------- Comment #10 from jh at suse dot cz 2005-10-18 18:17 -------
Subject: Re: ix86 prologue clobbers memory when it shouldn't
>
>
> ------- Comment #9 from hjl at lucon dot org 2005-10-18 17:50 -------
> We only run into the problem with red zone enabled, which is x86-64. We have
> 2 issues:
>
> 1. When prologue uses mov, memory shouldn't be clobbered. But
> ix86_expand_prologue calls pro_epilogue_adjust_stack which clobbers
> memory.
> 2. We convert stack pointer subtractions to push even when memory isn't
> clobbered with patterns like
>
> ;; Convert esp subtractions to push.
> (define_peephole2
> [(match_scratch:SI 0 "r")
> (parallel [(set (reg:SI SP_REG) (plus:SI (reg:SI SP_REG) (const_int
> -4)))
> (clobber (reg:CC FLAGS_REG))])]
> "optimize_size || !TARGET_SUB_ESP_4"
> [(clobber (match_dup 0))
> (set (mem:SI (pre_dec:SI (reg:SI SP_REG))) (match_dup 0))])
>
> I don't think we can do that since push will clobber memory.
Without red zone this is safe, but I see we do the conversion on 64bit
too that definitly is unsafe. What about this patch?
Index: i386.md
===================================================================
RCS file: /cvs/gcc/gcc/gcc/config/i386/i386.md,v
retrieving revision 1.655
diff -c -3 -p -r1.655 i386.md
*** i386.md 24 Sep 2005 15:47:57 -0000 1.655
--- i386.md 18 Oct 2005 18:16:00 -0000
***************
*** 19306,19316 ****
(clobber (mem:BLK (scratch)))])])
;; Convert esp subtractions to push.
(define_peephole2
[(match_scratch:SI 0 "r")
(parallel [(set (reg:SI SP_REG) (plus:SI (reg:SI SP_REG) (const_int -4)))
(clobber (reg:CC FLAGS_REG))])]
! "optimize_size || !TARGET_SUB_ESP_4"
[(clobber (match_dup 0))
(set (mem:SI (pre_dec:SI (reg:SI SP_REG))) (match_dup 0))])
--- 19306,19320 ----
(clobber (mem:BLK (scratch)))])])
;; Convert esp subtractions to push.
+ ;; This conversion is safe only under assumption that unallocated stack is
+ ;; implicitly clobbered as specified by 32bit ABI (for signal handlers and
such).
+ ;; This is not valid with red zone, but we can work harder and enable the
+ ;; optimization for functions that are not using it.
(define_peephole2
[(match_scratch:SI 0 "r")
(parallel [(set (reg:SI SP_REG) (plus:SI (reg:SI SP_REG) (const_int -4)))
(clobber (reg:CC FLAGS_REG))])]
! "(optimize_size || !TARGET_SUB_ESP_4) && !TARGET_RED_ZONE"
[(clobber (match_dup 0))
(set (mem:SI (pre_dec:SI (reg:SI SP_REG))) (match_dup 0))])
***************
*** 19318,19324 ****
[(match_scratch:SI 0 "r")
(parallel [(set (reg:SI SP_REG) (plus:SI (reg:SI SP_REG) (const_int -8)))
(clobber (reg:CC FLAGS_REG))])]
! "optimize_size || !TARGET_SUB_ESP_8"
[(clobber (match_dup 0))
(set (mem:SI (pre_dec:SI (reg:SI SP_REG))) (match_dup 0))
(set (mem:SI (pre_dec:SI (reg:SI SP_REG))) (match_dup 0))])
--- 19322,19328 ----
[(match_scratch:SI 0 "r")
(parallel [(set (reg:SI SP_REG) (plus:SI (reg:SI SP_REG) (const_int -8)))
(clobber (reg:CC FLAGS_REG))])]
! "(optimize_size || !TARGET_SUB_ESP_8) && !TARGET_RED_ZONE"
[(clobber (match_dup 0))
(set (mem:SI (pre_dec:SI (reg:SI SP_REG))) (match_dup 0))
(set (mem:SI (pre_dec:SI (reg:SI SP_REG))) (match_dup 0))])
***************
*** 19438,19448 ****
(clobber (mem:BLK (scratch)))])])
;; Convert esp subtractions to push.
(define_peephole2
[(match_scratch:DI 0 "r")
(parallel [(set (reg:DI SP_REG) (plus:DI (reg:DI SP_REG) (const_int -8)))
(clobber (reg:CC FLAGS_REG))])]
! "optimize_size || !TARGET_SUB_ESP_4"
[(clobber (match_dup 0))
(set (mem:DI (pre_dec:DI (reg:DI SP_REG))) (match_dup 0))])
--- 19442,19456 ----
(clobber (mem:BLK (scratch)))])])
;; Convert esp subtractions to push.
+ ;; This conversion is safe only under assumption that unallocated stack is
+ ;; implicitly clobbered as specified by 32bit ABI (for signal handlers and
such).
+ ;; This is not valid with red zone, but we can work harder and enable the
+ ;; optimization for functions that are not using it.
(define_peephole2
[(match_scratch:DI 0 "r")
(parallel [(set (reg:DI SP_REG) (plus:DI (reg:DI SP_REG) (const_int -8)))
(clobber (reg:CC FLAGS_REG))])]
! "(optimize_size || !TARGET_SUB_ESP_4) && !TARGET_RED_ZONE"
[(clobber (match_dup 0))
(set (mem:DI (pre_dec:DI (reg:DI SP_REG))) (match_dup 0))])
***************
*** 19450,19456 ****
[(match_scratch:DI 0 "r")
(parallel [(set (reg:DI SP_REG) (plus:DI (reg:DI SP_REG) (const_int -16)))
(clobber (reg:CC FLAGS_REG))])]
! "optimize_size || !TARGET_SUB_ESP_8"
[(clobber (match_dup 0))
(set (mem:DI (pre_dec:DI (reg:DI SP_REG))) (match_dup 0))
(set (mem:DI (pre_dec:DI (reg:DI SP_REG))) (match_dup 0))])
--- 19458,19464 ----
[(match_scratch:DI 0 "r")
(parallel [(set (reg:DI SP_REG) (plus:DI (reg:DI SP_REG) (const_int -16)))
(clobber (reg:CC FLAGS_REG))])]
! "(optimize_size || !TARGET_SUB_ESP_8) && !TARGET_RED_ZONE"
[(clobber (match_dup 0))
(set (mem:DI (pre_dec:DI (reg:DI SP_REG))) (match_dup 0))
(set (mem:DI (pre_dec:DI (reg:DI SP_REG))) (match_dup 0))])
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=24419
