gcc/0017-StructReorg-Some-bugfix-for-structure-reorganization.patch

From 2b4db34d3b21ff8597373e9e67858b3b60cc7dae Mon Sep 17 00:00:00 2001
From: eastb233 <xiezhiheng@huawei.com>
Date: Fri, 21 Jul 2023 11:20:51 +0800
Subject: [PATCH 17/22] [StructReorg] Some bugfix for structure reorganization

Some bugfix for structure reorganization,
1. disable type simplify in LTO within optimizations
2. only enable optimizations in C language
3. use new to initialize allocated memory in symbol-summary.h
4. cover escape scenarios not considered
---
 gcc/ipa-free-lang-data.cc                    |  11 ++
 gcc/ipa-struct-reorg/ipa-struct-reorg.cc     | 101 +++++++++++--------
 gcc/symbol-summary.h                         |  13 ++-
 gcc/testsuite/gcc.dg/struct/struct_reorg-5.c |  31 ++++++
 gcc/testsuite/gcc.dg/struct/struct_reorg-6.c |  54 ++++++++++
 gcc/testsuite/gcc.dg/struct/struct_reorg-7.c |  38 +++++++
 gcc/testsuite/gcc.dg/struct/struct_reorg-8.c |  25 +++++
 gcc/testsuite/gcc.dg/struct/struct_reorg-9.c |  54 ++++++++++
 8 files changed, 283 insertions(+), 44 deletions(-)
 create mode 100644 gcc/testsuite/gcc.dg/struct/struct_reorg-5.c
 create mode 100644 gcc/testsuite/gcc.dg/struct/struct_reorg-6.c
 create mode 100644 gcc/testsuite/gcc.dg/struct/struct_reorg-7.c
 create mode 100644 gcc/testsuite/gcc.dg/struct/struct_reorg-8.c
 create mode 100644 gcc/testsuite/gcc.dg/struct/struct_reorg-9.c

diff --git a/gcc/ipa-free-lang-data.cc b/gcc/ipa-free-lang-data.cc
index a74215685..5450be9fe 100644
--- a/gcc/ipa-free-lang-data.cc
+++ b/gcc/ipa-free-lang-data.cc
@@ -102,6 +102,12 @@ fld_worklist_push (tree t, class free_lang_data_d *fld)
 static tree
 fld_simplified_type_name (tree type)
 {
+  /* Simplify type will cause that struct A and struct A within
+     struct B are different type pointers, so skip it in structure
+     optimizations.  */
+  if (flag_ipa_struct_reorg)
+    return TYPE_NAME (type);
+
   if (!TYPE_NAME (type) || TREE_CODE (TYPE_NAME (type)) != TYPE_DECL)
     return TYPE_NAME (type);
   /* Drop TYPE_DECLs in TYPE_NAME in favor of the identifier in the
@@ -340,6 +346,11 @@ fld_simplified_type (tree t, class free_lang_data_d *fld)
 {
   if (!t)
     return t;
+  /* Simplify type will cause that struct A and struct A within
+     struct B are different type pointers, so skip it in structure
+     optimizations.  */
+  if (flag_ipa_struct_reorg)
+    return t;
   if (POINTER_TYPE_P (t))
     return fld_incomplete_type_of (t, fld);
   /* FIXME: This triggers verification error, see PR88140.  */
diff --git a/gcc/ipa-struct-reorg/ipa-struct-reorg.cc b/gcc/ipa-struct-reorg/ipa-struct-reorg.cc
index c8b975a92..9f790b28b 100644
--- a/gcc/ipa-struct-reorg/ipa-struct-reorg.cc
+++ b/gcc/ipa-struct-reorg/ipa-struct-reorg.cc
@@ -105,6 +105,7 @@ along with GCC; see the file COPYING3.  If not see
 #include "ipa-param-manipulation.h"
 #include "gimplify-me.h"
 #include "cfgloop.h"
+#include "langhooks.h"
 
 namespace {
 
@@ -196,6 +197,39 @@ gimplify_build1 (gimple_stmt_iterator *gsi, enum tree_code code, tree type,
 				   GSI_SAME_STMT);
 }
 
+/* Check whether in C language or LTO with only C language.  */
+
+static bool
+lang_c_p (void)
+{
+  const char *language_string = lang_hooks.name;
+
+  if (!language_string)
+    return false;
+
+  if (strcmp (language_string, "GNU GIMPLE") == 0)
+    {
+      unsigned i = 0;
+      tree t = NULL;
+      const char *unit_string = NULL;
+
+      FOR_EACH_VEC_SAFE_ELT (all_translation_units, i, t)
+	{
+	  unit_string = TRANSLATION_UNIT_LANGUAGE (t);
+	  if (!unit_string
+	      || (strncmp (unit_string, "GNU C", 5) != 0)
+	      || (!ISDIGIT (unit_string[5])))
+	    return false;
+	}
+      return true;
+    }
+  else if (strncmp (language_string, "GNU C", 5) == 0
+	   && ISDIGIT (language_string[5]))
+    return true;
+
+  return false;
+}
+
 enum srmode
 {
   NORMAL = 0,
@@ -1018,7 +1052,6 @@ public:
   void analyze_types (void);
   void clear_visited (void);
   bool create_new_types (void);
-  void restore_field_type (void);
   void create_new_decls (void);
   srdecl *find_decl (tree);
   void create_new_functions (void);
@@ -2107,7 +2140,12 @@ ipa_struct_reorg::find_vars (gimple *stmt)
 	      srtype *t = find_type (inner_type (TREE_TYPE (rhs)));
 	      srdecl *d = find_decl (lhs);
 	      if (!d && t)
-		current_function->record_decl (t, lhs, -1);
+		{
+		  current_function->record_decl (t, lhs, -1);
+		  tree var = SSA_NAME_VAR (lhs);
+		  if (var && VOID_POINTER_P (TREE_TYPE (var)))
+		    current_function->record_decl (t, var, -1);
+		}
 	    }
 	  if (TREE_CODE (rhs) == SSA_NAME
 	      && VOID_POINTER_P (TREE_TYPE (rhs))
@@ -2116,7 +2154,12 @@ ipa_struct_reorg::find_vars (gimple *stmt)
 	      srtype *t = find_type (inner_type (TREE_TYPE (lhs)));
 	      srdecl *d = find_decl (rhs);
 	      if (!d && t)
-		current_function->record_decl (t, rhs, -1);
+		{
+		  current_function->record_decl (t, rhs, -1);
+		  tree var = SSA_NAME_VAR (rhs);
+		  if (var && VOID_POINTER_P (TREE_TYPE (var)))
+		    current_function->record_decl (t, var, -1);
+		}
 	    }
 	}
       else
@@ -2796,8 +2839,14 @@ ipa_struct_reorg::maybe_record_call (cgraph_node *node, gcall *stmt)
   if (escapes != does_not_escape)
     {
       for (unsigned i = 0; i < gimple_call_num_args (stmt); i++)
-	mark_type_as_escape (TREE_TYPE (gimple_call_arg (stmt, i)),
-			     escapes);
+	{
+	  mark_type_as_escape (TREE_TYPE (gimple_call_arg (stmt, i)),
+			       escapes);
+	  srdecl *d = current_function->find_decl (
+					  gimple_call_arg (stmt, i));
+	  if (d)
+	    d->type->mark_escape (escapes, stmt);
+	}
       return;
     }
 
@@ -3731,42 +3780,6 @@ ipa_struct_reorg::analyze_types (void)
     }
 }
 
-/* When struct A has a struct B member, B's type info
-   is not stored in
-     TYPE_FIELDS (TREE_TYPE (TYPE_FIELDS (typeA)))
-   Try to restore B's type information.  */
-
-void
-ipa_struct_reorg::restore_field_type (void)
-{
-  for (unsigned i = 0; i < types.length (); i++)
-    {
-      for (unsigned j = 0; j < types[i]->fields.length (); j++)
-	{
-	  srfield *field = types[i]->fields[j];
-	  if (TREE_CODE (inner_type (field->fieldtype)) == RECORD_TYPE)
-	    {
-	      /* If field type has TYPE_FIELDS information,
-		 we do not need to do this.  */
-	      if (TYPE_FIELDS (field->type->type) != NULL)
-		continue;
-	      for (unsigned k = 0; k < types.length (); k++)
-		{
-		  if (i == k)
-		    continue;
-		  const char *type1 = get_type_name (field->type->type);
-		  const char *type2 = get_type_name (types[k]->type);
-		  if (type1 == NULL || type2 == NULL)
-		    continue;
-		  if (type1 == type2
-		      && TYPE_FIELDS (types[k]->type))
-		    field->type = types[k];
-		}
-	    }
-	}
-    }
-}
-
 /* Create all new types we want to create.  */
 
 bool
@@ -4647,7 +4660,6 @@ ipa_struct_reorg::rewrite_functions (void)
 {
   unsigned retval = 0;
 
-  restore_field_type ();
   /* Create new types, if we did not create any new types,
      then don't rewrite any accesses.  */
   if (!create_new_types ())
@@ -4866,7 +4878,10 @@ pass_ipa_struct_reorg::gate (function *)
 	  && flag_ipa_struct_reorg
 	  /* Don't bother doing anything if the program has errors.  */
 	  && !seen_error ()
-	  && flag_lto_partition == LTO_PARTITION_ONE);
+	  && flag_lto_partition == LTO_PARTITION_ONE
+	  /* Only enable struct optimizations in C since other
+	     languages' grammar forbid.  */
+	  && lang_c_p ());
 }
 
 } // anon namespace
diff --git a/gcc/symbol-summary.h b/gcc/symbol-summary.h
index c54d3084c..3fe64047c 100644
--- a/gcc/symbol-summary.h
+++ b/gcc/symbol-summary.h
@@ -103,6 +103,12 @@ protected:
   /* Allocates new data that are stored within map.  */
   T* allocate_new ()
   {
+    /* In structure optimizatons, we call new to ensure that
+       the allocated memory is initialized to 0.  */
+    if (flag_ipa_struct_reorg)
+      return is_ggc () ? new (ggc_internal_alloc (sizeof (T))) T ()
+		       : new T ();
+
     /* Call gcc_internal_because we do not want to call finalizer for
        a type T.  We call dtor explicitly.  */
     return is_ggc () ? new (ggc_internal_alloc (sizeof (T))) T ()
@@ -115,7 +121,12 @@ protected:
     if (is_ggc ())
       ggc_delete (item);
     else
-      m_allocator.remove (item);
+      {
+	if (flag_ipa_struct_reorg)
+	  delete item;
+	else
+	  m_allocator.remove (item);
+      }
   }
 
   /* Unregister all call-graph hooks.  */
diff --git a/gcc/testsuite/gcc.dg/struct/struct_reorg-5.c b/gcc/testsuite/gcc.dg/struct/struct_reorg-5.c
new file mode 100644
index 000000000..273baa9a3
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/struct/struct_reorg-5.c
@@ -0,0 +1,31 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-flto -fno-use-linker-plugin" } */
+
+struct D
+{
+  int n;
+  int c [8];
+};
+
+struct A
+{
+  int i;
+  char *p;
+};
+
+struct B
+{
+  struct A *a;
+  struct D *d;
+};
+
+int dtInsert1 (struct B *b)
+{
+  struct A a = { 0, 0 };
+  struct D *d;
+  b->a = &a;
+  d = b->d;
+  &d->c [d->n];
+  return 0;
+}
+
diff --git a/gcc/testsuite/gcc.dg/struct/struct_reorg-6.c b/gcc/testsuite/gcc.dg/struct/struct_reorg-6.c
new file mode 100644
index 000000000..455f9b501
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/struct/struct_reorg-6.c
@@ -0,0 +1,54 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-flto -fno-use-linker-plugin" } */
+
+typedef struct basic_block_def *basic_block;
+typedef struct gimple_seq_node_d *gimple_seq_node;
+typedef struct gimple_seq_d *gimple_seq;
+typedef struct
+{
+  gimple_seq_node ptr;
+  gimple_seq seq;
+  basic_block bb;
+} gimple_stmt_iterator;
+typedef void *gimple;
+extern void exit(int);
+struct gimple_seq_node_d
+{
+  gimple stmt;
+  struct gimple_seq_node_d *next;
+};
+struct gimple_seq_d
+{
+};
+static __inline__ gimple_stmt_iterator
+gsi_start (gimple_seq seq)
+{
+  gimple_stmt_iterator i;
+  i.seq = seq;
+  return i;
+}
+static __inline__ unsigned char
+gsi_end_p (gimple_stmt_iterator i)
+{
+  return i.ptr == ((void *)0);
+}
+static __inline__ void
+gsi_next (gimple_stmt_iterator *i)
+{
+  i->ptr = i->ptr->next;
+}
+static __inline__ gimple
+gsi_stmt (gimple_stmt_iterator i)
+{
+  return i.ptr->stmt;
+}
+void
+c_warn_unused_result (gimple_seq seq)
+{
+  gimple_stmt_iterator i;
+  for (i = gsi_start (seq); !gsi_end_p (i); gsi_next (&i))
+    {
+      gimple g = gsi_stmt (i);
+      if (!g) exit(0);
+    }
+}
diff --git a/gcc/testsuite/gcc.dg/struct/struct_reorg-7.c b/gcc/testsuite/gcc.dg/struct/struct_reorg-7.c
new file mode 100644
index 000000000..afc0bd86c
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/struct/struct_reorg-7.c
@@ -0,0 +1,38 @@
+/* { dg-do run } */
+
+#include <stdio.h>
+#include <stdlib.h>
+
+struct gki_elem {
+  char            *key;
+  int              idx;
+};
+
+typedef struct {
+  struct gki_elem *table;
+
+  int primelevel;
+  int nhash;
+  int nkeys;
+} GKI;
+
+void *
+sre_malloc(size_t size)
+{
+  void *ptr = malloc (size);
+  return ptr;
+}
+
+__attribute__((noinline)) int
+GKIStoreKey(GKI *hash)
+{
+  hash->table = sre_malloc(sizeof(struct gki_elem));
+}
+
+int
+main ()
+{
+  GKI *hash = malloc (sizeof(GKI));
+  GKIStoreKey(hash);
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.dg/struct/struct_reorg-8.c b/gcc/testsuite/gcc.dg/struct/struct_reorg-8.c
new file mode 100644
index 000000000..9bcfaf368
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/struct/struct_reorg-8.c
@@ -0,0 +1,25 @@
+/* { dg-do run } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+typedef struct {
+    unsigned char blue;
+    unsigned char green;
+} Pixel;
+
+typedef struct {
+    unsigned short colormaplength;
+    Pixel         *colormapdata;
+} TargaImage;
+
+TargaImage *img;
+
+int main() {
+    img = (TargaImage *) malloc( sizeof(TargaImage) );
+    if (img->colormaplength > 0) {
+        img->colormapdata = (Pixel *) malloc(sizeof(Pixel) * img->colormaplength);
+        memset(img->colormapdata, 0, (sizeof(Pixel) * img->colormaplength) );
+    }
+}
diff --git a/gcc/testsuite/gcc.dg/struct/struct_reorg-9.c b/gcc/testsuite/gcc.dg/struct/struct_reorg-9.c
new file mode 100644
index 000000000..052f4e3bd
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/struct/struct_reorg-9.c
@@ -0,0 +1,54 @@
+/* { dg-do run } */
+
+extern void abort(void);
+
+struct packed_ushort {
+    unsigned short ucs;
+} __attribute__((packed));
+
+struct source {
+    int pos, length;
+};
+
+static int flag;
+
+static void __attribute__((noinline)) fetch(struct source *p)
+{
+    p->length = 128;
+}
+    
+static struct packed_ushort __attribute__((noinline)) next(struct source *p)
+{
+    struct packed_ushort rv;
+
+    if (p->pos >= p->length) {
+	if (flag) {
+	    flag = 0;
+	    fetch(p);
+	    return next(p);
+	}
+	flag = 1;
+	rv.ucs = 0xffff;
+	return rv;
+    }
+    rv.ucs = 0;
+    return rv;
+}
+
+int main(void)
+{
+    struct source s;
+    int i;
+
+    s.pos = 0;
+    s.length = 0;
+    flag = 0;
+
+    for (i = 0; i < 16; i++) {
+	struct packed_ushort rv = next(&s);
+	if ((i == 0 && rv.ucs != 0xffff)
+	    || (i > 0 && rv.ucs != 0))
+	    abort();
+    }
+    return 0;
+}
-- 
2.33.0