Hi!

Working virtually out of Baker Island - AoE timezone.

The following patch implements __builtin_clear_padding builtin that clears
the padding bits in object representation (but preserves value
representation).  Inside of unions it clears only those padding bits that
are padding for all the union members (so that it never alters value
representation).

It handles trailing padding, padding in the middle of structs including
bitfields (PDP11 unhandled, I've never figured out how those bitfields
work), etc.
What isn't handled yet (plan to fix soon) are VLAs, which should be
implementable by adding runtime loop(s) performing the element clearing.
Also, I haven't managed yet to implement a code-size optimization, if
array types are large enough and have more than one element, again perform
a runtime loop for the clearing.

Tested on x86_64-linux, i686-linux and powerpc64-linux, ok for trunk?

2020-11-15  Jakub Jelinek  <ja...@redhat.com>

        PR libstdc++/88101
gcc/
        * builtins.def (BUILT_IN_CLEAR_PADDING): New built-in function.
        * gimple-fold.c (clear_padding_unit, clear_padding_buf_size): New
        const variables.
        (struct clear_padding_struct): New type.
        (clear_padding_flush, clear_padding_add_padding, clear_padding_type,
        clear_padding_union, clear_padding_real_needs_padding_p,
        clear_padding_type_may_have_padding_p,
        gimple_fold_builtin_clear_padding): New functions.
        (gimple_fold_builtin): Handle BUILT_IN_CLEAR_PADDING.
        * doc/extend.texi (__builtin_clear_padding): Document.
gcc/c-family/
        * c-common.c (check_builtin_function_arguments): Handle
        BUILT_IN_CLEAR_PADDING.
gcc/testsuite/
        * c-c++-common/builtin-clear-padding-1.c: New test.
        * c-c++-common/torture/builtin-clear-padding-1.c: New test.
        * c-c++-common/torture/builtin-clear-padding-2.c: New test.
        * c-c++-common/torture/builtin-clear-padding-3.c: New test.
        * gcc.dg/builtin-clear-padding-1.c: New test.

--- gcc/builtins.def.jj 2020-11-09 02:25:52.217020675 -1200
+++ gcc/builtins.def    2020-11-13 22:26:43.549287472 -1200
@@ -839,6 +839,7 @@ DEF_EXT_LIB_BUILTIN    (BUILT_IN_CLEAR_C
 /* [trans-mem]: Adjust BUILT_IN_TM_CALLOC if BUILT_IN_CALLOC is changed.  */
 DEF_LIB_BUILTIN        (BUILT_IN_CALLOC, "calloc", BT_FN_PTR_SIZE_SIZE, 
ATTR_MALLOC_WARN_UNUSED_RESULT_SIZE_1_2_NOTHROW_LEAF_LIST)
 DEF_GCC_BUILTIN        (BUILT_IN_CLASSIFY_TYPE, "classify_type", 
BT_FN_INT_VAR, ATTR_LEAF_LIST)
+DEF_GCC_BUILTIN        (BUILT_IN_CLEAR_PADDING, "clear_padding", 
BT_FN_VOID_VAR, ATTR_NOTHROW_NONNULL_TYPEGENERIC_LEAF)
 DEF_GCC_BUILTIN        (BUILT_IN_CLZ, "clz", BT_FN_INT_UINT, 
ATTR_CONST_NOTHROW_LEAF_LIST)
 DEF_GCC_BUILTIN        (BUILT_IN_CLZIMAX, "clzimax", BT_FN_INT_UINTMAX, 
ATTR_CONST_NOTHROW_LEAF_LIST)
 DEF_GCC_BUILTIN        (BUILT_IN_CLZL, "clzl", BT_FN_INT_ULONG, 
ATTR_CONST_NOTHROW_LEAF_LIST)
--- gcc/c-family/c-common.c.jj  2020-11-13 00:50:23.267552644 -1200
+++ gcc/c-family/c-common.c     2020-11-15 05:29:12.441618995 -1200
@@ -6171,6 +6171,25 @@ check_builtin_function_arguments (locati
        }
       return false;
 
+    case BUILT_IN_CLEAR_PADDING:
+      if (builtin_function_validate_nargs (loc, fndecl, nargs, 1))
+       {
+         if (!POINTER_TYPE_P (TREE_TYPE (args[0])))
+           {
+             error_at (ARG_LOCATION (0), "argument %u in call to function "
+                       "%qE does not have pointer type", 1, fndecl);
+             return false;
+           }
+         else if (!COMPLETE_TYPE_P (TREE_TYPE (TREE_TYPE (args[0]))))
+           {
+             error_at (ARG_LOCATION (0), "argument %u in call to function "
+                       "%qE points to incomplete type", 1, fndecl);
+             return false;
+           }
+         return true;
+       }
+      return false;
+
     default:
       return true;
     }
--- gcc/gimple-fold.c.jj        2020-11-05 22:14:19.926201410 -1200
+++ gcc/gimple-fold.c   2020-11-15 23:20:29.551779949 -1200
@@ -3948,6 +3948,603 @@ gimple_fold_builtin_realloc (gimple_stmt
   return false;
 }
 
+/* Number of bytes into which any type but aggregate or vector types
+   should fit.  */
+static constexpr size_t clear_padding_unit
+  = MAX_BITSIZE_MODE_ANY_MODE / BITS_PER_UNIT;
+/* Buffer size on which __builtin_clear_padding folding code works.  */
+static const size_t clear_padding_buf_size = 32 * clear_padding_unit;
+
+/* Data passed through __builtin_clear_padding folding.  */
+struct clear_padding_struct {
+  location_t loc;
+  tree base;
+  gimple_stmt_iterator *gsi;
+  /* Alignment of buf->base + 0.  */
+  unsigned align;
+  /* Offset from buf->base.  Should be always a multiple of UNITS_PER_WORD.  */
+  HOST_WIDE_INT off;
+  /* Number of padding bytes before buf->off that don't have padding clear
+     code emitted yet.  */
+  HOST_WIDE_INT padding_bytes;
+  /* The size of the whole object.  Never emit code to touch
+     buf->base + buf->sz or following bytes.  */
+  HOST_WIDE_INT sz;
+  /* Number of bytes recorded in buf->buf.  */
+  size_t size;
+  /* When inside union, instead of emitting code we and bits inside of
+     the union_ptr array.  */
+  unsigned char *union_ptr;
+  /* Set bits mean padding bits that need to be cleared by the builtin.  */
+  unsigned char buf[clear_padding_buf_size + clear_padding_unit];
+};
+
+/* Emit code to clear padding requested in BUF->buf - set bits
+   in there stand for padding that should be cleared.  FULL is true
+   if everything from the buffer should be flushed, otherwise
+   it can leave up to 2 * clear_padding_unit bytes for further
+   processing.  */
+
+static void
+clear_padding_flush (clear_padding_struct *buf, bool full)
+{
+  gcc_assert ((clear_padding_unit % UNITS_PER_WORD) == 0);
+  if (!full && buf->size < 2 * clear_padding_unit)
+    return;
+  gcc_assert ((buf->off % UNITS_PER_WORD) == 0);
+  size_t end = buf->size;
+  if (!full)
+    end = ((end - clear_padding_unit - 1) / clear_padding_unit
+          * clear_padding_unit);
+  size_t padding_bytes = buf->padding_bytes;
+  if (buf->union_ptr)
+    {
+      /* Inside of a union, instead of emitting any code, instead
+        clear all bits in the union_ptr buffer that are clear
+        in buf.  Whole padding bytes don't clear anything.  */
+      for (size_t i = 0; i < end; i++)
+       {
+         if (buf->buf[i] == (unsigned char) ~0)
+           padding_bytes++;
+         else
+           {
+             padding_bytes = 0;
+             buf->union_ptr[buf->off + i] &= buf->buf[i];
+           }
+       }
+      if (full)
+       {
+         buf->off = 0;
+         buf->size = 0;
+         buf->padding_bytes = 0;
+       }
+      else
+       {
+         memmove (buf->buf, buf->buf + end, buf->size - end);
+         buf->off += end;
+         buf->size -= end;
+         buf->padding_bytes = padding_bytes;
+       }
+      return;
+    }
+  size_t wordsize = UNITS_PER_WORD;
+  for (size_t i = 0; i < end; i += wordsize)
+    {
+      size_t nonzero_first = wordsize;
+      size_t nonzero_last = 0;
+      bool all_ones = true;
+      if ((unsigned HOST_WIDE_INT) (buf->off + i + wordsize)
+         > (unsigned HOST_WIDE_INT) buf->sz)
+       {
+         gcc_assert (wordsize > 1);
+         wordsize /= 2;
+         i -= wordsize;
+         continue;
+       }
+      for (size_t j = i; j < i + wordsize && j < end; j++)
+       {
+         if (buf->buf[j])
+           {
+             if (nonzero_first == wordsize)
+               {
+                 nonzero_first = j - i;
+                 nonzero_last = j - i;
+               }
+             if (nonzero_last != j - i)
+               all_ones = false;
+             nonzero_last = j + 1 - i;
+           }
+         if (buf->buf[j] != 0 && buf->buf[j] != (unsigned char) ~0)
+           all_ones = false;
+       }
+      if (padding_bytes)
+       {
+         if (nonzero_first == 0
+             && nonzero_last == wordsize
+             && all_ones)
+           {
+             /* All bits are padding and we had some padding
+                before too.  Just extend it.  */
+             padding_bytes += wordsize;
+             continue;
+           }
+         size_t padding_end = i;
+         if (all_ones && nonzero_first == 0)
+           {
+             padding_bytes += nonzero_last;
+             padding_end += nonzero_last;
+             nonzero_first = wordsize;
+             nonzero_last = 0;
+           }
+         tree atype = build_array_type_nelts (char_type_node, padding_bytes);
+         tree dst = build2_loc (buf->loc, MEM_REF, atype, buf->base,
+                                build_int_cst (ptr_type_node,
+                                               buf->off + padding_end
+                                               - padding_bytes));
+         tree src = build_constructor (atype, NULL);
+         gimple *g = gimple_build_assign (dst, src);
+         gimple_set_location (g, buf->loc);
+         gsi_insert_before (buf->gsi, g, GSI_SAME_STMT);
+         padding_bytes = 0;
+         buf->padding_bytes = 0;
+       }
+      if (nonzero_first == wordsize)
+       /* All bits in a word are 0, there are no padding bits.  */
+       continue;
+      if (all_ones && nonzero_last == wordsize)
+       {
+         /* All bits between nonzero_first and end of word are padding
+            bits, start counting padding_bytes.  */
+         padding_bytes = nonzero_last - nonzero_first;
+         continue;
+       }
+      for (size_t eltsz = 1; eltsz <= wordsize; eltsz <<= 1)
+       {
+         if (nonzero_last - nonzero_first <= eltsz
+             && ((nonzero_first & ~(eltsz - 1))
+                 == ((nonzero_last - 1) & ~(eltsz - 1))))
+           {
+             tree type;
+             if (eltsz == 1)
+               type = char_type_node;
+             else
+               type = lang_hooks.types.type_for_size (eltsz * BITS_PER_UNIT,
+                                                      0);
+             size_t start = nonzero_first & ~(eltsz - 1);
+             HOST_WIDE_INT off = buf->off + i + start;
+             tree atype = type;
+             if (eltsz > 1 && buf->align < TYPE_ALIGN (type))
+               atype = build_aligned_type (type, buf->align);
+             tree dst = build2_loc (buf->loc, MEM_REF, atype, buf->base,
+                                    build_int_cst (ptr_type_node, off));
+             tree src;
+             gimple *g;
+             if (all_ones
+                 && nonzero_first == start
+                 && nonzero_last == start + eltsz)
+               src = build_zero_cst (type);
+             else
+               {
+                 src = make_ssa_name (type);
+                 g = gimple_build_assign (src, unshare_expr (dst));
+                 gimple_set_location (g, buf->loc);
+                 gsi_insert_before (buf->gsi, g, GSI_SAME_STMT);
+                 tree mask = native_interpret_expr (type,
+                                                    buf->buf + i + start,
+                                                    eltsz);
+                 gcc_assert (mask && TREE_CODE (mask) == INTEGER_CST);
+                 mask = fold_build1 (BIT_NOT_EXPR, type, mask);
+                 tree src_masked = make_ssa_name (type);
+                 g = gimple_build_assign (src_masked, BIT_AND_EXPR,
+                                          src, mask);
+                 gimple_set_location (g, buf->loc);
+                 gsi_insert_before (buf->gsi, g, GSI_SAME_STMT);
+                 src = src_masked;
+               }
+             g = gimple_build_assign (dst, src);
+             gimple_set_location (g, buf->loc);
+             gsi_insert_before (buf->gsi, g, GSI_SAME_STMT);
+             break;
+           }
+       }
+    }
+  if (full)
+    {
+      if (padding_bytes)
+       {
+         tree atype = build_array_type_nelts (char_type_node, padding_bytes);
+         tree dst = build2_loc (buf->loc, MEM_REF, atype, buf->base,
+                                build_int_cst (ptr_type_node,
+                                               buf->off + end
+                                               - padding_bytes));
+         tree src = build_constructor (atype, NULL);
+         gimple *g = gimple_build_assign (dst, src);
+         gimple_set_location (g, buf->loc);
+         gsi_insert_before (buf->gsi, g, GSI_SAME_STMT);
+       }
+      size_t end_rem = end % UNITS_PER_WORD;
+      buf->off += end - end_rem;
+      buf->size = end_rem;
+      memset (buf->buf, 0, buf->size);
+      buf->padding_bytes = 0;
+    }
+  else
+    {
+      memmove (buf->buf, buf->buf + end, buf->size - end);
+      buf->off += end;
+      buf->size -= end;
+      buf->padding_bytes = padding_bytes;
+    }
+}
+
+/* Append PADDING_BYTES padding bytes.  */
+
+static void
+clear_padding_add_padding (clear_padding_struct *buf,
+                          HOST_WIDE_INT padding_bytes)
+{
+  if (padding_bytes == 0)
+    return;
+  if ((unsigned HOST_WIDE_INT) padding_bytes + buf->size
+      > (unsigned HOST_WIDE_INT) clear_padding_buf_size)
+    clear_padding_flush (buf, false);
+  if ((unsigned HOST_WIDE_INT) padding_bytes + buf->size
+      > (unsigned HOST_WIDE_INT) clear_padding_buf_size)
+    {
+      memset (buf->buf + buf->size, ~0, clear_padding_buf_size - buf->size);
+      padding_bytes -= clear_padding_buf_size - buf->size;
+      buf->size = clear_padding_buf_size;
+      clear_padding_flush (buf, false);
+      gcc_assert (buf->padding_bytes);
+      /* At this point buf->buf[0] through buf->buf[buf->size - 1]
+        is guaranteed to be all ones.  */
+      padding_bytes += buf->size;
+      buf->size = padding_bytes % UNITS_PER_WORD;
+      memset (buf->buf, ~0, buf->size);
+      buf->off += padding_bytes - buf->size;
+      buf->padding_bytes += padding_bytes - buf->size;
+    }
+  else
+    {
+      memset (buf->buf + buf->size, ~0, padding_bytes);
+      buf->size += padding_bytes;
+    }
+}
+
+static void clear_padding_type (clear_padding_struct *, tree);
+
+/* Clear padding bits of union type TYPE.  */
+
+static void
+clear_padding_union (clear_padding_struct *buf, tree type, HOST_WIDE_INT sz)
+{
+  clear_padding_struct *union_buf;
+  HOST_WIDE_INT start_off = 0, next_off = 0;
+  size_t start_size = 0;
+  if (buf->union_ptr)
+    {
+      start_off = buf->off + buf->size;
+      next_off = start_off + sz;
+      start_size = start_off % UNITS_PER_WORD;
+      start_off -= start_size;
+      clear_padding_flush (buf, true);
+      union_buf = buf;
+    }
+  else
+    {
+      if (sz + buf->size > clear_padding_buf_size)
+       clear_padding_flush (buf, false);
+      union_buf = XALLOCA (clear_padding_struct);
+      union_buf->loc = buf->loc;
+      union_buf->base = NULL_TREE;
+      union_buf->gsi = NULL;
+      union_buf->align = 0;
+      union_buf->off = 0;
+      union_buf->padding_bytes = 0;
+      union_buf->sz = sz;
+      union_buf->size = 0;
+      if (sz + buf->size <= clear_padding_buf_size)
+       union_buf->union_ptr = buf->buf + buf->size;
+      else
+       union_buf->union_ptr = XNEWVEC (unsigned char, sz);
+      memset (union_buf->union_ptr, ~0, sz);
+    }
+
+  for (tree field = TYPE_FIELDS (type); field; field = DECL_CHAIN (field))
+    if (TREE_CODE (field) == FIELD_DECL)
+      {
+       HOST_WIDE_INT fldsz = int_size_in_bytes (TREE_TYPE (field));
+       gcc_assert (union_buf->size == 0);
+       union_buf->off = start_off;
+       union_buf->size = start_size;
+       memset (union_buf->buf, ~0, start_size);
+       clear_padding_type (union_buf, TREE_TYPE (field));
+       clear_padding_add_padding (union_buf, sz - fldsz);
+       clear_padding_flush (union_buf, true);
+      }
+
+  if (buf == union_buf)
+    {
+      buf->off = next_off;
+      buf->size = next_off % UNITS_PER_WORD;
+      buf->off -= buf->size;
+      memset (buf->buf, ~0, buf->size);
+    }
+  else if (sz + buf->size <= clear_padding_buf_size)
+    buf->size += sz;
+  else
+    {
+      unsigned char *union_ptr = union_buf->union_ptr;
+      while (sz)
+       {
+         clear_padding_flush (buf, false);
+         HOST_WIDE_INT this_sz
+           = MIN ((unsigned HOST_WIDE_INT) sz,
+                  clear_padding_buf_size - buf->size);
+         memcpy (buf->buf + buf->size, union_ptr, this_sz);
+         buf->size += this_sz;
+         union_ptr += this_sz;
+         sz -= this_sz;
+       }
+      XDELETE (union_buf->union_ptr);
+    }
+}
+
+/* The only known floating point formats with padding bits are the
+   IEEE extended ones.  */
+
+static bool
+clear_padding_real_needs_padding_p (tree type)
+{
+  const struct real_format *fmt = REAL_MODE_FORMAT (TYPE_MODE (type));
+  return (fmt->b == 2
+         && fmt->signbit_ro == fmt->signbit_rw
+         && (fmt->signbit_ro == 79 || fmt->signbit_ro == 95));
+}
+
+/* Return true if TYPE might contain any padding bits.  */
+
+static bool
+clear_padding_type_may_have_padding_p (tree type)
+{
+  switch (TREE_CODE (type))
+    {
+    case RECORD_TYPE:
+    case UNION_TYPE:
+      return true;
+    case ARRAY_TYPE:
+    case COMPLEX_TYPE:
+    case VECTOR_TYPE:
+      return clear_padding_type_may_have_padding_p (TREE_TYPE (type));
+    case REAL_TYPE:
+      return clear_padding_real_needs_padding_p (type);
+    default:
+      return false;
+    }
+}
+
+/* Clear padding bits for TYPE.  Called recursively from
+   gimple_fold_builtin_clear_padding.  */
+
+static void
+clear_padding_type (clear_padding_struct *buf, tree type)
+{
+  HOST_WIDE_INT sz = int_size_in_bytes (type);
+  switch (TREE_CODE (type))
+    {
+    case RECORD_TYPE:
+      HOST_WIDE_INT cur_pos;
+      cur_pos = 0;
+      for (tree field = TYPE_FIELDS (type); field; field = DECL_CHAIN (field))
+       if (TREE_CODE (field) == FIELD_DECL)
+         {
+           if (DECL_BIT_FIELD (field))
+             {
+               if (DECL_NAME (field) == NULL_TREE)
+                 continue;
+               HOST_WIDE_INT fldsz = TYPE_PRECISION (TREE_TYPE (field));
+               if (fldsz == 0)
+                 continue;
+               HOST_WIDE_INT pos = int_byte_position (field);
+               HOST_WIDE_INT bpos
+                 = tree_to_uhwi (DECL_FIELD_BIT_OFFSET (field));
+               bpos %= BITS_PER_UNIT;
+               HOST_WIDE_INT end
+                 = ROUND_UP (bpos + fldsz, BITS_PER_UNIT) / BITS_PER_UNIT;
+               if (pos + end > cur_pos)
+                 {
+                   clear_padding_add_padding (buf, pos + end - cur_pos);
+                   cur_pos = pos + end;
+                 }
+               gcc_assert (cur_pos > pos
+                           && ((unsigned HOST_WIDE_INT) buf->size
+                               >= (unsigned HOST_WIDE_INT) cur_pos - pos));
+               unsigned char *p = buf->buf + buf->size - (cur_pos - pos);
+               if (BYTES_BIG_ENDIAN != WORDS_BIG_ENDIAN)
+                 sorry_at (buf->loc, "PDP11 bit-field handling unsupported"
+                                     " in %qs", "__builtin_clear_padding");
+               else if (BYTES_BIG_ENDIAN)
+                 {
+                   /* Big endian.  */
+                   if (bpos + fldsz <= BITS_PER_UNIT)
+                     *p &= ~(((1 << fldsz) - 1)
+                             << (BITS_PER_UNIT - bpos - fldsz));
+                   else
+                     {
+                       if (bpos)
+                         {
+                           *p &= ~(((1U << BITS_PER_UNIT) - 1) >> bpos);
+                           p++;
+                           fldsz -= BITS_PER_UNIT - bpos;
+                         }
+                       memset (p, 0, fldsz / BITS_PER_UNIT);
+                       p += fldsz / BITS_PER_UNIT;
+                       fldsz %= BITS_PER_UNIT;
+                       if (fldsz)
+                         *p &= ((1U << BITS_PER_UNIT) - 1) >> fldsz;
+                     }
+                 }
+               else
+                 {
+                   /* Little endian.  */
+                   if (bpos + fldsz <= BITS_PER_UNIT)
+                     *p &= ~(((1 << fldsz) - 1) << bpos);
+                   else
+                     {
+                       if (bpos)
+                         {
+                           *p &= ~(((1 << BITS_PER_UNIT) - 1) << bpos);
+                           p++;
+                           fldsz -= BITS_PER_UNIT - bpos;
+                         }
+                       memset (p, 0, fldsz / BITS_PER_UNIT);
+                       p += fldsz / BITS_PER_UNIT;
+                       fldsz %= BITS_PER_UNIT;
+                       if (fldsz)
+                         *p &= ~((1 << fldsz) - 1);
+                     }
+                 }
+             }
+           else
+             {
+               HOST_WIDE_INT pos = int_byte_position (field);
+               HOST_WIDE_INT fldsz = int_size_in_bytes (TREE_TYPE (field));
+               gcc_assert (pos >= 0 && fldsz >= 0 && pos >= cur_pos);
+               clear_padding_add_padding (buf, pos - cur_pos);
+               cur_pos = pos;
+               clear_padding_type (buf, TREE_TYPE (field));
+               cur_pos += fldsz;
+             }
+         }
+      gcc_assert (sz >= cur_pos);
+      clear_padding_add_padding (buf, sz - cur_pos);
+      break;
+    case ARRAY_TYPE:
+      HOST_WIDE_INT nelts;
+      nelts = int_size_in_bytes (TREE_TYPE (type));
+      nelts = sz / nelts;
+      if (nelts > 1 && sz > 8 * UNITS_PER_WORD && buf->union_ptr == NULL)
+       {
+         /* FIXME: If ARRAY_TYPE has nelts > 1 and sz over certain
+            small threshold, instead call clear_padding_flush (&buf, true);
+            and emit a runtime loop filling each array element separately.  */
+       }
+      for (HOST_WIDE_INT i = 0; i < nelts; i++)
+       clear_padding_type (buf, TREE_TYPE (type));
+      break;
+    case UNION_TYPE:
+      clear_padding_union (buf, type, sz);
+      break;
+    case REAL_TYPE:
+      gcc_assert ((size_t) sz <= clear_padding_unit);
+      if ((unsigned HOST_WIDE_INT) sz + buf->size > clear_padding_buf_size)
+       clear_padding_flush (buf, false);
+      if (clear_padding_real_needs_padding_p (type))
+       {
+         /* Use native_interpret_expr + native_encode_expr to figure out
+            which bits are padding.  */
+         memset (buf->buf + buf->size, ~0, sz);
+         tree cst = native_interpret_expr (type, buf->buf + buf->size, sz);
+         gcc_assert (cst && TREE_CODE (cst) == REAL_CST);
+         int len = native_encode_expr (cst, buf->buf + buf->size, sz);
+         gcc_assert (len > 0 && (size_t) len == (size_t) sz);
+         for (size_t i = 0; i < (size_t) sz; i++)
+           buf->buf[buf->size + i] ^= ~0;
+       }
+      else
+       memset (buf->buf + buf->size, 0, sz);
+      buf->size += sz;
+      break;
+    case COMPLEX_TYPE:
+      clear_padding_type (buf, TREE_TYPE (type));
+      clear_padding_type (buf, TREE_TYPE (type));
+      break;
+    case VECTOR_TYPE:
+      nelts = TYPE_VECTOR_SUBPARTS (type).to_constant ();
+      for (HOST_WIDE_INT i = 0; i < nelts; i++)
+       clear_padding_type (buf, TREE_TYPE (type));
+      break;
+    default:
+      gcc_assert ((size_t) sz <= clear_padding_unit);
+      if ((unsigned HOST_WIDE_INT) sz + buf->size > clear_padding_buf_size)
+       clear_padding_flush (buf, false);
+      memset (buf->buf + buf->size, 0, sz);
+      buf->size += sz;
+      break;
+    }
+}
+
+/* Fold __builtin_clear_padding builtin.  */
+
+static bool
+gimple_fold_builtin_clear_padding (gimple_stmt_iterator *gsi)
+{
+  gimple *stmt = gsi_stmt (*gsi);
+  tree ptr = gimple_call_arg (stmt, 0);
+  tree type = TREE_TYPE (TREE_TYPE (ptr));
+  location_t loc = gimple_location (stmt);
+  clear_padding_struct buf;
+  gimple_stmt_iterator gsiprev = *gsi;
+  /* This should be folded during the lower pass.  */
+  gcc_assert (!gimple_in_ssa_p (cfun) && cfun->cfg == NULL);
+  gcc_assert (COMPLETE_TYPE_P (type));
+  gsi_prev (&gsiprev);
+
+  buf.loc = loc;
+  buf.base = ptr;
+  buf.gsi = gsi;
+  buf.align = get_pointer_alignment (ptr);
+  unsigned int talign = min_align_of_type (type) * BITS_PER_UNIT;
+  buf.align = MAX (buf.align, talign);
+  buf.off = 0;
+  buf.padding_bytes = 0;
+  buf.size = 0;
+  buf.sz = int_size_in_bytes (type);
+  buf.union_ptr = NULL;
+  if (buf.sz < 0 && int_size_in_bytes (strip_array_types (type)) < 0)
+    sorry_at (loc, "%s not supported for variable length aggregates",
+             "__builtin_clear_padding");
+  /* The implementation currently assumes 8-bit host and target
+     chars which is the case for all currently supported targets
+     and hosts and is required e.g. for native_{encode,interpret}* APIs.  */
+  else if (CHAR_BIT != 8 || BITS_PER_UNIT != 8)
+    sorry_at (loc, "%s not supported on this target",
+             "__builtin_clear_padding");
+  else if (!clear_padding_type_may_have_padding_p (type))
+    ;
+  else if (TREE_CODE (type) == ARRAY_TYPE && buf.sz < 0)
+    {
+      /* FIXME: Handle VLAs.  These can be handled by adding runtime
+        loop (or multiple for multiple VLAs) calling clear_padding_type
+        only on each non-VLA element.  */
+      sorry_at (loc, "%s does not support VLAs yet",
+               "__builtin_clear_padding");
+    }
+  else
+    {
+      if (!is_gimple_mem_ref_addr (buf.base))
+       {
+         buf.base = make_ssa_name (TREE_TYPE (ptr));
+         gimple *g = gimple_build_assign (buf.base, ptr);
+         gimple_set_location (g, loc);
+         gsi_insert_before (gsi, g, GSI_SAME_STMT);
+       }
+      clear_padding_type (&buf, type);
+      clear_padding_flush (&buf, true);
+    }
+
+  gimple_stmt_iterator gsiprev2 = *gsi;
+  gsi_prev (&gsiprev2);
+  if (gsi_stmt (gsiprev) == gsi_stmt (gsiprev2))
+    gsi_replace (gsi, gimple_build_nop (), true);
+  else
+    {
+      gsi_remove (gsi, true);
+      *gsi = gsiprev2;
+    }
+  return true;
+}
+
 /* Fold the non-target builtin at *GSI and return whether any simplification
    was made.  */
 
@@ -4105,6 +4702,9 @@ gimple_fold_builtin (gimple_stmt_iterato
     case BUILT_IN_REALLOC:
       return gimple_fold_builtin_realloc (gsi);
 
+    case BUILT_IN_CLEAR_PADDING:
+      return gimple_fold_builtin_clear_padding (gsi);
+
     default:;
     }
 
--- gcc/doc/extend.texi.jj      2020-11-13 21:40:11.126410770 -1200
+++ gcc/doc/extend.texi 2020-11-15 23:34:03.193609155 -1200
@@ -13564,6 +13564,19 @@ initializers of variables usable in cons
 refer to the latest revision of the C++ standard.
 @end deftypefn
 
+@deftypefn {Built-in Function} void __builtin_clear_padding (@var{ptr})
+The built-in function @code{__builtin_clear_padding} function clears
+padding bits inside of the object representation of object pointed by
+@var{ptr}, which has to be a pointer.  The value representation of the
+object is not affected.  The type of the object is assumed to be the type
+the pointer points to.  Inside of a union, the only cleared bits are
+bits that are padding bits for all the union members.
+
+This built-in-function is useful if the padding bits of an object might
+have intederminate values and the object representation needs to be
+bitwise compared to some other object, for example for atomic operations.
+@end deftypefn
+
 @deftypefn {Built-in Function} long __builtin_expect (long @var{exp}, long 
@var{c})
 @opindex fprofile-arcs
 You may use @code{__builtin_expect} to provide the compiler with
--- gcc/testsuite/c-c++-common/builtin-clear-padding-1.c.jj     2020-11-15 
23:37:23.709347369 -1200
+++ gcc/testsuite/c-c++-common/builtin-clear-padding-1.c        2020-11-15 
23:39:37.778835083 -1200
@@ -0,0 +1,17 @@
+/* PR libstdc++/88101 */
+/* { dg-do compile } */
+
+struct S;
+
+void
+foo (struct S *p, void *q, char *r)
+{
+  __builtin_clear_padding ();          /* { dg-error "too few arguments to 
function '__builtin_clear_padding'" } */
+  __builtin_clear_padding (1);         /* { dg-error "argument 1 in call to 
function '__builtin_clear_padding' does not have pointer type" } */
+  __builtin_clear_padding (&p);
+  __builtin_clear_padding (&p, 1);     /* { dg-error "too many arguments to 
function '__builtin_clear_padding'" } */
+  __builtin_clear_padding (&p, &p);    /* { dg-error "too many arguments to 
function '__builtin_clear_padding'" } */
+  __builtin_clear_padding (p);         /* { dg-error "argument 1 in call to 
function '__builtin_clear_padding' points to incomplete type" } */
+  __builtin_clear_padding (q);         /* { dg-error "argument 1 in call to 
function '__builtin_clear_padding' points to incomplete type" } */
+  __builtin_clear_padding (r);
+}
--- gcc/testsuite/c-c++-common/torture/builtin-clear-padding-1.c.jj     
2020-11-15 06:54:02.415860651 -1200
+++ gcc/testsuite/c-c++-common/torture/builtin-clear-padding-1.c        
2020-11-15 21:10:53.126924166 -1200
@@ -0,0 +1,47 @@
+/* PR libstdc++/88101 */
+
+int i1, i2;
+long double l1, l2;
+struct S { char a; short b; char c; int d; char e; long long f; char g; long 
double h; } s1, s2;
+struct T { int a; struct S b[3]; int c; } t1, t2;
+struct U { int a : 3; int : 2; int b : 15; int : 14; int c : 1; int : 0; int : 
3; int d : 2; int : 3; int e : 13; int : 3; signed char f; } u1, u2;
+
+__attribute__((noipa)) void
+foo (int *i, long double *l, struct S *s, struct T *t, struct U *u)
+{
+  *i = 123;
+  *l = -123.456L;
+  s->a = 1; s->b = 2; s->c = 3; s->d = 4; s->e = 5; s->f = 6; s->g = 7; s->h = 
18.52L;
+  t->a = 8; t->c = 9;
+  t->b[0].a = 11; t->b[0].b = 12; t->b[0].c = 13; t->b[0].d = 14;
+  t->b[0].e = 15; t->b[0].f = 16; t->b[0].g = 17; t->b[0].h = 18.26L;
+  t->b[1].a = 21; t->b[1].b = 22; t->b[1].c = 23; t->b[1].d = 24;
+  t->b[1].e = 25; t->b[1].f = 26; t->b[1].g = 27; t->b[1].h = 28.26L;
+  t->b[2].a = 31; t->b[2].b = 32; t->b[2].c = 33; t->b[2].d = 34;
+  t->b[2].e = 35; t->b[2].f = 36; t->b[2].g = 37; t->b[2].h = 38.26L;
+  u->a = -1; u->b = -1; u->c = -1; u->d = -1; u->e = -1; u->f = -1;
+}
+
+int
+main ()
+{
+  __builtin_memset (&i2, -1, sizeof (i2));
+  __builtin_memset (&l2, -1, sizeof (i2));
+  __builtin_memset (&s2, -1, sizeof (s2));
+  __builtin_memset (&t2, -1, sizeof (t2));
+  __builtin_memset (&u2, -1, sizeof (u2));
+  foo (&i1, &l1, &s1, &t1, &u1);
+  foo (&i2, &l2, &s2, &t2, &u2);
+  __builtin_clear_padding (&i2);
+  __builtin_clear_padding (&l2);
+  __builtin_clear_padding (&s2);
+  __builtin_clear_padding (&t2);
+  __builtin_clear_padding (&u2);
+  if (__builtin_memcmp (&i1, &i2, sizeof (i1))
+      || __builtin_memcmp (&l1, &l2, sizeof (l1))
+      || __builtin_memcmp (&s1, &s2, sizeof (s1))
+      || __builtin_memcmp (&t1, &t2, sizeof (t1))
+      || __builtin_memcmp (&u1, &u2, sizeof (u1)))
+    __builtin_abort ();
+  return 0;
+}
--- gcc/testsuite/c-c++-common/torture/builtin-clear-padding-2.c.jj     
2020-11-15 19:40:01.096659838 -1200
+++ gcc/testsuite/c-c++-common/torture/builtin-clear-padding-2.c        
2020-11-15 19:33:51.487772285 -1200
@@ -0,0 +1,24 @@
+/* PR libstdc++/88101 */
+
+typedef int T __attribute__((aligned (16384)));
+struct S { char a; short b; long double c; T d; T e; long long f; };
+
+__attribute__((noipa)) void
+foo (struct S *s)
+{
+  s->a = -1; s->b = -1; s->c = -18.52L; s->d = -1; s->e = -1; s->f = -1;
+}
+
+int
+main ()
+{
+  struct S s1, s2;
+  __builtin_memset (&s1, 0, sizeof (s1));
+  __builtin_memset (&s2, -1, sizeof (s2));
+  foo (&s1);
+  foo (&s2);
+  __builtin_clear_padding (&s2);
+  if (__builtin_memcmp (&s1, &s2, sizeof (s1)))
+    __builtin_abort ();
+  return 0;
+}
--- gcc/testsuite/c-c++-common/torture/builtin-clear-padding-3.c.jj     
2020-11-15 23:00:06.036540255 -1200
+++ gcc/testsuite/c-c++-common/torture/builtin-clear-padding-3.c        
2020-11-15 23:02:37.487839371 -1200
@@ -0,0 +1,65 @@
+/* PR libstdc++/88101 */
+
+union V { char a; signed char b; unsigned char c; };
+struct T { char a; int b; union V c; };
+union U { int a; long double b; struct T c; };
+struct S { char a; union U b; long long c; char d; } s1, s2;
+
+__attribute__((noipa)) void
+foo (struct S *s, int x)
+{
+  s->a = -1; s->c = -1; s->d = -1;
+  switch (x)
+    {
+    case 0:
+      s->b.a = -1;
+      break;
+    case 1:
+      s->b.b = -12345.25L;
+      break;
+    case 2:
+      s->b.c.a = -1;
+      s->b.c.b = -1;
+      s->b.c.c.b = -1;
+      break;
+    }
+}
+
+int
+main ()
+{
+  __builtin_memset (&s1, 0, sizeof (s1));
+  __builtin_memset (&s2, -1, sizeof (s2));
+  foo (&s1, 0);
+  foo (&s2, 0);
+  __builtin_clear_padding (&s2);
+  if (s2.b.a != (char) -1)
+    __builtin_abort ();
+  __builtin_clear_padding (&s2.b.a);
+  __builtin_memset (&s2.b.a + 1, 0, sizeof (union U) - sizeof (s2.b.a));
+  if (__builtin_memcmp (&s1, &s2, sizeof (s1)))
+    __builtin_abort ();
+  __builtin_memset (&s1, 0, sizeof (s1));
+  __builtin_memset (&s2, -1, sizeof (s2));
+  foo (&s1, 1);
+  foo (&s2, 1);
+  __builtin_clear_padding (&s2);
+  if (s2.b.b != -12345.25L)
+    __builtin_abort ();
+  __builtin_clear_padding (&s2.b.b);
+  __builtin_memset (&s2.b.b + 1, 0, sizeof (union U) - sizeof (s2.b.b));
+  if (__builtin_memcmp (&s1, &s2, sizeof (s1)))
+    __builtin_abort ();
+  __builtin_memset (&s1, 0, sizeof (s1));
+  __builtin_memset (&s2, -1, sizeof (s2));
+  foo (&s1, 2);
+  foo (&s2, 2);
+  __builtin_clear_padding (&s2);
+  if (s2.b.c.a != (char) -1 || s2.b.c.b != -1 || s2.b.c.c.b != -1)
+    __builtin_abort ();
+  __builtin_clear_padding (&s2.b.c);
+  __builtin_memset (&s2.b.c + 1, 0, sizeof (union U) - sizeof (s2.b.c));
+  if (__builtin_memcmp (&s1, &s2, sizeof (s1)))
+    __builtin_abort ();
+  return 0;
+}
--- gcc/testsuite/gcc.dg/builtin-clear-padding-1.c.jj   2020-11-15 
23:40:03.976539576 -1200
+++ gcc/testsuite/gcc.dg/builtin-clear-padding-1.c      2020-11-15 
23:42:47.378696420 -1200
@@ -0,0 +1,10 @@
+/* PR libstdc++/88101 */
+/* { dg-do compile } */
+/* { dg-options "" } */
+
+void
+foo (int n)
+{
+  struct S { char a; int b[n]; long long c; } s;
+  __builtin_clear_padding (&s);                /* { dg-message "unimplemented: 
__builtin_clear_padding not supported for variable length aggregates" } */
+}

        Jakub

Reply via email to