[RFC] Patch candidate for PR81657

From 916fcf526ecac9eb73439cfee893e8447a1f3d53 Mon Sep 17 00:00:00 2001
From: marxin <mliska@suse.cz>
Date: Wed, 2 Aug 2017 10:56:03 +0200
Subject: [PATCH] Patch candidate.

---
 gcc/builtins.c         | 13 ++++++++++++-
 gcc/config/i386/i386.h |  3 +++
 gcc/defaults.h         |  7 +++++++
 gcc/doc/tm.texi        |  5 +++++
 gcc/doc/tm.texi.in     |  5 +++++
 gcc/expr.c             | 13 ++++++++++++-
 gcc/expr.h             |  4 +++-
 7 files changed, 47 insertions(+), 3 deletions(-)

diff --git a/gcc/builtins.c b/gcc/builtins.c
index 016f68d2cb6..f97655f3b3e 100644
--- a/gcc/builtins.c
+++ b/gcc/builtins.c
@@ -3485,13 +3485,24 @@  expand_builtin_memory_copy_args (tree dest, tree src, tree len,
   src_mem = get_memory_rtx (src, len);
   set_mem_align (src_mem, src_align);
 
+  bool is_move_done;
+
   /* Copy word part most expediently.  */
   dest_addr = emit_block_move_hints (dest_mem, src_mem, len_rtx,
 				     CALL_EXPR_TAILCALL (exp)
 				     && (endp == 0 || target == const0_rtx)
 				     ? BLOCK_OP_TAILCALL : BLOCK_OP_NORMAL,
 				     expected_align, expected_size,
-				     min_size, max_size, probable_max_size);
+				     min_size, max_size, probable_max_size,
+				     TARGET_HAS_FAST_MEMPCPY_ROUTINE
+				     && endp == 1,
+				     &is_move_done);
+
+  /* Bail out when a mempcpy call would be expanded as libcall and when
+     we have a target that provides a fast implementation
+     of mempcpy routine.  */
+  if (!is_move_done)
+    return NULL_RTX;
 
   if (dest_addr == 0)
     {
diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
index e8ae3e3b3cc..bf205f1345b 100644
--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
@@ -1964,6 +1964,9 @@  typedef struct ix86_args {
 
 #define CLEAR_RATIO(speed) ((speed) ? MIN (6, ix86_cost->move_ratio) : 2)
 
+/* C library provides fast implementation of mempcpy function.  */
+#define TARGET_HAS_FAST_MEMPCPY_ROUTINE 1
+
 /* Define if shifts truncate the shift count which implies one can
    omit a sign-extension or zero-extension of a shift count.
 
diff --git a/gcc/defaults.h b/gcc/defaults.h
index 7ad92d920f8..73325e93699 100644
--- a/gcc/defaults.h
+++ b/gcc/defaults.h
@@ -1346,6 +1346,13 @@  see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
 #define SET_RATIO(speed) MOVE_RATIO (speed)
 #endif
 
+/* By default do not generate libcall to mempcpy and rather use
+   libcall to memcpy and adjustment of return value.  */
+
+#ifndef TARGET_HAS_FAST_MEMPCPY_ROUTINE
+#define TARGET_HAS_FAST_MEMPCPY_ROUTINE 0
+#endif
+
 /* Supply a default definition for FUNCTION_ARG_PADDING:
    usually pad upward, but pad short args downward on
    big-endian machines.  */
diff --git a/gcc/doc/tm.texi b/gcc/doc/tm.texi
index 23e85c7afea..af076356910 100644
--- a/gcc/doc/tm.texi
+++ b/gcc/doc/tm.texi
@@ -6500,6 +6500,11 @@  optimized for speed rather than size.
 If you don't define this, it defaults to the value of @code{MOVE_RATIO}.
 @end defmac
 
+@defmac TARGET_HAS_FAST_MEMPCPY_ROUTINE
+By default do not generate libcall to mempcpy and rather use
+libcall to memcpy and adjustment of return value.
+@end defmac
+
 @defmac USE_LOAD_POST_INCREMENT (@var{mode})
 A C expression used to determine whether a load postincrement is a good
 thing to use for a given mode.  Defaults to the value of
diff --git a/gcc/doc/tm.texi.in b/gcc/doc/tm.texi.in
index 6df08a2c477..334258dd59d 100644
--- a/gcc/doc/tm.texi.in
+++ b/gcc/doc/tm.texi.in
@@ -4731,6 +4731,11 @@  optimized for speed rather than size.
 If you don't define this, it defaults to the value of @code{MOVE_RATIO}.
 @end defmac
 
+@defmac TARGET_HAS_FAST_MEMPCPY_ROUTINE
+By default do not generate libcall to mempcpy and rather use
+libcall to memcpy and adjustment of return value.
+@end defmac
+
 @defmac USE_LOAD_POST_INCREMENT (@var{mode})
 A C expression used to determine whether a load postincrement is a good
 thing to use for a given mode.  Defaults to the value of
diff --git a/gcc/expr.c b/gcc/expr.c
index b194866313d..b5b73ae12ca 100644
--- a/gcc/expr.c
+++ b/gcc/expr.c
@@ -1548,12 +1548,16 @@  emit_block_move_hints (rtx x, rtx y, rtx size, enum block_op_methods method,
 		       unsigned int expected_align, HOST_WIDE_INT expected_size,
 		       unsigned HOST_WIDE_INT min_size,
 		       unsigned HOST_WIDE_INT max_size,
-		       unsigned HOST_WIDE_INT probable_max_size)
+		       unsigned HOST_WIDE_INT probable_max_size,
+		       bool bail_out_libcall, bool *is_move_done)
 {
   bool may_use_call;
   rtx retval = 0;
   unsigned int align;
 
+  if (is_move_done)
+    *is_move_done = true;
+
   gcc_assert (size);
   if (CONST_INT_P (size) && INTVAL (size) == 0)
     return 0;
@@ -1610,6 +1614,13 @@  emit_block_move_hints (rtx x, rtx y, rtx size, enum block_op_methods method,
 	   && ADDR_SPACE_GENERIC_P (MEM_ADDR_SPACE (x))
 	   && ADDR_SPACE_GENERIC_P (MEM_ADDR_SPACE (y)))
     {
+      if (bail_out_libcall)
+	{
+	  if (is_move_done)
+	    *is_move_done = false;
+	  return retval;
+	}
+
       /* Since x and y are passed to a libcall, mark the corresponding
 	 tree EXPR as addressable.  */
       tree y_expr = MEM_EXPR (y);
diff --git a/gcc/expr.h b/gcc/expr.h
index b92ff3ce8a6..1cc82b9b00e 100644
--- a/gcc/expr.h
+++ b/gcc/expr.h
@@ -110,7 +110,9 @@  extern rtx emit_block_move_hints (rtx, rtx, rtx, enum block_op_methods,
 			          unsigned int, HOST_WIDE_INT,
 				  unsigned HOST_WIDE_INT,
 				  unsigned HOST_WIDE_INT,
-				  unsigned HOST_WIDE_INT);
+				  unsigned HOST_WIDE_INT,
+				  bool bail_out_libcall = false,
+				  bool *is_move_done = NULL);
 extern rtx emit_block_cmp_hints (rtx, rtx, rtx, tree, rtx, bool,
 				 by_pieces_constfn, void *);
 extern bool emit_storent_insn (rtx to, rtx from);
-- 
2.13.3