Original patch from gentoo: gentoo/src/patchsets/gcc/4.3.0/gentoo/20_all_gcc-x86-emit-cld.patch

bandaid for the cld issue.  to be dropped when gcc-4.3 goes stable.

http://gcc.gnu.org/ml/gcc-patches/2008-03/msg00417.html

2008-03-06  Uros Bizjak  <ubizjak@gmail.com>

	* config/i386/i386.h (TARGET_CLD): New define.

	(struct machine_function): Add needs_cld field.

	(ix86_current_function_needs_cld): New define.

	* config/i386/i386.md (UNSPEC_CLD): New unspec volatile constant.

	("cld"): New isns pattern.

	("strmov_singleop"): Set ix86_current_function_needs_cld flag.

	("rep_mov"): Ditto.

	("strset_singleop"): Ditto.

	("rep_stos"): Ditto.

	("cmpstrnqi_nz_1"): Ditto.

	("cmpstrnqi_1"): Ditto.

	("strlenqi_1"): Ditto.

	* config/i386/i386.c (ix86_expand_prologue): Emit cld insn for

	TARGET_CLD when ix86_current_function_needs_cld is set.

diff -durN gcc-4.3.0.orig/gcc/config/i386/i386.c gcc-4.3.0/gcc/config/i386/i386.c

--- gcc-4.3.0.orig/gcc/config/i386/i386.c	2008-02-21 13:30:00.000000000 +0100

+++ gcc-4.3.0/gcc/config/i386/i386.c	2008-06-10 14:44:37.000000000 +0200

@@ -6448,6 +6448,10 @@

 	emit_insn (gen_prologue_use (pic_offset_table_rtx));

       emit_insn (gen_blockage ());

     }

+

+  /* Emit cld instruction if stringops are used in the function.  */

+  if (TARGET_CLD && ix86_current_function_needs_cld)

+    emit_insn (gen_cld ());

 }

 /* Emit code to restore saved registers using MOV insns.  First register

diff -durN gcc-4.3.0.orig/gcc/config/i386/i386.h gcc-4.3.0/gcc/config/i386/i386.h

--- gcc-4.3.0.orig/gcc/config/i386/i386.h	2008-02-15 09:12:02.000000000 +0100

+++ gcc-4.3.0/gcc/config/i386/i386.h	2008-06-10 14:44:37.000000000 +0200

@@ -388,6 +388,7 @@

 extern int x86_prefetch_sse;

+#define TARGET_CLD		1

 #define TARGET_ABM		x86_abm

 #define TARGET_CMPXCHG16B	x86_cmpxchg16b

 #define TARGET_POPCNT		x86_popcnt

@@ -2443,8 +2444,9 @@

   int save_varrargs_registers;

   int accesses_prev_frame;

   int optimize_mode_switching[MAX_386_ENTITIES];

-  /* Set by ix86_compute_frame_layout and used by prologue/epilogue expander to

-     determine the style used.  */

+  int needs_cld;

+  /* Set by ix86_compute_frame_layout and used by prologue/epilogue

+     expander to determine the style used.  */

   int use_fast_prologue_epilogue;

   /* Number of saved registers USE_FAST_PROLOGUE_EPILOGUE has been computed

      for.  */

@@ -2464,6 +2466,7 @@

 #define ix86_stack_locals (cfun->machine->stack_locals)

 #define ix86_save_varrargs_registers (cfun->machine->save_varrargs_registers)

 #define ix86_optimize_mode_switching (cfun->machine->optimize_mode_switching)

+#define ix86_current_function_needs_cld (cfun->machine->needs_cld)

 #define ix86_tls_descriptor_calls_expanded_in_cfun \

   (cfun->machine->tls_descriptor_call_expanded_p)

 /* Since tls_descriptor_call_expanded is not cleared, even if all TLS

diff -durN gcc-4.3.0.orig/gcc/config/i386/i386.md gcc-4.3.0/gcc/config/i386/i386.md

--- gcc-4.3.0.orig/gcc/config/i386/i386.md	2008-02-06 12:34:00.000000000 +0100

+++ gcc-4.3.0/gcc/config/i386/i386.md	2008-06-10 14:44:37.000000000 +0200

@@ -205,6 +205,7 @@

    (UNSPECV_XCHG		12)

    (UNSPECV_LOCK		13)

    (UNSPECV_PROLOGUE_USE	14)

+   (UNSPECV_CLD			15)

   ])

 ;; Constants to represent pcomtrue/pcomfalse variants

@@ -18529,6 +18530,14 @@

 ;; Block operation instructions

+(define_insn "cld"

+  [(unspec_volatile [(const_int 0)] UNSPECV_CLD)]

+  ""

+  "cld"

+  [(set_attr "length" "1")

+   (set_attr "length_immediate" "0")

+   (set_attr "modrm" "0")])

+

 (define_expand "movmemsi"

   [(use (match_operand:BLK 0 "memory_operand" ""))

    (use (match_operand:BLK 1 "memory_operand" ""))

@@ -18601,7 +18610,7 @@

 	      (set (match_operand 2 "register_operand" "")

 		   (match_operand 5 "" ""))])]

   "TARGET_SINGLE_STRINGOP || optimize_size"

-  "")

+  "ix86_current_function_needs_cld = 1;")

 (define_insn "*strmovdi_rex_1"

   [(set (mem:DI (match_operand:DI 2 "register_operand" "0"))

@@ -18718,7 +18727,7 @@

 		   (match_operand 3 "memory_operand" ""))

 	      (use (match_dup 4))])]

   ""

-  "")

+  "ix86_current_function_needs_cld = 1;")

 (define_insn "*rep_movdi_rex64"

   [(set (match_operand:DI 2 "register_operand" "=c") (const_int 0))

@@ -18878,7 +18887,7 @@

 	      (set (match_operand 0 "register_operand" "")

 		   (match_operand 3 "" ""))])]

   "TARGET_SINGLE_STRINGOP || optimize_size"

-  "")

+  "ix86_current_function_needs_cld = 1;")

 (define_insn "*strsetdi_rex_1"

   [(set (mem:DI (match_operand:DI 1 "register_operand" "0"))

@@ -18972,7 +18981,7 @@

 	      (use (match_operand 3 "register_operand" ""))

 	      (use (match_dup 1))])]

   ""

-  "")

+  "ix86_current_function_needs_cld = 1;")

 (define_insn "*rep_stosdi_rex64"

   [(set (match_operand:DI 1 "register_operand" "=c") (const_int 0))

@@ -19148,7 +19157,7 @@

 	      (clobber (match_operand 1 "register_operand" ""))

 	      (clobber (match_dup 2))])]

   ""

-  "")

+  "ix86_current_function_needs_cld = 1;")

 (define_insn "*cmpstrnqi_nz_1"

   [(set (reg:CC FLAGS_REG)

@@ -19195,7 +19204,7 @@

 	      (clobber (match_operand 1 "register_operand" ""))

 	      (clobber (match_dup 2))])]

   ""

-  "")

+  "ix86_current_function_needs_cld = 1;")

 (define_insn "*cmpstrnqi_1"

   [(set (reg:CC FLAGS_REG)

@@ -19264,7 +19273,7 @@

 	      (clobber (match_operand 1 "register_operand" ""))

 	      (clobber (reg:CC FLAGS_REG))])]

   ""

-  "")

+  "ix86_current_function_needs_cld = 1;")

 (define_insn "*strlenqi_1"

   [(set (match_operand:SI 0 "register_operand" "=&c")