avoid
	gcc_unreachable for unexpected operations for the case where
	we're comparing an svalue against itself.

gcc/ChangeLog
	* doc/analyzer.texi (Limitations): Add note about NaN.

gcc/testsuite/ChangeLog:
	PR analyzer/93290
	* gcc.dg/analyzer/pr93290.c: New test.

gcc/ChangeLog

+2020-01-17  David Malcolm  <dmalcolm@redhat.com>
+
+	* doc/analyzer.texi (Limitations): Add note about NaN.
+
 2020-01-17  Mihail-Calin Ionescu <mihail.ionescu@arm.com>
 	    Sudakshina Das  <sudi.das@arm.com>
 

gcc/analyzer/ChangeLog

 2020-01-17  David Malcolm  <dmalcolm@redhat.com>
 
+	PR analyzer/93290
+	* region-model.cc (region_model::eval_condition_without_cm): Avoid
+	gcc_unreachable for unexpected operations for the case where
+	we're comparing an svalue against itself.
+
+2020-01-17  David Malcolm  <dmalcolm@redhat.com>
+
 	PR analyzer/93281
 	* region-model.cc
 	(region_model::convert_byte_offset_to_array_index): Convert to

gcc/analyzer/region-model.cc

@@ -5189,13 +5189,11 @@ region_model::eval_condition_without_cm (svalue_id lhs_sid,
     {
       if (lhs == rhs)
 	{
-	  /* If we have the same svalue, then we have equality.
+	  /* If we have the same svalue, then we have equality
+	     (apart from NaN-handling).
 	     TODO: should this definitely be the case for poisoned values?  */
 	  switch (op)
 	    {
-	    default:
-	      gcc_unreachable ();
-
 	    case EQ_EXPR:
 	    case GE_EXPR:
 	    case LE_EXPR:
@@ -5205,6 +5203,10 @@ region_model::eval_condition_without_cm (svalue_id lhs_sid,
 	    case GT_EXPR:
 	    case LT_EXPR:
 	      return tristate::TS_FALSE;
+
+	    default:
+	      /* For other ops, use the logic below.  */
+	      break;
 	    }
 	}
 

gcc/doc/analyzer.texi

@@ -388,6 +388,9 @@ The implementation of call summaries is currently very simplistic.
 @item
 Lack of function pointer analysis
 @item
+The constraint-handling code assumes reflexivity in some places
+(that values are equal to themselves), which is not the case for NaN.
+@item
 The region model code creates lots of little mutable objects at each
 @code{region_model} (and thus per @code{exploded_node}) rather than
 sharing immutable objects and having the mutable state in the

gcc/testsuite/ChangeLog

+2020-01-17  David Malcolm  <dmalcolm@redhat.com>
+
+	PR analyzer/93290
+	* gcc.dg/analyzer/pr93290.c: New test.
+
 2020-01-17  Paolo Carlini  <paolo.carlini@oracle.com>
 
 	PR c++/92542

gcc/testsuite/gcc.dg/analyzer/pr93290.c

+#include <math.h>
+
+int test_1 (void)
+{
+  float foo = 42.;
+  if (isnan (foo))
+    return 1;
+  return 0;
+}