Libatomic: AArch64: Convert all lse128 assembly to .insn directives

Given the lack of support for the LSE128 instructions in all but the
the most up-to-date version of Binutils (2.42), having the build-time
test for assembler support for these instructions often leads to the
building of Libatomic without support for LSE128-dependent atomic
function implementations.  This ultimately leads to different people
having different versions of Libatomic on their machines, depending on
which assembler was available at compilation time.

Furthermore, the conditional inclusion of these atomic function
implementations predicated on assembler support leads to a series of
`#if HAVE_FEAT_LSE128' guards scattered throughout the codebase and
the need for a series of aliases when the feature flag evaluates
to false.  The preprocessor macro guards, together with the
conditional aliasing leads to code that is cumbersome to understand
and maintain.

Both of the issues highlighted above will only get worse with the
coming support for LRCPC3 atomics which under the current scheme will
also require build-time checks.

Consequently, a better option for both consistency across builds and
code cleanness is to make recourse to the `.inst' directive.  By
replacing all novel assembly instructions for their hexadecimal
representation within `.inst's, we ensure that the Libatomic code is
both considerably cleaner and all machines build the same binary,
irrespective of binutils version available at compile time.

This patch therefore removes all configure checks for LSE128-support
in the assembler and all the guards and aliases that were associated
with `HAVE_FEAT_LSE128'

libatomic/ChangeLog:

	* acinclude.m4 (LIBAT_TEST_FEAT_AARCH64_LSE128): Delete.
	* auto-config.h.in (HAVE_FEAT_LSE128): Likewise
	* config/linux/aarch64/atomic_16.S: Replace all LSE128
	instructions with equivalent `.inst' directives.
	(HAVE_FEAT_LSE128): Remove all references.
	* configure: Regenerate.
	* configure.ac: Remove call to LIBAT_TEST_FEAT_AARCH64_LSE128.

5 files changed, 32 insertions, 111 deletions

diff --git a/libatomic/acinclude.m4 b/libatomic/acinclude.m4
index 6d2e0b1..f35ab5b 100644
--- a/libatomic/acinclude.m4
+++ b/libatomic/acinclude.m4
@@ -84,24 +84,6 @@ AC_DEFUN([LIBAT_TEST_ATOMIC_BUILTIN],[
 ])
 
 dnl
-dnl Test if the host assembler supports armv9.4-a LSE128 isns.
-dnl
-AC_DEFUN([LIBAT_TEST_FEAT_AARCH64_LSE128],[
-  AC_CACHE_CHECK([for armv9.4-a LSE128 insn support],
-    [libat_cv_have_feat_lse128],[
-    AC_LANG_CONFTEST([AC_LANG_PROGRAM([],[asm(".arch armv9-a+lse128")])])
-    if AC_TRY_EVAL(ac_compile); then
-      eval libat_cv_have_feat_lse128=yes
-    else
-      eval libat_cv_have_feat_lse128=no
-    fi
-    rm -f conftest*
-  ])
-  LIBAT_DEFINE_YESNO([HAVE_FEAT_LSE128], [$libat_cv_have_feat_lse128],
-	[Have LSE128 support for 16 byte integers.])
-])
-
-dnl
 dnl Test if we have __atomic_load and __atomic_store for mode $1, size $2
 dnl
 AC_DEFUN([LIBAT_HAVE_ATOMIC_LOADSTORE],[
diff --git a/libatomic/auto-config.h.in b/libatomic/auto-config.h.in
index 7c78933..ab3424a 100644
--- a/libatomic/auto-config.h.in
+++ b/libatomic/auto-config.h.in
@@ -105,9 +105,6 @@
 /* Define to 1 if you have the <dlfcn.h> header file. */
 #undef HAVE_DLFCN_H
 
-/* Have LSE128 support for 16 byte integers. */
-#undef HAVE_FEAT_LSE128
-
 /* Define to 1 if you have the <fenv.h> header file. */
 #undef HAVE_FENV_H
 
diff --git a/libatomic/config/linux/aarch64/atomic_16.S b/libatomic/config/linux/aarch64/atomic_16.S
index b63e97a..d6e71ba 100644
--- a/libatomic/config/linux/aarch64/atomic_16.S
+++ b/libatomic/config/linux/aarch64/atomic_16.S
@@ -40,18 +40,9 @@
 
 #include "auto-config.h"
 
-#if !HAVE_IFUNC
-# undef HAVE_FEAT_LSE128
-# define HAVE_FEAT_LSE128 0
-#endif
-
 #define HAVE_FEAT_LSE2	HAVE_IFUNC
 
-#if HAVE_FEAT_LSE128
-	.arch	armv9-a+lse128
-#else
 	.arch	armv8-a+lse
-#endif
 
 #define LSE128(NAME)	libat_##NAME##_i1
 #define LSE2(NAME)	libat_##NAME##_i2
@@ -226,7 +217,6 @@ ENTRY (exchange_16)
 END (exchange_16)
 
 
-#if HAVE_FEAT_LSE128
 ENTRY_FEAT (exchange_16, LSE128)
 	mov	tmp0, x0
 	mov	res0, in0
@@ -234,21 +224,23 @@ ENTRY_FEAT (exchange_16, LSE128)
 	cbnz	w4, 1f
 
 	/* RELAXED.  */
-	swpp	res0, res1, [tmp0]
+	/* swpp res0, res1, [tmp0]  */
+	.inst	0x192180c0
 	ret
 1:
 	cmp	w4, ACQUIRE
 	b.hi	2f
 
 	/* ACQUIRE/CONSUME.  */
-	swppa	res0, res1, [tmp0]
+	/* swppa res0, res1, [tmp0]  */
+	.inst	0x19a180c0
 	ret
 
 	/* RELEASE/ACQ_REL/SEQ_CST.  */
-2:	swppal	res0, res1, [tmp0]
+2:	/* swppal res0, res1, [tmp0]  */
+	.inst	0x19e180c0
 	ret
 END_FEAT (exchange_16, LSE128)
-#endif
 
 
 ENTRY (compare_exchange_16)
@@ -446,7 +438,6 @@ ENTRY (fetch_or_16)
 END (fetch_or_16)
 
 
-#if HAVE_FEAT_LSE128
 ENTRY_FEAT (fetch_or_16, LSE128)
 	mov	tmp0, x0
 	mov	res0, in0
@@ -454,21 +445,23 @@ ENTRY_FEAT (fetch_or_16, LSE128)
 	cbnz	w4, 1f
 
 	/* RELAXED.  */
-	ldsetp	res0, res1, [tmp0]
+	/* ldsetp res0, res1, [tmp0]  */
+	.inst	0x192130c0
 	ret
 1:
 	cmp	w4, ACQUIRE
 	b.hi	2f
 
 	/* ACQUIRE/CONSUME.  */
-	ldsetpa	res0, res1, [tmp0]
+	/* ldsetpa res0, res1, [tmp0]  */
+	.inst	0x19a130c0
 	ret
 
 	/* RELEASE/ACQ_REL/SEQ_CST.  */
-2:	ldsetpal	res0, res1, [tmp0]
+2:	/* ldsetpal res0, res1, [tmp0]  */
+	.inst	0x19e130c0
 	ret
 END_FEAT (fetch_or_16, LSE128)
-#endif
 
 
 ENTRY (or_fetch_16)
@@ -493,14 +486,14 @@ ENTRY (or_fetch_16)
 END (or_fetch_16)
 
 
-#if HAVE_FEAT_LSE128
 ENTRY_FEAT (or_fetch_16, LSE128)
 	cbnz	w4, 1f
 	mov	tmp0, in0
 	mov	tmp1, in1
 
 	/* RELAXED.  */
-	ldsetp	in0, in1, [x0]
+	/* ldsetp in0, in1, [x0]  */
+	.inst	0x19233002
 	orr	res0, in0, tmp0
 	orr	res1, in1, tmp1
 	ret
@@ -509,18 +502,19 @@ ENTRY_FEAT (or_fetch_16, LSE128)
 	b.hi	2f
 
 	/* ACQUIRE/CONSUME.  */
-	ldsetpa	in0, in1, [x0]
+	/* ldsetpa in0, in1, [x0]  */
+	.inst	0x19a33002
 	orr	res0, in0, tmp0
 	orr	res1, in1, tmp1
 	ret
 
 	/* RELEASE/ACQ_REL/SEQ_CST.  */
-2:	ldsetpal	in0, in1, [x0]
+2:	/* ldsetpal in0, in1, [x0]  */
+	.inst	0x19e33002
 	orr	res0, in0, tmp0
 	orr	res1, in1, tmp1
 	ret
 END_FEAT (or_fetch_16, LSE128)
-#endif
 
 
 ENTRY (fetch_and_16)
@@ -545,7 +539,6 @@ ENTRY (fetch_and_16)
 END (fetch_and_16)
 
 
-#if HAVE_FEAT_LSE128
 ENTRY_FEAT (fetch_and_16, LSE128)
 	mov	tmp0, x0
 	mvn	res0, in0
@@ -553,7 +546,8 @@ ENTRY_FEAT (fetch_and_16, LSE128)
 	cbnz	w4, 1f
 
 	/* RELAXED.  */
-	ldclrp	res0, res1, [tmp0]
+	/* ldclrp res0, res1, [tmp0]  */
+	.inst	0x192110c0
 	ret
 
 1:
@@ -561,14 +555,15 @@ ENTRY_FEAT (fetch_and_16, LSE128)
 	b.hi	2f
 
 	/* ACQUIRE/CONSUME.  */
-	ldclrpa res0, res1, [tmp0]
+	/* ldclrpa res0, res1, [tmp0]  */
+	.inst	0x19a110c0
 	ret
 
 	/* RELEASE/ACQ_REL/SEQ_CST.  */
-2:	ldclrpal	res0, res1, [tmp0]
+2:	/* ldclrpal res0, res1, [tmp0]  */
+	.inst	0x19e110c0
 	ret
 END_FEAT (fetch_and_16, LSE128)
-#endif
 
 
 ENTRY (and_fetch_16)
@@ -593,14 +588,14 @@ ENTRY (and_fetch_16)
 END (and_fetch_16)
 
 
-#if HAVE_FEAT_LSE128
 ENTRY_FEAT (and_fetch_16, LSE128)
 	mvn	tmp0, in0
 	mvn	tmp0, in1
 	cbnz	w4, 1f
 
 	/* RELAXED.  */
-	ldclrp	tmp0, tmp1, [x0]
+	/* ldclrp tmp0, tmp1, [x0]  */
+	.inst	0x19271006
 	and	res0, tmp0, in0
 	and	res1, tmp1, in1
 	ret
@@ -610,18 +605,19 @@ ENTRY_FEAT (and_fetch_16, LSE128)
 	b.hi	2f
 
 	/* ACQUIRE/CONSUME.  */
-	ldclrpa tmp0, tmp1, [x0]
+	/* ldclrpa tmp0, tmp1, [x0]  */
+	.inst	0x19a71006
 	and	res0, tmp0, in0
 	and	res1, tmp1, in1
 	ret
 
 	/* RELEASE/ACQ_REL/SEQ_CST.  */
-2:	ldclrpal	tmp0, tmp1, [x5]
+2:	/* ldclrpal	tmp0, tmp1, [x5]  */
+	.inst	0x19e710a6
 	and	res0, tmp0, in0
 	and	res1, tmp1, in1
 	ret
 END_FEAT (and_fetch_16, LSE128)
-#endif
 
 
 ENTRY (fetch_xor_16)
@@ -729,16 +725,9 @@ ENTRY (test_and_set_16)
 END (test_and_set_16)
 
 
-/* Alias entry points which are the same in LSE2 and LSE128.  */
-
 #if HAVE_IFUNC
-# if !HAVE_FEAT_LSE128
-ALIAS (exchange_16, LSE128, LSE2)
-ALIAS (fetch_or_16, LSE128, LSE2)
-ALIAS (fetch_and_16, LSE128, LSE2)
-ALIAS (or_fetch_16, LSE128, LSE2)
-ALIAS (and_fetch_16, LSE128, LSE2)
-# endif
+
+/* Alias entry points which are the same in LSE2 and LSE128.  */
 ALIAS (load_16, LSE128, LSE2)
 ALIAS (store_16, LSE128, LSE2)
 ALIAS (compare_exchange_16, LSE128, LSE2)
@@ -753,7 +742,6 @@ ALIAS (nand_fetch_16, LSE128, LSE2)
 ALIAS (test_and_set_16, LSE128, LSE2)
 
 /* Alias entry points which are the same in baseline and LSE2.  */
-
 ALIAS (exchange_16, LSE2, CORE)
 ALIAS (fetch_add_16, LSE2, CORE)
 ALIAS (add_fetch_16, LSE2, CORE)
diff --git a/libatomic/configure b/libatomic/configure
index 32cb3ec..d579bab 100755
--- a/libatomic/configure
+++ b/libatomic/configure
@@ -14697,49 +14697,6 @@ _ACEOF
 
 
 
-# Check for target-specific assembly-level support for atomic operations.
-
-  { $as_echo "$as_me:${as_lineno-$LINENO}: checking for armv9.4-a LSE128 insn support" >&5
-$as_echo_n "checking for armv9.4-a LSE128 insn support... " >&6; }
-if ${libat_cv_have_feat_lse128+:} false; then :
-  $as_echo_n "(cached) " >&6
-else
-
-    cat confdefs.h - <<_ACEOF >conftest.$ac_ext
-/* end confdefs.h.  */
-
-int
-main ()
-{
-asm(".arch armv9-a+lse128")
-  ;
-  return 0;
-}
-_ACEOF
-    if { { eval echo "\"\$as_me\":${as_lineno-$LINENO}: \"$ac_compile\""; } >&5
-  (eval $ac_compile) 2>&5
-  ac_status=$?
-  $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5
-  test $ac_status = 0; }; then
-      eval libat_cv_have_feat_lse128=yes
-    else
-      eval libat_cv_have_feat_lse128=no
-    fi
-    rm -f conftest*
-
-fi
-{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $libat_cv_have_feat_lse128" >&5
-$as_echo "$libat_cv_have_feat_lse128" >&6; }
-
-  yesno=`echo $libat_cv_have_feat_lse128 | tr 'yesno' '1  0 '`
-
-cat >>confdefs.h <<_ACEOF
-#define HAVE_FEAT_LSE128 $yesno
-_ACEOF
-
-
-
-
  { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether byte ordering is bigendian" >&5
 $as_echo_n "checking whether byte ordering is bigendian... " >&6; }
 if ${ac_cv_c_bigendian+:} false; then :
diff --git a/libatomic/configure.ac b/libatomic/configure.ac
index 85824fa..32a2cdb 100644
--- a/libatomic/configure.ac
+++ b/libatomic/configure.ac
@@ -206,9 +206,6 @@ LIBAT_FORALL_MODES([LIBAT_HAVE_ATOMIC_CAS])
 LIBAT_FORALL_MODES([LIBAT_HAVE_ATOMIC_FETCH_ADD])
 LIBAT_FORALL_MODES([LIBAT_HAVE_ATOMIC_FETCH_OP])
 
-# Check for target-specific assembly-level support for atomic operations.
-LIBAT_TEST_FEAT_AARCH64_LSE128()
-
 AC_C_BIGENDIAN
 # I don't like the default behaviour of WORDS_BIGENDIAN undefined for LE.
 AH_BOTTOM(