[PATCH] Fix couple of endianness issues in fold_ctor_reference

[Eric Botcazou <botcazou@adacore.com>]

[-- Attachment #1: Type: text/plain, Size: 1083 bytes --]

Hi,

fold_ctor_reference attempts to use a recursive local processing in order to 
call native_encode_expr on the leaf nodes of the constructor, before falling 
back to calling native_encode_initializer if this fails.  There are a couple 
of issues related to endianness present in it:
  1) it does not specifically handle integral bit-fields; now these are left 
justified on big-endian platforms so cannot be treated like ordinary fields.
  2) it does not check that the constructor uses the native storage order.

Proposed fix attached, tested on x86-64/Linux and SPARC/Solaris, OK for the 
mainline and some branches?


2023-06-30  Eric Botcazou  <ebotcazou@adacore.com>

	* gimple-fold.cc (fold_array_ctor_reference): Fix head comment.
	(fold_nonarray_ctor_reference): Likewise.  Specifically deal
	with integral bit-fields.
	(fold_ctor_reference): Check that the constructor uses the
	native storage order.


2023-06-30  Eric Botcazou  <ebotcazou@adacore.com>

	* gcc.c-torture/execute/20230630-1.c: New test.
	* gcc.c-torture/execute/20230630-2.c: Likewise.

-- 
Eric Botcazou

[-- Attachment #2: p.diff --]
[-- Type: text/x-patch, Size: 5389 bytes --]

diff --git a/gcc/gimple-fold.cc b/gcc/gimple-fold.cc
index 3d46b76edeb..e80a72dfa22 100644
--- a/gcc/gimple-fold.cc
+++ b/gcc/gimple-fold.cc
@@ -7849,12 +7849,11 @@ get_base_constructor (tree base, poly_int64_pod *bit_offset,
     }
 }
 
-/* CTOR is CONSTRUCTOR of an array type.  Fold a reference of SIZE bits
-   to the memory at bit OFFSET.     When non-null, TYPE is the expected
-   type of the reference; otherwise the type of the referenced element
-   is used instead. When SIZE is zero, attempt to fold a reference to
-   the entire element which OFFSET refers to.  Increment *SUBOFF by
-   the bit offset of the accessed element.  */
+/* CTOR is a CONSTRUCTOR of an array or vector type.  Fold a reference of SIZE
+   bits to the memory at bit OFFSET.  If non-null, TYPE is the expected type of
+   the reference; otherwise the type of the referenced element is used instead.
+   When SIZE is zero, attempt to fold a reference to the entire element OFFSET
+   refers to.  Increment *SUBOFF by the bit offset of the accessed element.  */
 
 static tree
 fold_array_ctor_reference (tree type, tree ctor,
@@ -8019,13 +8018,11 @@ fold_array_ctor_reference (tree type, tree ctor,
   return type ? build_zero_cst (type) : NULL_TREE;
 }
 
-/* CTOR is CONSTRUCTOR of an aggregate or vector.  Fold a reference
-   of SIZE bits to the memory at bit OFFSET.   When non-null, TYPE
-   is the expected type of the reference; otherwise the type of
-   the referenced member is used instead.  When SIZE is zero,
-   attempt to fold a reference to the entire member which OFFSET
-   refers to; in this case.  Increment *SUBOFF by the bit offset
-   of the accessed member.  */
+/* CTOR is a CONSTRUCTOR of a record or union type.  Fold a reference of SIZE
+   bits to the memory at bit OFFSET.  If non-null, TYPE is the expected type of
+   the reference; otherwise the type of the referenced member is used instead.
+   When SIZE is zero, attempt to fold a reference to the entire member OFFSET
+   refers to.  Increment *SUBOFF by the bit offset of the accessed member.  */
 
 static tree
 fold_nonarray_ctor_reference (tree type, tree ctor,
@@ -8037,8 +8034,7 @@ fold_nonarray_ctor_reference (tree type, tree ctor,
   unsigned HOST_WIDE_INT cnt;
   tree cfield, cval;
 
-  FOR_EACH_CONSTRUCTOR_ELT (CONSTRUCTOR_ELTS (ctor), cnt, cfield,
-			    cval)
+  FOR_EACH_CONSTRUCTOR_ELT (CONSTRUCTOR_ELTS (ctor), cnt, cfield, cval)
     {
       tree byte_offset = DECL_FIELD_OFFSET (cfield);
       tree field_offset = DECL_FIELD_BIT_OFFSET (cfield);
@@ -8110,6 +8106,19 @@ fold_nonarray_ctor_reference (tree type, tree ctor,
 	    return NULL_TREE;
 
 	  offset_int inner_offset = offset_int (offset) - bitoffset;
+
+	  /* Integral bit-fields are left-justified on big-endian targets, so
+	     we must arrange for native_encode_int to look at the MSB.  */
+          if (DECL_BIT_FIELD (cfield) && INTEGRAL_TYPE_P (TREE_TYPE (cfield)))
+	    {
+	      if (BYTES_BIG_ENDIAN != WORDS_BIG_ENDIAN)
+		return NULL_TREE;
+	      const unsigned int encoding_size
+		= GET_MODE_BITSIZE (SCALAR_INT_TYPE_MODE (TREE_TYPE (cfield)));
+	      if (BYTES_BIG_ENDIAN)
+		inner_offset += encoding_size - wi::to_offset (field_size);
+	    }
+
 	  return fold_ctor_reference (type, cval,
 				      inner_offset.to_uhwi (), size,
 				      from_decl, suboff);
@@ -8122,7 +8131,7 @@ fold_nonarray_ctor_reference (tree type, tree ctor,
   return build_zero_cst (type);
 }
 
-/* CTOR is value initializing memory.  Fold a reference of TYPE and
+/* CTOR is a value initializing memory.  Fold a reference of TYPE and
    bit size POLY_SIZE to the memory at bit POLY_OFFSET.  When POLY_SIZE
    is zero, attempt to fold a reference to the entire subobject
    which OFFSET refers to.  This is used when folding accesses to
@@ -8163,7 +8172,8 @@ fold_ctor_reference (tree type, tree ctor, const poly_uint64 &poly_offset,
 	}
       return ret;
     }
-  /* For constants and byte-aligned/sized reads try to go through
+
+  /* For constants and byte-aligned/sized reads, try to go through
      native_encode/interpret.  */
   if (CONSTANT_CLASS_P (ctor)
       && BITS_PER_UNIT == 8
@@ -8179,7 +8189,12 @@ fold_ctor_reference (tree type, tree ctor, const poly_uint64 &poly_offset,
       if (len > 0)
 	return native_interpret_expr (type, buf, len);
     }
-  if (TREE_CODE (ctor) == CONSTRUCTOR)
+
+  /* For constructors, try first a recursive local processing, but in any case
+     this requires the native storage order.  */
+  if (TREE_CODE (ctor) == CONSTRUCTOR
+      && !(AGGREGATE_TYPE_P (TREE_TYPE (ctor))
+	   && TYPE_REVERSE_STORAGE_ORDER (TREE_TYPE (ctor))))
     {
       unsigned HOST_WIDE_INT dummy = 0;
       if (!suboff)
@@ -8194,9 +8209,9 @@ fold_ctor_reference (tree type, tree ctor, const poly_uint64 &poly_offset,
 	ret = fold_nonarray_ctor_reference (type, ctor, offset, size,
 					    from_decl, suboff);
 
-      /* Fall back to native_encode_initializer.  Needs to be done
-	 only in the outermost fold_ctor_reference call (because it itself
-	 recurses into CONSTRUCTORs) and doesn't update suboff.  */
+      /* Otherwise fall back to native_encode_initializer.  This may be done
+	 only from the outermost fold_ctor_reference call (because it itself
+	 recurses into CONSTRUCTORs and doesn't update suboff).  */
       if (ret == NULL_TREE
 	  && suboff == &dummy
 	  && BITS_PER_UNIT == 8

[-- Attachment #3: 20230630-1.c --]
[-- Type: text/x-csrc, Size: 370 bytes --]

struct S {
  short int f : 12;
  char c1 : 1;
  char c2 : 1;
  char c3 : 1;
  char c4 : 1;
};

int main (void)
{
  struct S s0 = { 341, 1, 1, 1, 1 };
  char *p = (char *) &s0;

#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
  if (*p != 85)
    __builtin_abort ();
#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
  if (*p != 21)
    __builtin_abort ();
#endif

  return 0;
}

[-- Attachment #4: 20230630-2.c --]
[-- Type: text/x-csrc, Size: 591 bytes --]

#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
#define REVERSE_SSO __attribute__((scalar_storage_order("big-endian")));
#else
#define REVERSE_SSO __attribute__((scalar_storage_order("little-endian")));
#endif

struct S {
  short int f : 12;
  char c1 : 1;
  char c2 : 1;
  char c3 : 1;
  char c4 : 1;
} REVERSE_SSO;

int main (void)
{
  struct S s0 = { 341, 1, 1, 1, 1 };
  char *p = (char *) &s0;

#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
  if (*p != 21)
    __builtin_abort ();
#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
  if (*p != 85)
    __builtin_abort ();
#endif

  return 0;
}