[PATCH] x86: Avoid stack realignment when copying data with SSE register

["H.J. Lu" <hjl.tools@gmail.com>]

To avoid stack realignment, call ix86_gen_scratch_sse_rtx to get a
scratch SSE register to copy data with with SSE register from one
memory location to another.

gcc/

	PR target/101772
	* config/i386/i386-expand.c (ix86_expand_vector_move): Call
	ix86_gen_scratch_sse_rtx to get a scratch SSE register to copy
	data with SSE register from one memory location to another.

gcc/testsuite/

	PR target/101772
	* gcc.target/i386/eh_return-2.c: New test.
---
 gcc/config/i386/i386-expand.c               |  6 +++++-
 gcc/testsuite/gcc.target/i386/eh_return-2.c | 16 ++++++++++++++++
 2 files changed, 21 insertions(+), 1 deletion(-)
 create mode 100644 gcc/testsuite/gcc.target/i386/eh_return-2.c

diff --git a/gcc/config/i386/i386-expand.c b/gcc/config/i386/i386-expand.c
index 1d469bf7221..bd21efa9530 100644
--- a/gcc/config/i386/i386-expand.c
+++ b/gcc/config/i386/i386-expand.c
@@ -613,7 +613,11 @@ ix86_expand_vector_move (machine_mode mode, rtx operands[])
 	 arguments in memory.  */
       if (!register_operand (op0, mode)
 	  && !register_operand (op1, mode))
-	op1 = force_reg (mode, op1);
+	{
+	  rtx scratch = ix86_gen_scratch_sse_rtx (mode);
+	  emit_move_insn (scratch, op1);
+	  op1 = scratch;
+	}
 
       tmp[0] = op0; tmp[1] = op1;
       ix86_expand_vector_move_misalign (mode, tmp);
diff --git a/gcc/testsuite/gcc.target/i386/eh_return-2.c b/gcc/testsuite/gcc.target/i386/eh_return-2.c
new file mode 100644
index 00000000000..f23f4492dac
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/eh_return-2.c
@@ -0,0 +1,16 @@
+/* PR target/101772  */
+/* { dg-do compile } */
+/* { dg-additional-options "-O0 -march=x86-64 -mstackrealign" } */
+
+struct _Unwind_Context _Unwind_Resume_or_Rethrow_this_context;
+
+void offset (int);
+
+struct _Unwind_Context {
+  void *reg[7];
+} _Unwind_Resume_or_Rethrow() {
+  struct _Unwind_Context cur_contextcur_context =
+      _Unwind_Resume_or_Rethrow_this_context;
+  offset(0);
+  __builtin_eh_return ((long) offset, 0);
+}
-- 
2.31.1