[gcc r12-2665] x86: Avoid stack realignment when copying data

[gcc r12-2665] x86: Avoid stack realignment when copying data

[H.J. Lu]

https://gcc.gnu.org/g:7f4c3943f795fda33df648d2196b678bada1ba81

commit r12-2665-g7f4c3943f795fda33df648d2196b678bada1ba81
Author: H.J. Lu <hjl.tools@gmail.com>
Date:   Mon Aug 2 10:01:46 2021 -0700

    x86: Avoid stack realignment when copying data
    
    To avoid stack realignment, use SCRATCH_SSE_REG to copy data from one
    memory location to another.
    
    gcc/
    
            * config/i386/i386-expand.c (ix86_expand_vector_move): Call
            ix86_gen_scratch_sse_rtx to get a scratch SSE register to copy
            data from one memory location to another.
    
    gcc/testsuite/
    
            * gcc.target/i386/eh_return-1.c: New test.

Diff:
---
 gcc/config/i386/i386-expand.c               |  4 +++-
 gcc/testsuite/gcc.target/i386/eh_return-1.c | 26 ++++++++++++++++++++++++++
 2 files changed, 29 insertions(+), 1 deletion(-)

diff --git a/gcc/config/i386/i386-expand.c b/gcc/config/i386/i386-expand.c
index 896bd685b1f..1d469bf7221 100644
--- a/gcc/config/i386/i386-expand.c
+++ b/gcc/config/i386/i386-expand.c
@@ -625,7 +625,9 @@ ix86_expand_vector_move (machine_mode mode, rtx operands[])
       && !register_operand (op0, mode)
       && !register_operand (op1, mode))
     {
-      emit_move_insn (op0, force_reg (GET_MODE (op0), op1));
+      rtx tmp = ix86_gen_scratch_sse_rtx (GET_MODE (op0));
+      emit_move_insn (tmp, op1);
+      emit_move_insn (op0, tmp);
       return;
     }
 
diff --git a/gcc/testsuite/gcc.target/i386/eh_return-1.c b/gcc/testsuite/gcc.target/i386/eh_return-1.c
new file mode 100644
index 00000000000..671ba635e88
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/eh_return-1.c
@@ -0,0 +1,26 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=haswell -mno-avx512f" } */
+
+struct _Unwind_Context
+{
+  void *ra;
+  char array[48];
+};
+
+extern long uw_install_context_1 (struct _Unwind_Context *);
+
+void
+_Unwind_RaiseException (void)
+{
+  struct _Unwind_Context this_context, cur_context;
+  long offset = uw_install_context_1 (&this_context);
+  __builtin_memcpy (&this_context, &cur_context,
+		    sizeof (struct _Unwind_Context));
+  void *handler = __builtin_frob_return_addr ((&cur_context)->ra);
+  uw_install_context_1 (&cur_context);
+  __builtin_eh_return (offset, handler);
+}
+
+/* { dg-final { scan-assembler-times "vmovdqu\[ \\t\]+\[^\n\]*%ymm" 4 } } */
+/* No need to dynamically realign the stack here.  */
+/* { dg-final { scan-assembler-not "and\[^\n\r]*%\[re\]sp" } } */