[PATCH] PR target/66906: Replicate static chain on the stack

["H.J. Lu" <hongjiu dot lu at intel dot com>]

If we put static chain on the stack, we need to replicate it on the stack
so that static chain can be reached via (argp - 2) slot.  This is needed
for nested function with stack realignment.

OK for trunk if there are no regressions?

H.J.
---
gcc/

	PR target/66906
	* config/i386/i386.c (ix86_expand_prologue): Replicate static
	chain on the stack.

gcc/testsuite/

	PR target/66906
	* gcc.target/i386/pr66906.c: New test.
---
 gcc/config/i386/i386.c                  | 18 ++++++++++++-
 gcc/testsuite/gcc.target/i386/pr66906.c | 45 +++++++++++++++++++++++++++++++++
 2 files changed, 62 insertions(+), 1 deletion(-)
 create mode 100644 gcc/testsuite/gcc.target/i386/pr66906.c

diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 0551a75..3803dde 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -11495,6 +11495,7 @@ ix86_expand_prologue (void)
   HOST_WIDE_INT allocate;
   bool int_registers_saved;
   bool sse_registers_saved;
+  rtx static_chain = NULL_RTX;
 
   ix86_finalize_stack_realign_flags ();
 
@@ -11593,7 +11594,8 @@ ix86_expand_prologue (void)
      call.  This insn will be skipped by the trampoline.  */
   else if (ix86_static_chain_on_stack)
     {
-      insn = emit_insn (gen_push (ix86_static_chain (cfun->decl, false)));
+      static_chain = ix86_static_chain (cfun->decl, false);
+      insn = emit_insn (gen_push (static_chain));
       emit_insn (gen_blockage ());
 
       /* We don't want to interpret this push insn as a register save,
@@ -11645,6 +11647,20 @@ ix86_expand_prologue (void)
 	 we've started over with a new frame.  */
       m->fs.sp_offset = INCOMING_FRAME_SP_OFFSET;
       m->fs.realigned = true;
+
+      if (static_chain)
+	{
+	  /* Replicate static chain on the stack so that static chain
+	     can be reached via (argp - 2) slot.  This is needed for
+	     nested function with stack realignment.  */
+	  t = plus_constant (Pmode, stack_pointer_rtx, -UNITS_PER_WORD);
+	  t = gen_rtx_SET (stack_pointer_rtx, t);
+	  insn = emit_insn (t);
+	  RTX_FRAME_RELATED_P (insn) = 1;
+	  emit_move_insn (gen_rtx_MEM (Pmode, stack_pointer_rtx),
+			  static_chain);
+	  m->fs.sp_offset += UNITS_PER_WORD;
+	}
     }
 
   int_registers_saved = (frame.nregs == 0);
diff --git a/gcc/testsuite/gcc.target/i386/pr66906.c b/gcc/testsuite/gcc.target/i386/pr66906.c
new file mode 100644
index 0000000..969e183
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr66906.c
@@ -0,0 +1,45 @@
+/* { dg-do run { target ia32 } } */
+/* { dg-options "-O0 -mregparm=3" } */
+
+typedef int ptrdiff_t;
+extern void abort (void);
+int
+check_int (int *i, int align)
+{
+  *i = 20;
+  if ((((ptrdiff_t) i) & (align - 1)) != 0)
+    abort ();
+  return *i;
+}
+void
+check (void *p, int align)
+{
+  if ((((ptrdiff_t) p) & (align - 1)) != 0)
+    abort ();
+}
+typedef int aligned __attribute__((aligned(64)));
+void
+foo (void)
+{
+  aligned j;
+  void bar ()
+    {
+      aligned i;
+      if (check_int (&i, __alignof__(i)) != i)
+	abort ();
+      if (check_int (&j, __alignof__(j)) != j)
+	abort ();
+      j = -20;
+    }
+  bar ();
+  if (j != -20)
+    abort ();
+  if (check_int (&j, __alignof__(j)) != j)
+    abort ();
+}
+int
+main()
+{
+  foo ();
+  return 0;
+}
-- 
2.4.3