Save and restore AVX-512 zmm registers to x86-64 ld.so

AVX-512 ISA adds 512-bit zmm registers.  This patch updates
_dl_runtime_profile to pass zmm registers to run-time audit. It also
changes _dl_x86_64_save_sse and _dl_x86_64_restore_sse to upport zmm
registers, which are called when only when RTLD_PREPARE_FOREIGN_CALL
is used.  Its performance impact is minimum.

	* config.h.in (HAVE_AVX512_SUPPORT): New #undef.
	(HAVE_AVX512_ASM_SUPPORT): Likewise.
	* sysdeps/x86_64/bits/link.h (La_x86_64_zmm): New.
	(La_x86_64_vector): Add zmm.
	* sysdeps/x86_64/Makefile (tests): Add tst-audit10.
	(modules-names): Add tst-auditmod10a and tst-auditmod10b.
	($(objpfx)tst-audit10): New target.
	($(objpfx)tst-audit10.out): Likewise.
	(tst-audit10-ENV): New.
	(AVX512-CFLAGS): Likewise.
	(CFLAGS-tst-audit10.c): Likewise.
	(CFLAGS-tst-auditmod10a.c): Likewise.
	(CFLAGS-tst-auditmod10b.c): Likewise.
	* sysdeps/x86_64/configure.ac: Set config-cflags-avx512,
	HAVE_AVX512_SUPPORT and HAVE_AVX512_ASM_SUPPORT.
	* sysdeps/x86_64/configure: Regenerated.
	* sysdeps/x86_64/dl-trampoline.S (_dl_runtime_profile): Add
	AVX-512 zmm register support.
	(_dl_x86_64_save_sse): Likewise.
	(_dl_x86_64_restore_sse): Likewise.
	* sysdeps/x86_64/dl-trampoline.h: Updated to support different
	size vector registers.
	* sysdeps/x86_64/link-defines.sym (YMM_SIZE): New.
	(ZMM_SIZE): Likewise.
	* sysdeps/x86_64/tst-audit10.c: New file.
	* sysdeps/x86_64/tst-auditmod10a.c: Likewise.
	* sysdeps/x86_64/tst-auditmod10b.c: Likewise.

ChangeLog

@@ -1,3 +1,33 @@
+2014-03-13  Igor Zamyatin  <igor.zamyatin@intel.com>
+
+	* config.h.in (HAVE_AVX512_SUPPORT): New #undef.
+	(HAVE_AVX512_ASM_SUPPORT): Likewise.
+	* sysdeps/x86_64/bits/link.h (La_x86_64_zmm): New.
+	(La_x86_64_vector): Add zmm.
+	* sysdeps/x86_64/Makefile (tests): Add tst-audit10.
+	(modules-names): Add tst-auditmod10a and tst-auditmod10b.
+	($(objpfx)tst-audit10): New target.
+	($(objpfx)tst-audit10.out): Likewise.
+	(tst-audit10-ENV): New.
+	(AVX512-CFLAGS): Likewise.
+	(CFLAGS-tst-audit10.c): Likewise.
+	(CFLAGS-tst-auditmod10a.c): Likewise.
+	(CFLAGS-tst-auditmod10b.c): Likewise.
+	* sysdeps/x86_64/configure.ac: Set config-cflags-avx512,
+	HAVE_AVX512_SUPPORT and HAVE_AVX512_ASM_SUPPORT.
+	* sysdeps/x86_64/configure: Regenerated.
+	* sysdeps/x86_64/dl-trampoline.S (_dl_runtime_profile): Add
+	AVX-512 zmm register support.
+	(_dl_x86_64_save_sse): Likewise.
+	(_dl_x86_64_restore_sse): Likewise.
+	* sysdeps/x86_64/dl-trampoline.h: Updated to support different
+	size vector registers.
+	* sysdeps/x86_64/link-defines.sym (YMM_SIZE): New.
+	(ZMM_SIZE): Likewise.
+	* sysdeps/x86_64/tst-audit10.c: New file.
+	* sysdeps/x86_64/tst-auditmod10a.c: Likewise.
+	* sysdeps/x86_64/tst-auditmod10b.c: Likewise.
+
 2014-03-13  Roland McGrath  <roland@hack.frob.com>
 
 	* configure.ac (HAVE_EHDR_START): New check.

config.h.in

@@ -98,6 +98,12 @@
 /* Define if gcc supports VEX encoding.  */
 #undef	HAVE_SSE2AVX_SUPPORT
 
+/* Define if compiler supports AVX512.  */
+#undef  HAVE_AVX512_SUPPORT
+
+/* Define if assembler supports AVX512.  */
+#undef  HAVE_AVX512_ASM_SUPPORT
+
 /* Define if gcc supports FMA4.  */
 #undef	HAVE_FMA4_SUPPORT
 

sysdeps/x86/bits/link.h

@@ -66,6 +66,8 @@ __END_DECLS
 typedef float La_x86_64_xmm __attribute__ ((__vector_size__ (16)));
 typedef float La_x86_64_ymm
     __attribute__ ((__vector_size__ (32), __aligned__ (16)));
+typedef double La_x86_64_zmm
+    __attribute__ ((__vector_size__ (64), __aligned__ (16)));
 # else
 typedef float La_x86_64_xmm __attribute__ ((__mode__ (__V4SF__)));
 # endif
@@ -74,6 +76,7 @@ typedef union
 {
 # if __GNUC_PREREQ (4,0)
   La_x86_64_ymm ymm[2];
+  La_x86_64_zmm zmm[1];
 # endif
   La_x86_64_xmm xmm[4];
 } La_x86_64_vector __attribute__ ((__aligned__ (16)));

sysdeps/x86_64/Makefile

@@ -38,15 +38,16 @@ tests-pie += $(quad-pie-test)
 $(objpfx)tst-quad1pie: $(objpfx)tst-quadmod1pie.o
 $(objpfx)tst-quad2pie: $(objpfx)tst-quadmod2pie.o
 
-tests += tst-audit3 tst-audit4 tst-audit5
+tests += tst-audit3 tst-audit4 tst-audit5 tst-audit10
 ifeq (yes,$(config-cflags-avx))
 tests += tst-audit6 tst-audit7
 endif
 modules-names += tst-auditmod3a tst-auditmod3b \
 		tst-auditmod4a tst-auditmod4b \
 		tst-auditmod5a tst-auditmod5b \
 		tst-auditmod6a tst-auditmod6b tst-auditmod6c \
-		tst-auditmod7a tst-auditmod7b
+		tst-auditmod7a tst-auditmod7b \
+		tst-auditmod10a tst-auditmod10b
 
 $(objpfx)tst-audit3: $(objpfx)tst-auditmod3a.so
 $(objpfx)tst-audit3.out: $(objpfx)tst-auditmod3b.so
@@ -69,6 +70,10 @@ $(objpfx)tst-audit7: $(objpfx)tst-auditmod7a.so
 $(objpfx)tst-audit7.out: $(objpfx)tst-auditmod7b.so
 tst-audit7-ENV = LD_AUDIT=$(objpfx)tst-auditmod7b.so
 
+$(objpfx)tst-audit10: $(objpfx)tst-auditmod10a.so
+$(objpfx)tst-audit10.out: $(objpfx)tst-auditmod10b.so
+tst-audit10-ENV = LD_AUDIT=$(objpfx)tst-auditmod10b.so
+
 ifeq (yes,$(config-cflags-avx))
 AVX-CFLAGS=-mavx
 ifeq (yes,$(config-cflags-novzeroupper))
@@ -81,6 +86,12 @@ CFLAGS-tst-auditmod6b.c += $(AVX-CFLAGS)
 CFLAGS-tst-auditmod6c.c += $(AVX-CFLAGS)
 CFLAGS-tst-auditmod7b.c += $(AVX-CFLAGS)
 endif
+ifeq (yes,$(config-cflags-avx512))
+AVX512-CFLAGS = -mavx512f
+CFLAGS-tst-audit10.c += $(AVX512-CFLAGS)
+CFLAGS-tst-auditmod10a.c += $(AVX512-CFLAGS)
+CFLAGS-tst-auditmod10b.c += $(AVX512-CFLAGS)
+endif
 endif
 
 ifeq ($(subdir),csu)

sysdeps/x86_64/configure

@@ -95,6 +95,59 @@ fi
 config_vars="$config_vars
 config-cflags-avx = $libc_cv_cc_avx"
 
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for AVX512 support" >&5
+$as_echo_n "checking for AVX512 support... " >&6; }
+if ${libc_cv_cc_avx512+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  if { ac_try='${CC-cc} -mavx512f -xc /dev/null -S -o /dev/null'
+  { { eval echo "\"\$as_me\":${as_lineno-$LINENO}: \"$ac_try\""; } >&5
+  (eval $ac_try) 2>&5
+  ac_status=$?
+  $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5
+  test $ac_status = 0; }; }; then :
+  libc_cv_cc_avx512=yes
+else
+  libc_cv_cc_avx512=no
+fi
+
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $libc_cv_cc_avx512" >&5
+$as_echo "$libc_cv_cc_avx512" >&6; }
+if test $libc_cv_cc_avx512 = yes; then
+  $as_echo "#define HAVE_AVX512_SUPPORT 1" >>confdefs.h
+
+fi
+config_vars="$config_vars
+config-cflags-avx512 = $libc_cv_cc_avx512"
+
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for AVX512 support in assembler" >&5
+$as_echo_n "checking for AVX512 support in assembler... " >&6; }
+if ${libc_cv_asm_avx512+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  cat > conftest.s <<\EOF
+        vmovdqu64 %zmm0, (%rsp)
+EOF
+if { ac_try='${CC-cc} -c $ASFLAGS conftest.s 1>&5'
+  { { eval echo "\"\$as_me\":${as_lineno-$LINENO}: \"$ac_try\""; } >&5
+  (eval $ac_try) 2>&5
+  ac_status=$?
+  $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5
+  test $ac_status = 0; }; }; then
+  libc_cv_asm_avx512=yes
+else
+  libc_cv_asm_avx512=no
+fi
+rm -f conftest*
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $libc_cv_asm_avx512" >&5
+$as_echo "$libc_cv_asm_avx512" >&6; }
+if test $libc_cv_asm_avx512 == yes; then
+  $as_echo "#define HAVE_AVX512_ASM_SUPPORT 1" >>confdefs.h
+
+fi
+
 { $as_echo "$as_me:${as_lineno-$LINENO}: checking for AVX encoding of SSE instructions" >&5
 $as_echo_n "checking for AVX encoding of SSE instructions... " >&6; }
 if ${libc_cv_cc_sse2avx+:} false; then :

sysdeps/x86_64/configure.ac

@@ -23,6 +23,30 @@ if test $libc_cv_cc_avx = yes; then
 fi
 LIBC_CONFIG_VAR([config-cflags-avx], [$libc_cv_cc_avx])
 
+dnl Check if -mavx512f works.
+AC_CACHE_CHECK(for AVX512 support, libc_cv_cc_avx512, [dnl
+LIBC_TRY_CC_OPTION([-mavx512f], [libc_cv_cc_avx512=yes], [libc_cv_cc_avx512=no])
+])
+if test $libc_cv_cc_avx512 = yes; then
+  AC_DEFINE(HAVE_AVX512_SUPPORT)
+fi
+LIBC_CONFIG_VAR([config-cflags-avx512], [$libc_cv_cc_avx512])
+
+dnl Check if asm supports AVX512.
+AC_CACHE_CHECK(for AVX512 support in assembler, libc_cv_asm_avx512, [dnl
+cat > conftest.s <<\EOF
+        vmovdqu64 %zmm0, (%rsp)
+EOF
+if AC_TRY_COMMAND(${CC-cc} -c $ASFLAGS conftest.s 1>&AS_MESSAGE_LOG_FD); then
+  libc_cv_asm_avx512=yes
+else
+  libc_cv_asm_avx512=no
+fi
+rm -f conftest*])
+if test $libc_cv_asm_avx512 == yes; then
+  AC_DEFINE(HAVE_AVX512_ASM_SUPPORT)
+fi
+
 dnl Check if -msse2avx works.
 AC_CACHE_CHECK(for AVX encoding of SSE instructions, libc_cv_cc_sse2avx, [dnl
 LIBC_TRY_CC_OPTION([-msse2avx],