[gcc r14-2224] Fix couple of endianness issues in fold_ctor_reference

[gcc r14-2224] Fix couple of endianness issues in fold_ctor_reference

[Eric Botcazou]

https://gcc.gnu.org/g:db5d70632a6cb59521e41df7745cacb08d00a3f4

commit r14-2224-gdb5d70632a6cb59521e41df7745cacb08d00a3f4
Author: Eric Botcazou <ebotcazou@adacore.com>
Date:   Fri Jun 30 18:05:34 2023 +0200

    Fix couple of endianness issues in fold_ctor_reference
    
    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.
    
    gcc/
            * gimple-fold.cc (fold_array_ctor_reference): Fix head comment.
            (fold_nonarray_ctor_reference): Likewise.  Specifically deal
            with integral bit-fields.
            (fold_ctor_reference): Make sure that the constructor uses the
            native storage order.
    
    gcc/testsuite/
            * gcc.c-torture/execute/20230630-1.c: New test.
            * gcc.c-torture/execute/20230630-2.c: Likewise.
            * gcc.c-torture/execute/20230630-3.c: Likewise
            * gcc.c-torture/execute/20230630-4.c: Likewise

Diff:
---
 gcc/gimple-fold.cc                               | 57 +++++++++++++++---------
 gcc/testsuite/gcc.c-torture/execute/20230630-1.c | 23 ++++++++++
 gcc/testsuite/gcc.c-torture/execute/20230630-2.c | 29 ++++++++++++
 gcc/testsuite/gcc.c-torture/execute/20230630-3.c | 27 +++++++++++
 gcc/testsuite/gcc.c-torture/execute/20230630-4.c | 33 ++++++++++++++
 5 files changed, 148 insertions(+), 21 deletions(-)

diff --git a/gcc/gimple-fold.cc b/gcc/gimple-fold.cc
index 6d167b116b9..8434274f69d 100644
--- a/gcc/gimple-fold.cc
+++ b/gcc/gimple-fold.cc
@@ -7851,12 +7851,11 @@ 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,
@@ -8021,13 +8020,11 @@ 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,
@@ -8039,8 +8036,7 @@ 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);
@@ -8112,6 +8108,19 @@ 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 start at their 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);
@@ -8124,7 +8133,7 @@ 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
@@ -8165,7 +8174,8 @@ 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
@@ -8181,7 +8191,12 @@ 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)
@@ -8196,9 +8211,9 @@ 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
diff --git a/gcc/testsuite/gcc.c-torture/execute/20230630-1.c b/gcc/testsuite/gcc.c-torture/execute/20230630-1.c
new file mode 100644
index 00000000000..7c1f15c177f
--- /dev/null
+++ b/gcc/testsuite/gcc.c-torture/execute/20230630-1.c
@@ -0,0 +1,23 @@
+struct S {
+  short int i : 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;
+}
diff --git a/gcc/testsuite/gcc.c-torture/execute/20230630-2.c b/gcc/testsuite/gcc.c-torture/execute/20230630-2.c
new file mode 100644
index 00000000000..c05c1666516
--- /dev/null
+++ b/gcc/testsuite/gcc.c-torture/execute/20230630-2.c
@@ -0,0 +1,29 @@
+#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 i : 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;
+}
diff --git a/gcc/testsuite/gcc.c-torture/execute/20230630-3.c b/gcc/testsuite/gcc.c-torture/execute/20230630-3.c
new file mode 100644
index 00000000000..fc106c97b5b
--- /dev/null
+++ b/gcc/testsuite/gcc.c-torture/execute/20230630-3.c
@@ -0,0 +1,27 @@
+struct S {
+  int i : 24;
+  char c1 : 1;
+  char c2 : 1;
+  char c3 : 1;
+  char c4 : 1;
+  char c5 : 1;
+  char c6 : 1;
+  char c7 : 1;
+  char c8 : 1;
+};
+
+int main (void)
+{
+  struct S s0 = { 1193046, 1, 1, 1, 1, 1, 1, 1, 1 };
+  char *p = (char *) &s0;
+
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+  if (*p != 86)
+    __builtin_abort ();
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+  if (*p != 18)
+    __builtin_abort ();
+#endif
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.c-torture/execute/20230630-4.c b/gcc/testsuite/gcc.c-torture/execute/20230630-4.c
new file mode 100644
index 00000000000..df33c18a8cd
--- /dev/null
+++ b/gcc/testsuite/gcc.c-torture/execute/20230630-4.c
@@ -0,0 +1,33 @@
+#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 {
+  int i : 24;
+  char c1 : 1;
+  char c2 : 1;
+  char c3 : 1;
+  char c4 : 1;
+  char c5 : 1;
+  char c6 : 1;
+  char c7 : 1;
+  char c8 : 1;
+} REVERSE_SSO;
+
+int main (void)
+{
+  struct S s0 = { 1193046, 1, 1, 1, 1, 1, 1, 1, 1 };
+  char *p = (char *) &s0;
+
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+  if (*p != 18)
+    __builtin_abort ();
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+  if (*p != 86)
+    __builtin_abort ();
+#endif
+
+  return 0;
+}