x86-64: Generate push2/pop2 only if the incoming stack is 16-byte aligned

Since push2/pop2 requires 16-byte stack alignment, don't generate them
if the incoming stack isn't 16-byte aligned.

gcc/

	PR target/113912
	* config/i386/i386.cc (ix86_can_use_push2pop2): New.
	(ix86_pro_and_epilogue_can_use_push2pop2): Use it.
	(ix86_emit_save_regs): Don't generate push2 if
	ix86_can_use_push2pop2 return false.
	(ix86_expand_epilogue): Don't generate pop2 if
	ix86_can_use_push2pop2 return false.

gcc/testsuite/

	PR target/113912
	* gcc.target/i386/apx-push2pop2-2.c: New test.

2 files changed, 42 insertions, 6 deletions

diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
index a4e1260..46f2386 100644
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -6802,16 +6802,24 @@ get_probe_interval (void)
 
 #define SPLIT_STACK_AVAILABLE 256
 
-/* Helper function to determine whether push2/pop2 can be used in prologue or
-   epilogue for register save/restore.  */
+/* Return true if push2/pop2 can be generated.  */
+
 static bool
-ix86_pro_and_epilogue_can_use_push2pop2 (int nregs)
+ix86_can_use_push2pop2 (void)
 {
   /* Use push2/pop2 only if the incoming stack is 16-byte aligned.  */
   unsigned int incoming_stack_boundary
     = (crtl->parm_stack_boundary > ix86_incoming_stack_boundary
        ? crtl->parm_stack_boundary : ix86_incoming_stack_boundary);
-  if (incoming_stack_boundary % 128 != 0)
+  return incoming_stack_boundary % 128 == 0;
+}
+
+/* Helper function to determine whether push2/pop2 can be used in prologue or
+   epilogue for register save/restore.  */
+static bool
+ix86_pro_and_epilogue_can_use_push2pop2 (int nregs)
+{
+  if (!ix86_can_use_push2pop2 ())
     return false;
   int aligned = cfun->machine->fs.sp_offset % 16 == 0;
   return TARGET_APX_PUSH2POP2
@@ -7401,7 +7409,9 @@ ix86_emit_save_regs (void)
   int regno;
   rtx_insn *insn;
 
-  if (!TARGET_APX_PUSH2POP2 || cfun->machine->func_type != TYPE_NORMAL)
+  if (!TARGET_APX_PUSH2POP2
+      || !ix86_can_use_push2pop2 ()
+      || cfun->machine->func_type != TYPE_NORMAL)
     {
       for (regno = FIRST_PSEUDO_REGISTER - 1; regno >= 0; regno--)
 	if (GENERAL_REGNO_P (regno) && ix86_save_reg (regno, true, true))
@@ -10039,7 +10049,9 @@ ix86_expand_epilogue (int style)
 				     m->fs.cfa_reg == stack_pointer_rtx);
 	}
 
-      if (TARGET_APX_PUSH2POP2 && m->func_type == TYPE_NORMAL)
+      if (TARGET_APX_PUSH2POP2
+	  && ix86_can_use_push2pop2 ()
+	  && m->func_type == TYPE_NORMAL)
 	ix86_emit_restore_regs_using_pop2 ();
       else
 	ix86_emit_restore_regs_using_pop (TARGET_APX_PPX);
diff --git a/gcc/testsuite/gcc.target/i386/apx-push2pop2-2.c b/gcc/testsuite/gcc.target/i386/apx-push2pop2-2.c
new file mode 100644
index 0000000..975a621
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/apx-push2pop2-2.c
@@ -0,0 +1,24 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -mpreferred-stack-boundary=3 -mapx-features=push2pop2 -fomit-frame-pointer" } */
+
+extern int bar (int);
+
+void foo ()
+{
+  int a,b,c,d,e,f,i;
+  a = bar (5);
+  b = bar (a);
+  c = bar (b);
+  d = bar (c);
+  e = bar (d);
+  f = bar (e);
+  for (i = 1; i < 10; i++)
+  {
+    a += bar (a + i) + bar (b + i) +
+         bar (c + i) + bar (d + i) +
+         bar (e + i) + bar (f + i);
+  }
+}
+
+/* { dg-final { scan-assembler-not "push2(|p)\[\\t \]*%r" } } */
+/* { dg-final { scan-assembler-not "pop2(|p)\[\\t \]*%r" } } */