elf: Remove Intel MPX support (lazy PLT, ld.so profile, and LD_AUDIT)

Intel MPX failed to gain wide adoption and has been deprecated for a
while. GCC 9.1 removed Intel MPX support. Linux kernel removed MPX in
2019.

This patch removes the support code from the dynamic loader.

Reviewed-by: H.J. Lu <hjl.tools@gmail.com>

12 files changed, 7 insertions, 186 deletions

diff --git a/NEWS b/NEWS
index 2e3804e4..220d327 100644
--- a/NEWS
+++ b/NEWS
@@ -61,6 +61,8 @@ Deprecated and removed features, and other changes affecting compatibility:
 
   when audit modules or dlmopen are used.
 
+* Intel MPX support (lazy PLT, ld.so profile, and LD_AUDIT) has been removed.
+
 Changes to build and runtime requirements:
 
   [Add changes to build and runtime requirements here]
diff --git a/config.h.in b/config.h.in
index 964873f..0a6f57b 100644
--- a/config.h.in
+++ b/config.h.in
@@ -84,9 +84,6 @@
 /* Define if assembler supports arch13 instructions on S390.  */
 #undef  HAVE_S390_ARCH13_ASM_SUPPORT
 
-/* Define if assembler supports Intel MPX.  */
-#undef  HAVE_MPX_SUPPORT
-
 /* Define if the compiler\'s exception support is based on libunwind.  */
 #undef	HAVE_CC_WITH_LIBUNWIND
 
diff --git a/sysdeps/i386/configure b/sysdeps/i386/configure
index bb482ca..ed46d53 100644
--- a/sysdeps/i386/configure
+++ b/sysdeps/i386/configure
@@ -83,33 +83,6 @@ $as_echo "$libc_cv_ld_static_pie" >&6; }
   fi
 fi
 
-{ $as_echo "$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
 
 
diff --git a/sysdeps/i386/configure.ac b/sysdeps/i386/configure.ac
index 5e43eb0..a6a0672 100644
--- a/sysdeps/i386/configure.ac
+++ b/sysdeps/i386/configure.ac
@@ -53,21 +53,6 @@ rm -f conftest*])
   fi
 fi
 
-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)
diff --git a/sysdeps/i386/dl-trampoline.S b/sysdeps/i386/dl-trampoline.S
index b5ec032..5669ab1 100644
--- a/sysdeps/i386/dl-trampoline.S
+++ b/sysdeps/i386/dl-trampoline.S
@@ -19,12 +19,6 @@
 #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
 	.type _dl_runtime_resolve, @function
@@ -250,13 +244,6 @@ _dl_runtime_profile:
 	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)
 	# Address of La_i86_regs area.
@@ -270,17 +257,9 @@ _dl_runtime_profile:
 	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
diff --git a/sysdeps/i386/link-defines.sym b/sysdeps/i386/link-defines.sym
index 0995adb..a63dcb9 100644
--- a/sysdeps/i386/link-defines.sym
+++ b/sysdeps/i386/link-defines.sym
@@ -16,5 +16,3 @@ 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)
diff --git a/sysdeps/x86/bits/link.h b/sysdeps/x86/bits/link.h
index 0e1db1a..d0e1a55 100644
--- a/sysdeps/x86/bits/link.h
+++ b/sysdeps/x86/bits/link.h
@@ -38,8 +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;
+  uint64_t __glibc_unused1;
+  uint64_t __glibc_unused2;
 } La_i86_retval;
 
 
@@ -96,7 +96,7 @@ typedef struct La_x86_64_regs
   La_x86_64_xmm lr_xmm[8];
   La_x86_64_vector lr_vector[8];
 #ifndef __ILP32__
-  __int128_t lr_bnd[4];
+  __int128_t __glibc_unused1[4];
 #endif
 } La_x86_64_regs;
 
@@ -112,8 +112,8 @@ typedef struct La_x86_64_retval
   La_x86_64_vector lrv_vector0;
   La_x86_64_vector lrv_vector1;
 #ifndef __ILP32__
-  __int128_t lrv_bnd0;
-  __int128_t lrv_bnd1;
+  __int128_t __glibc_unused1;
+  __int128_t __glibc_unused2;
 #endif
 } La_x86_64_retval;
 
diff --git a/sysdeps/x86_64/configure b/sysdeps/x86_64/configure
index 585279f..d4dd0aa 100755
--- a/sysdeps/x86_64/configure
+++ b/sysdeps/x86_64/configure
@@ -23,33 +23,6 @@ $as_echo "$libc_cv_cc_mprefer_vector_width" >&6; }
 config_vars="$config_vars
 config-cflags-mprefer-vector-width = $libc_cv_cc_mprefer_vector_width"
 
-{ $as_echo "$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 :
-  $as_echo_n "(cached) " >&6
-else
-  cat > conftest.s <<\EOF
-        bndmov %bnd0,(%rsp)
-EOF
-if { ac_try='${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_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
-  $as_echo "#define HAVE_MPX_SUPPORT 1" >>confdefs.h
-
-fi
-
 if test x"$build_mathvec" = xnotset; then
   build_mathvec=yes
 fi
diff --git a/sysdeps/x86_64/configure.ac b/sysdeps/x86_64/configure.ac
index 29e1403..c4c748c 100644
--- a/sysdeps/x86_64/configure.ac
+++ b/sysdeps/x86_64/configure.ac
@@ -10,21 +10,6 @@ LIBC_TRY_CC_OPTION([-mprefer-vector-width=128],
 LIBC_CONFIG_VAR([config-cflags-mprefer-vector-width],
 		[$libc_cv_cc_mprefer_vector_width])
 
-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,(%rsp)
-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 $libc_cv_asm_mpx = yes; then
-  AC_DEFINE(HAVE_MPX_SUPPORT)
-fi
-
 if test x"$build_mathvec" = xnotset; then
   build_mathvec=yes
 fi
diff --git a/sysdeps/x86_64/dl-trampoline.S b/sysdeps/x86_64/dl-trampoline.S
index 90b2a6c..fa71330 100644
--- a/sysdeps/x86_64/dl-trampoline.S
+++ b/sysdeps/x86_64/dl-trampoline.S
@@ -42,15 +42,6 @@
 
 /* Area on stack to save and restore registers used for parameter
    passing when calling _dl_fixup.  */
-#ifdef __ILP32__
-# define PRESERVE_BND_REGS_PREFIX
-#else
-# ifdef HAVE_MPX_SUPPORT
-#  define PRESERVE_BND_REGS_PREFIX bnd
-# else
-#  define PRESERVE_BND_REGS_PREFIX .byte 0xf2
-# endif
-#endif
 #define REGISTER_SAVE_RAX	0
 #define REGISTER_SAVE_RCX	(REGISTER_SAVE_RAX + 8)
 #define REGISTER_SAVE_RDX	(REGISTER_SAVE_RCX + 8)
diff --git a/sysdeps/x86_64/dl-trampoline.h b/sysdeps/x86_64/dl-trampoline.h
index b9a1297..dfbfefb 100644
--- a/sysdeps/x86_64/dl-trampoline.h
+++ b/sysdeps/x86_64/dl-trampoline.h
@@ -149,8 +149,6 @@ _dl_runtime_resolve:
 	# 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
@@ -230,20 +228,6 @@ _dl_runtime_profile:
 	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.  */
 	VMOVA %VEC(0),		      (LR_VECTOR_OFFSET)(%rsp)
@@ -368,23 +352,8 @@ _dl_runtime_profile:
 1:
 # 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
@@ -403,7 +372,6 @@ _dl_runtime_profile:
 	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:
@@ -430,7 +398,6 @@ _dl_runtime_profile:
 	movq 32(%rdi), %rsi
 	movq 40(%rdi), %rdi
 
-	PRESERVE_BND_REGS_PREFIX
 	call *%r11
 
 	mov 24(%rbx), %RSP_LP	# Drop the copied stack content
@@ -475,16 +442,6 @@ _dl_runtime_profile:
 	vmovdqa %xmm1, (LRV_SIZE + XMM_SIZE)(%rcx)
 # endif
 
-# ifndef __ILP32__
-#  ifdef HAVE_MPX_SUPPORT
-	bndmov %bnd0, LRV_BND0_OFFSET(%rcx)  # Preserve returned bounds.
-	bndmov %bnd1, LRV_BND1_OFFSET(%rcx)
-#  else
-	.byte  0x66,0x0f,0x1b,0x81;.long (LRV_BND0_OFFSET)
-	.byte  0x66,0x0f,0x1b,0x89;.long (LRV_BND1_OFFSET)
-#  endif
-# endif
-
 	fstpt LRV_ST0_OFFSET(%rcx)
 	fstpt LRV_ST1_OFFSET(%rcx)
 
@@ -517,16 +474,6 @@ _dl_runtime_profile:
 1:
 # endif
 
-# 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
-
 	fldt LRV_ST1_OFFSET(%rsp)
 	fldt LRV_ST0_OFFSET(%rsp)
 
@@ -538,7 +485,6 @@ _dl_runtime_profile:
 	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
 
 	cfi_endproc
diff --git a/sysdeps/x86_64/link-defines.sym b/sysdeps/x86_64/link-defines.sym
index 963c69b..85d35ad 100644
--- a/sysdeps/x86_64/link-defines.sym
+++ b/sysdeps/x86_64/link-defines.sym
@@ -6,7 +6,6 @@ VECTOR_SIZE		sizeof (La_x86_64_vector)
 XMM_SIZE		sizeof (La_x86_64_xmm)
 YMM_SIZE		sizeof (La_x86_64_ymm)
 ZMM_SIZE		sizeof (La_x86_64_zmm)
-BND_SIZE		sizeof (__int128_t)
 
 LR_SIZE			sizeof (struct La_x86_64_regs)
 LR_RDX_OFFSET		offsetof (struct La_x86_64_regs, lr_rdx)
@@ -19,9 +18,6 @@ LR_RBP_OFFSET		offsetof (struct La_x86_64_regs, lr_rbp)
 LR_RSP_OFFSET		offsetof (struct La_x86_64_regs, lr_rsp)
 LR_XMM_OFFSET		offsetof (struct La_x86_64_regs, lr_xmm)
 LR_VECTOR_OFFSET	offsetof (struct La_x86_64_regs, lr_vector)
-#ifndef __ILP32__
-LR_BND_OFFSET		offsetof (struct La_x86_64_regs, lr_bnd)
-#endif
 
 LRV_SIZE		sizeof (struct La_x86_64_retval)
 LRV_RAX_OFFSET		offsetof (struct La_x86_64_retval, lrv_rax)
@@ -32,7 +28,3 @@ LRV_ST0_OFFSET		offsetof (struct La_x86_64_retval, lrv_st0)
 LRV_ST1_OFFSET		offsetof (struct La_x86_64_retval, lrv_st1)
 LRV_VECTOR0_OFFSET	offsetof (struct La_x86_64_retval, lrv_vector0)
 LRV_VECTOR1_OFFSET	offsetof (struct La_x86_64_retval, lrv_vector1)
-#ifndef __ILP32__
-LRV_BND0_OFFSET		offsetof (struct La_x86_64_retval, lrv_bnd0)
-LRV_BND1_OFFSET		offsetof (struct La_x86_64_retval, lrv_bnd1)
-#endif