s390.c (s390_register_info): Make the call-saved FPR loop to work also for 31bit ABI.

2013-10-07  Andreas Krebbel  <Andreas.Krebbel@de.ibm.com>

	* config/s390/s390.c (s390_register_info): Make the call-saved FPR
	loop to work also for 31bit ABI.
	Save the stack pointer for frame_size > 0.

2013-10-07  Andreas Krebbel  <Andreas.Krebbel@de.ibm.com>

	* gcc.target/s390/htm-nofloat-2.c: New testcase.

From-SVN: r203240

4 files changed, 75 insertions, 11 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index d91beec..d54cf03 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,5 +1,11 @@
 2013-10-07  Andreas Krebbel  <Andreas.Krebbel@de.ibm.com>
 
+	* config/s390/s390.c (s390_register_info): Make the call-saved FPR
+	loop to work also for 31bit ABI.
+	Save the stack pointer for frame_size > 0.
+
+2013-10-07  Andreas Krebbel  <Andreas.Krebbel@de.ibm.com>
+
 	* config/s390/s390.md ("tbegin", "tbegin_nofloat", "tbegin_retry")
 	("tbegin_retry_nofloat", "tend", "tabort", "tx_assist"): Remove
 	constraint letters from expanders.
diff --git a/gcc/config/s390/s390.c b/gcc/config/s390/s390.c
index 898e683..338a09e 100644
--- a/gcc/config/s390/s390.c
+++ b/gcc/config/s390/s390.c
@@ -7509,8 +7509,11 @@ s390_register_info (int clobbered_regs[])
     {
       cfun_frame_layout.fpr_bitmap = 0;
       cfun_frame_layout.high_fprs = 0;
-      if (TARGET_64BIT)
-	for (i = FPR8_REGNUM; i <= FPR15_REGNUM; i++)
+
+      for (i = FPR0_REGNUM; i <= FPR15_REGNUM; i++)
+	{
+	  if (call_really_used_regs[i])
+	    continue;
 	  /* During reload we have to use the df_regs_ever_live infos
 	     since reload is marking FPRs used as spill slots there as
 	     live before actually making the code changes.  Without
@@ -7523,8 +7526,11 @@ s390_register_info (int clobbered_regs[])
 	      && !global_regs[i])
 	    {
 	      cfun_set_fpr_save (i);
-	      cfun_frame_layout.high_fprs++;
+
+	      if (i >= FPR8_REGNUM)
+		cfun_frame_layout.high_fprs++;
 	    }
+	}
     }
 
   for (i = 0; i < 16; i++)
@@ -7554,6 +7560,7 @@ s390_register_info (int clobbered_regs[])
 	|| TARGET_TPF_PROFILING
 	|| cfun_save_high_fprs_p
 	|| get_frame_size () > 0
+	|| (reload_completed && cfun_frame_layout.frame_size > 0)
 	|| cfun->calls_alloca
 	|| cfun->stdarg);
 
@@ -7652,14 +7659,6 @@ s390_register_info (int clobbered_regs[])
 	    cfun_set_fpr_save (i + FPR0_REGNUM);
 	}
     }
-
-  if (!TARGET_64BIT)
-    {
-      if (df_regs_ever_live_p (FPR4_REGNUM) && !global_regs[FPR4_REGNUM])
-	cfun_set_fpr_save (FPR4_REGNUM);
-      if (df_regs_ever_live_p (FPR6_REGNUM) && !global_regs[FPR6_REGNUM])
-	cfun_set_fpr_save (FPR6_REGNUM);
-    }
 }
 
 /* Fill cfun->machine with info about frame of current function.  */
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 5dccbe7..2d3561d 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,5 +1,9 @@
 2013-10-07  Andreas Krebbel  <Andreas.Krebbel@de.ibm.com>
 
+	* gcc.target/s390/htm-nofloat-2.c: New testcase.
+
+2013-10-07  Andreas Krebbel  <Andreas.Krebbel@de.ibm.com>
+
 	* gcc.target/s390/htm-1.c: Add more tests to cover different
 	operand types.
 
diff --git a/gcc/testsuite/gcc.target/s390/htm-nofloat-2.c b/gcc/testsuite/gcc.target/s390/htm-nofloat-2.c
new file mode 100644
index 0000000..db90642
--- /dev/null
+++ b/gcc/testsuite/gcc.target/s390/htm-nofloat-2.c
@@ -0,0 +1,55 @@
+/* { dg-do run } */
+/* { dg-options "-O3 -mhtm -Wa,-march=zEC12 --save-temps" } */
+
+/* __builtin_tbegin has to emit clobbers for all FPRs since the tbegin
+   instruction does not automatically preserves them.  If the
+   transaction body is fully contained in a function the backend tries
+   after reload to get rid of the FPR save/restore operations
+   triggered by the clobbers.  This testcase failed since the backend
+   was able to get rid of all FPR saves/restores and since these were
+   the only stack operations also of the entire stack space.  So even
+   the save/restore of the stack pointer was omitted in the end.
+   However, since the frame layout has been fixed before, the prologue
+   still generated the stack pointer decrement making foo return with
+   a modified stack pointer.  */
+
+void abort(void);
+
+void __attribute__((noinline))
+foo (int a)
+{
+  /* This is just to prevent the tbegin code from actually being
+     executed.  That way the test may even run on machines prior to
+     zEC12.  */
+  if (a == 42)
+    return;
+
+  if (__builtin_tbegin (0) == 0)
+    __builtin_tend ();
+}
+
+#ifdef __s390x__
+#define GET_STACK_POINTER(SP)			\
+  asm volatile ("stg %%r15, %0" : "=QRST" (SP));
+#else
+#define GET_STACK_POINTER(SP)			\
+  asm volatile ("st %%r15, %0" : "=QR" (SP));
+#endif
+
+int main(void)
+{
+  unsigned long new_sp, old_sp;
+
+  GET_STACK_POINTER (old_sp);
+  foo(42);
+  GET_STACK_POINTER (new_sp);
+
+  if (old_sp != new_sp)
+    abort ();
+
+  return 0;
+}
+
+/* Make sure no FPR saves/restores are emitted.  */
+/* { dg-final { scan-assembler-not "\tstd\t" } } */
+/* { dg-final { scan-assembler-not "\tld\t" } } */