analyzer: More features for CPython analyzer plugin [PR107646]

This patch adds known function subclasses for Python/C API functions
PyList_New, PyLong_FromLong, and PyList_Append. It also adds new
optional parameters for
region_model::get_or_create_region_for_heap_alloc, allowing for the
newly allocated region to immediately transition from the start state to
the assumed non-null state in the malloc state machine if desired.
Finally, it adds a new procedure, dg-require-python-h, intended as a
directive in Python-related analyzer tests, to append necessary Python
flags during the tests' build process.

The main warnings we gain in this patch with respect to the known function
subclasses mentioned are leak related. For example:

rc3.c: In function ‘create_py_object’:
│
rc3.c:21:10: warning: leak of ‘item’ [CWE-401] [-Wanalyzer-malloc-leak]
│
   21 |   return list;
      │
      |          ^~~~
│
  ‘create_py_object’: events 1-4
│
    |
│
    |    4 |   PyObject* item = PyLong_FromLong(10);
│
    |      |                    ^~~~~~~~~~~~~~~~~~~
│
    |      |                    |
│
    |      |                    (1) allocated here
│
    |      |                    (2) when ‘PyLong_FromLong’ succeeds
│
    |    5 |   PyObject* list = PyList_New(2);
│
    |      |                    ~~~~~~~~~~~~~
│
    |      |                    |
│
    |      |                    (3) when ‘PyList_New’ fails
│
    |......
│
    |   21 |   return list;
│
    |      |          ~~~~
│
    |      |          |
│
    |      |          (4) ‘item’ leaks here; was allocated at (1)
│

Some concessions were made to
simplify the analysis process when comparing kf_PyList_Append with the
real implementation. In particular, PyList_Append performs some
optimization internally to try and avoid calls to realloc if
possible. For simplicity, we assume that realloc is called every time.
Also, we grow the size by just 1 (to ensure enough space for adding a
new element) rather than abide by the heuristics that the actual implementation
follows.

gcc/analyzer/ChangeLog:
	PR analyzer/107646
	* call-details.h: New function.
	* region-model.cc (region_model::get_or_create_region_for_heap_alloc):
	New optional parameters.
	* region-model.h (class region_model): New optional parameters.
	* sm-malloc.cc (on_realloc_with_move): New function.
	(region_model::transition_ptr_sval_non_null): New function.

gcc/testsuite/ChangeLog:
	PR analyzer/107646
	* gcc.dg/plugin/analyzer_cpython_plugin.c: Analyzer support for
	PyList_New, PyList_Append, PyLong_FromLong
	* gcc.dg/plugin/plugin.exp: New test.
	* lib/target-supports.exp: New procedure.
	* gcc.dg/plugin/cpython-plugin-test-2.c: New test.

Signed-off-by: Eric Feng <ef2648@columbia.edu>

4 files changed, 72 insertions, 5 deletions

diff --git a/gcc/analyzer/call-details.h b/gcc/analyzer/call-details.h
index 24be224..bf26011 100644
--- a/gcc/analyzer/call-details.h
+++ b/gcc/analyzer/call-details.h
@@ -49,6 +49,10 @@ public:
     return POINTER_TYPE_P (get_arg_type (idx));
   }
   bool arg_is_size_p (unsigned idx) const;
+  bool arg_is_integral_p (unsigned idx) const
+  {
+    return INTEGRAL_TYPE_P (get_arg_type (idx));
+  }
 
   const gcall *get_call_stmt () const { return m_call; }
   location_t get_location () const;
diff --git a/gcc/analyzer/region-model.cc b/gcc/analyzer/region-model.cc
index 094b7af..aa9fe00 100644
--- a/gcc/analyzer/region-model.cc
+++ b/gcc/analyzer/region-model.cc
@@ -4991,11 +4991,16 @@ region_model::check_dynamic_size_for_floats (const svalue *size_in_bytes,
    Use CTXT to complain about tainted sizes.
 
    Reuse an existing heap_allocated_region if it's not being referenced by
-   this region_model; otherwise create a new one.  */
+   this region_model; otherwise create a new one.
+
+   Optionally (update_state_machine) transitions the pointer pointing to the
+   heap_allocated_region from start to assumed non-null.  */
 
 const region *
 region_model::get_or_create_region_for_heap_alloc (const svalue *size_in_bytes,
-						   region_model_context *ctxt)
+       region_model_context *ctxt,
+       bool update_state_machine,
+       const call_details *cd)
 {
   /* Determine which regions are referenced in this region_model, so that
      we can reuse an existing heap_allocated_region if it's not in use on
@@ -5017,6 +5022,14 @@ region_model::get_or_create_region_for_heap_alloc (const svalue *size_in_bytes,
   if (size_in_bytes)
     if (compat_types_p (size_in_bytes->get_type (), size_type_node))
       set_dynamic_extents (reg, size_in_bytes, ctxt);
+
+	if (update_state_machine && cd)
+		{
+			const svalue *ptr_sval
+			= m_mgr->get_ptr_svalue (cd->get_lhs_type (), reg);
+      transition_ptr_sval_non_null (ctxt, ptr_sval);
+		}
+
   return reg;
 }
 
diff --git a/gcc/analyzer/region-model.h b/gcc/analyzer/region-model.h
index 0cf3871..a8acad8 100644
--- a/gcc/analyzer/region-model.h
+++ b/gcc/analyzer/region-model.h
@@ -387,9 +387,12 @@ class region_model
 		       region_model_context *ctxt,
 		       rejected_constraint **out);
 
-  const region *
-  get_or_create_region_for_heap_alloc (const svalue *size_in_bytes,
-				       region_model_context *ctxt);
+	const region *
+	get_or_create_region_for_heap_alloc (const svalue *size_in_bytes,
+				region_model_context *ctxt,
+				bool update_state_machine = false,
+				const call_details *cd = nullptr);
+
   const region *create_region_for_alloca (const svalue *size_in_bytes,
 					  region_model_context *ctxt);
   void get_referenced_base_regions (auto_bitmap &out_ids) const;
@@ -476,6 +479,11 @@ class region_model
 			     const svalue *old_ptr_sval,
 			     const svalue *new_ptr_sval);
 
+  /* Implemented in sm-malloc.cc.  */
+  void
+  transition_ptr_sval_non_null (region_model_context *ctxt,
+      const svalue *new_ptr_sval);
+
   /* Implemented in sm-taint.cc.  */
   void mark_as_tainted (const svalue *sval,
 			region_model_context *ctxt);
diff --git a/gcc/analyzer/sm-malloc.cc b/gcc/analyzer/sm-malloc.cc
index a8c63eb..ec76325 100644
--- a/gcc/analyzer/sm-malloc.cc
+++ b/gcc/analyzer/sm-malloc.cc
@@ -434,6 +434,11 @@ public:
 			     const svalue *new_ptr_sval,
 			     const extrinsic_state &ext_state) const;
 
+  void transition_ptr_sval_non_null (region_model *model,
+      sm_state_map *smap,
+      const svalue *new_ptr_sval,
+      const extrinsic_state &ext_state) const;
+
   standard_deallocator_set m_free;
   standard_deallocator_set m_scalar_delete;
   standard_deallocator_set m_vector_delete;
@@ -2504,6 +2509,17 @@ on_realloc_with_move (region_model *model,
 		   NULL, ext_state);
 }
 
+/*  Hook for get_or_create_region_for_heap_alloc for the case when we want
+   ptr_sval to mark a newly created region as assumed non null on malloc SM.  */
+void
+malloc_state_machine::transition_ptr_sval_non_null (region_model *model,
+    sm_state_map *smap,
+    const svalue *new_ptr_sval,
+    const extrinsic_state &ext_state) const
+{
+  smap->set_state (model, new_ptr_sval, m_free.m_nonnull, NULL, ext_state);
+}
+
 } // anonymous namespace
 
 /* Internal interface to this file. */
@@ -2548,6 +2564,32 @@ region_model::on_realloc_with_move (const call_details &cd,
 				  *ext_state);
 }
 
+/* Moves ptr_sval from start to assumed non-null, for use by
+   region_model::get_or_create_region_for_heap_alloc.  */
+void
+region_model::transition_ptr_sval_non_null (region_model_context *ctxt,
+const svalue *ptr_sval)
+{
+  if (!ctxt)
+    return;
+  const extrinsic_state *ext_state = ctxt->get_ext_state ();
+  if (!ext_state)
+    return;
+
+  sm_state_map *smap;
+  const state_machine *sm;
+  unsigned sm_idx;
+  if (!ctxt->get_malloc_map (&smap, &sm, &sm_idx))
+    return;
+
+  gcc_assert (smap);
+  gcc_assert (sm);
+
+  const malloc_state_machine &malloc_sm = (const malloc_state_machine &)*sm;
+
+  malloc_sm.transition_ptr_sval_non_null (this, smap, ptr_sval, *ext_state);
+}
+
 } // namespace ana
 
 #endif /* #if ENABLE_ANALYZER */