Blob Blame History Raw
Full backports of the following patches:

commit b97eb2bdb1ed72982a7821c3078be591051cef59
Author: H.J. Lu <hjl.tools@gmail.com>
Date:   Mon Mar 16 14:58:43 2015 -0700

    Preserve bound registers in _dl_runtime_resolve
    
    We need to add a BND prefix before indirect branch at the end of
    _dl_runtime_resolve to preserve bound registers.

commit ddd85a65b6e3d6ec1e756c1f78559f99a2c943ca
Author: H.J. Lu <hjl.tools@gmail.com>
Date:   Tue Jul 7 05:23:24 2015 -0700

    Add and use sysdeps/i386/link-defines.sym
    
    Define macros for fields in La_i86_regs and La_i86_retval and use them
    in dl-trampoline.S, instead of hardcoded values.

commit 14c5cbabc2d11004ab223ae5eae761ddf83ef99e
Author: Igor Zamyatin <igor.zamyatin@intel.com>
Date:   Thu Jul 9 06:50:12 2015 -0700

    Preserve bound registers for pointer pass/return
    
    We need to save/restore bound registers and add a BND prefix before
    branches in _dl_runtime_profile so that bound registers for pointer
    pass and return are preserved when LD_AUDIT is used.


commit f3dcae82d54e5097e18e1d6ef4ff55c2ea4e621e
Author: H.J. Lu <hjl.tools@gmail.com>
Date:   Tue Aug 25 04:33:54 2015 -0700

    Save and restore vector registers in x86-64 ld.so
    
    This patch adds SSE, AVX and AVX512 versions of _dl_runtime_resolve
    and _dl_runtime_profile, which save and restore the first 8 vector
    registers used for parameter passing.  elf_machine_runtime_setup
    selects the proper _dl_runtime_resolve or _dl_runtime_profile based
    on _dl_x86_cpu_features.  It avoids race condition caused by
    FOREIGN_CALL macros, which are only used for x86-64.
    
    Performance impact of saving and restoring 8 vector registers are
    negligible on Nehalem, Sandy Bridge, Ivy Bridge and Haswell when
    ld.so is optimized with SSE2.

commit fb0f7a6755c1bfaec38f490fbfcaa39a66ee3604
Author: H.J. Lu <hjl.tools@gmail.com>
Date:   Tue Sep 6 08:50:55 2016 -0700

    X86-64: Add _dl_runtime_resolve_avx[512]_{opt|slow} [BZ #20508]
    
    There is transition penalty when SSE instructions are mixed with 256-bit
    AVX or 512-bit AVX512 load instructions.  Since _dl_runtime_resolve_avx
    and _dl_runtime_profile_avx512 save/restore 256-bit YMM/512-bit ZMM
    registers, there is transition penalty when SSE instructions are used
    with lazy binding on AVX and AVX512 processors.
    
    To avoid SSE transition penalty, if only the lower 128 bits of the first
    8 vector registers are non-zero, we can preserve %xmm0 - %xmm7 registers
    with the zero upper bits.
    
    For AVX and AVX512 processors which support XGETBV with ECX == 1, we can
    use XGETBV with ECX == 1 to check if the upper 128 bits of YMM registers
    or the upper 256 bits of ZMM registers are zero.  We can restore only the
    non-zero portion of vector registers with AVX/AVX512 load instructions
    which will zero-extend upper bits of vector registers.
    
    This patch adds _dl_runtime_resolve_sse_vex which saves and restores
    XMM registers with 128-bit AVX store/load instructions.  It is used to
    preserve YMM/ZMM registers when only the lower 128 bits are non-zero.
    _dl_runtime_resolve_avx_opt and _dl_runtime_resolve_avx512_opt are added
    and used on AVX/AVX512 processors supporting XGETBV with ECX == 1 so
    that we store and load only the non-zero portion of vector registers.
    This avoids SSE transition penalty caused by _dl_runtime_resolve_avx and
    _dl_runtime_profile_avx512 when only the lower 128 bits of vector
    registers are used.
    
    _dl_runtime_resolve_avx_slow is added and used for AVX processors which
    don't support XGETBV with ECX == 1.  Since there is no SSE transition
    penalty on AVX512 processors which don't support XGETBV with ECX == 1,
    _dl_runtime_resolve_avx512_slow isn't provided.

commit 3403a17fea8ccef7dc5f99553a13231acf838744
Author: H.J. Lu <hjl.tools@gmail.com>
Date:   Thu Feb 9 12:19:44 2017 -0800

    x86-64: Verify that _dl_runtime_resolve preserves vector registers
    
    On x86-64, _dl_runtime_resolve must preserve the first 8 vector
    registers.  Add 3 _dl_runtime_resolve tests to verify that SSE,
    AVX and AVX512 registers are preserved.

commit c15f8eb50cea7ad1a4ccece6e0982bf426d52c00
Author: H.J. Lu <hjl.tools@gmail.com>
Date:   Tue Mar 21 10:59:31 2017 -0700

    x86-64: Improve branch predication in _dl_runtime_resolve_avx512_opt [BZ #21258]
    
    On Skylake server, _dl_runtime_resolve_avx512_opt is used to preserve
    the first 8 vector registers.  The code layout is
    
      if only %xmm0 - %xmm7 registers are used
         preserve %xmm0 - %xmm7 registers
      if only %ymm0 - %ymm7 registers are used
         preserve %ymm0 - %ymm7 registers
      preserve %zmm0 - %zmm7 registers
    
    Branch predication always executes the fallthrough code path to preserve
    %zmm0 - %zmm7 registers speculatively, even though only %xmm0 - %xmm7
    registers are used.  This leads to lower CPU frequency on Skylake
    server.  This patch changes the fallthrough code path to preserve
    %xmm0 - %xmm7 registers instead:
    
      if whole %zmm0 - %zmm7 registers are used
        preserve %zmm0 - %zmm7 registers
      if only %ymm0 - %ymm7 registers are used
         preserve %ymm0 - %ymm7 registers
      preserve %xmm0 - %xmm7 registers

    Tested on Skylake server.
    
            [BZ #21258]
            * sysdeps/x86_64/dl-trampoline.S (_dl_runtime_resolve_opt):
            Define only if _dl_runtime_resolve is defined to
            _dl_runtime_resolve_sse_vex.
            * sysdeps/x86_64/dl-trampoline.h (_dl_runtime_resolve_opt):
            Fallthrough to _dl_runtime_resolve_sse_vex.

Index: glibc-2.17-c758a686/nptl/sysdeps/x86_64/tcb-offsets.sym
===================================================================
--- glibc-2.17-c758a686.orig/nptl/sysdeps/x86_64/tcb-offsets.sym
+++ glibc-2.17-c758a686/nptl/sysdeps/x86_64/tcb-offsets.sym
@@ -15,7 +15,6 @@ VGETCPU_CACHE_OFFSET	offsetof (tcbhead_t
 #ifndef __ASSUME_PRIVATE_FUTEX
 PRIVATE_FUTEX		offsetof (tcbhead_t, private_futex)
 #endif
-RTLD_SAVESPACE_SSE	offsetof (tcbhead_t, rtld_savespace_sse)
 
 -- Not strictly offsets, but these values are also used in the TCB.
 TCB_CANCELSTATE_BITMASK	 CANCELSTATE_BITMASK
Index: glibc-2.17-c758a686/nptl/sysdeps/x86_64/tls.h
===================================================================
--- glibc-2.17-c758a686.orig/nptl/sysdeps/x86_64/tls.h
+++ glibc-2.17-c758a686/nptl/sysdeps/x86_64/tls.h
@@ -67,12 +67,13 @@ typedef struct
 # else
   int __unused1;
 # endif
-  int rtld_must_xmm_save;
+  int __glibc_unused1;
   /* Reservation of some values for the TM ABI.  */
   void *__private_tm[5];
   long int __unused2;
-  /* Have space for the post-AVX register size.  */
-  __128bits rtld_savespace_sse[8][4] __attribute__ ((aligned (32)));
+  /* Must be kept even if it is no longer used by glibc since programs,
+     like AddressSanitizer, depend on the size of tcbhead_t.  */
+  __128bits __glibc_unused2[8][4] __attribute__ ((aligned (32)));
 
   void *__padding[8];
 } tcbhead_t;
@@ -380,41 +381,6 @@ typedef struct
 # define THREAD_GSCOPE_WAIT() \
   GL(dl_wait_lookup_done) ()
 
-
-# ifdef SHARED
-/* Defined in dl-trampoline.S.  */
-extern void _dl_x86_64_save_sse (void);
-extern void _dl_x86_64_restore_sse (void);
-
-# define RTLD_CHECK_FOREIGN_CALL \
-  (THREAD_GETMEM (THREAD_SELF, header.rtld_must_xmm_save) != 0)
-
-/* NB: Don't use the xchg operation because that would imply a lock
-   prefix which is expensive and unnecessary.  The cache line is also
-   not contested at all.  */
-#  define RTLD_ENABLE_FOREIGN_CALL \
-  int old_rtld_must_xmm_save = THREAD_GETMEM (THREAD_SELF,		      \
-					      header.rtld_must_xmm_save);     \
-  THREAD_SETMEM (THREAD_SELF, header.rtld_must_xmm_save, 1)
-
-#  define RTLD_PREPARE_FOREIGN_CALL \
-  do if (THREAD_GETMEM (THREAD_SELF, header.rtld_must_xmm_save))	      \
-    {									      \
-      _dl_x86_64_save_sse ();						      \
-      THREAD_SETMEM (THREAD_SELF, header.rtld_must_xmm_save, 0);	      \
-    }									      \
-  while (0)
-
-#  define RTLD_FINALIZE_FOREIGN_CALL \
-  do {									      \
-    if (THREAD_GETMEM (THREAD_SELF, header.rtld_must_xmm_save) == 0)	      \
-      _dl_x86_64_restore_sse ();					      \
-    THREAD_SETMEM (THREAD_SELF, header.rtld_must_xmm_save,		      \
-		   old_rtld_must_xmm_save);				      \
-  } while (0)
-# endif
-
-
 #endif /* __ASSEMBLER__ */
 
 #endif	/* tls.h */
Index: glibc-2.17-c758a686/sysdeps/i386/Makefile
===================================================================
--- glibc-2.17-c758a686.orig/sysdeps/i386/Makefile
+++ glibc-2.17-c758a686/sysdeps/i386/Makefile
@@ -33,6 +33,7 @@ sysdep-CFLAGS += -mpreferred-stack-bound
 else
 ifeq ($(subdir),csu)
 sysdep-CFLAGS += -mpreferred-stack-boundary=4
+gen-as-const-headers += link-defines.sym
 else
 # Likewise, any function which calls user callbacks
 uses-callbacks += -mpreferred-stack-boundary=4
Index: glibc-2.17-c758a686/sysdeps/i386/configure
===================================================================
--- glibc-2.17-c758a686.orig/sysdeps/i386/configure
+++ glibc-2.17-c758a686/sysdeps/i386/configure
@@ -179,5 +179,32 @@ fi
 { $as_echo "$as_me:${as_lineno-$LINENO}: result: $libc_cv_cc_novzeroupper" >&5
 $as_echo "$libc_cv_cc_novzeroupper" >&6; }
 
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for Intel MPX support" >&5
+$as_echo_n "checking for Intel MPX support... " >&6; }
+if ${libc_cv_asm_mpx+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  cat > conftest.s <<\EOF
+        bndmov %bnd0,(%esp)
+EOF
+if { ac_try='${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_mpx=yes
+else
+  libc_cv_asm_mpx=no
+fi
+rm -f conftest*
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $libc_cv_asm_mpx" >&5
+$as_echo "$libc_cv_asm_mpx" >&6; }
+if test $libc_cv_asm_mpx == yes; then
+  $as_echo "#define HAVE_MPX_SUPPORT 1" >>confdefs.h
+
+fi
+
 $as_echo "#define PI_STATIC_AND_HIDDEN 1" >>confdefs.h
 
Index: glibc-2.17-c758a686/sysdeps/i386/configure.in
===================================================================
--- glibc-2.17-c758a686.orig/sysdeps/i386/configure.in
+++ glibc-2.17-c758a686/sysdeps/i386/configure.in
@@ -53,6 +53,21 @@ LIBC_TRY_CC_OPTION([-mno-vzeroupper],
 		   [libc_cv_cc_novzeroupper=no])
 ])
 
+dnl Check whether asm supports Intel MPX
+AC_CACHE_CHECK(for Intel MPX support, libc_cv_asm_mpx, [dnl
+cat > conftest.s <<\EOF
+        bndmov %bnd0,(%esp)
+EOF
+if AC_TRY_COMMAND(${CC-cc} -c $ASFLAGS conftest.s 1>&AS_MESSAGE_LOG_FD); then
+  libc_cv_asm_mpx=yes
+else
+  libc_cv_asm_mpx=no
+fi
+rm -f conftest*])
+if test $libc_cv_asm_mpx == yes; then
+  AC_DEFINE(HAVE_MPX_SUPPORT)
+fi
+
 dnl It is always possible to access static and hidden symbols in an
 dnl position independent way.
 AC_DEFINE(PI_STATIC_AND_HIDDEN)
Index: glibc-2.17-c758a686/sysdeps/i386/dl-trampoline.S
===================================================================
--- glibc-2.17-c758a686.orig/sysdeps/i386/dl-trampoline.S
+++ glibc-2.17-c758a686/sysdeps/i386/dl-trampoline.S
@@ -17,6 +17,13 @@
    <http://www.gnu.org/licenses/>.  */
 
 #include <sysdep.h>
+#include <link-defines.h>
+
+#ifdef HAVE_MPX_SUPPORT
+# define PRESERVE_BND_REGS_PREFIX bnd
+#else
+# define PRESERVE_BND_REGS_PREFIX .byte 0xf2
+#endif
 
 	.text
 	.globl _dl_runtime_resolve
@@ -161,24 +168,47 @@ _dl_runtime_profile:
 	    +4      free
 	   %esp     free
 	*/
-	subl $20, %esp
-	cfi_adjust_cfa_offset (20)
-	movl %eax, (%esp)
-	movl %edx, 4(%esp)
-	fstpt 8(%esp)
-	fstpt 20(%esp)
+#if LONG_DOUBLE_SIZE != 12
+# error "long double size must be 12 bytes"
+#endif
+	# Allocate space for La_i86_retval and subtract 12 free bytes.
+	subl $(LRV_SIZE - 12), %esp
+	cfi_adjust_cfa_offset (LRV_SIZE - 12)
+	movl %eax, LRV_EAX_OFFSET(%esp)
+	movl %edx, LRV_EDX_OFFSET(%esp)
+	fstpt LRV_ST0_OFFSET(%esp)
+	fstpt LRV_ST1_OFFSET(%esp)
+#ifdef HAVE_MPX_SUPPORT
+	bndmov %bnd0, LRV_BND0_OFFSET(%esp)
+	bndmov %bnd1, LRV_BND1_OFFSET(%esp)
+#else
+	.byte 0x66,0x0f,0x1b,0x44,0x24,LRV_BND0_OFFSET
+	.byte 0x66,0x0f,0x1b,0x4c,0x24,LRV_BND1_OFFSET
+#endif
 	pushl %esp
 	cfi_adjust_cfa_offset (4)
-	leal 36(%esp), %ecx
-	movl 56(%esp), %eax
-	movl 60(%esp), %edx
+	# Address of La_i86_regs area.
+	leal (LRV_SIZE + 4)(%esp), %ecx
+	# PLT2
+	movl (LRV_SIZE + 4 + LR_SIZE)(%esp), %eax
+	# PLT1
+	movl (LRV_SIZE + 4 + LR_SIZE + 4)(%esp), %edx
 	call _dl_call_pltexit
-	movl (%esp), %eax
-	movl 4(%esp), %edx
-	fldt 20(%esp)
-	fldt 8(%esp)
-	addl $60, %esp
-	cfi_adjust_cfa_offset (-60)
+	movl LRV_EAX_OFFSET(%esp), %eax
+	movl LRV_EDX_OFFSET(%esp), %edx
+	fldt LRV_ST1_OFFSET(%esp)
+	fldt LRV_ST0_OFFSET(%esp)
+#ifdef HAVE_MPX_SUPPORT
+	bndmov LRV_BND0_OFFSET(%esp), %bnd0
+	bndmov LRV_BND1_OFFSET(%esp), %bnd1
+#else
+	.byte 0x66,0x0f,0x1a,0x44,0x24,LRV_BND0_OFFSET
+	.byte 0x66,0x0f,0x1a,0x4c,0x24,LRV_BND1_OFFSET
+#endif
+	# Restore stack before return.
+	addl $(LRV_SIZE + 4 + LR_SIZE + 4), %esp
+	cfi_adjust_cfa_offset (-(LRV_SIZE + 4 + LR_SIZE + 4))
+	PRESERVE_BND_REGS_PREFIX
 	ret
 	cfi_endproc
 	.size _dl_runtime_profile, .-_dl_runtime_profile
Index: glibc-2.17-c758a686/sysdeps/i386/link-defines.sym
===================================================================
--- /dev/null
+++ glibc-2.17-c758a686/sysdeps/i386/link-defines.sym
@@ -0,0 +1,20 @@
+#include "link.h"
+#include <stddef.h>
+
+--
+LONG_DOUBLE_SIZE	sizeof (long double)
+
+LR_SIZE			sizeof (struct La_i86_regs)
+LR_EDX_OFFSET		offsetof (struct La_i86_regs, lr_edx)
+LR_ECX_OFFSET		offsetof (struct La_i86_regs, lr_ecx)
+LR_EAX_OFFSET		offsetof (struct La_i86_regs, lr_eax)
+LR_EBP_OFFSET		offsetof (struct La_i86_regs, lr_ebp)
+LR_ESP_OFFSET		offsetof (struct La_i86_regs, lr_esp)
+
+LRV_SIZE		sizeof (struct La_i86_retval)
+LRV_EAX_OFFSET		offsetof (struct La_i86_retval, lrv_eax)
+LRV_EDX_OFFSET		offsetof (struct La_i86_retval, lrv_edx)
+LRV_ST0_OFFSET		offsetof (struct La_i86_retval, lrv_st0)
+LRV_ST1_OFFSET		offsetof (struct La_i86_retval, lrv_st1)
+LRV_BND0_OFFSET		offsetof (struct La_i86_retval, lrv_bnd0)
+LRV_BND1_OFFSET		offsetof (struct La_i86_retval, lrv_bnd1)
Index: glibc-2.17-c758a686/sysdeps/x86/bits/link.h
===================================================================
--- glibc-2.17-c758a686.orig/sysdeps/x86/bits/link.h
+++ glibc-2.17-c758a686/sysdeps/x86/bits/link.h
@@ -38,6 +38,8 @@ typedef struct La_i86_retval
   uint32_t lrv_edx;
   long double lrv_st0;
   long double lrv_st1;
+  uint64_t lrv_bnd0;
+  uint64_t lrv_bnd1;
 } La_i86_retval;
 
 
Index: glibc-2.17-c758a686/sysdeps/x86/cpu-features.c
===================================================================
--- glibc-2.17-c758a686.orig/sysdeps/x86/cpu-features.c
+++ glibc-2.17-c758a686/sysdeps/x86/cpu-features.c
@@ -130,6 +130,20 @@ init_cpu_features (struct cpu_features *
 	      break;
 	    }
 	}
+
+      /* To avoid SSE transition penalty, use _dl_runtime_resolve_slow.
+         If XGETBV suports ECX == 1, use _dl_runtime_resolve_opt.  */
+      cpu_features->feature[index_Use_dl_runtime_resolve_slow]
+	|= bit_Use_dl_runtime_resolve_slow;
+      if (cpu_features->max_cpuid >= 0xd)
+	{
+	  unsigned int eax;
+
+	  __cpuid_count (0xd, 1, eax, ebx, ecx, edx);
+	  if ((eax & (1 << 2)) != 0)
+	    cpu_features->feature[index_Use_dl_runtime_resolve_opt]
+	      |= bit_Use_dl_runtime_resolve_opt;
+	}
     }
   /* This spells out "AuthenticAMD".  */
   else if (ebx == 0x68747541 && ecx == 0x444d4163 && edx == 0x69746e65)
Index: glibc-2.17-c758a686/sysdeps/x86/cpu-features.h
===================================================================
--- glibc-2.17-c758a686.orig/sysdeps/x86/cpu-features.h
+++ glibc-2.17-c758a686/sysdeps/x86/cpu-features.h
@@ -34,6 +34,9 @@
 #define bit_AVX512DQ_Usable		(1 << 13)
 #define bit_Prefer_MAP_32BIT_EXEC	(1 << 16)
 #define bit_Prefer_No_VZEROUPPER	(1 << 17)
+#define bit_Use_dl_runtime_resolve_opt	(1 << 20)
+#define bit_Use_dl_runtime_resolve_slow	(1 << 21)
+
 
 /* CPUID Feature flags.  */
 
@@ -95,6 +98,9 @@
 # define index_AVX512DQ_Usable		FEATURE_INDEX_1*FEATURE_SIZE
 # define index_Prefer_MAP_32BIT_EXEC	FEATURE_INDEX_1*FEATURE_SIZE
 # define index_Prefer_No_VZEROUPPER	FEATURE_INDEX_1*FEATURE_SIZE
+# define index_Use_dl_runtime_resolve_opt FEATURE_INDEX_1*FEATURE_SIZE
+# define index_Use_dl_runtime_resolve_slow FEATURE_INDEX_1*FEATURE_SIZE
+
 
 # if defined (_LIBC) && !IS_IN (nonlib)
 #  ifdef __x86_64__
@@ -273,6 +279,8 @@ extern const struct cpu_features *__get_
 # define index_AVX512DQ_Usable		FEATURE_INDEX_1
 # define index_Prefer_MAP_32BIT_EXEC	FEATURE_INDEX_1
 # define index_Prefer_No_VZEROUPPER     FEATURE_INDEX_1
+# define index_Use_dl_runtime_resolve_opt FEATURE_INDEX_1
+# define index_Use_dl_runtime_resolve_slow FEATURE_INDEX_1
 
 #endif	/* !__ASSEMBLER__ */
 
Index: glibc-2.17-c758a686/sysdeps/x86_64/Makefile
===================================================================
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/Makefile
+++ glibc-2.17-c758a686/sysdeps/x86_64/Makefile
@@ -21,6 +21,11 @@ endif
 ifeq ($(subdir),elf)
 sysdep-dl-routines += tlsdesc dl-tlsdesc
 
+tests += ifuncmain8
+modules-names += ifuncmod8
+
+$(objpfx)ifuncmain8: $(objpfx)ifuncmod8.so
+
 tests += tst-quad1 tst-quad2
 modules-names += tst-quadmod1 tst-quadmod2
 
@@ -34,18 +39,32 @@ tests-pie += $(quad-pie-test)
 $(objpfx)tst-quad1pie: $(objpfx)tst-quadmod1pie.o
 $(objpfx)tst-quad2pie: $(objpfx)tst-quadmod2pie.o
 
+tests += tst-sse tst-avx tst-avx512
+test-extras += tst-avx-aux tst-avx512-aux
+extra-test-objs += tst-avx-aux.o tst-avx512-aux.o
+
 tests += tst-audit10
-modules-names += tst-auditmod10a tst-auditmod10b
+modules-names += tst-auditmod10a tst-auditmod10b \
+		 tst-ssemod tst-avxmod tst-avx512mod
 
 $(objpfx)tst-audit10: $(objpfx)tst-auditmod10a.so
 $(objpfx)tst-audit10.out: $(objpfx)tst-auditmod10b.so
 tst-audit10-ENV = LD_AUDIT=$(objpfx)tst-auditmod10b.so
 
+$(objpfx)tst-sse: $(objpfx)tst-ssemod.so
+$(objpfx)tst-avx: $(objpfx)tst-avx-aux.o $(objpfx)tst-avxmod.so
+$(objpfx)tst-avx512: $(objpfx)tst-avx512-aux.o $(objpfx)tst-avx512mod.so
+
+CFLAGS-tst-avx-aux.c += $(AVX-CFLAGS)
+CFLAGS-tst-avxmod.c += $(AVX-CFLAGS)
+
 ifeq (yes,$(config-cflags-avx512))
 AVX512-CFLAGS = -mavx512f
 CFLAGS-tst-audit10.c += $(AVX512-CFLAGS)
 CFLAGS-tst-auditmod10a.c += $(AVX512-CFLAGS)
 CFLAGS-tst-auditmod10b.c += $(AVX512-CFLAGS)
+CFLAGS-tst-avx512-aux.c += $(AVX512-CFLAGS)
+CFLAGS-tst-avx512mod.c += $(AVX512-CFLAGS)
 endif
 endif
 
Index: glibc-2.17-c758a686/sysdeps/x86_64/dl-machine.h
===================================================================
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/dl-machine.h
+++ glibc-2.17-c758a686/sysdeps/x86_64/dl-machine.h
@@ -66,8 +66,15 @@ static inline int __attribute__ ((unused
 elf_machine_runtime_setup (struct link_map *l, int lazy, int profile)
 {
   Elf64_Addr *got;
-  extern void _dl_runtime_resolve (ElfW(Word)) attribute_hidden;
-  extern void _dl_runtime_profile (ElfW(Word)) attribute_hidden;
+  extern void _dl_runtime_resolve_sse (ElfW(Word)) attribute_hidden;
+  extern void _dl_runtime_resolve_avx (ElfW(Word)) attribute_hidden;
+  extern void _dl_runtime_resolve_avx_slow (ElfW(Word)) attribute_hidden;
+  extern void _dl_runtime_resolve_avx_opt (ElfW(Word)) attribute_hidden;
+  extern void _dl_runtime_resolve_avx512 (ElfW(Word)) attribute_hidden;
+  extern void _dl_runtime_resolve_avx512_opt (ElfW(Word)) attribute_hidden;
+  extern void _dl_runtime_profile_sse (ElfW(Word)) attribute_hidden;
+  extern void _dl_runtime_profile_avx (ElfW(Word)) attribute_hidden;
+  extern void _dl_runtime_profile_avx512 (ElfW(Word)) attribute_hidden;
 
   if (l->l_info[DT_JMPREL] && lazy)
     {
@@ -95,7 +102,12 @@ elf_machine_runtime_setup (struct link_m
 	 end in this function.  */
       if (__builtin_expect (profile, 0))
 	{
-	  *(ElfW(Addr) *) (got + 2) = (ElfW(Addr)) &_dl_runtime_profile;
+	  if (HAS_ARCH_FEATURE (AVX512F_Usable))
+	    *(ElfW(Addr) *) (got + 2) = (ElfW(Addr)) &_dl_runtime_profile_avx512;
+	  else if (HAS_ARCH_FEATURE (AVX_Usable))
+	    *(ElfW(Addr) *) (got + 2) = (ElfW(Addr)) &_dl_runtime_profile_avx;
+	  else
+	    *(ElfW(Addr) *) (got + 2) = (ElfW(Addr)) &_dl_runtime_profile_sse;
 
 	  if (GLRO(dl_profile) != NULL
 	      && _dl_name_match_p (GLRO(dl_profile), l))
@@ -104,9 +116,34 @@ elf_machine_runtime_setup (struct link_m
 	    GL(dl_profile_map) = l;
 	}
       else
-	/* This function will get called to fix up the GOT entry indicated by
-	   the offset on the stack, and then jump to the resolved address.  */
-	*(ElfW(Addr) *) (got + 2) = (ElfW(Addr)) &_dl_runtime_resolve;
+	{
+	  /* This function will get called to fix up the GOT entry
+	     indicated by the offset on the stack, and then jump to
+	     the resolved address.  */
+	  if (HAS_ARCH_FEATURE (AVX512F_Usable))
+	    {
+	      if (HAS_ARCH_FEATURE (Use_dl_runtime_resolve_opt))
+		*(ElfW(Addr) *) (got + 2)
+		  = (ElfW(Addr)) &_dl_runtime_resolve_avx512_opt;
+	      else
+		*(ElfW(Addr) *) (got + 2)
+		  = (ElfW(Addr)) &_dl_runtime_resolve_avx512;
+	    }
+	  else if (HAS_ARCH_FEATURE (AVX_Usable))
+	    {
+	      if (HAS_ARCH_FEATURE (Use_dl_runtime_resolve_opt))
+		*(ElfW(Addr) *) (got + 2)
+		  = (ElfW(Addr)) &_dl_runtime_resolve_avx_opt;
+	      else if (HAS_ARCH_FEATURE (Use_dl_runtime_resolve_slow))
+		*(ElfW(Addr) *) (got + 2)
+		  = (ElfW(Addr)) &_dl_runtime_resolve_avx_slow;
+	      else
+		*(ElfW(Addr) *) (got + 2)
+		  = (ElfW(Addr)) &_dl_runtime_resolve_avx;
+	    }
+	  else
+	    *(ElfW(Addr) *) (got + 2) = (ElfW(Addr)) &_dl_runtime_resolve_sse;
+	}
     }
 
   if (l->l_info[ADDRIDX (DT_TLSDESC_GOT)] && lazy)
Index: glibc-2.17-c758a686/sysdeps/x86_64/dl-trampoline.S
===================================================================
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/dl-trampoline.S
+++ glibc-2.17-c758a686/sysdeps/x86_64/dl-trampoline.S
@@ -18,28 +18,52 @@
 
 #include <config.h>
 #include <sysdep.h>
+#include <cpu-features.h>
 #include <link-defines.h>
 
-#if (RTLD_SAVESPACE_SSE % 32) != 0
-# error RTLD_SAVESPACE_SSE must be aligned to 32 bytes
+#ifndef DL_STACK_ALIGNMENT
+/* Due to GCC bug:
+
+   https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58066
+
+   __tls_get_addr may be called with 8-byte stack alignment.  Although
+   this bug has been fixed in GCC 4.9.4, 5.3 and 6, we can't assume
+   that stack will be always aligned at 16 bytes.  We use unaligned
+   16-byte move to load and store SSE registers, which has no penalty
+   on modern processors if stack is 16-byte aligned.  */
+# define DL_STACK_ALIGNMENT 8
 #endif
 
+#ifndef DL_RUNIME_UNALIGNED_VEC_SIZE
+/* The maximum size of unaligned vector load and store.  */
+# define DL_RUNIME_UNALIGNED_VEC_SIZE 16
+#endif
+
+/* True if _dl_runtime_resolve should align stack to VEC_SIZE bytes.  */
+#define DL_RUNIME_RESOLVE_REALIGN_STACK \
+  (VEC_SIZE > DL_STACK_ALIGNMENT \
+   && VEC_SIZE > DL_RUNIME_UNALIGNED_VEC_SIZE)
+
+/* Align vector register save area to 16 bytes.  */
+#define REGISTER_SAVE_VEC_OFF	0
+
 /* Area on stack to save and restore registers used for parameter
    passing when calling _dl_fixup.  */
 #ifdef __ILP32__
-/* X32 saves RCX, RDX, RSI, RDI, R8 and R9 plus RAX.  */
-# define REGISTER_SAVE_AREA	(8 * 7)
-# define REGISTER_SAVE_RAX	0
+# define REGISTER_SAVE_RAX	(REGISTER_SAVE_VEC_OFF + VEC_SIZE * 8)
+# define PRESERVE_BND_REGS_PREFIX
 #else
-/* X86-64 saves RCX, RDX, RSI, RDI, R8 and R9 plus RAX as well as BND0,
-   BND1, BND2, BND3.  */
-# define REGISTER_SAVE_AREA	(8 * 7 + 16 * 4)
 /* Align bound register save area to 16 bytes.  */
-# define REGISTER_SAVE_BND0	0
+# define REGISTER_SAVE_BND0	(REGISTER_SAVE_VEC_OFF + VEC_SIZE * 8)
 # define REGISTER_SAVE_BND1	(REGISTER_SAVE_BND0 + 16)
 # define REGISTER_SAVE_BND2	(REGISTER_SAVE_BND1 + 16)
 # define REGISTER_SAVE_BND3	(REGISTER_SAVE_BND2 + 16)
 # define REGISTER_SAVE_RAX	(REGISTER_SAVE_BND3 + 16)
+# ifdef HAVE_MPX_SUPPORT
+#  define PRESERVE_BND_REGS_PREFIX bnd
+# else
+#  define PRESERVE_BND_REGS_PREFIX .byte 0xf2
+# endif
 #endif
 #define REGISTER_SAVE_RCX	(REGISTER_SAVE_RAX + 8)
 #define REGISTER_SAVE_RDX	(REGISTER_SAVE_RCX + 8)
@@ -48,376 +72,71 @@
 #define REGISTER_SAVE_R8	(REGISTER_SAVE_RDI + 8)
 #define REGISTER_SAVE_R9	(REGISTER_SAVE_R8 + 8)
 
-	.text
-	.globl _dl_runtime_resolve
-	.type _dl_runtime_resolve, @function
-	.align 16
-	cfi_startproc
-_dl_runtime_resolve:
-	cfi_adjust_cfa_offset(16) # Incorporate PLT
-	subq $REGISTER_SAVE_AREA,%rsp
-	cfi_adjust_cfa_offset(REGISTER_SAVE_AREA)
-	# Preserve registers otherwise clobbered.
-	movq %rax, REGISTER_SAVE_RAX(%rsp)
-	movq %rcx, REGISTER_SAVE_RCX(%rsp)
-	movq %rdx, REGISTER_SAVE_RDX(%rsp)
-	movq %rsi, REGISTER_SAVE_RSI(%rsp)
-	movq %rdi, REGISTER_SAVE_RDI(%rsp)
-	movq %r8, REGISTER_SAVE_R8(%rsp)
-	movq %r9, REGISTER_SAVE_R9(%rsp)
-#ifndef __ILP32__
-	# We also have to preserve bound registers.  These are nops if
-	# Intel MPX isn't available or disabled.
-# ifdef HAVE_MPX_SUPPORT
-	bndmov %bnd0, REGISTER_SAVE_BND0(%rsp)
-	bndmov %bnd1, REGISTER_SAVE_BND1(%rsp)
-	bndmov %bnd2, REGISTER_SAVE_BND2(%rsp)
-	bndmov %bnd3, REGISTER_SAVE_BND3(%rsp)
-# else
-	.byte 0x66,0x0f,0x1b,0x44,0x24,REGISTER_SAVE_BND0
-	.byte 0x66,0x0f,0x1b,0x4c,0x24,REGISTER_SAVE_BND1
-	.byte 0x66,0x0f,0x1b,0x54,0x24,REGISTER_SAVE_BND2
-	.byte 0x66,0x0f,0x1b,0x5c,0x24,REGISTER_SAVE_BND3
-# endif
-#endif
-	# Copy args pushed by PLT in register.
-	# %rdi: link_map, %rsi: reloc_index
-	movq (REGISTER_SAVE_AREA + 8)(%rsp), %rsi
-	movq REGISTER_SAVE_AREA(%rsp), %rdi
-	call _dl_fixup		# Call resolver.
-	movq %rax, %r11		# Save return value
-#ifndef __ILP32__
-	# Restore bound registers.  These are nops if Intel MPX isn't
-	# avaiable or disabled.
-# ifdef HAVE_MPX_SUPPORT
-	bndmov REGISTER_SAVE_BND3(%rsp), %bnd3
-	bndmov REGISTER_SAVE_BND2(%rsp), %bnd2
-	bndmov REGISTER_SAVE_BND1(%rsp), %bnd1
-	bndmov REGISTER_SAVE_BND0(%rsp), %bnd0
-# else
-	.byte 0x66,0x0f,0x1a,0x5c,0x24,REGISTER_SAVE_BND3
-	.byte 0x66,0x0f,0x1a,0x54,0x24,REGISTER_SAVE_BND2
-	.byte 0x66,0x0f,0x1a,0x4c,0x24,REGISTER_SAVE_BND1
-	.byte 0x66,0x0f,0x1a,0x44,0x24,REGISTER_SAVE_BND0
-# endif
+#define VEC_SIZE		64
+#define VMOVA			vmovdqa64
+#if DL_RUNIME_RESOLVE_REALIGN_STACK || VEC_SIZE <= DL_STACK_ALIGNMENT
+# define VMOV			vmovdqa64
+#else
+# define VMOV			vmovdqu64
 #endif
-	# Get register content back.
-	movq REGISTER_SAVE_R9(%rsp), %r9
-	movq REGISTER_SAVE_R8(%rsp), %r8
-	movq REGISTER_SAVE_RDI(%rsp), %rdi
-	movq REGISTER_SAVE_RSI(%rsp), %rsi
-	movq REGISTER_SAVE_RDX(%rsp), %rdx
-	movq REGISTER_SAVE_RCX(%rsp), %rcx
-	movq REGISTER_SAVE_RAX(%rsp), %rax
-	# Adjust stack(PLT did 2 pushes)
-	addq $(REGISTER_SAVE_AREA + 16), %rsp
-	cfi_adjust_cfa_offset(-(REGISTER_SAVE_AREA + 16))
-	jmp *%r11		# Jump to function address.
-	cfi_endproc
-	.size _dl_runtime_resolve, .-_dl_runtime_resolve
-
-
-#ifndef PROF
-	.globl _dl_runtime_profile
-	.type _dl_runtime_profile, @function
-	.align 16
-	cfi_startproc
-
-_dl_runtime_profile:
-	cfi_adjust_cfa_offset(16) # Incorporate PLT
-	/* The La_x86_64_regs data structure pointed to by the
-	   fourth paramater must be 16-byte aligned.  This must
-	   be explicitly enforced.  We have the set up a dynamically
-	   sized stack frame.  %rbx points to the top half which
-	   has a fixed size and preserves the original stack pointer.  */
-
-	subq $32, %rsp		# Allocate the local storage.
-	cfi_adjust_cfa_offset(32)
-	movq %rbx, (%rsp)
-	cfi_rel_offset(%rbx, 0)
-
-	/* On the stack:
-		56(%rbx)	parameter #1
-		48(%rbx)	return address
-
-		40(%rbx)	reloc index
-		32(%rbx)	link_map
-
-		24(%rbx)	La_x86_64_regs pointer
-		16(%rbx)	framesize
-		 8(%rbx)	rax
-		  (%rbx)	rbx
-	*/
-
-	movq %rax, 8(%rsp)
-	movq %rsp, %rbx
-	cfi_def_cfa_register(%rbx)
-
-	/* Actively align the La_x86_64_regs structure.  */
-	andq $0xfffffffffffffff0, %rsp
-# if defined HAVE_AVX_SUPPORT || defined HAVE_AVX512_ASM_SUPPORT
-	/* sizeof(La_x86_64_regs).  Need extra space for 8 SSE registers
-	   to detect if any xmm0-xmm7 registers are changed by audit
-	   module.  */
-	subq $(LR_SIZE + XMM_SIZE*8), %rsp
-# else
-	subq $LR_SIZE, %rsp		# sizeof(La_x86_64_regs)
-# endif
-	movq %rsp, 24(%rbx)
-
-	/* Fill the La_x86_64_regs structure.  */
-	movq %rdx, LR_RDX_OFFSET(%rsp)
-	movq %r8,  LR_R8_OFFSET(%rsp)
-	movq %r9,  LR_R9_OFFSET(%rsp)
-	movq %rcx, LR_RCX_OFFSET(%rsp)
-	movq %rsi, LR_RSI_OFFSET(%rsp)
-	movq %rdi, LR_RDI_OFFSET(%rsp)
-	movq %rbp, LR_RBP_OFFSET(%rsp)
-
-	leaq 48(%rbx), %rax
-	movq %rax, LR_RSP_OFFSET(%rsp)
-
-	/* We always store the XMM registers even if AVX is available.
-	   This is to provide backward binary compatility for existing
-	   audit modules.  */
-	movaps %xmm0,		   (LR_XMM_OFFSET)(%rsp)
-	movaps %xmm1, (LR_XMM_OFFSET +   XMM_SIZE)(%rsp)
-	movaps %xmm2, (LR_XMM_OFFSET + XMM_SIZE*2)(%rsp)
-	movaps %xmm3, (LR_XMM_OFFSET + XMM_SIZE*3)(%rsp)
-	movaps %xmm4, (LR_XMM_OFFSET + XMM_SIZE*4)(%rsp)
-	movaps %xmm5, (LR_XMM_OFFSET + XMM_SIZE*5)(%rsp)
-	movaps %xmm6, (LR_XMM_OFFSET + XMM_SIZE*6)(%rsp)
-	movaps %xmm7, (LR_XMM_OFFSET + XMM_SIZE*7)(%rsp)
-
-# ifndef __ILP32__
-#  ifdef HAVE_MPX_SUPPORT
-	bndmov %bnd0, 		   (LR_BND_OFFSET)(%rsp)  # Preserve bound
-	bndmov %bnd1, (LR_BND_OFFSET +   BND_SIZE)(%rsp)  # registers. Nops if
-	bndmov %bnd2, (LR_BND_OFFSET + BND_SIZE*2)(%rsp)  # MPX not available
-	bndmov %bnd3, (LR_BND_OFFSET + BND_SIZE*3)(%rsp)  # or disabled.
-#  else
-	.byte 0x66,0x0f,0x1b,0x84,0x24;.long (LR_BND_OFFSET)
-	.byte 0x66,0x0f,0x1b,0x8c,0x24;.long (LR_BND_OFFSET + BND_SIZE)
-	.byte 0x66,0x0f,0x1b,0x84,0x24;.long (LR_BND_OFFSET + BND_SIZE*2)
-	.byte 0x66,0x0f,0x1b,0x8c,0x24;.long (LR_BND_OFFSET + BND_SIZE*3)
-#  endif
-# endif
-
-# if defined HAVE_AVX_SUPPORT || defined HAVE_AVX512_ASM_SUPPORT
-	.data
-L(have_avx):
-	.zero 4
-	.size L(have_avx), 4
-	.previous
-
-	cmpl	$0, L(have_avx)(%rip)
-	jne	L(defined)
-	movq	%rbx, %r11		# Save rbx
-	movl	$1, %eax
-	cpuid
-	movq	%r11,%rbx		# Restore rbx
-	xorl	%eax, %eax
-	// AVX and XSAVE supported?
-	andl	$((1 << 28) | (1 << 27)), %ecx
-	cmpl	$((1 << 28) | (1 << 27)), %ecx
-	jne	10f
-#  ifdef HAVE_AVX512_ASM_SUPPORT
-	// AVX512 supported in processor?
-	movq	%rbx, %r11		# Save rbx
-	xorl	%ecx, %ecx
-	mov	$0x7, %eax
-	cpuid
-	andl	$(1 << 16), %ebx
-#  endif
-	xorl	%ecx, %ecx
-	// Get XFEATURE_ENABLED_MASK
-	xgetbv
-#  ifdef HAVE_AVX512_ASM_SUPPORT
-	test	%ebx, %ebx
-	movq	%r11, %rbx		# Restore rbx
-	je	20f
-	// Verify that XCR0[7:5] = '111b' and
-	// XCR0[2:1] = '11b' which means
-	// that zmm state is enabled
-	andl	$0xe6, %eax
-	cmpl	$0xe6, %eax
-	jne	20f
-	movl	%eax, L(have_avx)(%rip)
-L(avx512):
-#   define RESTORE_AVX
-#   define VMOV    vmovdqu64
-#   define VEC(i)  zmm##i
-#   define MORE_CODE
-#   include "dl-trampoline.h"
-#   undef VMOV
-#   undef VEC
-#   undef RESTORE_AVX
-#  endif
-20:	andl	$0x6, %eax
-10:	subl	$0x5, %eax
-	movl	%eax, L(have_avx)(%rip)
-	cmpl	$0, %eax
-
-L(defined):
-	js	L(no_avx)
-#  ifdef HAVE_AVX512_ASM_SUPPORT
-	cmpl	$0xe6, L(have_avx)(%rip)
-	je	L(avx512)
-#  endif
-
-#  define RESTORE_AVX
-#  define VMOV    vmovdqu
-#  define VEC(i)  ymm##i
-#  define MORE_CODE
-#  include "dl-trampoline.h"
-
-	.align 16
-L(no_avx):
-# endif
-
-# undef RESTORE_AVX
-# include "dl-trampoline.h"
-
-	cfi_endproc
-	.size _dl_runtime_profile, .-_dl_runtime_profile
+#define VEC(i)			zmm##i
+#define _dl_runtime_resolve	_dl_runtime_resolve_avx512
+#define _dl_runtime_profile	_dl_runtime_profile_avx512
+#define RESTORE_AVX
+#include "dl-trampoline.h"
+#undef _dl_runtime_resolve
+#undef _dl_runtime_profile
+#undef VEC
+#undef VMOV
+#undef VMOVA
+#undef VEC_SIZE
+
+#define VEC_SIZE		32
+#define VMOVA			vmovdqa
+#if DL_RUNIME_RESOLVE_REALIGN_STACK || VEC_SIZE <= DL_STACK_ALIGNMENT
+# define VMOV			vmovdqa
+#else
+# define VMOV			vmovdqu
 #endif
-
-
-#ifdef SHARED
-	.globl _dl_x86_64_save_sse
-	.type _dl_x86_64_save_sse, @function
-	.align 16
-	cfi_startproc
-_dl_x86_64_save_sse:
-# if defined HAVE_AVX_SUPPORT || defined HAVE_AVX512_ASM_SUPPORT
-	cmpl	$0, L(have_avx)(%rip)
-	jne	L(defined_5)
-	movq	%rbx, %r11		# Save rbx
-	movl	$1, %eax
-	cpuid
-	movq	%r11,%rbx		# Restore rbx
-	xorl	%eax, %eax
-	// AVX and XSAVE supported?
-	andl	$((1 << 28) | (1 << 27)), %ecx
-	cmpl	$((1 << 28) | (1 << 27)), %ecx
-	jne	1f
-#  ifdef HAVE_AVX512_ASM_SUPPORT
-	// AVX512 supported in a processor?
-	movq	%rbx, %r11              # Save rbx
-	xorl	%ecx,%ecx
-	mov	$0x7,%eax
-	cpuid
-	andl	$(1 << 16), %ebx
-#  endif
-	xorl	%ecx, %ecx
-	// Get XFEATURE_ENABLED_MASK
-	xgetbv
-#  ifdef HAVE_AVX512_ASM_SUPPORT
-	test	%ebx, %ebx
-	movq	%r11, %rbx		# Restore rbx
-	je	2f
-	// Verify that XCR0[7:5] = '111b' and
-	// XCR0[2:1] = '11b' which means
-	// that zmm state is enabled
-	andl	$0xe6, %eax
-	movl	%eax, L(have_avx)(%rip)
-	cmpl	$0xe6, %eax
-	je	L(avx512_5)
-#  endif
-
-2:	andl	$0x6, %eax
-1:	subl	$0x5, %eax
-	movl	%eax, L(have_avx)(%rip)
-	cmpl	$0, %eax
-
-L(defined_5):
-	js	L(no_avx5)
-#  ifdef HAVE_AVX512_ASM_SUPPORT
-	cmpl	$0xe6, L(have_avx)(%rip)
-	je	L(avx512_5)
-#  endif
-
-	vmovdqa %ymm0, %fs:RTLD_SAVESPACE_SSE+0*YMM_SIZE
-	vmovdqa %ymm1, %fs:RTLD_SAVESPACE_SSE+1*YMM_SIZE
-	vmovdqa %ymm2, %fs:RTLD_SAVESPACE_SSE+2*YMM_SIZE
-	vmovdqa %ymm3, %fs:RTLD_SAVESPACE_SSE+3*YMM_SIZE
-	vmovdqa %ymm4, %fs:RTLD_SAVESPACE_SSE+4*YMM_SIZE
-	vmovdqa %ymm5, %fs:RTLD_SAVESPACE_SSE+5*YMM_SIZE
-	vmovdqa %ymm6, %fs:RTLD_SAVESPACE_SSE+6*YMM_SIZE
-	vmovdqa %ymm7, %fs:RTLD_SAVESPACE_SSE+7*YMM_SIZE
-	ret
-#  ifdef HAVE_AVX512_ASM_SUPPORT
-L(avx512_5):
-	vmovdqu64 %zmm0, %fs:RTLD_SAVESPACE_SSE+0*ZMM_SIZE
-	vmovdqu64 %zmm1, %fs:RTLD_SAVESPACE_SSE+1*ZMM_SIZE
-	vmovdqu64 %zmm2, %fs:RTLD_SAVESPACE_SSE+2*ZMM_SIZE
-	vmovdqu64 %zmm3, %fs:RTLD_SAVESPACE_SSE+3*ZMM_SIZE
-	vmovdqu64 %zmm4, %fs:RTLD_SAVESPACE_SSE+4*ZMM_SIZE
-	vmovdqu64 %zmm5, %fs:RTLD_SAVESPACE_SSE+5*ZMM_SIZE
-	vmovdqu64 %zmm6, %fs:RTLD_SAVESPACE_SSE+6*ZMM_SIZE
-	vmovdqu64 %zmm7, %fs:RTLD_SAVESPACE_SSE+7*ZMM_SIZE
-	ret
-#  endif
-L(no_avx5):
-# endif
-	movdqa	%xmm0, %fs:RTLD_SAVESPACE_SSE+0*XMM_SIZE
-	movdqa	%xmm1, %fs:RTLD_SAVESPACE_SSE+1*XMM_SIZE
-	movdqa	%xmm2, %fs:RTLD_SAVESPACE_SSE+2*XMM_SIZE
-	movdqa	%xmm3, %fs:RTLD_SAVESPACE_SSE+3*XMM_SIZE
-	movdqa	%xmm4, %fs:RTLD_SAVESPACE_SSE+4*XMM_SIZE
-	movdqa	%xmm5, %fs:RTLD_SAVESPACE_SSE+5*XMM_SIZE
-	movdqa	%xmm6, %fs:RTLD_SAVESPACE_SSE+6*XMM_SIZE
-	movdqa	%xmm7, %fs:RTLD_SAVESPACE_SSE+7*XMM_SIZE
-	ret
-	cfi_endproc
-	.size _dl_x86_64_save_sse, .-_dl_x86_64_save_sse
-
-
-	.globl _dl_x86_64_restore_sse
-	.type _dl_x86_64_restore_sse, @function
-	.align 16
-	cfi_startproc
-_dl_x86_64_restore_sse:
-# if defined HAVE_AVX_SUPPORT || defined HAVE_AVX512_ASM_SUPPORT
-	cmpl	$0, L(have_avx)(%rip)
-	js	L(no_avx6)
-#  ifdef HAVE_AVX512_ASM_SUPPORT
-	cmpl	$0xe6, L(have_avx)(%rip)
-	je	L(avx512_6)
-#  endif
-
-	vmovdqa %fs:RTLD_SAVESPACE_SSE+0*YMM_SIZE, %ymm0
-	vmovdqa %fs:RTLD_SAVESPACE_SSE+1*YMM_SIZE, %ymm1
-	vmovdqa %fs:RTLD_SAVESPACE_SSE+2*YMM_SIZE, %ymm2
-	vmovdqa %fs:RTLD_SAVESPACE_SSE+3*YMM_SIZE, %ymm3
-	vmovdqa %fs:RTLD_SAVESPACE_SSE+4*YMM_SIZE, %ymm4
-	vmovdqa %fs:RTLD_SAVESPACE_SSE+5*YMM_SIZE, %ymm5
-	vmovdqa %fs:RTLD_SAVESPACE_SSE+6*YMM_SIZE, %ymm6
-	vmovdqa %fs:RTLD_SAVESPACE_SSE+7*YMM_SIZE, %ymm7
-	ret
-#  ifdef HAVE_AVX512_ASM_SUPPORT
-L(avx512_6):
-	vmovdqu64 %fs:RTLD_SAVESPACE_SSE+0*ZMM_SIZE, %zmm0
-	vmovdqu64 %fs:RTLD_SAVESPACE_SSE+1*ZMM_SIZE, %zmm1
-	vmovdqu64 %fs:RTLD_SAVESPACE_SSE+2*ZMM_SIZE, %zmm2
-	vmovdqu64 %fs:RTLD_SAVESPACE_SSE+3*ZMM_SIZE, %zmm3
-	vmovdqu64 %fs:RTLD_SAVESPACE_SSE+4*ZMM_SIZE, %zmm4
-	vmovdqu64 %fs:RTLD_SAVESPACE_SSE+5*ZMM_SIZE, %zmm5
-	vmovdqu64 %fs:RTLD_SAVESPACE_SSE+6*ZMM_SIZE, %zmm6
-	vmovdqu64 %fs:RTLD_SAVESPACE_SSE+7*ZMM_SIZE, %zmm7
-	ret
-#  endif
-L(no_avx6):
-# endif
-	movdqa	%fs:RTLD_SAVESPACE_SSE+0*XMM_SIZE, %xmm0
-	movdqa	%fs:RTLD_SAVESPACE_SSE+1*XMM_SIZE, %xmm1
-	movdqa	%fs:RTLD_SAVESPACE_SSE+2*XMM_SIZE, %xmm2
-	movdqa	%fs:RTLD_SAVESPACE_SSE+3*XMM_SIZE, %xmm3
-	movdqa	%fs:RTLD_SAVESPACE_SSE+4*XMM_SIZE, %xmm4
-	movdqa	%fs:RTLD_SAVESPACE_SSE+5*XMM_SIZE, %xmm5
-	movdqa	%fs:RTLD_SAVESPACE_SSE+6*XMM_SIZE, %xmm6
-	movdqa	%fs:RTLD_SAVESPACE_SSE+7*XMM_SIZE, %xmm7
-	ret
-	cfi_endproc
-	.size _dl_x86_64_restore_sse, .-_dl_x86_64_restore_sse
+#define VEC(i)			ymm##i
+#define _dl_runtime_resolve	_dl_runtime_resolve_avx
+#define _dl_runtime_resolve_opt	_dl_runtime_resolve_avx_opt
+#define _dl_runtime_profile	_dl_runtime_profile_avx
+#include "dl-trampoline.h"
+#undef _dl_runtime_resolve
+#undef _dl_runtime_resolve_opt
+#undef _dl_runtime_profile
+#undef VEC
+#undef VMOV
+#undef VMOVA
+#undef VEC_SIZE
+
+/* movaps/movups is 1-byte shorter.  */
+#define VEC_SIZE		16
+#define VMOVA			movaps
+#if DL_RUNIME_RESOLVE_REALIGN_STACK || VEC_SIZE <= DL_STACK_ALIGNMENT
+# define VMOV			movaps
+#else
+# define VMOV			movups
+ #endif
+#define VEC(i)			xmm##i
+#define _dl_runtime_resolve	_dl_runtime_resolve_sse
+#define _dl_runtime_profile	_dl_runtime_profile_sse
+#undef RESTORE_AVX
+#include "dl-trampoline.h"
+#undef _dl_runtime_resolve
+#undef _dl_runtime_profile
+#undef VMOV
+#undef VMOVA
+
+/* Used by _dl_runtime_resolve_avx_opt/_dl_runtime_resolve_avx512_opt
+   to preserve the full vector registers with zero upper bits.  */
+#define VMOVA			vmovdqa
+#if DL_RUNTIME_RESOLVE_REALIGN_STACK || VEC_SIZE <= DL_STACK_ALIGNMENT
+# define VMOV			vmovdqa
+#else
+# define VMOV			vmovdqu
 #endif
+#define _dl_runtime_resolve	_dl_runtime_resolve_sse_vex
+#define _dl_runtime_resolve_opt	_dl_runtime_resolve_avx512_opt
+#include "dl-trampoline.h"
Index: glibc-2.17-c758a686/sysdeps/x86_64/dl-trampoline.h
===================================================================
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/dl-trampoline.h
+++ glibc-2.17-c758a686/sysdeps/x86_64/dl-trampoline.h
@@ -1,6 +1,5 @@
-/* Partial PLT profile trampoline to save and restore x86-64 vector
-   registers.
-   Copyright (C) 2009, 2011 Free Software Foundation, Inc.
+/* PLT trampolines.  x86-64 version.
+   Copyright (C) 2009-2015 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
@@ -17,16 +16,355 @@
    License along with the GNU C Library; if not, see
    <http://www.gnu.org/licenses/>.  */
 
-#ifdef RESTORE_AVX
+#undef REGISTER_SAVE_AREA_RAW
+#ifdef __ILP32__
+/* X32 saves RCX, RDX, RSI, RDI, R8 and R9 plus RAX as well as VEC0 to
+   VEC7.  */
+# define REGISTER_SAVE_AREA_RAW	(8 * 7 + VEC_SIZE * 8)
+#else
+/* X86-64 saves RCX, RDX, RSI, RDI, R8 and R9 plus RAX as well as
+   BND0, BND1, BND2, BND3 and VEC0 to VEC7. */
+# define REGISTER_SAVE_AREA_RAW	(8 * 7 + 16 * 4 + VEC_SIZE * 8)
+#endif
+
+#undef REGISTER_SAVE_AREA
+#undef LOCAL_STORAGE_AREA
+#undef BASE
+#if DL_RUNIME_RESOLVE_REALIGN_STACK
+# define REGISTER_SAVE_AREA	(REGISTER_SAVE_AREA_RAW + 8)
+/* Local stack area before jumping to function address: RBX.  */
+# define LOCAL_STORAGE_AREA	8
+# define BASE			rbx
+# if (REGISTER_SAVE_AREA % VEC_SIZE) != 0
+#  error REGISTER_SAVE_AREA must be multples of VEC_SIZE
+# endif
+#else
+# define REGISTER_SAVE_AREA	REGISTER_SAVE_AREA_RAW
+/* Local stack area before jumping to function address:  All saved
+   registers.  */
+# define LOCAL_STORAGE_AREA	REGISTER_SAVE_AREA
+# define BASE			rsp
+# if (REGISTER_SAVE_AREA % 16) != 8
+#  error REGISTER_SAVE_AREA must be odd multples of 8
+# endif
+#endif
+
+	.text
+#ifdef _dl_runtime_resolve_opt
+/* Use the smallest vector registers to preserve the full YMM/ZMM
+   registers to avoid SSE transition penalty.  */
+
+# if VEC_SIZE == 32
+/* Check if the upper 128 bits in %ymm0 - %ymm7 registers are non-zero
+   and preserve %xmm0 - %xmm7 registers with the zero upper bits.  Since
+   there is no SSE transition penalty on AVX512 processors which don't
+   support XGETBV with ECX == 1, _dl_runtime_resolve_avx512_slow isn't
+   provided.   */
+	.globl _dl_runtime_resolve_avx_slow
+	.hidden _dl_runtime_resolve_avx_slow
+	.type _dl_runtime_resolve_avx_slow, @function
+	.align 16
+_dl_runtime_resolve_avx_slow:
+	cfi_startproc
+	cfi_adjust_cfa_offset(16) # Incorporate PLT
+	vorpd %ymm0, %ymm1, %ymm8
+	vorpd %ymm2, %ymm3, %ymm9
+	vorpd %ymm4, %ymm5, %ymm10
+	vorpd %ymm6, %ymm7, %ymm11
+	vorpd %ymm8, %ymm9, %ymm9
+	vorpd %ymm10, %ymm11, %ymm10
+	vpcmpeqd %xmm8, %xmm8, %xmm8
+	vorpd %ymm9, %ymm10, %ymm10
+	vptest %ymm10, %ymm8
+	# Preserve %ymm0 - %ymm7 registers if the upper 128 bits of any
+	# %ymm0 - %ymm7 registers aren't zero.
+	PRESERVE_BND_REGS_PREFIX
+	jnc _dl_runtime_resolve_avx
+	# Use vzeroupper to avoid SSE transition penalty.
+	vzeroupper
+	# Preserve %xmm0 - %xmm7 registers with the zero upper 128 bits
+	# when the upper 128 bits of %ymm0 - %ymm7 registers are zero.
+	PRESERVE_BND_REGS_PREFIX
+	jmp _dl_runtime_resolve_sse_vex
+	cfi_adjust_cfa_offset(-16) # Restore PLT adjustment
+	cfi_endproc
+	.size _dl_runtime_resolve_avx_slow, .-_dl_runtime_resolve_avx_slow
+# endif
+
+/* Use XGETBV with ECX == 1 to check which bits in vector registers are
+   non-zero and only preserve the non-zero lower bits with zero upper
+   bits.  */
+	.globl _dl_runtime_resolve_opt
+	.hidden _dl_runtime_resolve_opt
+	.type _dl_runtime_resolve_opt, @function
+	.align 16
+_dl_runtime_resolve_opt:
+	cfi_startproc
+	cfi_adjust_cfa_offset(16) # Incorporate PLT
+	pushq %rax
+	cfi_adjust_cfa_offset(8)
+	cfi_rel_offset(%rax, 0)
+	pushq %rcx
+	cfi_adjust_cfa_offset(8)
+	cfi_rel_offset(%rcx, 0)
+	pushq %rdx
+	cfi_adjust_cfa_offset(8)
+	cfi_rel_offset(%rdx, 0)
+	movl $1, %ecx
+	xgetbv
+	movl %eax, %r11d
+	popq %rdx
+	cfi_adjust_cfa_offset(-8)
+	cfi_restore (%rdx)
+	popq %rcx
+	cfi_adjust_cfa_offset(-8)
+	cfi_restore (%rcx)
+	popq %rax
+	cfi_adjust_cfa_offset(-8)
+	cfi_restore (%rax)
+# if VEC_SIZE == 32
+	# For YMM registers, check if YMM state is in use.
+	andl $bit_YMM_state, %r11d
+	# Preserve %xmm0 - %xmm7 registers with the zero upper 128 bits if
+	# YMM state isn't in use.
+	PRESERVE_BND_REGS_PREFIX
+	jz _dl_runtime_resolve_sse_vex
+# elif VEC_SIZE == 16
+	# For ZMM registers, check if YMM state and ZMM state are in
+	# use.
+	andl $(bit_YMM_state | bit_ZMM0_15_state), %r11d
+	cmpl $bit_YMM_state, %r11d
+	# Preserve %zmm0 - %zmm7 registers if ZMM state is in use.
+	PRESERVE_BND_REGS_PREFIX
+	jg _dl_runtime_resolve_avx512
+	# Preserve %ymm0 - %ymm7 registers with the zero upper 256 bits if
+	# ZMM state isn't in use.
+	PRESERVE_BND_REGS_PREFIX
+	je _dl_runtime_resolve_avx
+	# Preserve %xmm0 - %xmm7 registers with the zero upper 384 bits if
+	# neither YMM state nor ZMM state are in use.
+# else
+#  error Unsupported VEC_SIZE!
+# endif
+	cfi_adjust_cfa_offset(-16) # Restore PLT adjustment
+	cfi_endproc
+	.size _dl_runtime_resolve_opt, .-_dl_runtime_resolve_opt
+#endif
+	.globl _dl_runtime_resolve
+	.hidden _dl_runtime_resolve
+	.type _dl_runtime_resolve, @function
+	.align 16
+	cfi_startproc
+_dl_runtime_resolve:
+	cfi_adjust_cfa_offset(16) # Incorporate PLT
+#if DL_RUNIME_RESOLVE_REALIGN_STACK
+# if LOCAL_STORAGE_AREA != 8
+#  error LOCAL_STORAGE_AREA must be 8
+# endif
+	pushq %rbx			# push subtracts stack by 8.
+	cfi_adjust_cfa_offset(8)
+	cfi_rel_offset(%rbx, 0)
+	mov %RSP_LP, %RBX_LP
+	cfi_def_cfa_register(%rbx)
+	and $-VEC_SIZE, %RSP_LP
+#endif
+	sub $REGISTER_SAVE_AREA, %RSP_LP
+	cfi_adjust_cfa_offset(REGISTER_SAVE_AREA)
+	# Preserve registers otherwise clobbered.
+	movq %rax, REGISTER_SAVE_RAX(%rsp)
+	movq %rcx, REGISTER_SAVE_RCX(%rsp)
+	movq %rdx, REGISTER_SAVE_RDX(%rsp)
+	movq %rsi, REGISTER_SAVE_RSI(%rsp)
+	movq %rdi, REGISTER_SAVE_RDI(%rsp)
+	movq %r8, REGISTER_SAVE_R8(%rsp)
+	movq %r9, REGISTER_SAVE_R9(%rsp)
+	VMOV %VEC(0), (REGISTER_SAVE_VEC_OFF)(%rsp)
+	VMOV %VEC(1), (REGISTER_SAVE_VEC_OFF + VEC_SIZE)(%rsp)
+	VMOV %VEC(2), (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 2)(%rsp)
+	VMOV %VEC(3), (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 3)(%rsp)
+	VMOV %VEC(4), (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 4)(%rsp)
+	VMOV %VEC(5), (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 5)(%rsp)
+	VMOV %VEC(6), (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 6)(%rsp)
+	VMOV %VEC(7), (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 7)(%rsp)
+#ifndef __ILP32__
+	# We also have to preserve bound registers.  These are nops if
+	# Intel MPX isn't available or disabled.
+# ifdef HAVE_MPX_SUPPORT
+	bndmov %bnd0, REGISTER_SAVE_BND0(%rsp)
+	bndmov %bnd1, REGISTER_SAVE_BND1(%rsp)
+	bndmov %bnd2, REGISTER_SAVE_BND2(%rsp)
+	bndmov %bnd3, REGISTER_SAVE_BND3(%rsp)
+# else
+#  if REGISTER_SAVE_BND0 == 0
+	.byte 0x66,0x0f,0x1b,0x04,0x24
+#  else
+	.byte 0x66,0x0f,0x1b,0x44,0x24,REGISTER_SAVE_BND0
+#  endif
+	.byte 0x66,0x0f,0x1b,0x4c,0x24,REGISTER_SAVE_BND1
+	.byte 0x66,0x0f,0x1b,0x54,0x24,REGISTER_SAVE_BND2
+	.byte 0x66,0x0f,0x1b,0x5c,0x24,REGISTER_SAVE_BND3
+# endif
+#endif
+	# Copy args pushed by PLT in register.
+	# %rdi: link_map, %rsi: reloc_index
+	mov (LOCAL_STORAGE_AREA + 8)(%BASE), %RSI_LP
+	mov LOCAL_STORAGE_AREA(%BASE), %RDI_LP
+	call _dl_fixup		# Call resolver.
+	mov %RAX_LP, %R11_LP	# Save return value
+#ifndef __ILP32__
+	# Restore bound registers.  These are nops if Intel MPX isn't
+	# avaiable or disabled.
+# ifdef HAVE_MPX_SUPPORT
+	bndmov REGISTER_SAVE_BND3(%rsp), %bnd3
+	bndmov REGISTER_SAVE_BND2(%rsp), %bnd2
+	bndmov REGISTER_SAVE_BND1(%rsp), %bnd1
+	bndmov REGISTER_SAVE_BND0(%rsp), %bnd0
+# else
+	.byte 0x66,0x0f,0x1a,0x5c,0x24,REGISTER_SAVE_BND3
+	.byte 0x66,0x0f,0x1a,0x54,0x24,REGISTER_SAVE_BND2
+	.byte 0x66,0x0f,0x1a,0x4c,0x24,REGISTER_SAVE_BND1
+#  if REGISTER_SAVE_BND0 == 0
+	.byte 0x66,0x0f,0x1a,0x04,0x24
+#  else
+	.byte 0x66,0x0f,0x1a,0x44,0x24,REGISTER_SAVE_BND0
+#  endif
+# endif
+#endif
+	# Get register content back.
+	movq REGISTER_SAVE_R9(%rsp), %r9
+	movq REGISTER_SAVE_R8(%rsp), %r8
+	movq REGISTER_SAVE_RDI(%rsp), %rdi
+	movq REGISTER_SAVE_RSI(%rsp), %rsi
+	movq REGISTER_SAVE_RDX(%rsp), %rdx
+	movq REGISTER_SAVE_RCX(%rsp), %rcx
+	movq REGISTER_SAVE_RAX(%rsp), %rax
+	VMOV (REGISTER_SAVE_VEC_OFF)(%rsp), %VEC(0)
+	VMOV (REGISTER_SAVE_VEC_OFF + VEC_SIZE)(%rsp), %VEC(1)
+	VMOV (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 2)(%rsp), %VEC(2)
+	VMOV (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 3)(%rsp), %VEC(3)
+	VMOV (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 4)(%rsp), %VEC(4)
+	VMOV (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 5)(%rsp), %VEC(5)
+	VMOV (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 6)(%rsp), %VEC(6)
+	VMOV (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 7)(%rsp), %VEC(7)
+#if DL_RUNIME_RESOLVE_REALIGN_STACK
+	mov %RBX_LP, %RSP_LP
+	cfi_def_cfa_register(%rsp)
+	movq (%rsp), %rbx
+	cfi_restore(%rbx)
+#endif
+	# Adjust stack(PLT did 2 pushes)
+	add $(LOCAL_STORAGE_AREA + 16), %RSP_LP
+	cfi_adjust_cfa_offset(-(LOCAL_STORAGE_AREA + 16))
+	# Preserve bound registers.
+	PRESERVE_BND_REGS_PREFIX
+	jmp *%r11		# Jump to function address.
+	cfi_endproc
+	.size _dl_runtime_resolve, .-_dl_runtime_resolve
+
+
+/* To preserve %xmm0 - %xmm7 registers, dl-trampoline.h is included
+   twice, for _dl_runtime_resolve_sse and _dl_runtime_resolve_sse_vex.
+   But we don't need another _dl_runtime_profile for XMM registers.  */
+#if !defined PROF && defined _dl_runtime_profile
+# if (LR_VECTOR_OFFSET % VEC_SIZE) != 0
+#  error LR_VECTOR_OFFSET must be multples of VEC_SIZE
+# endif
+
+	.globl _dl_runtime_profile
+	.hidden _dl_runtime_profile
+	.type _dl_runtime_profile, @function
+	.align 16
+_dl_runtime_profile:
+	cfi_startproc
+	cfi_adjust_cfa_offset(16) # Incorporate PLT
+	/* The La_x86_64_regs data structure pointed to by the
+	   fourth paramater must be VEC_SIZE-byte aligned.  This must
+	   be explicitly enforced.  We have the set up a dynamically
+	   sized stack frame.  %rbx points to the top half which
+	   has a fixed size and preserves the original stack pointer.  */
+
+	sub $32, %RSP_LP	# Allocate the local storage.
+	cfi_adjust_cfa_offset(32)
+	movq %rbx, (%rsp)
+	cfi_rel_offset(%rbx, 0)
+
+	/* On the stack:
+		56(%rbx)	parameter #1
+		48(%rbx)	return address
+
+		40(%rbx)	reloc index
+		32(%rbx)	link_map
+
+		24(%rbx)	La_x86_64_regs pointer
+		16(%rbx)	framesize
+		 8(%rbx)	rax
+		  (%rbx)	rbx
+	*/
+
+	movq %rax, 8(%rsp)
+	mov %RSP_LP, %RBX_LP
+	cfi_def_cfa_register(%rbx)
+
+	/* Actively align the La_x86_64_regs structure.  */
+	and $-VEC_SIZE, %RSP_LP
+# if defined HAVE_AVX_SUPPORT || defined HAVE_AVX512_ASM_SUPPORT
+	/* sizeof(La_x86_64_regs).  Need extra space for 8 SSE registers
+	   to detect if any xmm0-xmm7 registers are changed by audit
+	   module.  */
+	sub $(LR_SIZE + XMM_SIZE*8), %RSP_LP
+# else
+	sub $LR_SIZE, %RSP_LP		# sizeof(La_x86_64_regs)
+# endif
+	movq %rsp, 24(%rbx)
+
+	/* Fill the La_x86_64_regs structure.  */
+	movq %rdx, LR_RDX_OFFSET(%rsp)
+	movq %r8,  LR_R8_OFFSET(%rsp)
+	movq %r9,  LR_R9_OFFSET(%rsp)
+	movq %rcx, LR_RCX_OFFSET(%rsp)
+	movq %rsi, LR_RSI_OFFSET(%rsp)
+	movq %rdi, LR_RDI_OFFSET(%rsp)
+	movq %rbp, LR_RBP_OFFSET(%rsp)
+
+	lea 48(%rbx), %RAX_LP
+	movq %rax, LR_RSP_OFFSET(%rsp)
+
+	/* We always store the XMM registers even if AVX is available.
+	   This is to provide backward binary compatibility for existing
+	   audit modules.  */
+	movaps %xmm0,		   (LR_XMM_OFFSET)(%rsp)
+	movaps %xmm1, (LR_XMM_OFFSET +   XMM_SIZE)(%rsp)
+	movaps %xmm2, (LR_XMM_OFFSET + XMM_SIZE*2)(%rsp)
+	movaps %xmm3, (LR_XMM_OFFSET + XMM_SIZE*3)(%rsp)
+	movaps %xmm4, (LR_XMM_OFFSET + XMM_SIZE*4)(%rsp)
+	movaps %xmm5, (LR_XMM_OFFSET + XMM_SIZE*5)(%rsp)
+	movaps %xmm6, (LR_XMM_OFFSET + XMM_SIZE*6)(%rsp)
+	movaps %xmm7, (LR_XMM_OFFSET + XMM_SIZE*7)(%rsp)
+
+# ifndef __ILP32__
+#  ifdef HAVE_MPX_SUPPORT
+	bndmov %bnd0, 		   (LR_BND_OFFSET)(%rsp)  # Preserve bound
+	bndmov %bnd1, (LR_BND_OFFSET +   BND_SIZE)(%rsp)  # registers. Nops if
+	bndmov %bnd2, (LR_BND_OFFSET + BND_SIZE*2)(%rsp)  # MPX not available
+	bndmov %bnd3, (LR_BND_OFFSET + BND_SIZE*3)(%rsp)  # or disabled.
+#  else
+	.byte 0x66,0x0f,0x1b,0x84,0x24;.long (LR_BND_OFFSET)
+	.byte 0x66,0x0f,0x1b,0x8c,0x24;.long (LR_BND_OFFSET + BND_SIZE)
+	.byte 0x66,0x0f,0x1b,0x94,0x24;.long (LR_BND_OFFSET + BND_SIZE*2)
+	.byte 0x66,0x0f,0x1b,0x9c,0x24;.long (LR_BND_OFFSET + BND_SIZE*3)
+#  endif
+# endif
+
+# ifdef RESTORE_AVX
 	/* This is to support AVX audit modules.  */
-	VMOV %VEC(0),		      (LR_VECTOR_OFFSET)(%rsp)
-	VMOV %VEC(1), (LR_VECTOR_OFFSET +   VECTOR_SIZE)(%rsp)
-	VMOV %VEC(2), (LR_VECTOR_OFFSET + VECTOR_SIZE*2)(%rsp)
-	VMOV %VEC(3), (LR_VECTOR_OFFSET + VECTOR_SIZE*3)(%rsp)
-	VMOV %VEC(4), (LR_VECTOR_OFFSET + VECTOR_SIZE*4)(%rsp)
-	VMOV %VEC(5), (LR_VECTOR_OFFSET + VECTOR_SIZE*5)(%rsp)
-	VMOV %VEC(6), (LR_VECTOR_OFFSET + VECTOR_SIZE*6)(%rsp)
-	VMOV %VEC(7), (LR_VECTOR_OFFSET + VECTOR_SIZE*7)(%rsp)
+	VMOVA %VEC(0),		      (LR_VECTOR_OFFSET)(%rsp)
+	VMOVA %VEC(1), (LR_VECTOR_OFFSET +   VECTOR_SIZE)(%rsp)
+	VMOVA %VEC(2), (LR_VECTOR_OFFSET + VECTOR_SIZE*2)(%rsp)
+	VMOVA %VEC(3), (LR_VECTOR_OFFSET + VECTOR_SIZE*3)(%rsp)
+	VMOVA %VEC(4), (LR_VECTOR_OFFSET + VECTOR_SIZE*4)(%rsp)
+	VMOVA %VEC(5), (LR_VECTOR_OFFSET + VECTOR_SIZE*5)(%rsp)
+	VMOVA %VEC(6), (LR_VECTOR_OFFSET + VECTOR_SIZE*6)(%rsp)
+	VMOVA %VEC(7), (LR_VECTOR_OFFSET + VECTOR_SIZE*7)(%rsp)
 
 	/* Save xmm0-xmm7 registers to detect if any of them are
 	   changed by audit module.  */
@@ -38,7 +376,7 @@
 	vmovdqa %xmm5, (LR_SIZE + XMM_SIZE*5)(%rsp)
 	vmovdqa %xmm6, (LR_SIZE + XMM_SIZE*6)(%rsp)
 	vmovdqa %xmm7, (LR_SIZE + XMM_SIZE*7)(%rsp)
-#endif
+# endif
 
 	mov %RSP_LP, %RCX_LP	# La_x86_64_regs pointer to %rcx.
 	mov 48(%rbx), %RDX_LP	# Load return address if needed.
@@ -63,21 +401,7 @@
 	movaps (LR_XMM_OFFSET + XMM_SIZE*6)(%rsp), %xmm6
 	movaps (LR_XMM_OFFSET + XMM_SIZE*7)(%rsp), %xmm7
 
-#ifndef __ILP32__
-# ifdef HAVE_MPX_SUPPORT
-	bndmov 		    (LR_BND_OFFSET)(%rsp), %bnd0  # Restore bound
-	bndmov (LR_BND_OFFSET +   BND_SIZE)(%rsp), %bnd1  # registers.
-	bndmov (LR_BND_OFFSET + BND_SIZE*2)(%rsp), %bnd2
-	bndmov (LR_BND_OFFSET + BND_SIZE*3)(%rsp), %bnd3
-# else
-	.byte 0x66,0x0f,0x1a,0x84,0x24;.long (LR_BND_OFFSET)
-	.byte 0x66,0x0f,0x1a,0x8c,0x24;.long (LR_BND_OFFSET + BND_SIZE)
-	.byte 0x66,0x0f,0x1a,0x94,0x24;.long (LR_BND_OFFSET + BND_SIZE*2)
-	.byte 0x66,0x0f,0x1a,0x9c,0x24;.long (LR_BND_OFFSET + BND_SIZE*3)
-# endif
-#endif
-
-#ifdef RESTORE_AVX
+# ifdef RESTORE_AVX
 	/* Check if any xmm0-xmm7 registers are changed by audit
 	   module.  */
 	vpcmpeqq (LR_SIZE)(%rsp), %xmm0, %xmm8
@@ -86,7 +410,7 @@
 	je 2f
 	vmovdqa	%xmm0, (LR_VECTOR_OFFSET)(%rsp)
 	jmp 1f
-2:	VMOV (LR_VECTOR_OFFSET)(%rsp), %VEC(0)
+2:	VMOVA (LR_VECTOR_OFFSET)(%rsp), %VEC(0)
 	vmovdqa	%xmm0, (LR_XMM_OFFSET)(%rsp)
 
 1:	vpcmpeqq (LR_SIZE + XMM_SIZE)(%rsp), %xmm1, %xmm8
@@ -95,7 +419,7 @@
 	je 2f
 	vmovdqa	%xmm1, (LR_VECTOR_OFFSET + VECTOR_SIZE)(%rsp)
 	jmp 1f
-2:	VMOV (LR_VECTOR_OFFSET + VECTOR_SIZE)(%rsp), %VEC(1)
+2:	VMOVA (LR_VECTOR_OFFSET + VECTOR_SIZE)(%rsp), %VEC(1)
 	vmovdqa	%xmm1, (LR_XMM_OFFSET + XMM_SIZE)(%rsp)
 
 1:	vpcmpeqq (LR_SIZE + XMM_SIZE*2)(%rsp), %xmm2, %xmm8
@@ -104,7 +428,7 @@
 	je 2f
 	vmovdqa	%xmm2, (LR_VECTOR_OFFSET + VECTOR_SIZE*2)(%rsp)
 	jmp 1f
-2:	VMOV (LR_VECTOR_OFFSET + VECTOR_SIZE*2)(%rsp), %VEC(2)
+2:	VMOVA (LR_VECTOR_OFFSET + VECTOR_SIZE*2)(%rsp), %VEC(2)
 	vmovdqa	%xmm2, (LR_XMM_OFFSET + XMM_SIZE*2)(%rsp)
 
 1:	vpcmpeqq (LR_SIZE + XMM_SIZE*3)(%rsp), %xmm3, %xmm8
@@ -113,7 +437,7 @@
 	je 2f
 	vmovdqa	%xmm3, (LR_VECTOR_OFFSET + VECTOR_SIZE*3)(%rsp)
 	jmp 1f
-2:	VMOV (LR_VECTOR_OFFSET + VECTOR_SIZE*3)(%rsp), %VEC(3)
+2:	VMOVA (LR_VECTOR_OFFSET + VECTOR_SIZE*3)(%rsp), %VEC(3)
 	vmovdqa	%xmm3, (LR_XMM_OFFSET + XMM_SIZE*3)(%rsp)
 
 1:	vpcmpeqq (LR_SIZE + XMM_SIZE*4)(%rsp), %xmm4, %xmm8
@@ -122,7 +446,7 @@
 	je 2f
 	vmovdqa	%xmm4, (LR_VECTOR_OFFSET + VECTOR_SIZE*4)(%rsp)
 	jmp 1f
-2:	VMOV (LR_VECTOR_OFFSET + VECTOR_SIZE*4)(%rsp), %VEC(4)
+2:	VMOVA (LR_VECTOR_OFFSET + VECTOR_SIZE*4)(%rsp), %VEC(4)
 	vmovdqa	%xmm4, (LR_XMM_OFFSET + XMM_SIZE*4)(%rsp)
 
 1:	vpcmpeqq (LR_SIZE + XMM_SIZE*5)(%rsp), %xmm5, %xmm8
@@ -131,7 +455,7 @@
 	je 2f
 	vmovdqa	%xmm5, (LR_VECTOR_OFFSET + VECTOR_SIZE*5)(%rsp)
 	jmp 1f
-2:	VMOV (LR_VECTOR_OFFSET + VECTOR_SIZE*5)(%rsp), %VEC(5)
+2:	VMOVA (LR_VECTOR_OFFSET + VECTOR_SIZE*5)(%rsp), %VEC(5)
 	vmovdqa	%xmm5, (LR_XMM_OFFSET + XMM_SIZE*5)(%rsp)
 
 1:	vpcmpeqq (LR_SIZE + XMM_SIZE*6)(%rsp), %xmm6, %xmm8
@@ -140,7 +464,7 @@
 	je 2f
 	vmovdqa	%xmm6, (LR_VECTOR_OFFSET + VECTOR_SIZE*6)(%rsp)
 	jmp 1f
-2:	VMOV (LR_VECTOR_OFFSET + VECTOR_SIZE*6)(%rsp), %VEC(6)
+2:	VMOVA (LR_VECTOR_OFFSET + VECTOR_SIZE*6)(%rsp), %VEC(6)
 	vmovdqa	%xmm6, (LR_XMM_OFFSET + XMM_SIZE*6)(%rsp)
 
 1:	vpcmpeqq (LR_SIZE + XMM_SIZE*7)(%rsp), %xmm7, %xmm8
@@ -149,13 +473,29 @@
 	je 2f
 	vmovdqa	%xmm7, (LR_VECTOR_OFFSET + VECTOR_SIZE*7)(%rsp)
 	jmp 1f
-2:	VMOV (LR_VECTOR_OFFSET + VECTOR_SIZE*7)(%rsp), %VEC(7)
+2:	VMOVA (LR_VECTOR_OFFSET + VECTOR_SIZE*7)(%rsp), %VEC(7)
 	vmovdqa	%xmm7, (LR_XMM_OFFSET + XMM_SIZE*7)(%rsp)
 
 1:
-#endif
+# endif
+
+# ifndef __ILP32__
+#  ifdef HAVE_MPX_SUPPORT
+	bndmov              (LR_BND_OFFSET)(%rsp), %bnd0  # Restore bound
+	bndmov (LR_BND_OFFSET +   BND_SIZE)(%rsp), %bnd1  # registers.
+	bndmov (LR_BND_OFFSET + BND_SIZE*2)(%rsp), %bnd2
+	bndmov (LR_BND_OFFSET + BND_SIZE*3)(%rsp), %bnd3
+#  else
+	.byte 0x66,0x0f,0x1a,0x84,0x24;.long (LR_BND_OFFSET)
+	.byte 0x66,0x0f,0x1a,0x8c,0x24;.long (LR_BND_OFFSET + BND_SIZE)
+	.byte 0x66,0x0f,0x1a,0x94,0x24;.long (LR_BND_OFFSET + BND_SIZE*2)
+	.byte 0x66,0x0f,0x1a,0x9c,0x24;.long (LR_BND_OFFSET + BND_SIZE*3)
+#  endif
+# endif
+
 	mov  16(%rbx), %R10_LP	# Anything in framesize?
 	test %R10_LP, %R10_LP
+	PRESERVE_BND_REGS_PREFIX
 	jns 3f
 
 	/* There's nothing in the frame size, so there
@@ -166,14 +506,15 @@
 	movq LR_RSI_OFFSET(%rsp), %rsi
 	movq LR_RDI_OFFSET(%rsp), %rdi
 
-	movq %rbx, %rsp
+	mov %RBX_LP, %RSP_LP
 	movq (%rsp), %rbx
-	cfi_restore(rbx)
+	cfi_restore(%rbx)
 	cfi_def_cfa_register(%rsp)
 
-	addq $48, %rsp		# Adjust the stack to the return value
+	add $48, %RSP_LP	# Adjust the stack to the return value
 				# (eats the reloc index and link_map)
 	cfi_adjust_cfa_offset(-48)
+	PRESERVE_BND_REGS_PREFIX
 	jmp *%r11		# Jump to function address.
 
 3:
@@ -186,13 +527,13 @@
 	   temporary buffer of the size specified by the 'framesize'
 	   returned from _dl_profile_fixup */
 
-	leaq LR_RSP_OFFSET(%rbx), %rsi	# stack
-	addq $8, %r10
-	andq $0xfffffffffffffff0, %r10
-	movq %r10, %rcx
-	subq %r10, %rsp
-	movq %rsp, %rdi
-	shrq $3, %rcx
+	lea LR_RSP_OFFSET(%rbx), %RSI_LP # stack
+	add $8, %R10_LP
+	and $-16, %R10_LP
+	mov %R10_LP, %RCX_LP
+	sub %R10_LP, %RSP_LP
+	mov %RSP_LP, %RDI_LP
+	shr $3, %RCX_LP
 	rep
 	movsq
 
@@ -200,23 +541,24 @@
 	movq 32(%rdi), %rsi
 	movq 40(%rdi), %rdi
 
+	PRESERVE_BND_REGS_PREFIX
 	call *%r11
 
-	mov 24(%rbx), %rsp	# Drop the copied stack content
+	mov 24(%rbx), %RSP_LP	# Drop the copied stack content
 
 	/* Now we have to prepare the La_x86_64_retval structure for the
 	   _dl_call_pltexit.  The La_x86_64_regs is being pointed by rsp now,
 	   so we just need to allocate the sizeof(La_x86_64_retval) space on
 	   the stack, since the alignment has already been taken care of. */
-#ifdef RESTORE_AVX
+# ifdef RESTORE_AVX
 	/* sizeof(La_x86_64_retval).  Need extra space for 2 SSE
 	   registers to detect if xmm0/xmm1 registers are changed
 	   by audit module.  */
-	subq $(LRV_SIZE + XMM_SIZE*2), %rsp
-#else
-	subq $LRV_SIZE, %rsp	# sizeof(La_x86_64_retval)
-#endif
-	movq %rsp, %rcx		# La_x86_64_retval argument to %rcx.
+	sub $(LRV_SIZE + XMM_SIZE*2), %RSP_LP
+# else
+	sub $LRV_SIZE, %RSP_LP	# sizeof(La_x86_64_retval)
+# endif
+	mov %RSP_LP, %RCX_LP	# La_x86_64_retval argument to %rcx.
 
 	/* Fill in the La_x86_64_retval structure.  */
 	movq %rax, LRV_RAX_OFFSET(%rcx)
@@ -225,26 +567,26 @@
 	movaps %xmm0, LRV_XMM0_OFFSET(%rcx)
 	movaps %xmm1, LRV_XMM1_OFFSET(%rcx)
 
-#ifdef RESTORE_AVX
+# ifdef RESTORE_AVX
 	/* This is to support AVX audit modules.  */
-	VMOV %VEC(0), LRV_VECTOR0_OFFSET(%rcx)
-	VMOV %VEC(1), LRV_VECTOR1_OFFSET(%rcx)
+	VMOVA %VEC(0), LRV_VECTOR0_OFFSET(%rcx)
+	VMOVA %VEC(1), LRV_VECTOR1_OFFSET(%rcx)
 
 	/* Save xmm0/xmm1 registers to detect if they are changed
 	   by audit module.  */
 	vmovdqa %xmm0,		  (LRV_SIZE)(%rcx)
 	vmovdqa %xmm1, (LRV_SIZE + XMM_SIZE)(%rcx)
-#endif
+# endif
 
-#ifndef __ILP32__
-# ifdef HAVE_MPX_SUPPORT
+# ifndef __ILP32__
+#  ifdef HAVE_MPX_SUPPORT
 	bndmov %bnd0, LRV_BND0_OFFSET(%rcx)  # Preserve returned bounds.
 	bndmov %bnd1, LRV_BND1_OFFSET(%rcx)
-# else
+#  else
 	.byte  0x66,0x0f,0x1b,0x81;.long (LRV_BND0_OFFSET)
 	.byte  0x66,0x0f,0x1b,0x89;.long (LRV_BND1_OFFSET)
+#  endif
 # endif
-#endif
 
 	fstpt LRV_ST0_OFFSET(%rcx)
 	fstpt LRV_ST1_OFFSET(%rcx)
@@ -261,49 +603,47 @@
 	movaps LRV_XMM0_OFFSET(%rsp), %xmm0
 	movaps LRV_XMM1_OFFSET(%rsp), %xmm1
 
-#ifdef RESTORE_AVX
+# ifdef RESTORE_AVX
 	/* Check if xmm0/xmm1 registers are changed by audit module.  */
 	vpcmpeqq (LRV_SIZE)(%rsp), %xmm0, %xmm2
 	vpmovmskb %xmm2, %esi
 	cmpl $0xffff, %esi
 	jne 1f
-	VMOV LRV_VECTOR0_OFFSET(%rsp), %VEC(0)
+	VMOVA LRV_VECTOR0_OFFSET(%rsp), %VEC(0)
 
 1:	vpcmpeqq (LRV_SIZE + XMM_SIZE)(%rsp), %xmm1, %xmm2
 	vpmovmskb %xmm2, %esi
 	cmpl $0xffff, %esi
 	jne 1f
-	VMOV LRV_VECTOR1_OFFSET(%rsp), %VEC(1)
+	VMOVA LRV_VECTOR1_OFFSET(%rsp), %VEC(1)
 
 1:
-#endif
+# endif
 
-#ifndef __ILP32__
-# ifdef HAVE_MPX_SUPPORT
-	bndmov LRV_BND0_OFFSET(%rcx), %bnd0  # Restore bound registers.
-	bndmov LRV_BND1_OFFSET(%rcx), %bnd1
-# else
-	.byte  0x66,0x0f,0x1a,0x81;.long (LRV_BND0_OFFSET)
-	.byte  0x66,0x0f,0x1a,0x89;.long (LRV_BND1_OFFSET)
+# ifndef __ILP32__
+#  ifdef HAVE_MPX_SUPPORT
+	bndmov LRV_BND0_OFFSET(%rsp), %bnd0  # Restore bound registers.
+	bndmov LRV_BND1_OFFSET(%rsp), %bnd1
+#  else
+	.byte  0x66,0x0f,0x1a,0x84,0x24;.long (LRV_BND0_OFFSET)
+	.byte  0x66,0x0f,0x1a,0x8c,0x24;.long (LRV_BND1_OFFSET)
+#  endif
 # endif
-#endif
 
 	fldt LRV_ST1_OFFSET(%rsp)
 	fldt LRV_ST0_OFFSET(%rsp)
 
-	movq %rbx, %rsp
+	mov %RBX_LP, %RSP_LP
 	movq (%rsp), %rbx
-	cfi_restore(rbx)
+	cfi_restore(%rbx)
 	cfi_def_cfa_register(%rsp)
 
-	addq $48, %rsp		# Adjust the stack to the return value
+	add $48, %RSP_LP	# Adjust the stack to the return value
 				# (eats the reloc index and link_map)
 	cfi_adjust_cfa_offset(-48)
+	PRESERVE_BND_REGS_PREFIX
 	retq
 
-#ifdef MORE_CODE
-	cfi_adjust_cfa_offset(48)
-	cfi_rel_offset(%rbx, 0)
-	cfi_def_cfa_register(%rbx)
-# undef MORE_CODE
+	cfi_endproc
+	.size _dl_runtime_profile, .-_dl_runtime_profile
 #endif
Index: glibc-2.17-c758a686/sysdeps/x86_64/ifuncmain8.c
===================================================================
--- /dev/null
+++ glibc-2.17-c758a686/sysdeps/x86_64/ifuncmain8.c
@@ -0,0 +1,32 @@
+/* Test IFUNC selector with floating-point parameters.
+   Copyright (C) 2015 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
+   modify it under the terms of the GNU Lesser General Public
+   License as published by the Free Software Foundation; either
+   version 2.1 of the License, or (at your option) any later version.
+
+   The GNU C Library is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   Lesser General Public License for more details.
+
+   You should have received a copy of the GNU Lesser General Public
+   License along with the GNU C Library; if not, see
+   <http://www.gnu.org/licenses/>.  */
+
+#include <stdlib.h>
+
+extern float foo (float);
+
+static int
+do_test (void)
+{
+  if (foo (2) != 3)
+    abort ();
+  return 0;
+}
+
+#define TEST_FUNCTION do_test ()
+#include "../test-skeleton.c"
Index: glibc-2.17-c758a686/sysdeps/x86_64/ifuncmod8.c
===================================================================
--- /dev/null
+++ glibc-2.17-c758a686/sysdeps/x86_64/ifuncmod8.c
@@ -0,0 +1,36 @@
+/* Test IFUNC selector with floating-point parameters.
+   Copyright (C) 2015 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
+   modify it under the terms of the GNU Lesser General Public
+   License as published by the Free Software Foundation; either
+   version 2.1 of the License, or (at your option) any later version.
+
+   The GNU C Library is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   Lesser General Public License for more details.
+
+   You should have received a copy of the GNU Lesser General Public
+   License along with the GNU C Library; if not, see
+   <http://www.gnu.org/licenses/>.  */
+
+#include <emmintrin.h>
+
+void * foo_ifunc (void) __asm__ ("foo");
+__asm__(".type foo, %gnu_indirect_function");
+
+static float
+foo_impl (float x)
+{
+  return x + 1;
+}
+
+void *
+foo_ifunc (void)
+{
+  __m128i xmm = _mm_set1_epi32 (-1);
+  asm volatile ("movdqa %0, %%xmm0" : : "x" (xmm) : "xmm0" );
+  return foo_impl;
+}
Index: glibc-2.17-c758a686/sysdeps/x86_64/tst-avx-aux.c
===================================================================
--- /dev/null
+++ glibc-2.17-c758a686/sysdeps/x86_64/tst-avx-aux.c
@@ -0,0 +1,47 @@
+/* Test case for preserved AVX registers in dynamic linker, -mavx part.
+   Copyright (C) 2017 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
+   modify it under the terms of the GNU Lesser General Public
+   License as published by the Free Software Foundation; either
+   version 2.1 of the License, or (at your option) any later version.
+
+   The GNU C Library is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   Lesser General Public License for more details.
+
+   You should have received a copy of the GNU Lesser General Public
+   License along with the GNU C Library; if not, see
+   <http://www.gnu.org/licenses/>.  */
+
+#include <immintrin.h>
+#include <stdlib.h>
+#include <string.h>
+
+int
+tst_avx_aux (void)
+{
+#ifdef __AVX__
+  extern __m256i avx_test (__m256i, __m256i, __m256i, __m256i,
+			   __m256i, __m256i, __m256i, __m256i);
+
+  __m256i ymm0 = _mm256_set1_epi32 (0);
+  __m256i ymm1 = _mm256_set1_epi32 (1);
+  __m256i ymm2 = _mm256_set1_epi32 (2);
+  __m256i ymm3 = _mm256_set1_epi32 (3);
+  __m256i ymm4 = _mm256_set1_epi32 (4);
+  __m256i ymm5 = _mm256_set1_epi32 (5);
+  __m256i ymm6 = _mm256_set1_epi32 (6);
+  __m256i ymm7 = _mm256_set1_epi32 (7);
+  __m256i ret = avx_test (ymm0, ymm1, ymm2, ymm3,
+			  ymm4, ymm5, ymm6, ymm7);
+  ymm0 =  _mm256_set1_epi32 (0x12349876);
+  if (memcmp (&ymm0, &ret, sizeof (ret)))
+    abort ();
+  return 0;
+#else  /* __AVX__ */
+  return 77;
+#endif  /* __AVX__ */
+}
Index: glibc-2.17-c758a686/sysdeps/x86_64/tst-avx.c
===================================================================
--- /dev/null
+++ glibc-2.17-c758a686/sysdeps/x86_64/tst-avx.c
@@ -0,0 +1,49 @@
+/* Test case for preserved AVX registers in dynamic linker.
+   Copyright (C) 2017 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
+   modify it under the terms of the GNU Lesser General Public
+   License as published by the Free Software Foundation; either
+   version 2.1 of the License, or (at your option) any later version.
+
+   The GNU C Library is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   Lesser General Public License for more details.
+
+   You should have received a copy of the GNU Lesser General Public
+   License along with the GNU C Library; if not, see
+   <http://www.gnu.org/licenses/>.  */
+
+#include <cpuid.h>
+
+int tst_avx_aux (void);
+
+static int
+avx_enabled (void)
+{
+  unsigned int eax, ebx, ecx, edx;
+
+  if (__get_cpuid (1, &eax, &ebx, &ecx, &edx) == 0
+      || (ecx & (bit_AVX | bit_OSXSAVE)) != (bit_AVX | bit_OSXSAVE))
+    return 0;
+
+  /* Check the OS has AVX and SSE saving enabled.  */
+  asm ("xgetbv" : "=a" (eax), "=d" (edx) : "c" (0));
+
+  return (eax & 6) == 6;
+}
+
+static int
+do_test (void)
+{
+  /* Run AVX test only if AVX is supported.  */
+  if (avx_enabled ())
+    return tst_avx_aux ();
+  else
+    return 77;
+}
+
+#define TEST_FUNCTION do_test ()
+#include "../../test-skeleton.c"
Index: glibc-2.17-c758a686/sysdeps/x86_64/tst-avx512-aux.c
===================================================================
--- /dev/null
+++ glibc-2.17-c758a686/sysdeps/x86_64/tst-avx512-aux.c
@@ -0,0 +1,48 @@
+/* Test case for preserved AVX512 registers in dynamic linker,
+   -mavx512 part.
+   Copyright (C) 2017 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
+   modify it under the terms of the GNU Lesser General Public
+   License as published by the Free Software Foundation; either
+   version 2.1 of the License, or (at your option) any later version.
+
+   The GNU C Library is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   Lesser General Public License for more details.
+
+   You should have received a copy of the GNU Lesser General Public
+   License along with the GNU C Library; if not, see
+   <http://www.gnu.org/licenses/>.  */
+
+#include <immintrin.h>
+#include <stdlib.h>
+#include <string.h>
+
+int
+tst_avx512_aux (void)
+{
+#ifdef __AVX512F__
+  extern __m512i avx512_test (__m512i, __m512i, __m512i, __m512i,
+			      __m512i, __m512i, __m512i, __m512i);
+
+  __m512i zmm0 = _mm512_set1_epi32 (0);
+  __m512i zmm1 = _mm512_set1_epi32 (1);
+  __m512i zmm2 = _mm512_set1_epi32 (2);
+  __m512i zmm3 = _mm512_set1_epi32 (3);
+  __m512i zmm4 = _mm512_set1_epi32 (4);
+  __m512i zmm5 = _mm512_set1_epi32 (5);
+  __m512i zmm6 = _mm512_set1_epi32 (6);
+  __m512i zmm7 = _mm512_set1_epi32 (7);
+  __m512i ret = avx512_test (zmm0, zmm1, zmm2, zmm3,
+			     zmm4, zmm5, zmm6, zmm7);
+  zmm0 =  _mm512_set1_epi32 (0x12349876);
+  if (memcmp (&zmm0, &ret, sizeof (ret)))
+    abort ();
+  return 0;
+#else  /* __AVX512F__ */
+  return 77;
+#endif  /* __AVX512F__ */
+}
Index: glibc-2.17-c758a686/sysdeps/x86_64/tst-avx512.c
===================================================================
--- /dev/null
+++ glibc-2.17-c758a686/sysdeps/x86_64/tst-avx512.c
@@ -0,0 +1,57 @@
+/* Test case for preserved AVX512 registers in dynamic linker.
+   Copyright (C) 2017 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
+   modify it under the terms of the GNU Lesser General Public
+   License as published by the Free Software Foundation; either
+   version 2.1 of the License, or (at your option) any later version.
+
+   The GNU C Library is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   Lesser General Public License for more details.
+
+   You should have received a copy of the GNU Lesser General Public
+   License along with the GNU C Library; if not, see
+   <http://www.gnu.org/licenses/>.  */
+
+#include <cpuid.h>
+
+int tst_avx512_aux (void);
+
+static int
+avx512_enabled (void)
+{
+#ifdef bit_AVX512F
+  unsigned int eax, ebx, ecx, edx;
+
+  if (__get_cpuid (1, &eax, &ebx, &ecx, &edx) == 0
+      || (ecx & (bit_AVX | bit_OSXSAVE)) != (bit_AVX | bit_OSXSAVE))
+    return 0;
+
+  __cpuid_count (7, 0, eax, ebx, ecx, edx);
+  if (!(ebx & bit_AVX512F))
+    return 0;
+
+  asm ("xgetbv" : "=a" (eax), "=d" (edx) : "c" (0));
+
+  /* Verify that ZMM, YMM and XMM states are enabled.  */
+  return (eax & 0xe6) == 0xe6;
+#else
+  return 0;
+#endif
+}
+
+static int
+do_test (void)
+{
+  /* Run AVX512 test only if AVX512 is supported.  */
+  if (avx512_enabled ())
+    return tst_avx512_aux ();
+  else
+    return 77;
+}
+
+#define TEST_FUNCTION do_test ()
+#include "../../test-skeleton.c"
Index: glibc-2.17-c758a686/sysdeps/x86_64/tst-avx512mod.c
===================================================================
--- /dev/null
+++ glibc-2.17-c758a686/sysdeps/x86_64/tst-avx512mod.c
@@ -0,0 +1,48 @@
+/* Test case for x86-64 preserved AVX512 registers in dynamic linker.  */
+
+#ifdef __AVX512F__
+#include <stdlib.h>
+#include <string.h>
+#include <immintrin.h>
+
+__m512i
+avx512_test (__m512i x0, __m512i x1, __m512i x2, __m512i x3,
+	     __m512i x4, __m512i x5, __m512i x6, __m512i x7)
+{
+  __m512i zmm;
+
+  zmm = _mm512_set1_epi32 (0);
+  if (memcmp (&zmm, &x0, sizeof (zmm)))
+    abort ();
+
+  zmm = _mm512_set1_epi32 (1);
+  if (memcmp (&zmm, &x1, sizeof (zmm)))
+    abort ();
+
+  zmm = _mm512_set1_epi32 (2);
+  if (memcmp (&zmm, &x2, sizeof (zmm)))
+    abort ();
+
+  zmm = _mm512_set1_epi32 (3);
+  if (memcmp (&zmm, &x3, sizeof (zmm)))
+    abort ();
+
+  zmm = _mm512_set1_epi32 (4);
+  if (memcmp (&zmm, &x4, sizeof (zmm)))
+    abort ();
+
+  zmm = _mm512_set1_epi32 (5);
+  if (memcmp (&zmm, &x5, sizeof (zmm)))
+    abort ();
+
+  zmm = _mm512_set1_epi32 (6);
+  if (memcmp (&zmm, &x6, sizeof (zmm)))
+    abort ();
+
+  zmm = _mm512_set1_epi32 (7);
+  if (memcmp (&zmm, &x7, sizeof (zmm)))
+    abort ();
+
+  return _mm512_set1_epi32 (0x12349876);
+}
+#endif
Index: glibc-2.17-c758a686/sysdeps/x86_64/tst-ssemod.c
===================================================================
--- /dev/null
+++ glibc-2.17-c758a686/sysdeps/x86_64/tst-ssemod.c
@@ -0,0 +1,46 @@
+/* Test case for x86-64 preserved SSE registers in dynamic linker.  */
+
+#include <stdlib.h>
+#include <string.h>
+#include <immintrin.h>
+
+__m128i
+sse_test (__m128i x0, __m128i x1, __m128i x2, __m128i x3,
+	  __m128i x4, __m128i x5, __m128i x6, __m128i x7)
+{
+  __m128i xmm;
+
+  xmm = _mm_set1_epi32 (0);
+  if (memcmp (&xmm, &x0, sizeof (xmm)))
+    abort ();
+
+  xmm = _mm_set1_epi32 (1);
+  if (memcmp (&xmm, &x1, sizeof (xmm)))
+    abort ();
+
+  xmm = _mm_set1_epi32 (2);
+  if (memcmp (&xmm, &x2, sizeof (xmm)))
+    abort ();
+
+  xmm = _mm_set1_epi32 (3);
+  if (memcmp (&xmm, &x3, sizeof (xmm)))
+    abort ();
+
+  xmm = _mm_set1_epi32 (4);
+  if (memcmp (&xmm, &x4, sizeof (xmm)))
+    abort ();
+
+  xmm = _mm_set1_epi32 (5);
+  if (memcmp (&xmm, &x5, sizeof (xmm)))
+    abort ();
+
+  xmm = _mm_set1_epi32 (6);
+  if (memcmp (&xmm, &x6, sizeof (xmm)))
+    abort ();
+
+  xmm = _mm_set1_epi32 (7);
+  if (memcmp (&xmm, &x7, sizeof (xmm)))
+    abort ();
+
+  return _mm_set1_epi32 (0x12349876);
+}
Index: glibc-2.17-c758a686/sysdeps/x86_64/tst-sse.c
===================================================================
--- /dev/null
+++ glibc-2.17-c758a686/sysdeps/x86_64/tst-sse.c
@@ -0,0 +1,46 @@
+/* Test case for preserved SSE registers in dynamic linker.
+   Copyright (C) 2017 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
+   modify it under the terms of the GNU Lesser General Public
+   License as published by the Free Software Foundation; either
+   version 2.1 of the License, or (at your option) any later version.
+
+   The GNU C Library is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   Lesser General Public License for more details.
+
+   You should have received a copy of the GNU Lesser General Public
+   License along with the GNU C Library; if not, see
+   <http://www.gnu.org/licenses/>.  */
+
+#include <immintrin.h>
+#include <stdlib.h>
+#include <string.h>
+
+extern __m128i sse_test (__m128i, __m128i, __m128i, __m128i,
+                        __m128i, __m128i, __m128i, __m128i);
+
+static int
+do_test (void)
+{
+  __m128i xmm0 = _mm_set1_epi32 (0);
+  __m128i xmm1 = _mm_set1_epi32 (1);
+  __m128i xmm2 = _mm_set1_epi32 (2);
+  __m128i xmm3 = _mm_set1_epi32 (3);
+  __m128i xmm4 = _mm_set1_epi32 (4);
+  __m128i xmm5 = _mm_set1_epi32 (5);
+  __m128i xmm6 = _mm_set1_epi32 (6);
+  __m128i xmm7 = _mm_set1_epi32 (7);
+  __m128i ret = sse_test (xmm0, xmm1, xmm2, xmm3,
+                         xmm4, xmm5, xmm6, xmm7);
+  xmm0 =  _mm_set1_epi32 (0x12349876);
+  if (memcmp (&xmm0, &ret, sizeof (ret)))
+    abort ();
+  return 0;
+}
+
+#define TEST_FUNCTION do_test ()
+#include "../../test-skeleton.c"
Index: glibc-2.17-c758a686/sysdeps/x86_64/tst-avxmod.c
===================================================================
--- /dev/null
+++ glibc-2.17-c758a686/sysdeps/x86_64/tst-avxmod.c
@@ -0,0 +1,49 @@
+
+/* Test case for x86-64 preserved AVX registers in dynamic linker.  */
+
+#ifdef __AVX__
+#include <stdlib.h>
+#include <string.h>
+#include <immintrin.h>
+
+__m256i
+avx_test (__m256i x0, __m256i x1, __m256i x2, __m256i x3,
+	  __m256i x4, __m256i x5, __m256i x6, __m256i x7)
+{
+  __m256i ymm;
+
+  ymm = _mm256_set1_epi32 (0);
+  if (memcmp (&ymm, &x0, sizeof (ymm)))
+    abort ();
+
+  ymm = _mm256_set1_epi32 (1);
+  if (memcmp (&ymm, &x1, sizeof (ymm)))
+    abort ();
+
+  ymm = _mm256_set1_epi32 (2);
+  if (memcmp (&ymm, &x2, sizeof (ymm)))
+    abort ();
+
+  ymm = _mm256_set1_epi32 (3);
+  if (memcmp (&ymm, &x3, sizeof (ymm)))
+    abort ();
+
+  ymm = _mm256_set1_epi32 (4);
+  if (memcmp (&ymm, &x4, sizeof (ymm)))
+    abort ();
+
+  ymm = _mm256_set1_epi32 (5);
+  if (memcmp (&ymm, &x5, sizeof (ymm)))
+    abort ();
+
+  ymm = _mm256_set1_epi32 (6);
+  if (memcmp (&ymm, &x6, sizeof (ymm)))
+    abort ();
+
+  ymm = _mm256_set1_epi32 (7);
+  if (memcmp (&ymm, &x7, sizeof (ymm)))
+    abort ();
+
+  return _mm256_set1_epi32 (0x12349876);
+}
+#endif