Re: [PATCH 1/6]: Ping: Merge from Stack Branch - New data in function.h

[Jan Hubicka <jh at suse dot cz>]

> Jan, 
> 
> Can you please review for mainline?
> 
> http://gcc.gnu.org/ml/gcc-patches/2008-04/msg01019.html
Hi,
I can not really approve the generic bits of the patch, so RTL
maintainer will have to take a look.
The new placement in rtl_data seems fine to me. Do you have any idea how
often the code gets false positives (ie that stack_realign_needed is set
and stack_realign_really is not).
If I understand correctly, then we end up wasting pointer for argument
pointer (pseudo) register, but we don't actually emit the alignment prologue,
right?

The earlier attempt by Bernd to solve same problem
http://gcc.gnu.org/ml/gcc-patches/2002-05/msg02282.html
got around via reload's ellimination, but as I understand its major
problem was fixing esi and thus failing in combination with asm
statements and stringops...

Honza
> 
> 2008-04-28  Joey Ye  <joey.ye@intel.com>
> 	    H.J. Lu  <hongjiu.lu@intel.com>
> 
> 	* function.h (function): Move  
> 	stack_realign_needed, preferred_stack_boundary
> 	to rtl_data.
> 	(rtl_data): Add new field drap_reg, stack_alignment_estimated,
> 	stack_realign_really, need_drap, save_param_ptr_reg,
> 	stack_realign_processed, stack_realign_finalized and 
> 	stack_realign_used, stack_realign_needed.
> 	(stack_realign_fp): New macro.
> 	(stack_realign_drap): Likewise.
> 
> 	* flags.h (frame_pointer_needed): Removed.
> 	* final.c (frame_pointer_needed): Likewise.
> 
> Index: function.h
> ===================================================================
> --- function.h	(revision 134716)
> +++ function.h	(working copy)
> @@ -306,6 +306,9 @@ struct rtl_data GTY(())
>       needed by inner routines.  */
>    rtx x_arg_pointer_save_area;
>  
> +  /* Dynamic Realign Argument Pointer used for realigning stack.  */
> +  rtx drap_reg;
> +
>    /* Offset to end of allocated area of stack frame.
>       If stack grows down, this is the address of the last stack slot
> allocated.
>       If stack grows up, this is the address for the next slot.  */
> @@ -323,12 +326,19 @@ struct rtl_data GTY(())
>    /* Current nesting level for temporaries.  */
>    int x_temp_slot_level;
>  
> -  /* The largest alignment of slot allocated on the stack.  */
> +  /* The largest alignment needed on the stack, including requirement
> +     for outgoing stack alignment.  */
>    unsigned int stack_alignment_needed;
>  
>    /* Preferred alignment of the end of stack frame.  */
>    unsigned int preferred_stack_boundary;
>  
> +  /* The largest alignment of slot allocated on the stack.  */
> +  unsigned int stack_alignment_used;
> +
> +  /* The estimated stack alignment.  */
> +  unsigned int stack_alignment_estimated;
> +
>    /* For reorg.  */
>  
>    /* If some insns can be deferred to the delay slots of the epilogue,
> the
> @@ -387,6 +397,38 @@ struct rtl_data GTY(())
>  
>    /* Nonzero if code to initialize arg_pointer_save_area has been
> emitted.  */
>    bool arg_pointer_save_area_init;
> +
> +  /* Nonzero if current function must be given a frame pointer.
> +     Set in global.c if anything is allocated on the stack there.  */
> +  bool need_frame_pointer;
> +
> +  /* Nonzero if need_frame_pointer has been set.  */
> +  bool need_frame_pointer_set;
> +
> +  /* Nonzero if, by estimation, current function stack needs
> realignment. */
> +  bool stack_realign_needed;
> +
> +  /* Nonzero if function stack realignment is really needed. This flag
> +     will be set after reload if by then criteria of stack realignment
> +     is still true. Its value may be contridition to
> stack_realign_needed
> +     since the latter was set before reload. This flag is more accurate
> +     than stack_realign_needed so prologue/epilogue should be generated
> +     according to both flags  */
> +  bool stack_realign_really;
> +
> +  /* Nonzero if function being compiled needs dynamic realigned
> +     argument pointer (drap) if stack needs realigning.  */
> +  bool need_drap;
> +
> +  /* Nonzero if current function needs to save/restore parameter
> +     pointer register in prolog, because it is a callee save reg.  */
> +  bool save_param_ptr_reg;
> +
> +  /* Nonzero if function stack realignment estimatoin is done.  */
> +  bool stack_realign_processed;
> +
> +  /* Nonzero if function stack realignment has been finalized.  */
> +  bool stack_realign_finalized;
>  };
>  
>  #define return_label (crtl->x_return_label)
> @@ -400,6 +442,9 @@ struct rtl_data GTY(())
>  #define avail_temp_slots (crtl->x_avail_temp_slots)
>  #define temp_slot_level (crtl->x_temp_slot_level)
>  #define nonlocal_goto_handler_labels
> (crtl->x_nonlocal_goto_handler_labels)
> +#define frame_pointer_needed (crtl->need_frame_pointer)
> +#define stack_realign_fp (crtl->stack_realign_needed &&
> !crtl->need_drap)
> +#define stack_realign_drap (crtl->stack_realign_needed &&
> crtl->need_drap)
>  
>  extern GTY(()) struct rtl_data x_rtl;
>  
> Index: flags.h
> ===================================================================
> --- flags.h	(revision 134716)
> +++ flags.h	(working copy)
> @@ -223,12 +223,6 @@ extern int flag_dump_rtl_in_asm;
>  
>  /* Other basic status info about current function.  */
>  
> -/* Nonzero means current function must be given a frame pointer.
> -   Set in stmt.c if anything is allocated on the stack there.
> -   Set in reload1.c if anything is allocated on the stack there.  */
> -
> -extern int frame_pointer_needed;
> -
>  /* Nonzero if subexpressions must be evaluated from left-to-right.  */
>  extern int flag_evaluation_order;
>  
> Index: final.c
> ===================================================================
> --- final.c	(revision 134716)
> +++ final.c	(working copy)
> @@ -178,12 +178,6 @@ CC_STATUS cc_status;
>  CC_STATUS cc_prev_status;
>  #endif
>  
> -/* Nonzero means current function must be given a frame pointer.
> -   Initialized in function.c to 0.  Set only in reload1.c as per
> -   the needs of the function.  */
> -
> -int frame_pointer_needed;
> -
>  /* Number of unmatched NOTE_INSN_BLOCK_BEG notes we have seen.  */
>  
>  static int block_depth;