re PR target/39118 (x86_64 red zone violation)

	PR target/39118
	* config/i386/i386.md (UNSPEC_MEMORY_BLOCKAGE): New constant.
	(memory_blockage): New expander.
	(*memory_blockage): New insn pattern.
	* config/i386/i386.c (ix86_expand_prologue): Use memory_blockage
	instead of general blockage at the end of function prologue when
	frame pointer is used to access red zone area.  Do not emit blockage
	when profiling, it is emitted in generic code.
	(ix86_expand_epilogue): Emit memory_blockage at the beginning of
	function epilogue when frame pointer is used to access red zone area.

From-SVN: r144100

3 files changed, 52 insertions, 21 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 4dd1672..71c859e 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,17 @@
+2009-02-11  Uros Bizjak  <ubizjak@gmail.com>
+	    Jakub Jelinek  <jakub@redhat.com>
+
+	PR target/39118
+	* config/i386/i386.md (UNSPEC_MEMORY_BLOCKAGE): New constant.
+	(memory_blockage): New expander.
+	(*memory_blockage): New insn pattern.
+	* config/i386/i386.c (ix86_expand_prologue): Use memory_blockage
+	instead of general blockage at the end of function prologue when
+	frame pointer is used to access red zone area.  Do not emit blockage
+	when profiling, it is emitted in generic code.
+	(ix86_expand_epilogue): Emit memory_blockage at the beginning of
+	function epilogue when frame pointer is used to access red zone area.
+
 2009-02-11  Paolo Bonzini  <bonzini@gnu.org>
 
 	* config/i386/i386.md: Add two new peephole2 to avoid mov followed
@@ -32,8 +46,7 @@
 	cancel_loop_tree, not before it.
 
 	PR target/39139
-	* function.h (struct function): Add has_local_explicit_reg_vars
-	bit.
+	* function.h (struct function): Add has_local_explicit_reg_vars bit.
 	* gimplify.c (gimplify_bind_expr): Set it if local DECL_HARD_REGISTER
 	VAR_DECLs were seen.
 	* tree-ssa-live.c (remove_unused_locals): Recompute
@@ -89,8 +102,8 @@
 2009-02-09  Sebastian Pop  <sebastian.pop@amd.com>
 
 	PR middle-end/38953
-	* graphite.c (if_region_set_false_region): After moving a region 
-	in the false branch of a condition, remove the empty dummy basic block.
+	* graphite.c (if_region_set_false_region): After moving a region in
+	the false branch of a condition, remove the empty dummy basic block.
 	(gloog): Remove wrong fix for PR38953.
 
 2009-02-09  Ulrich Weigand  <Ulrich.Weigand@de.ibm.com>
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index e64bcc6..3e02102 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -7997,7 +7997,6 @@ ix86_expand_prologue (void)
 {
   rtx insn;
   bool pic_reg_used;
-  bool emit_blockage = false;
   struct ix86_frame frame;
   HOST_WIDE_INT allocate;
 
@@ -8209,14 +8208,12 @@ ix86_expand_prologue (void)
         insn = emit_insn (gen_set_got (pic_offset_table_rtx));
     }
 
-  /* Prevent function calls from being scheduled before the call to mcount.
-     In the pic_reg_used case, make sure that the got load isn't deleted.  */
-  if (crtl->profile)
-    {
-      if (pic_reg_used)
-	emit_insn (gen_prologue_use (pic_offset_table_rtx));
-      emit_blockage = true;
-    }
+  /* In the pic_reg_used case, make sure that the got load isn't deleted
+     when mcount needs it.  Blockage to avoid call movement across mcount
+     call is emitted in generic code after the NOTE_INSN_PROLOGUE_END
+     note.  */
+  if (crtl->profile && pic_reg_used)
+    emit_insn (gen_prologue_use (pic_offset_table_rtx));
 
   if (crtl->drap_reg && !crtl->stack_realign_needed)
     {
@@ -8235,10 +8232,7 @@ ix86_expand_prologue (void)
      prologue, and moving instructions that access redzone area via frame
      pointer inside push sequence violates this assumption.  */
   if (frame_pointer_needed && frame.red_zone_size)
-    emit_blockage = true;
-
-  if (emit_blockage)
-    emit_insn (gen_blockage ()); 
+    emit_insn (gen_memory_blockage ());
 
   /* Emit cld instruction if stringops are used in the function.  */
   if (TARGET_CLD && ix86_current_function_needs_cld)
@@ -8326,6 +8320,11 @@ ix86_expand_epilogue (int style)
 
   ix86_compute_frame_layout (&frame);
 
+  /* See the comment about red zone and frame
+     pointer usage in ix86_expand_prologue.  */
+  if (frame_pointer_needed && frame.red_zone_size)
+    emit_insn (gen_memory_blockage ()); 
+
   /* Calculate start of saved registers relative to ebp.  Special care
      must be taken for the normal return case of a function using
      eh_return: the eax and edx registers are marked as saved, but not
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index 7a4511f..1516237 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -68,12 +68,13 @@
    (UNSPEC_DEF_CFA		15)
    (UNSPEC_SET_RIP		16)
    (UNSPEC_SET_GOT_OFFSET	17)
+   (UNSPEC_MEMORY_BLOCKAGE	18)
 
    ; TLS support
-   (UNSPEC_TP			18)
-   (UNSPEC_TLS_GD		19)
-   (UNSPEC_TLS_LD_BASE		20)
-   (UNSPEC_TLSDESC		21)
+   (UNSPEC_TP			20)
+   (UNSPEC_TLS_GD		21)
+   (UNSPEC_TLS_LD_BASE		22)
+   (UNSPEC_TLSDESC		23)
 
    ; Other random patterns
    (UNSPEC_SCAS			30)
@@ -15175,6 +15176,24 @@
   ""
   [(set_attr "length" "0")])
 
+;; Do not schedule instructions accessing memory across this point.
+
+(define_expand "memory_blockage"
+  [(set (match_dup 0)
+	(unspec:BLK [(match_dup 0)] UNSPEC_MEMORY_BLOCKAGE))]
+  ""
+{
+  operands[0] = gen_rtx_MEM (BLKmode, gen_rtx_SCRATCH (Pmode));
+  MEM_VOLATILE_P (operands[0]) = 1;
+})
+
+(define_insn "*memory_blockage"
+  [(set (match_operand:BLK 0 "" "")
+	(unspec:BLK [(match_dup 0)] UNSPEC_MEMORY_BLOCKAGE))]
+  ""
+  ""
+  [(set_attr "length" "0")])
+
 ;; As USE insns aren't meaningful after reload, this is used instead
 ;; to prevent deleting instructions setting registers for PIC code
 (define_insn "prologue_use"