bfin.c (n_regs_to_save): New static variable.

	* config/bfin/bfin.c (n_regs_to_save): New static variable.
	(push_multiple_operation, pop_multiple_operation): Set it.
	(workaround_rts_anomaly): New function.
	(workaround_speculation): New function, broken out of bfin_reorg.
	(bfin_reorg): Call the new functions.

From-SVN: r140146

gcc/ChangeLog

+2008-09-09  Bernd Schmidt  <bernd.schmidt@analog.com>
+
+	* config/bfin/bfin.c (n_regs_to_save): New static variable.
+	(push_multiple_operation, pop_multiple_operation): Set it.
+	(workaround_rts_anomaly): New function.
+	(workaround_speculation): New function, broken out of bfin_reorg.
+	(bfin_reorg): Call the new functions.
+
 2008-09-09  Richard Guenther  <rguenther@suse.de>
 
 	PR middle-end/37354

gcc/config/bfin/bfin.c

@@ -3100,6 +3100,7 @@ bfin_rtx_costs (rtx x, int code, int outer_code, int *total, bool speed)
 /* Used for communication between {push,pop}_multiple_operation (which
    we use not only as a predicate) and the corresponding output functions.  */
 static int first_preg_to_save, first_dreg_to_save;
+static int n_regs_to_save;
 
 int
 push_multiple_operation (rtx op, enum machine_mode mode ATTRIBUTE_UNUSED)
@@ -3168,6 +3169,7 @@ push_multiple_operation (rtx op, enum machine_mode mode ATTRIBUTE_UNUSED)
 	  lastpreg++;
 	}
     }
+  n_regs_to_save = 8 - first_dreg_to_save + 6 - first_preg_to_save;
   return 1;
 }
 
@@ -3227,6 +3229,7 @@ pop_multiple_operation (rtx op, enum machine_mode mode ATTRIBUTE_UNUSED)
     }
   first_dreg_to_save = lastdreg;
   first_preg_to_save = lastpreg;
+  n_regs_to_save = 8 - first_dreg_to_save + 6 - first_preg_to_save;
   return 1;
 }
 
@@ -4631,6 +4634,85 @@ reorder_var_tracking_notes (void)
     }
 }
 
+/* On some silicon revisions, functions shorter than a certain number of cycles
+   can cause unpredictable behaviour.  Work around this by adding NOPs as
+   needed.  */
+static void
+workaround_rts_anomaly (void)
+{
+  rtx insn, first_insn = NULL_RTX;
+  int cycles = 4;
+
+  if (! ENABLE_WA_RETS)
+    return;
+
+  for (insn = get_insns (); insn; insn = NEXT_INSN (insn))
+    {
+      rtx pat;
+
+      if (BARRIER_P (insn))
+	return;
+      
+      if (NOTE_P (insn) || LABEL_P (insn))
+	continue;
+
+      if (first_insn == NULL_RTX)
+	first_insn = insn;
+      pat = PATTERN (insn);
+      if (GET_CODE (pat) == USE || GET_CODE (pat) == CLOBBER
+	  || GET_CODE (pat) == ASM_INPUT || GET_CODE (pat) == ADDR_VEC
+	  || GET_CODE (pat) == ADDR_DIFF_VEC || asm_noperands (pat) >= 0)
+	continue;
+
+      if (CALL_P (insn))
+	return;
+
+      if (JUMP_P (insn))
+	{
+	  if (recog_memoized (insn) == CODE_FOR_return_internal)
+	    break;
+
+	  /* Nothing to worry about for direct jumps.  */
+	  if (!any_condjump_p (insn))
+	    return;
+	  if (cycles <= 1)
+	    return;
+	  cycles--;
+	}
+      else if (INSN_P (insn))
+	{
+	  rtx pat = PATTERN (insn);
+	  int this_cycles = 1;
+
+	  if (GET_CODE (pat) == PARALLEL)
+	    {
+	      if (push_multiple_operation (pat, VOIDmode)
+		  || pop_multiple_operation (pat, VOIDmode))
+		this_cycles = n_regs_to_save;
+	    }
+	  else
+	    {
+	      enum insn_code icode = recog_memoized (insn);
+	      if (icode == CODE_FOR_link)
+		this_cycles = 4;
+	      else if (icode == CODE_FOR_unlink)
+		this_cycles = 3;
+	      else if (icode == CODE_FOR_mulsi3)
+		this_cycles = 5;
+	    }
+	  if (this_cycles >= cycles)
+	    return;
+
+	  cycles -= this_cycles;
+	}
+    }
+  while (cycles > 0)
+    {
+      emit_insn_before (gen_nop (), first_insn);
+      cycles--;
+    }
+}
+
 /* Return an insn type for INSN that can be used by the caller for anomaly
    workarounds.  This differs from plain get_attr_type in that it handles
    SEQUENCEs.  */
@@ -4711,58 +4793,13 @@ find_load (rtx insn)
   return NULL_RTX;
 }
 
-/* We use the machine specific reorg pass for emitting CSYNC instructions
-   after conditional branches as needed.
-
-   The Blackfin is unusual in that a code sequence like
-     if cc jump label
-     r0 = (p0)
-   may speculatively perform the load even if the condition isn't true.  This
-   happens for a branch that is predicted not taken, because the pipeline
-   isn't flushed or stalled, so the early stages of the following instructions,
-   which perform the memory reference, are allowed to execute before the
-   jump condition is evaluated.
-   Therefore, we must insert additional instructions in all places where this
-   could lead to incorrect behavior.  The manual recommends CSYNC, while
-   VDSP seems to use NOPs (even though its corresponding compiler option is
-   named CSYNC).
-
-   When optimizing for speed, we emit NOPs, which seems faster than a CSYNC.
-   When optimizing for size, we turn the branch into a predicted taken one.
-   This may be slower due to mispredicts, but saves code size.  */
-
 static void
-bfin_reorg (void)
+workaround_speculation (void)
 {
   rtx insn, next;
   rtx last_condjump = NULL_RTX;
   int cycles_since_jump = INT_MAX;
 
-  /* We are freeing block_for_insn in the toplev to keep compatibility
-     with old MDEP_REORGS that are not CFG based.  Recompute it now.  */
-  compute_bb_for_insn ();
-
-  if (bfin_flag_schedule_insns2)
-    {
-      splitting_for_sched = 1;
-      split_all_insns ();
-      splitting_for_sched = 0;
-
-      timevar_push (TV_SCHED2);
-      schedule_insns ();
-      timevar_pop (TV_SCHED2);
-
-      /* Examine the schedule and insert nops as necessary for 64-bit parallel
-	 instructions.  */
-      bfin_gen_bundles ();
-    }
-
-  df_analyze ();
-
-  /* Doloop optimization */
-  if (cfun->machine->has_hardware_loops)
-    bfin_reorg_loops (dump_file);
-
   if (! ENABLE_WA_SPECULATIVE_LOADS && ! ENABLE_WA_SPECULATIVE_SYNCS)
     return;
 
@@ -4841,11 +4878,9 @@ bfin_reorg (void)
   if (! ENABLE_WA_SPECULATIVE_SYNCS)
     return;
 
-  if (! ENABLE_WA_RETS)
-    return;
-
   for (insn = get_insns (); insn; insn = NEXT_INSN (insn))
     {
+      int cycles_since_jump;
       if (JUMP_P (insn)
 	  && any_condjump_p (insn)
 	  && (INSN_CODE (insn) == CODE_FOR_cbranch_predicted_taken
@@ -4907,6 +4942,57 @@ bfin_reorg (void)
 	    }
 	}
     }
+}
+
+/* We use the machine specific reorg pass for emitting CSYNC instructions
+   after conditional branches as needed.
+
+   The Blackfin is unusual in that a code sequence like
+     if cc jump label
+     r0 = (p0)
+   may speculatively perform the load even if the condition isn't true.  This
+   happens for a branch that is predicted not taken, because the pipeline
+   isn't flushed or stalled, so the early stages of the following instructions,
+   which perform the memory reference, are allowed to execute before the
+   jump condition is evaluated.
+   Therefore, we must insert additional instructions in all places where this
+   could lead to incorrect behavior.  The manual recommends CSYNC, while
+   VDSP seems to use NOPs (even though its corresponding compiler option is
+   named CSYNC).
+
+   When optimizing for speed, we emit NOPs, which seems faster than a CSYNC.
+   When optimizing for size, we turn the branch into a predicted taken one.
+   This may be slower due to mispredicts, but saves code size.  */
+
+static void
+bfin_reorg (void)
+{
+  /* We are freeing block_for_insn in the toplev to keep compatibility
+     with old MDEP_REORGS that are not CFG based.  Recompute it now.  */
+  compute_bb_for_insn ();
+
+  if (bfin_flag_schedule_insns2)
+    {
+      splitting_for_sched = 1;
+      split_all_insns ();
+      splitting_for_sched = 0;
+
+      timevar_push (TV_SCHED2);
+      schedule_insns ();
+      timevar_pop (TV_SCHED2);
+
+      /* Examine the schedule and insert nops as necessary for 64-bit parallel
+	 instructions.  */
+      bfin_gen_bundles ();
+    }
+
+  df_analyze ();
+
+  /* Doloop optimization */
+  if (cfun->machine->has_hardware_loops)
+    bfin_reorg_loops (dump_file);
+
+  workaround_speculation ();
 
   if (bfin_flag_var_tracking)
     {
@@ -4915,7 +5001,10 @@ bfin_reorg (void)
       reorder_var_tracking_notes ();
       timevar_pop (TV_VAR_TRACKING);
     }
+
   df_finish_pass (false);
+
+  workaround_rts_anomaly ();
 }
 
 /* Handle interrupt_handler, exception_handler and nmi_handler function