i386: Insert ENDBR before the profiling counter call

ENDBR must be the first instruction of a function.  This patch queues
ENDBR if we need to put the profiling counter call before the prologue
and generate ENDBR before the profiling counter call.

gcc/

	PR target/82699
	* config/i386/i386.c (rest_of_insert_endbranch): Set
	endbr_queued_at_entrance to true and don't insert ENDBR if
	x86_function_profiler will be called.
	(x86_function_profiler): Insert ENDBR if endbr_queued_at_entrance
	is true.
	* config/i386/i386.h (machine_function): Add
	endbr_queued_at_entrance.

gcc/testsuite/

	PR target/82699
	* gcc.target/i386/pr82699-1.c: New file.
	* gcc.target/i386/pr82699-2.c: Likewise.
	* gcc.target/i386/pr82699-3.c: Likewise.
	* gcc.target/i386/pr82699-4.c: Likewise.
	* gcc.target/i386/pr82699-5.c: Likewise.
	* gcc.target/i386/pr82699-6.c: Likewise.

From-SVN: r264540

gcc/ChangeLog

+2018-09-24  H.J. Lu  <hongjiu.lu@intel.com>
+
+	PR target/82699
+	* config/i386/i386.c (rest_of_insert_endbranch): Set
+	endbr_queued_at_entrance to true and don't insert ENDBR if
+	x86_function_profiler will be called.
+	(x86_function_profiler): Insert ENDBR if endbr_queued_at_entrance
+	is true.
+	* config/i386/i386.h (machine_function): Add
+	endbr_queued_at_entrance.
+
 2018-09-24  Ilya Leoshkevich  <iii@linux.ibm.com>
 
 	* genattrtab.c (mk_attr_alt): Use alternative_mask.

gcc/config/i386/i386.c

@@ -2593,11 +2593,17 @@ rest_of_insert_endbranch (void)
 			 TYPE_ATTRIBUTES (TREE_TYPE (cfun->decl)))
       && !cgraph_node::get (cfun->decl)->only_called_directly_p ())
     {
-      cet_eb = gen_nop_endbr ();
+      /* Queue ENDBR insertion to x86_function_profiler.  */
+      if (crtl->profile && flag_fentry)
+	cfun->machine->endbr_queued_at_entrance = true;
+      else
+	{
+	  cet_eb = gen_nop_endbr ();
 
-      bb = ENTRY_BLOCK_PTR_FOR_FN (cfun)->next_bb;
-      insn = BB_HEAD (bb);
-      emit_insn_before (cet_eb, insn);
+	  bb = ENTRY_BLOCK_PTR_FOR_FN (cfun)->next_bb;
+	  insn = BB_HEAD (bb);
+	  emit_insn_before (cet_eb, insn);
+	}
     }
 
   bb = 0;
@@ -41203,6 +41209,10 @@ x86_function_profiler (FILE *file, int labelno ATTRIBUTE_UNUSED)
 {
   const char *mcount_name = (flag_fentry ? MCOUNT_NAME_BEFORE_PROLOGUE
 					 : MCOUNT_NAME);
+
+  if (cfun->machine->endbr_queued_at_entrance)
+    fprintf (file, "\t%s\n", TARGET_64BIT ? "endbr64" : "endbr32");
+
   if (TARGET_64BIT)
     {
 #ifndef NO_PROFILE_COUNTERS

gcc/config/i386/i386.h

@@ -2747,6 +2747,9 @@ struct GTY(()) machine_function {
   /* Nonzero if the function places outgoing arguments on stack.  */
   BOOL_BITFIELD outgoing_args_on_stack : 1;
 
+  /* If true, ENDBR is queued at function entrance.  */
+  BOOL_BITFIELD endbr_queued_at_entrance : 1;
+
   /* The largest alignment, in bytes, of stack slot actually used.  */
   unsigned int max_used_stack_alignment;
 

gcc/testsuite/ChangeLog

+2018-09-24  H.J. Lu  <hongjiu.lu@intel.com>
+
+	PR target/82699
+	* gcc.target/i386/pr82699-1.c: New file.
+	* gcc.target/i386/pr82699-2.c: Likewise.
+	* gcc.target/i386/pr82699-3.c: Likewise.
+	* gcc.target/i386/pr82699-4.c: Likewise.
+	* gcc.target/i386/pr82699-5.c: Likewise.
+	* gcc.target/i386/pr82699-6.c: Likewise.
+
 2018-09-24  Thomas Koenig  <tkoenig@gcc.gnu.org>
 
 	PR fortran/87401

gcc/testsuite/gcc.target/i386/pr82699-1.c

+/* { dg-do compile { target *-*-linux* } } */
+/* { dg-options "-O2 -fno-pic -fcf-protection -pg -fasynchronous-unwind-tables" } */
+/* { dg-final { scan-assembler-times {\t\.cfi_startproc\n\tendbr} 1 } } */
+
+extern int bar (int);
+
+int
+foo (int i)
+{
+  return bar (i);
+}

gcc/testsuite/gcc.target/i386/pr82699-2.c

+/* { dg-do compile { target *-*-linux* } } */
+/* { dg-options "-O2 -fno-pic -fcf-protection -pg -mfentry -fasynchronous-unwind-tables" } */
+/* { dg-final { scan-assembler-times {\t\.cfi_startproc\n\tendbr} 1 } } */
+
+extern int bar (int);
+
+int
+foo (int i)
+{
+  return bar (i);
+}

gcc/testsuite/gcc.target/i386/pr82699-3.c

+/* { dg-do compile { target *-*-linux* } } */
+/* { dg-options "-O2 -fpic -fcf-protection -pg -fasynchronous-unwind-tables" } */
+/* { dg-final { scan-assembler-times {\t\.cfi_startproc\n\tendbr} 1 } } */
+
+extern int bar (int);
+
+int
+foo (int i)
+{
+  return bar (i);
+}

gcc/testsuite/gcc.target/i386/pr82699-4.c

+/* { dg-do compile { target { *-*-linux* && { ! ia32 } } } } */
+/* { dg-options "-O2 -fpic -fcf-protection -pg -mfentry -fasynchronous-unwind-tables" } */
+/* { dg-final { scan-assembler-times {\t\.cfi_startproc\n\tendbr} 1 } } */
+
+extern int bar (int);
+
+int
+foo (int i)
+{
+  return bar (i);
+}

gcc/testsuite/gcc.target/i386/pr82699-5.c

+/* { dg-do compile { target *-*-linux* } } */
+/* { dg-options "-O2 -fcf-protection -mfentry -fasynchronous-unwind-tables" } */
+/* { dg-final { scan-assembler-times {\t\.cfi_startproc\n\tendbr} 1 } } */
+
+extern int bar (int);
+
+int
+foo (int i)
+{
+  return bar (i);
+}

gcc/testsuite/gcc.target/i386/pr82699-6.c

+/* { dg-do compile { target *-*-linux* } } */
+/* { dg-options "-O2 -fcf-protection -pg -mfentry -mrecord-mcount -mnop-mcount -fasynchronous-unwind-tables" } */
+/* { dg-final { scan-assembler-times {\t\.cfi_startproc\n\tendbr} 1 } } */
+
+extern int bar (int);
+
+int
+foo (int i)
+{
+  return bar (i);
+}