S390: Implement 64-bit __fentry__

* Since __fentry__ is almost the same as _mcount, reuse the code by
  #including it twice with different #defines around.
* Remove LA usages - they are needed in 31-bit mode to clear the top
  bit, but in 64-bit they appear to do nothing.
* Add CFI rule for the nonstandard return register. This rule applies
  to the current function (binutils generates a new CIE - see
  gas/dw2gencfi.c:select_cie_for_fde()), so it is not necessary to put
  __fentry__ into a new file.
* Fix CFI offset for %r14.
* Add CFI rule for %r0.
* Fix unwound value of %r15 being off by 244 bytes.
* Unwinding in __fentry__@plt does not work, no plan to fix it - it
  would require asking linker to generate CFI for return address in
  %r0.  From functional perspective keeping it broken is fine, since
  the callee did not have a chance to do anything yet.  From
  convenience perspective it would be possible to enhance GDB in the
  future to treat __fentry__@plt in a special way.
* Fix whitespace.
* Fix offsets in comments, which were copied from 32-bit code.
* 32-bit version will not be implemented, since it's not compatible
  with the corresponding PLT stubs: they assume %r12 points to GOT,
  which is not the case for gcc-emitted __fentry__ stub, which runs
  before the prolog.

This patch adds the runtime support in glibc for the -mfentry
gcc feature introduced in [1] and [2].

[1] https://gcc.gnu.org/ml/gcc-patches/2018-07/msg00784.html
[2] https://gcc.gnu.org/ml/gcc-patches/2018-07/msg00912.html

ChangeLog:

	* sysdeps/s390/s390-64/Versions (__fentry__): Add.
	* sysdeps/s390/s390-64/s390x-mcount.S: Move the common
	code to s390x-mcount.h and #include it.
	* sysdeps/s390/s390-64/s390x-mcount.h: New file.
	* sysdeps/unix/sysv/linux/s390/s390-64/libc.abilist
	(__fentry__): Add.

1 files changed, 20 insertions, 57 deletions

diff --git a/sysdeps/s390/s390-64/s390x-mcount.S b/sysdeps/s390/s390-64/s390x-mcount.S
index c6b5d65e17..6c1271032b 100644
--- a/sysdeps/s390/s390-64/s390x-mcount.S
+++ b/sysdeps/s390/s390-64/s390x-mcount.S
@@ -1,6 +1,5 @@
 /* 64 bit S/390-specific implementation of profiling support.
-   Copyright (C) 2001-2018 Free Software Foundation, Inc.
-   Contributed by Martin Schwidefsky (schwidefsky@de.ibm.com)
+   Copyright (C) 2018 Free Software Foundation, Inc.
    This file is part of the GNU C Library.
 
    The GNU C Library is free software; you can redistribute it and/or
@@ -17,61 +16,25 @@
    License along with the GNU C Library; if not, see
    <http://www.gnu.org/licenses/>.  */
 
-#include <sysdep.h>
-
-/* How profiling works on 64 bit S/390:
-   On the start of each function _mcount is called with the address of a
-   data word in %r1 (initialized to 0, used for counting). The compiler
-   with the option -p generates code of the form:
-
-           STM    6,15,24(15)
-           BRAS   13,.LTN0_0
-   .LT0_0:
-   .LC13:  .long  .LP0
-           .data
-           .align 4
-   .LP0:   .long  0
-           .text
-   # function profiler
-           stg    14,4(15)
-           lg     1,.LC13-.LT0_0(13)
-           brasl  14,_mcount
-           lg     14,4(15)
-
-   The _mcount implementation now has to call __mcount_internal with the
-   address of .LP0 as first parameter and the return address as second
-   parameter. &.LP0 was loaded to %r1 and the return address is in %r14.
-   _mcount may not modify any register.  */
-
-	.globl C_SYMBOL_NAME(_mcount)
-	.type C_SYMBOL_NAME(_mcount), @function
-	cfi_startproc
-	.align ALIGNARG(4)
-C_LABEL(_mcount)
-	/* Save the caller-clobbered registers.  */
-        aghi  %r15,-224
-	cfi_adjust_cfa_offset (224)
-        stmg  %r14,%r5,160(%r15)
-	cfi_offset (r14, 0)
-	cfi_offset (r15, 8)
-        lg    %r2,232(%r15)       # callers address  = first parameter
-        la    %r2,0(%r2)          # clear bit 0
-        la    %r3,0(%r14)         # callees address  = second parameter
-
-#ifdef PIC
-	brasl %r14,__mcount_internal@PLT
-#else
-	brasl %r14,__mcount_internal
-#endif
-
-	/* Pop the saved registers.  Please note that `mcount' has no
-	   return value.  */
-	lmg   %r14,%r5,160(%r15)
-        aghi   %r15,224
-	cfi_adjust_cfa_offset (-224)
-        br    %r14
-	cfi_endproc
-	ASM_SIZE_DIRECTIVE(C_SYMBOL_NAME(_mcount))
+#define MCOUNT_SYMBOL _mcount
+#define MCOUNT_CALLER_OFF 232	/* Pushed by the _mcount stub.  */
+#define MCOUNT_CALLEE_REG 14	/* Normal calling convention.  */
+#define MCOUNT_RETURN_REG 14
+#include "s390x-mcount.h"
+#undef MCOUNT_SYMBOL
+#undef MCOUNT_CALLER_OFF
+#undef MCOUNT_CALLEE_REG
+#undef MCOUNT_RETURN_REG
+
+#define MCOUNT_SYMBOL __fentry__
+#define MCOUNT_CALLER_OFF 160	/* Saved %r14.  */
+#define MCOUNT_CALLEE_REG 0	/* __fentry__ calling convention.  */
+#define MCOUNT_RETURN_REG 1	/* Cannot return via %r0.  */
+#include "s390x-mcount.h"
+#undef MCOUNT_SYMBOL
+#undef MCOUNT_CALLER_OFF
+#undef MCOUNT_CALLEE_REG
+#undef MCOUNT_RETURN_REG
 
 #undef mcount
 weak_alias (_mcount, mcount)