re PR target/65697 (__atomic memory barriers not strong enough for __sync builtins)

	PR target/65697
	* config/aarch64/aarch64.c (aarch64_split_compare_and_swap): Check
	for __sync memory models, emit initial loads and final barriers as
	appropriate.

From-SVN: r223984

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 0c109c33c0a50d9bde8b259ccf4bbf60ec1f4821..b0c172c6f15eca2cb3d839ab0b37a28f70112807 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,10 @@
+2015-06-01  Matthew Wahab  <matthew.wahab@arm.com>
+
+       PR target/65697
+       * config/aarch64/aarch64.c (aarch64_split_compare_and_swap): Check
+       for __sync memory models, emit initial loads and final barriers as
+       appropriate.
+
 2015-06-01  Matthew Wahab  <matthew.wahab@arm.com>
 
         PR target/65697

diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index 93bea074d6831b2aea2c0a40dacddc9ad20788c7..62c8c8fe47ab94ebaa58bcb6de29c6da7cb01975 100644 (file)
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -9436,14 +9436,18 @@ aarch64_split_compare_and_swap (rtx operands[])
   bool is_weak;
   rtx_code_label *label1, *label2;
   rtx x, cond;
+  enum memmodel model;
+  rtx model_rtx;
 
   rval = operands[0];
   mem = operands[1];
   oldval = operands[2];
   newval = operands[3];
   is_weak = (operands[4] != const0_rtx);
+  model_rtx = operands[5];
   scratch = operands[7];
   mode = GET_MODE (mem);
+  model = memmodel_from_int (INTVAL (model_rtx));
 
   label1 = NULL;
   if (!is_weak)
@@ -9453,7 +9457,13 @@ aarch64_split_compare_and_swap (rtx operands[])
     }
   label2 = gen_label_rtx ();
 
-  aarch64_emit_load_exclusive (mode, rval, mem, operands[5]);
+  /* The initial load can be relaxed for a __sync operation since a final
+     barrier will be emitted to stop code hoisting.  */
+  if (is_mm_sync (model))
+    aarch64_emit_load_exclusive (mode, rval, mem,
+                                GEN_INT (MEMMODEL_RELAXED));
+  else
+    aarch64_emit_load_exclusive (mode, rval, mem, model_rtx);
 
   cond = aarch64_gen_compare_reg (NE, rval, oldval);
   x = gen_rtx_NE (VOIDmode, cond, const0_rtx);
@@ -9461,7 +9471,7 @@ aarch64_split_compare_and_swap (rtx operands[])
                            gen_rtx_LABEL_REF (Pmode, label2), pc_rtx);
   aarch64_emit_unlikely_jump (gen_rtx_SET (pc_rtx, x));
 
-  aarch64_emit_store_exclusive (mode, scratch, mem, newval, operands[5]);
+  aarch64_emit_store_exclusive (mode, scratch, mem, newval, model_rtx);
 
   if (!is_weak)
     {
@@ -9478,6 +9488,10 @@ aarch64_split_compare_and_swap (rtx operands[])
     }
 
   emit_label (label2);
+
+  /* Emit any final barrier needed for a __sync operation.  */
+  if (is_mm_sync (model))
+    aarch64_emit_post_barrier (model);
 }
 
 /* Split an atomic operation.  */