S/390: Add -fsplit-stack support

libgcc/ChangeLog:

	* config.host: Use t-stack and t-stack-s390 for s390*-*-linux.
	* config/s390/morestack.S: New file.
	* config/s390/t-stack-s390: New file.
	* generic-morestack.c (__splitstack_find): Add s390-specific code.

gcc/ChangeLog:

	* common/config/s390/s390-common.c (s390_supports_split_stack):
	New function.
	(TARGET_SUPPORTS_SPLIT_STACK): New macro.
	* config/s390/s390-protos.h: Add s390_expand_split_stack_prologue.
	* config/s390/s390.c (struct machine_function): New field
	split_stack_varargs_pointer.
	(s390_register_info): Mark r12 as clobbered if it'll be used as temp
	in s390_emit_prologue.
	(s390_emit_prologue): Use r12 as temp if r1 is taken by split-stack
	vararg pointer.
	(morestack_ref): New global.
	(SPLIT_STACK_AVAILABLE): New macro.
	(s390_expand_split_stack_prologue): New function.
	(s390_live_on_entry): New function.
	(s390_va_start): Use split-stack vararg pointer if appropriate.
	(s390_asm_file_end): Emit the split-stack note sections.
	(TARGET_EXTRA_LIVE_ON_ENTRY): New macro.
	* config/s390/s390.md (UNSPEC_STACK_CHECK): New unspec.
	(UNSPECV_SPLIT_STACK_CALL): New unspec.
	(UNSPECV_SPLIT_STACK_DATA): New unspec.
	(split_stack_prologue): New expand.
	(split_stack_space_check): New expand.
	(split_stack_data): New insn.
	(split_stack_call): New expand.
	(split_stack_call_*): New insn.
	(split_stack_cond_call): New expand.
	(split_stack_cond_call_*): New insn.

From-SVN: r233421

5 files changed, 392 insertions, 5 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 6ef134f..cf178e7 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,33 @@
+2016-02-15  Marcin Kościelnicki  <koriakin@0x04.net>
+
+	* common/config/s390/s390-common.c (s390_supports_split_stack):
+	New function.
+	(TARGET_SUPPORTS_SPLIT_STACK): New macro.
+	* config/s390/s390-protos.h: Add s390_expand_split_stack_prologue.
+	* config/s390/s390.c (struct machine_function): New field
+	split_stack_varargs_pointer.
+	(s390_register_info): Mark r12 as clobbered if it'll be used as temp
+	in s390_emit_prologue.
+	(s390_emit_prologue): Use r12 as temp if r1 is taken by split-stack
+	vararg pointer.
+	(morestack_ref): New global.
+	(SPLIT_STACK_AVAILABLE): New macro.
+	(s390_expand_split_stack_prologue): New function.
+	(s390_live_on_entry): New function.
+	(s390_va_start): Use split-stack vararg pointer if appropriate.
+	(s390_asm_file_end): Emit the split-stack note sections.
+	(TARGET_EXTRA_LIVE_ON_ENTRY): New macro.
+	* config/s390/s390.md (UNSPEC_STACK_CHECK): New unspec.
+	(UNSPECV_SPLIT_STACK_CALL): New unspec.
+	(UNSPECV_SPLIT_STACK_DATA): New unspec.
+	(split_stack_prologue): New expand.
+	(split_stack_space_check): New expand.
+	(split_stack_data): New insn.
+	(split_stack_call): New expand.
+	(split_stack_call_*): New insn.
+	(split_stack_cond_call): New expand.
+	(split_stack_cond_call_*): New insn.
+
 2016-02-15  Richard Biener  <rguenther@suse.de>
 
 	PR tree-optimization/69783
diff --git a/gcc/common/config/s390/s390-common.c b/gcc/common/config/s390/s390-common.c
index 4519c21..1e497e6 100644
--- a/gcc/common/config/s390/s390-common.c
+++ b/gcc/common/config/s390/s390-common.c
@@ -105,6 +105,17 @@ s390_handle_option (struct gcc_options *opts ATTRIBUTE_UNUSED,
     }
 }
 
+/* -fsplit-stack uses a field in the TCB, available with glibc-2.23.
+   We don't verify it, since earlier versions just have padding at
+   its place, which works just as well.  */
+
+static bool
+s390_supports_split_stack (bool report ATTRIBUTE_UNUSED,
+			   struct gcc_options *opts ATTRIBUTE_UNUSED)
+{
+  return true;
+}
+
 #undef TARGET_DEFAULT_TARGET_FLAGS
 #define TARGET_DEFAULT_TARGET_FLAGS (TARGET_DEFAULT)
 
@@ -117,4 +128,7 @@ s390_handle_option (struct gcc_options *opts ATTRIBUTE_UNUSED,
 #undef TARGET_OPTION_INIT_STRUCT
 #define TARGET_OPTION_INIT_STRUCT s390_option_init_struct
 
+#undef TARGET_SUPPORTS_SPLIT_STACK
+#define TARGET_SUPPORTS_SPLIT_STACK s390_supports_split_stack
+
 struct gcc_targetm_common targetm_common = TARGETM_COMMON_INITIALIZER;
diff --git a/gcc/config/s390/s390-protos.h b/gcc/config/s390/s390-protos.h
index 633bc1e..09032c9 100644
--- a/gcc/config/s390/s390-protos.h
+++ b/gcc/config/s390/s390-protos.h
@@ -42,6 +42,7 @@ extern bool s390_handle_option (struct gcc_options *opts ATTRIBUTE_UNUSED,
 extern HOST_WIDE_INT s390_initial_elimination_offset (int, int);
 extern void s390_emit_prologue (void);
 extern void s390_emit_epilogue (bool);
+extern void s390_expand_split_stack_prologue (void);
 extern bool s390_can_use_simple_return_insn (void);
 extern bool s390_can_use_return_insn (void);
 extern void s390_function_profiler (FILE *, int);
diff --git a/gcc/config/s390/s390.c b/gcc/config/s390/s390.c
index 9facd96..aa82d1c 100644
--- a/gcc/config/s390/s390.c
+++ b/gcc/config/s390/s390.c
@@ -428,6 +428,13 @@ struct GTY(()) machine_function
   /* True if the current function may contain a tbegin clobbering
      FPRs.  */
   bool tbegin_p;
+
+  /* For -fsplit-stack support: A stack local which holds a pointer to
+     the stack arguments for a function with a variable number of
+     arguments.  This is set at the start of the function and is used
+     to initialize the overflow_arg_area field of the va_list
+     structure.  */
+  rtx split_stack_varargs_pointer;
 };
 
 /* Few accessor macros for struct cfun->machine->s390_frame_layout.  */
@@ -9371,9 +9378,13 @@ s390_register_info ()
 	  cfun_frame_layout.high_fprs++;
       }
 
-  if (flag_pic)
-    clobbered_regs[PIC_OFFSET_TABLE_REGNUM]
-      |= !!df_regs_ever_live_p (PIC_OFFSET_TABLE_REGNUM);
+  /* Register 12 is used for GOT address, but also as temp in prologue
+     for split-stack stdarg functions (unless r14 is available).  */
+  clobbered_regs[12]
+    |= ((flag_pic && df_regs_ever_live_p (PIC_OFFSET_TABLE_REGNUM))
+	|| (flag_split_stack && cfun->stdarg
+	    && (crtl->is_leaf || TARGET_TPF_PROFILING
+		|| has_hard_reg_initial_val (Pmode, RETURN_REGNUM))));
 
   clobbered_regs[BASE_REGNUM]
     |= (cfun->machine->base_reg
@@ -10473,12 +10484,15 @@ s390_emit_prologue (void)
   int next_fpr = 0;
 
   /* Choose best register to use for temp use within prologue.
-     See below for why TPF must use the register 1.  */
+     TPF with profiling must avoid the register 14 - the tracing function
+     needs the original contents of r14 to be preserved.  */
 
   if (!has_hard_reg_initial_val (Pmode, RETURN_REGNUM)
       && !crtl->is_leaf
       && !TARGET_TPF_PROFILING)
     temp_reg = gen_rtx_REG (Pmode, RETURN_REGNUM);
+  else if (flag_split_stack && cfun->stdarg)
+    temp_reg = gen_rtx_REG (Pmode, 12);
   else
     temp_reg = gen_rtx_REG (Pmode, 1);
 
@@ -10972,6 +10986,166 @@ s300_set_up_by_prologue (hard_reg_set_container *regs)
     SET_HARD_REG_BIT (regs->set, REGNO (cfun->machine->base_reg));
 }
 
+/* -fsplit-stack support.  */
+
+/* A SYMBOL_REF for __morestack.  */
+static GTY(()) rtx morestack_ref;
+
+/* When using -fsplit-stack, the allocation routines set a field in
+   the TCB to the bottom of the stack plus this much space, measured
+   in bytes.  */
+
+#define SPLIT_STACK_AVAILABLE 1024
+
+/* Emit -fsplit-stack prologue, which goes before the regular function
+   prologue.  */
+
+void
+s390_expand_split_stack_prologue (void)
+{
+  rtx r1, guard, cc = NULL;
+  rtx_insn *insn;
+  /* Offset from thread pointer to __private_ss.  */
+  int psso = TARGET_64BIT ? 0x38 : 0x20;
+  /* Pointer size in bytes.  */
+  /* Frame size and argument size - the two parameters to __morestack.  */
+  HOST_WIDE_INT frame_size = cfun_frame_layout.frame_size;
+  /* Align argument size to 8 bytes - simplifies __morestack code.  */
+  HOST_WIDE_INT args_size = crtl->args.size >= 0
+			    ? ((crtl->args.size + 7) & ~7)
+			    : 0;
+  /* Label to be called by __morestack.  */
+  rtx_code_label *call_done = NULL;
+  rtx_code_label *parm_base = NULL;
+  rtx tmp;
+
+  gcc_assert (flag_split_stack && reload_completed);
+  if (!TARGET_CPU_ZARCH)
+    {
+      sorry ("CPUs older than z900 are not supported for -fsplit-stack");
+      return;
+    }
+
+  r1 = gen_rtx_REG (Pmode, 1);
+
+  /* If no stack frame will be allocated, don't do anything.  */
+  if (!frame_size)
+    {
+      if (cfun->machine->split_stack_varargs_pointer != NULL_RTX)
+	{
+	  /* If va_start is used, just use r15.  */
+	  emit_move_insn (r1,
+			 gen_rtx_PLUS (Pmode, stack_pointer_rtx,
+				       GEN_INT (STACK_POINTER_OFFSET)));
+
+	}
+      return;
+    }
+
+  if (morestack_ref == NULL_RTX)
+    {
+      morestack_ref = gen_rtx_SYMBOL_REF (Pmode, "__morestack");
+      SYMBOL_REF_FLAGS (morestack_ref) |= (SYMBOL_FLAG_LOCAL
+					   | SYMBOL_FLAG_FUNCTION);
+    }
+
+  if (CONST_OK_FOR_K (frame_size) || CONST_OK_FOR_Op (frame_size))
+    {
+      /* If frame_size will fit in an add instruction, do a stack space
+	 check, and only call __morestack if there's not enough space.  */
+
+      /* Get thread pointer.  r1 is the only register we can always destroy - r0
+	 could contain a static chain (and cannot be used to address memory
+	 anyway), r2-r6 can contain parameters, and r6-r15 are callee-saved.  */
+      emit_move_insn (r1, gen_rtx_REG (Pmode, TP_REGNUM));
+      /* Aim at __private_ss.  */
+      guard = gen_rtx_MEM (Pmode, plus_constant (Pmode, r1, psso));
+
+      /* If less that 1kiB used, skip addition and compare directly with
+	 __private_ss.  */
+      if (frame_size > SPLIT_STACK_AVAILABLE)
+	{
+	  emit_move_insn (r1, guard);
+	  if (TARGET_64BIT)
+	    emit_insn (gen_adddi3 (r1, r1, GEN_INT (frame_size)));
+	  else
+	    emit_insn (gen_addsi3 (r1, r1, GEN_INT (frame_size)));
+	  guard = r1;
+	}
+
+      /* Compare the (maybe adjusted) guard with the stack pointer.  */
+      cc = s390_emit_compare (LT, stack_pointer_rtx, guard);
+    }
+
+  call_done = gen_label_rtx ();
+  parm_base = gen_label_rtx ();
+
+  /* Emit the parameter block.  */
+  tmp = gen_split_stack_data (parm_base, call_done,
+			      GEN_INT (frame_size),
+			      GEN_INT (args_size));
+  insn = emit_insn (tmp);
+  add_reg_note (insn, REG_LABEL_OPERAND, call_done);
+  LABEL_NUSES (call_done)++;
+  add_reg_note (insn, REG_LABEL_OPERAND, parm_base);
+  LABEL_NUSES (parm_base)++;
+
+  /* %r1 = litbase.  */
+  insn = emit_move_insn (r1, gen_rtx_LABEL_REF (VOIDmode, parm_base));
+  add_reg_note (insn, REG_LABEL_OPERAND, parm_base);
+  LABEL_NUSES (parm_base)++;
+
+  /* Now, we need to call __morestack.  It has very special calling
+     conventions: it preserves param/return/static chain registers for
+     calling main function body, and looks for its own parameters at %r1. */
+
+  if (cc != NULL)
+    {
+      tmp = gen_split_stack_cond_call (morestack_ref, cc, call_done);
+
+      insn = emit_jump_insn (tmp);
+      JUMP_LABEL (insn) = call_done;
+      LABEL_NUSES (call_done)++;
+
+      /* Mark the jump as very unlikely to be taken.  */
+      add_int_reg_note (insn, REG_BR_PROB, REG_BR_PROB_BASE / 100);
+
+      if (cfun->machine->split_stack_varargs_pointer != NULL_RTX)
+	{
+	  /* If va_start is used, and __morestack was not called, just use
+	     r15.  */
+	  emit_move_insn (r1,
+			 gen_rtx_PLUS (Pmode, stack_pointer_rtx,
+				       GEN_INT (STACK_POINTER_OFFSET)));
+	}
+    }
+  else
+    {
+      tmp = gen_split_stack_call (morestack_ref, call_done);
+      insn = emit_jump_insn (tmp);
+      JUMP_LABEL (insn) = call_done;
+      LABEL_NUSES (call_done)++;
+      emit_barrier ();
+    }
+
+  /* __morestack will call us here.  */
+
+  emit_label (call_done);
+}
+
+/* We may have to tell the dataflow pass that the split stack prologue
+   is initializing a register.  */
+
+static void
+s390_live_on_entry (bitmap regs)
+{
+  if (cfun->machine->split_stack_varargs_pointer != NULL_RTX)
+    {
+      gcc_assert (flag_split_stack);
+      bitmap_set_bit (regs, 1);
+    }
+}
+
 /* Return true if the function can use simple_return to return outside
    of a shrink-wrapped region.  At present shrink-wrapping is supported
    in all cases.  */
@@ -11574,6 +11748,27 @@ s390_va_start (tree valist, rtx nextarg ATTRIBUTE_UNUSED)
       expand_expr (t, const0_rtx, VOIDmode, EXPAND_NORMAL);
     }
 
+  if (flag_split_stack
+     && (lookup_attribute ("no_split_stack", DECL_ATTRIBUTES (cfun->decl))
+         == NULL)
+     && cfun->machine->split_stack_varargs_pointer == NULL_RTX)
+    {
+      rtx reg;
+      rtx_insn *seq;
+
+      reg = gen_reg_rtx (Pmode);
+      cfun->machine->split_stack_varargs_pointer = reg;
+
+      start_sequence ();
+      emit_move_insn (reg, gen_rtx_REG (Pmode, 1));
+      seq = get_insns ();
+      end_sequence ();
+
+      push_topmost_sequence ();
+      emit_insn_after (seq, entry_of_function ());
+      pop_topmost_sequence ();
+    }
+
   /* Find the overflow area.
      FIXME: This currently is too pessimistic when the vector ABI is
      enabled.  In that case we *always* set up the overflow area
@@ -11582,7 +11777,10 @@ s390_va_start (tree valist, rtx nextarg ATTRIBUTE_UNUSED)
       || n_fpr + cfun->va_list_fpr_size > FP_ARG_NUM_REG
       || TARGET_VX_ABI)
     {
-      t = make_tree (TREE_TYPE (ovf), virtual_incoming_args_rtx);
+      if (cfun->machine->split_stack_varargs_pointer == NULL_RTX)
+        t = make_tree (TREE_TYPE (ovf), virtual_incoming_args_rtx);
+      else
+        t = make_tree (TREE_TYPE (ovf), cfun->machine->split_stack_varargs_pointer);
 
       off = INTVAL (crtl->args.arg_offset_rtx);
       off = off < 0 ? 0 : off;
@@ -14502,6 +14700,9 @@ s390_asm_file_end (void)
 	     s390_vector_abi);
 #endif
   file_end_indicate_exec_stack ();
+
+  if (flag_split_stack)
+    file_end_indicate_split_stack ();
 }
 
 /* Return true if TYPE is a vector bool type.  */
@@ -14757,6 +14958,9 @@ s390_invalid_binary_op (int op ATTRIBUTE_UNUSED, const_tree type1, const_tree ty
 #undef TARGET_SET_UP_BY_PROLOGUE
 #define TARGET_SET_UP_BY_PROLOGUE s300_set_up_by_prologue
 
+#undef TARGET_EXTRA_LIVE_ON_ENTRY
+#define TARGET_EXTRA_LIVE_ON_ENTRY s390_live_on_entry
+
 #undef TARGET_USE_BY_PIECES_INFRASTRUCTURE_P
 #define TARGET_USE_BY_PIECES_INFRASTRUCTURE_P \
   s390_use_by_pieces_infrastructure_p
diff --git a/gcc/config/s390/s390.md b/gcc/config/s390/s390.md
index ccedead..6f0e172 100644
--- a/gcc/config/s390/s390.md
+++ b/gcc/config/s390/s390.md
@@ -114,6 +114,9 @@
    UNSPEC_SP_SET
    UNSPEC_SP_TEST
 
+   ; Split stack support
+   UNSPEC_STACK_CHECK
+
    ; Test Data Class (TDC)
    UNSPEC_TDC_INSN
 
@@ -276,6 +279,10 @@
    ; Set and get floating point control register
    UNSPECV_SFPC
    UNSPECV_EFPC
+
+   ; Split stack support
+   UNSPECV_SPLIT_STACK_CALL
+   UNSPECV_SPLIT_STACK_DATA
   ])
 
 ;;
@@ -10909,3 +10916,134 @@
   "TARGET_Z13"
   "lcbb\t%0,%1,%b2"
   [(set_attr "op_type" "VRX")])
+
+; Handle -fsplit-stack.
+
+(define_expand "split_stack_prologue"
+  [(const_int 0)]
+  ""
+{
+  s390_expand_split_stack_prologue ();
+  DONE;
+})
+
+;; If there are operand 0 bytes available on the stack, jump to
+;; operand 1.
+
+(define_expand "split_stack_space_check"
+  [(set (pc) (if_then_else
+	      (ltu (minus (reg 15)
+			  (match_operand 0 "register_operand"))
+		   (unspec [(const_int 0)] UNSPEC_STACK_CHECK))
+	      (label_ref (match_operand 1))
+	      (pc)))]
+  ""
+{
+  /* Offset from thread pointer to __private_ss.  */
+  int psso = TARGET_64BIT ? 0x38 : 0x20;
+  rtx tp = s390_get_thread_pointer ();
+  rtx guard = gen_rtx_MEM (Pmode, plus_constant (Pmode, tp, psso));
+  rtx reg = gen_reg_rtx (Pmode);
+  rtx cc;
+  if (TARGET_64BIT)
+    emit_insn (gen_subdi3 (reg, stack_pointer_rtx, operands[0]));
+  else
+    emit_insn (gen_subsi3 (reg, stack_pointer_rtx, operands[0]));
+  cc = s390_emit_compare (GT, reg, guard);
+  s390_emit_jump (operands[1], cc);
+
+  DONE;
+})
+
+;; __morestack parameter block for split stack prologue.  Parameters are:
+;; parameter block label, label to be called by __morestack, frame size,
+;; stack parameter size.
+
+(define_insn "split_stack_data"
+  [(unspec_volatile [(match_operand 0 "" "X")
+		     (match_operand 1 "" "X")
+		     (match_operand 2 "const_int_operand" "X")
+		     (match_operand 3 "const_int_operand" "X")]
+		    UNSPECV_SPLIT_STACK_DATA)]
+  "TARGET_CPU_ZARCH"
+{
+  switch_to_section (targetm.asm_out.function_rodata_section
+		 (current_function_decl));
+
+  if (TARGET_64BIT)
+    output_asm_insn (".align\t8", operands);
+  else
+    output_asm_insn (".align\t4", operands);
+  (*targetm.asm_out.internal_label) (asm_out_file, "L",
+				     CODE_LABEL_NUMBER (operands[0]));
+  if (TARGET_64BIT)
+    {
+      output_asm_insn (".quad\t%2", operands);
+      output_asm_insn (".quad\t%3", operands);
+      output_asm_insn (".quad\t%1-%0", operands);
+    }
+  else
+    {
+      output_asm_insn (".long\t%2", operands);
+      output_asm_insn (".long\t%3", operands);
+      output_asm_insn (".long\t%1-%0", operands);
+    }
+
+  switch_to_section (current_function_section ());
+  return "";
+}
+  [(set_attr "length" "0")])
+
+
+;; A jg with minimal fuss for use in split stack prologue.
+
+(define_expand "split_stack_call"
+  [(match_operand 0 "bras_sym_operand" "X")
+   (match_operand 1 "" "")]
+  "TARGET_CPU_ZARCH"
+{
+  if (TARGET_64BIT)
+    emit_jump_insn (gen_split_stack_call_di (operands[0], operands[1]));
+  else
+    emit_jump_insn (gen_split_stack_call_si (operands[0], operands[1]));
+  DONE;
+})
+
+(define_insn "split_stack_call_<mode>"
+  [(set (pc) (label_ref (match_operand 1 "" "")))
+   (set (reg:P 1) (unspec_volatile [(match_operand 0 "bras_sym_operand" "X")
+				    (reg:P 1)]
+				   UNSPECV_SPLIT_STACK_CALL))]
+  "TARGET_CPU_ZARCH"
+  "jg\t%0"
+  [(set_attr "op_type" "RIL")
+   (set_attr "type"  "branch")])
+
+;; Also a conditional one.
+
+(define_expand "split_stack_cond_call"
+  [(match_operand 0 "bras_sym_operand" "X")
+   (match_operand 1 "" "")
+   (match_operand 2 "" "")]
+  "TARGET_CPU_ZARCH"
+{
+  if (TARGET_64BIT)
+    emit_jump_insn (gen_split_stack_cond_call_di (operands[0], operands[1], operands[2]));
+  else
+    emit_jump_insn (gen_split_stack_cond_call_si (operands[0], operands[1], operands[2]));
+  DONE;
+})
+
+(define_insn "split_stack_cond_call_<mode>"
+  [(set (pc)
+	(if_then_else
+	  (match_operand 1 "" "")
+	  (label_ref (match_operand 2 "" ""))
+	  (pc)))
+   (set (reg:P 1) (unspec_volatile [(match_operand 0 "bras_sym_operand" "X")
+				    (reg:P 1)]
+				   UNSPECV_SPLIT_STACK_CALL))]
+  "TARGET_CPU_ZARCH"
+  "jg%C1\t%0"
+  [(set_attr "op_type" "RIL")
+   (set_attr "type"  "branch")])