[PATCH v2 08/10] Introduce strub: strub modes

[Alexandre Oliva <oliva@adacore.com>]

This initial fragment of ipa-strub.cc covers strub modes and their
internal representation.

for  gcc/ChangeLog

	* ipa-strub.cc: New.

diff --git a/gcc/ipa-strub.cc b/gcc/ipa-strub.cc
new file mode 100644
index 0000000000000..d61b7e2e36e43
--- /dev/null
+++ b/gcc/ipa-strub.cc
@@ -0,0 +1,3489 @@
+/* strub (stack scrubbing) support.
+   Copyright (C) 2021-2022 Free Software Foundation, Inc.
+   Contributed by Alexandre Oliva <oliva@adacore.com>.
+
+This file is part of GCC.
+
+GCC is free software; you can redistribute it and/or modify it under
+the terms of the GNU General Public License as published by the Free
+Software Foundation; either version 3, or (at your option) any later
+version.
+
+GCC is distributed in the hope that it will be useful, but WITHOUT ANY
+WARRANTY; without even the implied warranty of MERCHANTABILITY or
+FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+for more details.
+
+You should have received a copy of the GNU General Public License
+along with GCC; see the file COPYING3.  If not see
+<http://www.gnu.org/licenses/>.  */
+
+#include "config.h"
+#include "system.h"
+#include "coretypes.h"
+#include "backend.h"
+#include "tree.h"
+#include "gimple.h"
+#include "gimplify.h"
+#include "tree-pass.h"
+#include "ssa.h"
+#include "gimple-iterator.h"
+#include "gimplify-me.h"
+#include "tree-into-ssa.h"
+#include "tree-ssa.h"
+#include "tree-cfg.h"
+#include "cfghooks.h"
+#include "cfgloop.h"
+#include "cfgcleanup.h"
+#include "tree-eh.h"
+#include "except.h"
+#include "builtins.h"
+#include "attribs.h"
+#include "tree-inline.h"
+#include "cgraph.h"
+#include "alloc-pool.h"
+#include "symbol-summary.h"
+#include "ipa-prop.h"
+#include "ipa-fnsummary.h"
+#include "gimple-fold.h"
+#include "fold-const.h"
+#include "gimple-walk.h"
+#include "tree-dfa.h"
+#include "langhooks.h"
+#include "calls.h"
+#include "vec.h"
+#include "stor-layout.h"
+#include "varasm.h"
+#include "alias.h"
+#include "diagnostic.h"
+#include "intl.h"
+#include "ipa-strub.h"
+
+#if BUILDING_GCC_MAJOR >= 11
+# include "symtab-thunks.h"
+# include "attr-fnspec.h"
+# define HAVE_ATTR_FNSPEC 1
+# define FOR_GCC_11P 1
+#else
+# define HAVE_ATTR_FNSPEC 0
+# define FOR_GCC_11P 0
+#endif
+
+/* Const and pure functions that gain a watermark parameter for strub purposes
+   are still regarded as such, which may cause the inline expansions of the
+   __strub builtins to malfunction.  Ideally, attribute "fn spec" would enable
+   us to inform the backend about requirements and side effects of the call, but
+   call_fusage building in calls.c:expand_call does not even look at
+   attr_fnspec, so we resort to asm loads and updates to attain an equivalent
+   effect.  Once expand_call gains the ability to issue extra memory uses and
+   clobbers based on pure/const function's fnspec, we can define this to 1.  */
+#define ATTR_FNSPEC_DECONST_WATERMARK 0
+
+enum strub_mode {
+  /* This mode denotes a regular function, that does not require stack
+     scrubbing (strubbing).  It may call any other functions, but if
+     it calls AT_CALLS (or WRAPPED) ones, strubbing logic is
+     automatically introduced around those calls (the latter, by
+     inlining INTERNAL wrappers).  */
+  STRUB_DISABLED = 0,
+
+  /* This denotes a function whose signature is (to be) modified to
+     take an extra parameter, for stack use annotation, and its
+     callers must initialize and pass that argument, and perform the
+     strubbing.  Functions that are explicitly marked with attribute
+     strub must have the mark visible wherever the function is,
+     including aliases, and overriders and overriding methods.
+     Functions that are implicitly marked for strubbing, for accessing
+     variables explicitly marked as such, will only select this
+     strubbing method if they are internal to a translation unit.  It
+     can only be inlined into other strubbing functions, i.e.,
+     STRUB_AT_CALLS or STRUB_WRAPPED.  */
+  STRUB_AT_CALLS = 1,
+
+  /* This denotes a function that is to perform strubbing internally,
+     without any changes to its interface (the function is turned into
+     a strubbing wrapper, and its original body is moved to a separate
+     STRUB_WRAPPED function, with a modified interface).  Functions
+     may be explicitly marked with attribute strub(2), and the
+     attribute must be visible at the point of definition.  Functions
+     that are explicitly marked for strubbing, for accessing variables
+     explicitly marked as such, may select this strubbing mode if
+     their interface cannot change, e.g. because its interface is
+     visible to other translation units, directly, by indirection
+     (having its address taken), inheritance, etc.  Functions that use
+     this method must not have the noclone attribute, nor the noipa
+     one.  Functions marked as always_inline may select this mode, but
+     they are NOT wrapped, they remain unchanged, and are only inlined
+     into strubbed contexts.  Once non-always_inline functions are
+     wrapped, the wrapper becomes STRUB_WRAPPER, and the wrapped becomes
+     STRUB_WRAPPED.  */
+  STRUB_INTERNAL = 2,
+
+  /* This denotes a function whose stack is not strubbed, but that is
+     nevertheless explicitly or implicitly marked as callable from strubbing
+     functions.  Normally, only STRUB_AT_CALLS (and STRUB_INTERNAL ->
+     STRUB_WRAPPED) functions can be called from strubbing contexts (bodies of
+     STRUB_AT_CALLS, STRUB_INTERNAL and STRUB_WRAPPED functions), but attribute
+     strub(3) enables other functions to be (indirectly) called from these
+     contexts.  Some builtins and internal functions may be implicitly marked as
+     STRUB_CALLABLE.  */
+  STRUB_CALLABLE = 3,
+
+  /* This denotes the function that took over the body of a
+     STRUB_INTERNAL function.  At first, it's only called by its
+     wrapper, but the wrapper may be inlined.  The wrapped function,
+     in turn, can only be inlined into other functions whose stack
+     frames are strubbed, i.e., that are STRUB_WRAPPED or
+     STRUB_AT_CALLS.  */
+  STRUB_WRAPPED = -1,
+
+  /* This denotes the wrapper function that replaced the STRUB_INTERNAL
+     function.  This mode overrides the STRUB_INTERNAL mode at the time the
+     internal to-be-wrapped function becomes a wrapper, so that inlining logic
+     can tell one from the other.  */
+  STRUB_WRAPPER = -2,
+
+  /* This denotes an always_inline function that requires strubbing.  It can
+     only be called from, and inlined into, other strubbing contexts.  */
+  STRUB_INLINABLE = -3,
+
+  /* This denotes a function that accesses strub variables, so it would call for
+     internal strubbing (whether or not it's eligible for that), but since
+     at-calls strubbing is viable, that's selected as an optimization.  This
+     mode addresses the inconvenience that such functions may have different
+     modes selected depending on optimization flags, and get a different
+     callable status depending on that choice: if we assigned them
+     STRUB_AT_CALLS mode, they would be callable when optimizing, whereas
+     STRUB_INTERNAL would not be callable.  */
+  STRUB_AT_CALLS_OPT = -4,
+
+};
+
+/* Look up a strub attribute in TYPE, and return it.  */
+
+static tree
+get_strub_attr_from_type (tree type)
+{
+  return lookup_attribute ("strub", TYPE_ATTRIBUTES (type));
+}
+
+/* Look up a strub attribute in DECL or in its type, and return it.  */
+
+static tree
+get_strub_attr_from_decl (tree decl)
+{
+  tree ret = lookup_attribute ("strub", DECL_ATTRIBUTES (decl));
+  if (ret)
+    return ret;
+  return get_strub_attr_from_type (TREE_TYPE (decl));
+}
+
+/* Define a function to cache identifier ID, to be used as a strub attribute
+   parameter for a strub mode named after NAME.  */
+#define DEF_STRUB_IDS(NAME, ID)				\
+static inline tree get_strub_mode_id_ ## NAME () {	\
+  static tree identifier = NULL_TREE;			\
+  if (!identifier)					\
+    identifier = get_identifier (ID);			\
+  return identifier;					\
+}
+/* Same as DEF_STRUB_IDS, but use the string expansion of NAME as ID.  */
+#define DEF_STRUB_ID(NAME)				\
+DEF_STRUB_IDS (NAME, #NAME)
+
+/* Define functions for each of the strub mode identifiers.
+   Expose dashes rather than underscores.  */
+DEF_STRUB_ID (disabled)
+DEF_STRUB_IDS (at_calls, "at-calls")
+DEF_STRUB_ID (internal)
+DEF_STRUB_ID (callable)
+DEF_STRUB_ID (wrapped)
+DEF_STRUB_ID (wrapper)
+DEF_STRUB_ID (inlinable)
+DEF_STRUB_IDS (at_calls_opt, "at-calls-opt")
+
+/* Release the temporary macro names.  */
+#undef DEF_STRUB_IDS
+#undef DEF_STRUB_ID
+
+/* Return the identifier corresponding to strub MODE.  */
+
+static tree
+get_strub_mode_attr_parm (enum strub_mode mode)
+{
+  switch (mode)
+    {
+    case STRUB_DISABLED:
+      return get_strub_mode_id_disabled ();
+
+    case STRUB_AT_CALLS:
+      return get_strub_mode_id_at_calls ();
+
+    case STRUB_INTERNAL:
+      return get_strub_mode_id_internal ();
+
+    case STRUB_CALLABLE:
+      return get_strub_mode_id_callable ();
+
+    case STRUB_WRAPPED:
+      return get_strub_mode_id_wrapped ();
+
+    case STRUB_WRAPPER:
+      return get_strub_mode_id_wrapper ();
+
+    case STRUB_INLINABLE:
+      return get_strub_mode_id_inlinable ();
+
+    case STRUB_AT_CALLS_OPT:
+      return get_strub_mode_id_at_calls_opt ();
+
+    default:
+      gcc_unreachable ();
+    }
+}
+
+/* Return the parmeters (TREE_VALUE) for a strub attribute of MODE.
+   We know we use a single parameter, so we bypass the creation of a
+   tree list.  */
+
+static tree
+get_strub_mode_attr_value (enum strub_mode mode)
+{
+  return get_strub_mode_attr_parm (mode);
+}
+
+/* Determine whether ID is a well-formed strub mode-specifying attribute
+   parameter for a function (type).  Only user-visible modes are accepted, and
+   ID must be non-NULL.
+
+   For unacceptable parms, return 0, otherwise a nonzero value as below.
+
+   If the parm enables strub, return positive, otherwise negative.
+
+   If the affected type must be a distinct, incompatible type,return an integer
+   of absolute value 2, otherwise 1.  */
+
+int
+strub_validate_fn_attr_parm (tree id)
+{
+  int ret;
+  const char *s = NULL;
+  size_t len = 0;
+
+  /* do NOT test for NULL.  This is only to be called with non-NULL arguments.
+     We assume that the strub parameter applies to a function, because only
+     functions accept an explicit argument.  If we accepted NULL, and we
+     happened to be called to verify the argument for a variable, our return
+     values would be wrong.  */
+  if (TREE_CODE (id) == STRING_CST)
+    {
+      s = TREE_STRING_POINTER (id);
+      len = TREE_STRING_LENGTH (id) - 1;
+    }
+  else if (TREE_CODE (id) == IDENTIFIER_NODE)
+    {
+      s = IDENTIFIER_POINTER (id);
+      len = IDENTIFIER_LENGTH (id);
+    }
+  else
+    return 0;
+
+  enum strub_mode mode;
+
+  if (len != 8)
+    return 0;
+
+  switch (s[0])
+    {
+    case 'd':
+      mode = STRUB_DISABLED;
+      ret = -1;
+      break;
+
+    case 'a':
+      mode = STRUB_AT_CALLS;
+      ret = 2;
+      break;
+
+    case 'i':
+      mode = STRUB_INTERNAL;
+      ret = 1;
+      break;
+
+    case 'c':
+      mode = STRUB_CALLABLE;
+      ret = -2;
+      break;
+
+    default:
+      /* Other parms are for internal use only.  */
+      return 0;
+    }
+
+  tree mode_id = get_strub_mode_attr_parm (mode);
+
+  if (TREE_CODE (id) == IDENTIFIER_NODE
+      ? id != mode_id
+      : strncmp (s, IDENTIFIER_POINTER (mode_id), len) != 0)
+    return 0;
+
+  return ret;
+}
+
+/* Return the strub mode from STRUB_ATTR.  VAR_P should be TRUE if the attribute
+   is taken from a variable, rather than from a function, or a type thereof.  */
+
+static enum strub_mode
+get_strub_mode_from_attr (tree strub_attr, bool var_p = false)
+{
+  enum strub_mode mode = STRUB_DISABLED;
+
+  if (strub_attr)
+    {
+      if (!TREE_VALUE (strub_attr))
+	mode = !var_p ? STRUB_AT_CALLS : STRUB_INTERNAL;
+      else
+	{
+	  gcc_checking_assert (!var_p);
+	  tree id = TREE_VALUE (strub_attr);
+	  if (TREE_CODE (id) == TREE_LIST)
+	    id = TREE_VALUE (id);
+	  const char *s = (TREE_CODE (id) == STRING_CST
+			   ? TREE_STRING_POINTER (id)
+			   : IDENTIFIER_POINTER (id));
+	  size_t len = (TREE_CODE (id) == STRING_CST
+			? TREE_STRING_LENGTH (id) - 1
+			: IDENTIFIER_LENGTH (id));
+
+	  switch (len)
+	    {
+	    case 7:
+	      switch (s[6])
+		{
+		case 'r':
+		  mode = STRUB_WRAPPER;
+		  break;
+
+		case 'd':
+		  mode = STRUB_WRAPPED;
+		  break;
+
+		default:
+		  gcc_unreachable ();
+		}
+	      break;
+
+	    case 8:
+	      switch (s[0])
+		{
+		case 'd':
+		  mode = STRUB_DISABLED;
+		  break;
+
+		case 'a':
+		  mode = STRUB_AT_CALLS;
+		  break;
+
+		case 'i':
+		  mode = STRUB_INTERNAL;
+		  break;
+
+		case 'c':
+		  mode = STRUB_CALLABLE;
+		  break;
+
+		default:
+		  gcc_unreachable ();
+		}
+	      break;
+
+	    case 9:
+	      mode = STRUB_INLINABLE;
+	      break;
+
+	    case 12:
+	      mode = STRUB_AT_CALLS_OPT;
+	      break;
+
+	    default:
+	      gcc_unreachable ();
+	    }
+
+	  gcc_checking_assert (TREE_CODE (id) == IDENTIFIER_NODE
+			       ? id == get_strub_mode_attr_parm (mode)
+			       : strncmp (IDENTIFIER_POINTER
+					  (get_strub_mode_attr_parm (mode)),
+					  s, len) == 0);
+	}
+    }
+
+  return mode;
+}
+
+/* Look up, decode and return the strub mode associated with FNDECL.  */
+
+static enum strub_mode
+get_strub_mode_from_fndecl (tree fndecl)
+{
+  return get_strub_mode_from_attr (get_strub_attr_from_decl (fndecl));
+}
+
+/* Look up, decode and return the strub mode associated with NODE.  */
+
+static enum strub_mode
+get_strub_mode (cgraph_node *node)
+{
+  return get_strub_mode_from_fndecl (node->decl);
+}
+
+/* Look up, decode and return the strub mode associated with TYPE.  */
+
+static enum strub_mode
+get_strub_mode_from_type (tree type)
+{
+  bool var_p = !FUNC_OR_METHOD_TYPE_P (type);
+  tree attr = get_strub_attr_from_type (type);
+
+  if (attr)
+    return get_strub_mode_from_attr (attr, var_p);
+
+  if (flag_strub >= -1 && !var_p)
+    return STRUB_CALLABLE;
+
+  return STRUB_DISABLED;
+}
+
+\f

-- 
Alexandre Oliva, happy hacker                https://FSFLA.org/blogs/lxo/
   Free Software Activist                       GNU Toolchain Engineer
Disinformation flourishes because many people care deeply about injustice
but very few check the facts.  Ask me about <https://stallmansupport.org>