[gcc r10-9747] aarch64: Fix SVE ACLE builtins with LTO [PR99216]

[gcc r10-9747] aarch64: Fix SVE ACLE builtins with LTO [PR99216]

[Alex Coplan]

https://gcc.gnu.org/g:34a9bc1f95027eea1560369765b8b2b5722b6779

commit r10-9747-g34a9bc1f95027eea1560369765b8b2b5722b6779
Author: Alex Coplan <alex.coplan@arm.com>
Date:   Thu Apr 22 14:37:12 2021 +0100

    aarch64: Fix SVE ACLE builtins with LTO [PR99216]
    
    This is a GCC 10 backport of the fix for PR99216
    (e4005cf8717abe8c949f840c707e02e6c394c2e7). The only change w.r.t the
    original patch is a bump of lto-streamer.h:LTO_minor_version.
    
    As discussed in the PR, we currently have two different numbering
    schemes for SVE builtins: one for C, and one for C++. This is
    problematic for LTO, where we end up getting confused about which
    intrinsic we're talking about. This patch inserts placeholders into the
    registered_functions vector to ensure that there is a consistent
    numbering scheme for both C and C++.
    
    This version uses integer_zero_node as a placeholder node instead of
    building a function decl. This is safe because the node is only returned
    by the TARGET_BUILTIN_DECL hook, which (on AArch64) is only used for
    validation when builtin decls are streamed into lto1.
    
    gcc/ChangeLog:
    
            PR target/99216
            * config/aarch64/aarch64-sve-builtins.cc
            (function_builder::add_function): Add placeholder_p argument, use
            placeholder decls if this is set.
            (function_builder::add_unique_function): Instead of conditionally adding
            direct overloads, unconditionally add either a direct overload or a
            placeholder.
            (function_builder::add_overloaded_function): Set placeholder_p if we're
            using C++ overloads. Use the obstack for string storage instead
            of relying on the tree nodes.
            (function_builder::add_overloaded_functions): Don't return early for
            m_direct_overloads: we need to add placeholders.
            * config/aarch64/aarch64-sve-builtins.h
            (function_builder::add_function): Add placeholder_p argument.
            * lto-streamer.h (LTO_minor_version): Bump.
    
    gcc/testsuite/ChangeLog:
    
            PR target/99216
            * g++.target/aarch64/sve/pr99216.C: New test.

Diff:
---
 gcc/config/aarch64/aarch64-sve-builtins.cc     | 59 ++++++++++++++++----------
 gcc/config/aarch64/aarch64-sve-builtins.h      |  3 +-
 gcc/lto-streamer.h                             |  2 +-
 gcc/testsuite/g++.target/aarch64/sve/pr99216.C |  5 +++
 4 files changed, 44 insertions(+), 25 deletions(-)

diff --git a/gcc/config/aarch64/aarch64-sve-builtins.cc b/gcc/config/aarch64/aarch64-sve-builtins.cc
index d534ca923d9..336a1db662b 100644
--- a/gcc/config/aarch64/aarch64-sve-builtins.cc
+++ b/gcc/config/aarch64/aarch64-sve-builtins.cc
@@ -995,12 +995,29 @@ registered_function &
 function_builder::add_function (const function_instance &instance,
 				const char *name, tree fntype, tree attrs,
 				uint64_t required_extensions,
-				bool overloaded_p)
+				bool overloaded_p,
+				bool placeholder_p)
 {
   unsigned int code = vec_safe_length (registered_functions);
   code = (code << AARCH64_BUILTIN_SHIFT) | AARCH64_BUILTIN_SVE;
-  tree decl = simulate_builtin_function_decl (input_location, name, fntype,
-					      code, NULL, attrs);
+
+  /* We need to be able to generate placeholders to enusre that we have a
+     consistent numbering scheme for function codes between the C and C++
+     frontends, so that everything ties up in LTO.
+
+     Currently, tree-streamer-in.c:unpack_ts_function_decl_value_fields
+     validates that tree nodes returned by TARGET_BUILTIN_DECL are non-NULL and
+     some node other than error_mark_node. This is a holdover from when builtin
+     decls were streamed by code rather than by value.
+
+     Ultimately, we should be able to remove this validation of BUILT_IN_MD
+     nodes and remove the target hook. For now, however, we need to appease the
+     validation and return a non-NULL, non-error_mark_node node, so we
+     arbitrarily choose integer_zero_node.  */
+  tree decl = placeholder_p
+    ? integer_zero_node
+    : simulate_builtin_function_decl (input_location, name, fntype,
+				      code, NULL, attrs);
 
   registered_function &rfn = *ggc_alloc <registered_function> ();
   rfn.instance = instance;
@@ -1032,7 +1049,7 @@ function_builder::add_unique_function (const function_instance &instance,
 					   argument_types.address ());
   tree attrs = get_attributes (instance);
   registered_function &rfn = add_function (instance, name, fntype, attrs,
-					   required_extensions, false);
+					   required_extensions, false, false);
 
   /* Enter the function into the hash table.  */
   hashval_t hash = instance.hash ();
@@ -1043,16 +1060,14 @@ function_builder::add_unique_function (const function_instance &instance,
 
   /* Also add the function under its overloaded alias, if we want
      a separate decl for each instance of an overloaded function.  */
-  if (m_direct_overloads || force_direct_overloads)
+  char *overload_name = get_name (instance, true);
+  if (strcmp (name, overload_name) != 0)
     {
-      char *overload_name = get_name (instance, true);
-      if (strcmp (name, overload_name) != 0)
-	{
-	  /* Attribute lists shouldn't be shared.  */
-	  tree attrs = get_attributes (instance);
-	  add_function (instance, overload_name, fntype, attrs,
-			required_extensions, false);
-	}
+      /* Attribute lists shouldn't be shared.  */
+      tree attrs = get_attributes (instance);
+      bool placeholder_p = !(m_direct_overloads || force_direct_overloads);
+      add_function (instance, overload_name, fntype, attrs,
+		    required_extensions, false, placeholder_p);
     }
 
   obstack_free (&m_string_obstack, name);
@@ -1073,18 +1088,19 @@ function_builder::add_overloaded_function (const function_instance &instance,
 {
   char *name = get_name (instance, true);
   if (registered_function **map_value = m_overload_names.get (name))
-    gcc_assert ((*map_value)->instance == instance
-		&& ((*map_value)->required_extensions
-		    & ~required_extensions) == 0);
+    {
+      gcc_assert ((*map_value)->instance == instance
+		  && ((*map_value)->required_extensions
+		      & ~required_extensions) == 0);
+      obstack_free (&m_string_obstack, name);
+    }
   else
     {
       registered_function &rfn
 	= add_function (instance, name, m_overload_type, NULL_TREE,
-			required_extensions, true);
-      const char *permanent_name = IDENTIFIER_POINTER (DECL_NAME (rfn.decl));
-      m_overload_names.put (permanent_name, &rfn);
+			required_extensions, true, m_direct_overloads);
+      m_overload_names.put (name, &rfn);
     }
-  obstack_free (&m_string_obstack, name);
 }
 
 /* If we are using manual overload resolution, add one function decl
@@ -1094,9 +1110,6 @@ void
 function_builder::add_overloaded_functions (const function_group_info &group,
 					    mode_suffix_index mode)
 {
-  if (m_direct_overloads)
-    return;
-
   unsigned int explicit_type0 = (*group.shape)->explicit_type_suffix_p (0);
   unsigned int explicit_type1 = (*group.shape)->explicit_type_suffix_p (1);
   for (unsigned int pi = 0; group.preds[pi] != NUM_PREDS; ++pi)
diff --git a/gcc/config/aarch64/aarch64-sve-builtins.h b/gcc/config/aarch64/aarch64-sve-builtins.h
index 526d9f55e7b..5ffc58cab0a 100644
--- a/gcc/config/aarch64/aarch64-sve-builtins.h
+++ b/gcc/config/aarch64/aarch64-sve-builtins.h
@@ -337,7 +337,8 @@ private:
   tree get_attributes (const function_instance &);
 
   registered_function &add_function (const function_instance &,
-				     const char *, tree, tree, uint64_t, bool);
+				     const char *, tree, tree,
+				     uint64_t, bool, bool);
 
   /* The function type to use for functions that are resolved by
      function_resolver.  */
diff --git a/gcc/lto-streamer.h b/gcc/lto-streamer.h
index 03440f0254c..7ac3b63fd33 100644
--- a/gcc/lto-streamer.h
+++ b/gcc/lto-streamer.h
@@ -121,7 +121,7 @@ along with GCC; see the file COPYING3.  If not see
      form followed by the data for the string.  */
 
 #define LTO_major_version 9
-#define LTO_minor_version 3
+#define LTO_minor_version 4
 
 typedef unsigned char	lto_decl_flags_t;
 
diff --git a/gcc/testsuite/g++.target/aarch64/sve/pr99216.C b/gcc/testsuite/g++.target/aarch64/sve/pr99216.C
new file mode 100644
index 00000000000..61a58a7fcf4
--- /dev/null
+++ b/gcc/testsuite/g++.target/aarch64/sve/pr99216.C
@@ -0,0 +1,5 @@
+/* { dg-do link { target aarch64_asm_sve_ok } } */
+/* { dg-additional-options "-flto" } */
+#include <arm_sve.h>
+bool a;
+int main() { a = svaddv(svptrue_b8(), svdup_s8(0)); }