i386: Remove CET support

CET is only support for x86_64, this patch reverts:

  - faaee1f07ed x86: Support shadow stack pointer in setjmp/longjmp.
  - be9ccd27c09 i386: Add _CET_ENDBR to indirect jump targets in
    add_n.S/sub_n.S
  - c02695d7764 x86/CET: Update vfork to prevent child return
  - 5d844e1b725 i386: Enable CET support in ucontext functions
  - 124bcde683 x86: Add _CET_ENDBR to functions in crti.S
  - 562837c002 x86: Add _CET_ENDBR to functions in dl-tlsdesc.S
  - f753fa7dea x86: Support IBT and SHSTK in Intel CET [BZ #21598]
  - 825b58f3fb i386-mcount.S: Add _CET_ENDBR to _mcount and __fentry__
  - 7e119cd582 i386: Use _CET_NOTRACK in i686/memcmp.S
  - 177824e232 i386: Use _CET_NOTRACK in memcmp-sse4.S
  - 0a899af097 i386: Use _CET_NOTRACK in memcpy-ssse3-rep.S
  - 7fb613361c i386: Use _CET_NOTRACK in memcpy-ssse3.S
  - 77a8ae0948 i386: Use _CET_NOTRACK in memset-sse2-rep.S
  - 00e7b76a8f i386: Use _CET_NOTRACK in memset-sse2.S
  - 90d15dc577 i386: Use _CET_NOTRACK in strcat-sse2.S
  - f1574581c7 i386: Use _CET_NOTRACK in strcpy-sse2.S
  - 4031d7484a i386/sub_n.S: Add a missing _CET_ENDBR to indirect jump
  - target
  -
Checked on i686-linux-gnu.

21 files changed, 29 insertions, 241 deletions

diff --git a/sysdeps/i386/__longjmp.S b/sysdeps/i386/__longjmp.S
index 302c00a..bb83609 100644
--- a/sysdeps/i386/__longjmp.S
+++ b/sysdeps/i386/__longjmp.S
@@ -19,55 +19,14 @@
 #include <sysdep.h>
 #include <pointer_guard.h>
 #include <jmpbuf-offsets.h>
-#include <jmp_buf-ssp.h>
 #include <asm-syntax.h>
 #include <stap-probe.h>
 
-/* Don't restore shadow stack register if
-   1. Shadow stack isn't enabled.  Or
-   2. __longjmp is defined for __longjmp_cancel.
- */
-#if !SHSTK_ENABLED || defined __longjmp
-# undef SHADOW_STACK_POINTER_OFFSET
-#endif
-
 	.text
 ENTRY (__longjmp)
 #ifdef PTR_DEMANGLE
 	movl 4(%esp), %eax	/* User's jmp_buf in %eax.  */
 
-# ifdef SHADOW_STACK_POINTER_OFFSET
-#  if IS_IN (libc) && defined SHARED && defined FEATURE_1_OFFSET
-	/* Check if Shadow Stack is enabled.  */
-	testl $X86_FEATURE_1_SHSTK, %gs:FEATURE_1_OFFSET
-	jz L(skip_ssp)
-#  else
-	xorl %edx, %edx
-#  endif
-	/* Check and adjust the Shadow-Stack-Pointer.  */
-	rdsspd %edx
-	/* And compare it with the saved ssp value.  */
-	subl SHADOW_STACK_POINTER_OFFSET(%eax), %edx
-	je L(skip_ssp)
-	/* Count the number of frames to adjust and adjust it
-	   with incssp instruction.  The instruction can adjust
-	   the ssp by [0..255] value only thus use a loop if
-	   the number of frames is bigger than 255.  */
-	negl %edx
-	shrl $2, %edx
-	/* NB: We saved Shadow-Stack-Pointer of setjmp.  Since we are
-	       restoring Shadow-Stack-Pointer of setjmp's caller, we
-	       need to unwind shadow stack by one more frame.  */
-	addl $1, %edx
-	movl	$255, %ebx
-L(loop):
-	cmpl	%ebx, %edx
-	cmovb	%edx, %ebx
-	incsspd	%ebx
-	subl	%ebx, %edx
-	ja	L(loop)
-L(skip_ssp):
-# endif
 	/* Save the return address now.  */
 	movl (JB_PC*4)(%eax), %edx
 	/* Get the stack pointer.  */
@@ -98,38 +57,6 @@ L(skip_ssp):
 #else
 	movl 4(%esp), %ecx	/* User's jmp_buf in %ecx.  */
 	movl 8(%esp), %eax	/* Second argument is return value.  */
-# ifdef SHADOW_STACK_POINTER_OFFSET
-#  if IS_IN (libc) && defined SHARED
-	/* Check if Shadow Stack is enabled.  */
-	testl $X86_FEATURE_1_SHSTK, %gs:FEATURE_1_OFFSET
-	jz L(skip_ssp)
-#  endif
-	/* Check and adjust the Shadow-Stack-Pointer.  */
-	xorl %edx, %edx
-	/* Get the current ssp.  */
-	rdsspd	%edx
-	/* And compare it with the saved ssp value.  */
-	subl SHADOW_STACK_POINTER_OFFSET(%ecx), %edx
-	je L(skip_ssp)
-	/* Count the number of frames to adjust and adjust it
-	   with incssp instruction.  The instruction can adjust
-	   the ssp by [0..255] value only thus use a loop if
-	   the number of frames is bigger than 255.  */
-	negl %edx
-	shrl $2, %edx
-	/* NB: We saved Shadow-Stack-Pointer of setjmp.  Since we are
-	       restoring Shadow-Stack-Pointer of setjmp's caller, we
-	       need to unwind shadow stack by one more frame.  */
-	addl $1, %edx
-	movl	$255, %ebx
-L(loop):
-	cmpl	%ebx, %edx
-	cmovb	%edx, %ebx
-	incsspd	%ebx
-	subl	%ebx, %edx
-	ja	L(loop)
-L(skip_ssp):
-# endif
 	/* Save the return address now.  */
 	movl (JB_PC*4)(%ecx), %edx
 	LIBC_PROBE (longjmp, 3, 4@%ecx, -4@%eax, 4@%edx)
diff --git a/sysdeps/i386/add_n.S b/sysdeps/i386/add_n.S
index d4af6d9..c1b7098b1 100644
--- a/sysdeps/i386/add_n.S
+++ b/sysdeps/i386/add_n.S
@@ -40,13 +40,6 @@ ENTRY (__mpn_add_n)
 	cfi_rel_offset (esi, 0)
 	movl S2(%esp),%edx
 	movl SIZE(%esp),%ecx
-
-#if IBT_ENABLED
-	pushl	%ebx
-	cfi_adjust_cfa_offset (4)
-	cfi_rel_offset (ebx, 0)
-#endif
-
 	movl	%ecx,%eax
 	shrl	$3,%ecx			/* compute count for unrolled loop */
 	negl	%eax
@@ -58,9 +51,6 @@ ENTRY (__mpn_add_n)
 	subl	%eax,%esi		/* ... by a constant when we ... */
 	subl	%eax,%edx		/* ... enter the loop */
 	shrl	$2,%eax			/* restore previous value */
-#if IBT_ENABLED
-	leal	-4(,%eax,4),%ebx	/* Count for 4-byte endbr32 */
-#endif
 #ifdef PIC
 /* Calculate start address in loop for PIC.  Due to limitations in some
    assemblers, Loop-L0-3 cannot be put into the leal */
@@ -75,39 +65,29 @@ L(0):	leal	(%eax,%eax,8),%eax
 /* Calculate start address in loop for non-PIC.  */
  	leal	(L(oop) - 3)(%eax,%eax,8),%eax
 #endif
-#if IBT_ENABLED
-	addl	%ebx,%eax		/* Adjust for endbr32 */
-#endif
 	jmp	*%eax			/* jump into loop */
 	ALIGN (3)
 L(oop):	movl	(%esi),%eax
 	adcl	(%edx),%eax
 	movl	%eax,(%edi)
-	_CET_ENDBR
 	movl	4(%esi),%eax
 	adcl	4(%edx),%eax
 	movl	%eax,4(%edi)
-	_CET_ENDBR
 	movl	8(%esi),%eax
 	adcl	8(%edx),%eax
 	movl	%eax,8(%edi)
-	_CET_ENDBR
 	movl	12(%esi),%eax
 	adcl	12(%edx),%eax
 	movl	%eax,12(%edi)
-	_CET_ENDBR
 	movl	16(%esi),%eax
 	adcl	16(%edx),%eax
 	movl	%eax,16(%edi)
-	_CET_ENDBR
 	movl	20(%esi),%eax
 	adcl	20(%edx),%eax
 	movl	%eax,20(%edi)
-	_CET_ENDBR
 	movl	24(%esi),%eax
 	adcl	24(%edx),%eax
 	movl	%eax,24(%edi)
-	_CET_ENDBR
 	movl	28(%esi),%eax
 	adcl	28(%edx),%eax
 	movl	%eax,28(%edi)
@@ -120,11 +100,6 @@ L(oop):	movl	(%esi),%eax
 	sbbl	%eax,%eax
 	negl	%eax
 
-#if IBT_ENABLED
-	popl	%ebx
-	cfi_adjust_cfa_offset (-4)
-	cfi_restore (ebx)
-#endif
 	popl %esi
 	cfi_adjust_cfa_offset (-4)
 	cfi_restore (esi)
diff --git a/sysdeps/i386/bsd-_setjmp.S b/sysdeps/i386/bsd-_setjmp.S
index eb3ac9c..5fd671a 100644
--- a/sysdeps/i386/bsd-_setjmp.S
+++ b/sysdeps/i386/bsd-_setjmp.S
@@ -23,18 +23,12 @@
 #include <sysdep.h>
 #include <pointer_guard.h>
 #include <jmpbuf-offsets.h>
-#include <jmp_buf-ssp.h>
 #include <stap-probe.h>
 
 #define PARMS	4		/* no space for saved regs */
 #define JMPBUF	PARMS
 #define SIGMSK	JMPBUF+4
 
-/* Don't save shadow stack register if shadow stack isn't enabled.  */
-#if !SHSTK_ENABLED
-# undef SHADOW_STACK_POINTER_OFFSET
-#endif
-
 ENTRY (_setjmp)
 
 	xorl %eax, %eax
@@ -58,21 +52,6 @@ ENTRY (_setjmp)
 	movl %ebp, (JB_BP*4)(%edx) /* Save caller's frame pointer.  */
 
 	movl %eax, JB_SIZE(%edx) /* No signal mask set.  */
-#ifdef SHADOW_STACK_POINTER_OFFSET
-# if IS_IN (libc) && defined SHARED && defined FEATURE_1_OFFSET
-	/* Check if Shadow Stack is enabled.  */
-	testl $X86_FEATURE_1_SHSTK, %gs:FEATURE_1_OFFSET
-	jz L(skip_ssp)
-# else
-	xorl %ecx, %ecx
-# endif
-	/* Get the current Shadow-Stack-Pointer and save it.  */
-	rdsspd %ecx
-	movl %ecx, SHADOW_STACK_POINTER_OFFSET(%edx)
-# if IS_IN (libc) && defined SHARED && defined FEATURE_1_OFFSET
-L(skip_ssp):
-# endif
-#endif
 	ret
 END (_setjmp)
 libc_hidden_def (_setjmp)
diff --git a/sysdeps/i386/bsd-setjmp.S b/sysdeps/i386/bsd-setjmp.S
index c03f235..13338a6 100644
--- a/sysdeps/i386/bsd-setjmp.S
+++ b/sysdeps/i386/bsd-setjmp.S
@@ -23,18 +23,12 @@
 #include <sysdep.h>
 #include <pointer_guard.h>
 #include <jmpbuf-offsets.h>
-#include <jmp_buf-ssp.h>
 #include <stap-probe.h>
 
 #define PARMS  4		/* no space for saved regs */
 #define JMPBUF PARMS
 #define SIGMSK JMPBUF+4
 
-/* Don't save shadow stack register if shadow stack isn't enabled.  */
-#if !SHSTK_ENABLED
-# undef SHADOW_STACK_POINTER_OFFSET
-#endif
-
 ENTRY (setjmp)
 	/* Note that we have to use a non-exported symbol in the next
 	   jump since otherwise gas will emit it as a jump through the
@@ -58,21 +52,6 @@ ENTRY (setjmp)
 #endif
 	movl %ecx, (JB_PC*4)(%eax)
 	movl %ebp, (JB_BP*4)(%eax) /* Save caller's frame pointer.  */
-#ifdef SHADOW_STACK_POINTER_OFFSET
-# if IS_IN (libc) && defined SHARED && defined FEATURE_1_OFFSET
-	/* Check if Shadow Stack is enabled.  */
-	testl $X86_FEATURE_1_SHSTK, %gs:FEATURE_1_OFFSET
-	jz L(skip_ssp)
-# else
-	xorl %ecx, %ecx
-# endif
-	/* Get the current Shadow-Stack-Pointer and save it.  */
-	rdsspd %ecx
-	movl %ecx, SHADOW_STACK_POINTER_OFFSET(%eax)
-# if IS_IN (libc) && defined SHARED && defined FEATURE_1_OFFSET
-L(skip_ssp):
-# endif
-#endif
 
 	/* Call __sigjmp_save.  */
 	pushl $1
diff --git a/sysdeps/i386/crti.S b/sysdeps/i386/crti.S
index 71d19b6..f9662ee 100644
--- a/sysdeps/i386/crti.S
+++ b/sysdeps/i386/crti.S
@@ -61,7 +61,6 @@
 	.hidden	_init
 	.type _init, @function
 _init:
-	_CET_ENDBR
 	pushl %ebx
 	/* Maintain 16-byte stack alignment for called functions.  */
 	subl $8, %esp
@@ -82,7 +81,6 @@ _init:
 	.hidden	_fini
 	.type _fini, @function
 _fini:
-	_CET_ENDBR
 	pushl %ebx
 	subl $8, %esp
 	LOAD_PIC_REG (bx)
diff --git a/sysdeps/i386/dl-tlsdesc.S b/sysdeps/i386/dl-tlsdesc.S
index 318b82a..90d93ca 100644
--- a/sysdeps/i386/dl-tlsdesc.S
+++ b/sysdeps/i386/dl-tlsdesc.S
@@ -37,7 +37,6 @@
 	cfi_startproc
 	.align 16
 _dl_tlsdesc_return:
-	_CET_ENDBR
 	movl	4(%eax), %eax
 	ret
 	cfi_endproc
@@ -59,7 +58,6 @@ _dl_tlsdesc_return:
 	cfi_startproc
 	.align 16
 _dl_tlsdesc_undefweak:
-	_CET_ENDBR
 	movl	4(%eax), %eax
 	subl	%gs:0, %eax
 	ret
@@ -101,7 +99,6 @@ _dl_tlsdesc_dynamic (struct tlsdesc *tdp)
 	cfi_startproc
 	.align 16
 _dl_tlsdesc_dynamic:
-	_CET_ENDBR
 	/* Like all TLS resolvers, preserve call-clobbered registers.
 	   We need two scratch regs anyway.  */
 	subl	$28, %esp
diff --git a/sysdeps/i386/dl-trampoline.S b/sysdeps/i386/dl-trampoline.S
index ecba034..2632020 100644
--- a/sysdeps/i386/dl-trampoline.S
+++ b/sysdeps/i386/dl-trampoline.S
@@ -26,7 +26,6 @@
 	.align 16
 _dl_runtime_resolve:
 	cfi_adjust_cfa_offset (8)
-	_CET_ENDBR
 	pushl %eax		# Preserve registers otherwise clobbered.
 	cfi_adjust_cfa_offset (4)
 	pushl %ecx
@@ -53,7 +52,6 @@ _dl_runtime_resolve:
 	.align 16
 _dl_runtime_resolve_shstk:
 	cfi_adjust_cfa_offset (8)
-	_CET_ENDBR
 	pushl %eax		# Preserve registers otherwise clobbered.
 	cfi_adjust_cfa_offset (4)
 	pushl %edx
@@ -78,7 +76,6 @@ _dl_runtime_resolve_shstk:
 	.align 16
 _dl_runtime_profile_shstk:
 	cfi_adjust_cfa_offset (8)
-	_CET_ENDBR
 	pushl %esp
 	cfi_adjust_cfa_offset (4)
 	addl $8, (%esp)		# Account for the pushed PLT data
@@ -123,7 +120,6 @@ _dl_runtime_profile_shstk:
 	.align 16
 _dl_runtime_profile:
 	cfi_adjust_cfa_offset (8)
-	_CET_ENDBR
 	pushl %esp
 	cfi_adjust_cfa_offset (4)
 	addl $8, (%esp)		# Account for the pushed PLT data
diff --git a/sysdeps/i386/i386-mcount.S b/sysdeps/i386/i386-mcount.S
index 8066649..6082e1a 100644
--- a/sysdeps/i386/i386-mcount.S
+++ b/sysdeps/i386/i386-mcount.S
@@ -29,7 +29,6 @@
 	.type C_SYMBOL_NAME(_mcount), @function
 	.align ALIGNARG(4)
 C_LABEL(_mcount)
-	_CET_ENDBR
 	/* Save the caller-clobbered registers.  */
 	pushl %eax
 	pushl %ecx
@@ -58,7 +57,6 @@ weak_alias (_mcount, mcount)
 	.type C_SYMBOL_NAME(__fentry__), @function
 	.align ALIGNARG(4)
 C_LABEL(__fentry__)
-	_CET_ENDBR
 	/* Save the caller-clobbered registers.  */
 	pushl %eax
 	pushl %ecx
diff --git a/sysdeps/i386/i686/add_n.S b/sysdeps/i386/i686/add_n.S
index c2bc798..bbc0cc7 100644
--- a/sysdeps/i386/i686/add_n.S
+++ b/sysdeps/i386/i686/add_n.S
@@ -44,13 +44,6 @@ ENTRY (__mpn_add_n)
 	cfi_rel_offset (esi, 0)
 	movl	S2(%esp),%edx
 	movl	SIZE(%esp),%ecx
-
-#if IBT_ENABLED
-	pushl	%ebx
-	cfi_adjust_cfa_offset (4)
-	cfi_rel_offset (ebx, 0)
-#endif
-
 	movl	%ecx,%eax
 	shrl	$3,%ecx			/* compute count for unrolled loop */
 	negl	%eax
@@ -62,9 +55,6 @@ ENTRY (__mpn_add_n)
 	subl	%eax,%esi		/* ... by a constant when we ... */
 	subl	%eax,%edx		/* ... enter the loop */
 	shrl	$2,%eax			/* restore previous value */
-#if IBT_ENABLED
-	leal	-4(,%eax,4),%ebx	/* Count for 4-byte endbr32 */
-#endif
 #ifdef PIC
 /* Calculate start address in loop for PIC.  */
 	leal	(L(oop)-L(0)-3)(%eax,%eax,8),%eax
@@ -74,39 +64,29 @@ L(0):
 /* Calculate start address in loop for non-PIC.  */
  	leal	(L(oop) - 3)(%eax,%eax,8),%eax
 #endif
-#if IBT_ENABLED
-	addl	%ebx,%eax		/* Adjust for endbr32 */
-#endif
 	jmp	*%eax			/* jump into loop */
 	ALIGN (3)
 L(oop):	movl	(%esi),%eax
 	adcl	(%edx),%eax
 	movl	%eax,(%edi)
-	_CET_ENDBR
 	movl	4(%esi),%eax
 	adcl	4(%edx),%eax
 	movl	%eax,4(%edi)
-	_CET_ENDBR
 	movl	8(%esi),%eax
 	adcl	8(%edx),%eax
 	movl	%eax,8(%edi)
-	_CET_ENDBR
 	movl	12(%esi),%eax
 	adcl	12(%edx),%eax
 	movl	%eax,12(%edi)
-	_CET_ENDBR
 	movl	16(%esi),%eax
 	adcl	16(%edx),%eax
 	movl	%eax,16(%edi)
-	_CET_ENDBR
 	movl	20(%esi),%eax
 	adcl	20(%edx),%eax
 	movl	%eax,20(%edi)
-	_CET_ENDBR
 	movl	24(%esi),%eax
 	adcl	24(%edx),%eax
 	movl	%eax,24(%edi)
-	_CET_ENDBR
 	movl	28(%esi),%eax
 	adcl	28(%edx),%eax
 	movl	%eax,28(%edi)
@@ -119,11 +99,6 @@ L(oop):	movl	(%esi),%eax
 	sbbl	%eax,%eax
 	negl	%eax
 
-#if IBT_ENABLED
-	popl	%ebx
-	cfi_adjust_cfa_offset (-4)
-	cfi_restore (ebx)
-#endif
 	popl %esi
 	cfi_adjust_cfa_offset (-4)
 	cfi_restore (esi)
diff --git a/sysdeps/i386/i686/memcmp.S b/sysdeps/i386/i686/memcmp.S
index 94600f5..0738ee9 100644
--- a/sysdeps/i386/i686/memcmp.S
+++ b/sysdeps/i386/i686/memcmp.S
@@ -80,7 +80,7 @@ L(not_1):
 	LOAD_JUMP_TABLE_ENTRY (L(table_32bytes), %ecx)
 	addl	%ecx, %edx
 	addl	%ecx, %esi
-	_CET_NOTRACK jmp *%ebx
+	jmp	*%ebx
 
 	ALIGN (4)
 L(28bytes):
@@ -326,7 +326,7 @@ L(32bytesormore):
 	LOAD_JUMP_TABLE_ENTRY (L(table_32bytes), %ecx)
 	addl	%ecx, %edx
 	addl	%ecx, %esi
-	_CET_NOTRACK jmp *%ebx
+	jmp	*%ebx
 
 L(load_ecx_28):
 	addl	$0x4, %edx
diff --git a/sysdeps/i386/i686/multiarch/memcmp-sse4.S b/sysdeps/i386/i686/multiarch/memcmp-sse4.S
index f0b2d84..2cdda5f 100644
--- a/sysdeps/i386/i686/multiarch/memcmp-sse4.S
+++ b/sysdeps/i386/i686/multiarch/memcmp-sse4.S
@@ -58,7 +58,7 @@
 	absolute	address.  */	\
 	addl	(%ebx,INDEX,SCALE), %ebx;	\
 /* We loaded the jump table and adjusted EDX/ESI. Go.  */	\
-	_CET_NOTRACK jmp *%ebx
+	jmp *%ebx
 # else
 #  define JMPTBL(I, B)	I
 
@@ -66,7 +66,7 @@
 	jump	table with relative offsets.  INDEX is a register contains the
 	index	into the jump table.   SCALE is the scale of INDEX. */
 #  define BRANCH_TO_JMPTBL_ENTRY(TABLE, INDEX, SCALE)	\
-	_CET_NOTRACK jmp *TABLE(,INDEX,SCALE)
+	jmp *TABLE(,INDEX,SCALE)
 # endif
 
 
diff --git a/sysdeps/i386/i686/multiarch/memcpy-ssse3-rep.S b/sysdeps/i386/i686/multiarch/memcpy-ssse3-rep.S
index abdde55..a7e80dc 100644
--- a/sysdeps/i386/i686/multiarch/memcpy-ssse3-rep.S
+++ b/sysdeps/i386/i686/multiarch/memcpy-ssse3-rep.S
@@ -64,7 +64,7 @@
        absolute address.  */					\
     addl	(%ebx,INDEX,SCALE), %ebx;			\
     /* We loaded the jump table.  Go.  */			\
-    _CET_NOTRACK jmp *%ebx
+    jmp *%ebx
 
 # define BRANCH_TO_JMPTBL_ENTRY_VALUE(TABLE)			\
     addl	$(TABLE - .), %ebx
@@ -72,7 +72,7 @@
 # define BRANCH_TO_JMPTBL_ENTRY_TAIL(TABLE, INDEX, SCALE)	\
     addl	(%ebx,INDEX,SCALE), %ebx;			\
     /* We loaded the jump table.  Go.  */			\
-    _CET_NOTRACK jmp *%ebx
+    jmp *%ebx
 #else
 # define PARMS		4
 # define ENTRANCE
@@ -84,12 +84,12 @@
    absolute offsets.  INDEX is a register contains the index into the
    jump table.  SCALE is the scale of INDEX. */
 # define BRANCH_TO_JMPTBL_ENTRY(TABLE, INDEX, SCALE)		\
-    _CET_NOTRACK jmp *TABLE(,INDEX,SCALE)
+    jmp *TABLE(,INDEX,SCALE)
 
 # define BRANCH_TO_JMPTBL_ENTRY_VALUE(TABLE)
 
 # define BRANCH_TO_JMPTBL_ENTRY_TAIL(TABLE, INDEX, SCALE)		\
-    _CET_NOTRACK jmp *TABLE(,INDEX,SCALE)
+    jmp *TABLE(,INDEX,SCALE)
 #endif
 
 	.section .text.ssse3,"ax",@progbits
diff --git a/sysdeps/i386/i686/multiarch/memcpy-ssse3.S b/sysdeps/i386/i686/multiarch/memcpy-ssse3.S
index 60cc5f1..713c5bd 100644
--- a/sysdeps/i386/i686/multiarch/memcpy-ssse3.S
+++ b/sysdeps/i386/i686/multiarch/memcpy-ssse3.S
@@ -64,7 +64,7 @@
 	absolute	address.  */		\
 	addl	(%ebx, INDEX, SCALE), %ebx;		\
     /* We loaded the jump table.  Go.  */		\
-	_CET_NOTRACK jmp *%ebx
+	jmp *%ebx
 # else
 
 #  define PARMS		4
@@ -78,7 +78,7 @@
 	jump table.  SCALE is the scale of INDEX. */
 
 #  define BRANCH_TO_JMPTBL_ENTRY(TABLE, INDEX, SCALE)		\
-	_CET_NOTRACK jmp *TABLE(, INDEX, SCALE)
+	jmp *TABLE(, INDEX, SCALE)
 # endif
 
 	.section .text.ssse3,"ax",@progbits
diff --git a/sysdeps/i386/i686/multiarch/memset-sse2-rep.S b/sysdeps/i386/i686/multiarch/memset-sse2-rep.S
index 52d046d..d1a0473 100644
--- a/sysdeps/i386/i686/multiarch/memset-sse2-rep.S
+++ b/sysdeps/i386/i686/multiarch/memset-sse2-rep.S
@@ -56,7 +56,7 @@
     add		(%ebx,%ecx,4), %ebx;				\
     add		%ecx, %edx;					\
     /* We loaded the jump table and adjusted EDX. Go.  */	\
-    _CET_NOTRACK jmp *%ebx
+    jmp *%ebx
 #else
 # define ENTRANCE
 # define RETURN_END	ret
@@ -68,7 +68,7 @@
    absolute offsets.  */
 # define BRANCH_TO_JMPTBL_ENTRY(TABLE)				\
     add		%ecx, %edx;					\
-    _CET_NOTRACK jmp *TABLE(,%ecx,4)
+    jmp *TABLE(,%ecx,4)
 #endif
 
 	.section .text.sse2,"ax",@progbits
diff --git a/sysdeps/i386/i686/multiarch/memset-sse2.S b/sysdeps/i386/i686/multiarch/memset-sse2.S
index ac21fcb..2e00743 100644
--- a/sysdeps/i386/i686/multiarch/memset-sse2.S
+++ b/sysdeps/i386/i686/multiarch/memset-sse2.S
@@ -56,7 +56,7 @@
     add		(%ebx,%ecx,4), %ebx;				\
     add		%ecx, %edx;					\
     /* We loaded the jump table and adjusted EDX. Go.  */	\
-    _CET_NOTRACK jmp	*%ebx
+    jmp	*%ebx
 #else
 # define ENTRANCE
 # define RETURN_END	ret
@@ -68,7 +68,7 @@
    absolute offsets.  */
 # define BRANCH_TO_JMPTBL_ENTRY(TABLE)				\
     add		%ecx, %edx;					\
-    _CET_NOTRACK jmp *TABLE(,%ecx,4)
+    jmp *TABLE(,%ecx,4)
 #endif
 
 	.section .text.sse2,"ax",@progbits
diff --git a/sysdeps/i386/i686/multiarch/strcat-sse2.S b/sysdeps/i386/i686/multiarch/strcat-sse2.S
index 7ac4827..682f43f 100644
--- a/sysdeps/i386/i686/multiarch/strcat-sse2.S
+++ b/sysdeps/i386/i686/multiarch/strcat-sse2.S
@@ -49,7 +49,7 @@
 	absolute address.  */	\
 	addl	(%ecx,INDEX,SCALE), %ecx;	\
 	/* We loaded the jump table and adjusted ECX. Go.  */	\
-	_CET_NOTRACK jmp *%ecx
+	jmp *%ecx
 # else
 #  define JMPTBL(I, B) I
 
@@ -58,7 +58,7 @@
 	jump table.  SCALE is the scale of INDEX. */
 
 #  define BRANCH_TO_JMPTBL_ENTRY(TABLE, INDEX, SCALE)	\
-	_CET_NOTRACK jmp *TABLE(,INDEX,SCALE)
+	jmp *TABLE(,INDEX,SCALE)
 # endif
 
 # ifndef STRCAT
diff --git a/sysdeps/i386/i686/multiarch/strcpy-sse2.S b/sysdeps/i386/i686/multiarch/strcpy-sse2.S
index 5c358e5..a18a8ca 100644
--- a/sysdeps/i386/i686/multiarch/strcpy-sse2.S
+++ b/sysdeps/i386/i686/multiarch/strcpy-sse2.S
@@ -64,7 +64,7 @@
 	absolute	address.  */                            \
 	addl	(%ecx,INDEX,SCALE), %ecx;                       \
 	/* We loaded the jump table and adjusted ECX. Go.  */  \
-	_CET_NOTRACK jmp *%ecx
+	jmp *%ecx
 # else
 #  define JMPTBL(I, B)	I
 
@@ -73,7 +73,7 @@
 	jump	table.  SCALE is the scale of INDEX. */
 
 #  define BRANCH_TO_JMPTBL_ENTRY(TABLE, INDEX, SCALE)		\
-	_CET_NOTRACK jmp *TABLE(,INDEX,SCALE)
+	jmp *TABLE(,INDEX,SCALE)
 # endif
 
 .text
diff --git a/sysdeps/i386/setjmp.S b/sysdeps/i386/setjmp.S
index ab1a809..08a98f2 100644
--- a/sysdeps/i386/setjmp.S
+++ b/sysdeps/i386/setjmp.S
@@ -19,7 +19,6 @@
 #include <sysdep.h>
 #include <pointer_guard.h>
 #include <jmpbuf-offsets.h>
-#include <jmp_buf-ssp.h>
 #include <asm-syntax.h>
 #include <stap-probe.h>
 
@@ -27,11 +26,6 @@
 #define JMPBUF	PARMS
 #define SIGMSK	JMPBUF+4
 
-/* Don't save shadow stack register if shadow stack isn't enabled.  */
-#if !SHSTK_ENABLED
-# undef SHADOW_STACK_POINTER_OFFSET
-#endif
-
 ENTRY (__sigsetjmp)
 
 	movl JMPBUF(%esp), %eax
@@ -53,21 +47,6 @@ ENTRY (__sigsetjmp)
 	movl %ecx, (JB_PC*4)(%eax)
 	movl %ebp, (JB_BP*4)(%eax) /* Save caller's frame pointer.  */
 
-#ifdef SHADOW_STACK_POINTER_OFFSET
-# if IS_IN (libc) && defined SHARED && defined FEATURE_1_OFFSET
-	/* Check if Shadow Stack is enabled.  */
-	testl $X86_FEATURE_1_SHSTK, %gs:FEATURE_1_OFFSET
-	jz L(skip_ssp)
-# else
-	xorl %ecx, %ecx
-# endif
-	/* Get the current Shadow-Stack-Pointer and save it.  */
-	rdsspd %ecx
-	movl %ecx, SHADOW_STACK_POINTER_OFFSET(%eax)
-# if IS_IN (libc) && defined SHARED && defined FEATURE_1_OFFSET
-L(skip_ssp):
-# endif
-#endif
 #if IS_IN (rtld)
 	/* In ld.so we never save the signal mask.  */
 	xorl %eax, %eax
diff --git a/sysdeps/i386/start.S b/sysdeps/i386/start.S
index e042ed1..3057717 100644
--- a/sysdeps/i386/start.S
+++ b/sysdeps/i386/start.S
@@ -132,7 +132,6 @@ ENTRY (_start)
 
 #if defined PIC && !defined SHARED
 __wrap_main:
-	_CET_ENDBR
 	jmp	main@PLT
 #endif
 END (_start)
diff --git a/sysdeps/i386/sub_n.S b/sysdeps/i386/sub_n.S
index 3ebe984..c111bf3 100644
--- a/sysdeps/i386/sub_n.S
+++ b/sysdeps/i386/sub_n.S
@@ -40,13 +40,6 @@ ENTRY (__mpn_sub_n)
 	cfi_rel_offset (esi, 0)
 	movl	S2(%esp),%edx
 	movl	SIZE(%esp),%ecx
-
-#if IBT_ENABLED
-	pushl	%ebx
-	cfi_adjust_cfa_offset (4)
-	cfi_rel_offset (ebx, 0)
-#endif
-
 	movl	%ecx,%eax
 	shrl	$3,%ecx			/* compute count for unrolled loop */
 	negl	%eax
@@ -58,9 +51,6 @@ ENTRY (__mpn_sub_n)
 	subl	%eax,%esi		/* ... by a constant when we ... */
 	subl	%eax,%edx		/* ... enter the loop */
 	shrl	$2,%eax			/* restore previous value */
-#if defined __CET__ && (__CET__ & 1) != 0
-	leal	-4(,%eax,4),%ebx	/* Count for 4-byte endbr32 */
-#endif
 #ifdef PIC
 /* Calculate start address in loop for PIC.  Due to limitations in some
    assemblers, Loop-L0-3 cannot be put into the leal */
@@ -75,39 +65,29 @@ L(0):	leal	(%eax,%eax,8),%eax
 /* Calculate start address in loop for non-PIC.  */
  	leal	(L(oop) - 3)(%eax,%eax,8),%eax
 #endif
-#if defined __CET__ && (__CET__ & 1) != 0
-	addl	%ebx,%eax		/* Adjust for endbr32 */
-#endif
 	jmp	*%eax			/* jump into loop */
 	ALIGN (3)
 L(oop):	movl	(%esi),%eax
 	sbbl	(%edx),%eax
 	movl	%eax,(%edi)
-	_CET_ENDBR
 	movl	4(%esi),%eax
 	sbbl	4(%edx),%eax
 	movl	%eax,4(%edi)
-	_CET_ENDBR
 	movl	8(%esi),%eax
 	sbbl	8(%edx),%eax
 	movl	%eax,8(%edi)
-	_CET_ENDBR
 	movl	12(%esi),%eax
 	sbbl	12(%edx),%eax
 	movl	%eax,12(%edi)
-	_CET_ENDBR
 	movl	16(%esi),%eax
 	sbbl	16(%edx),%eax
 	movl	%eax,16(%edi)
-	_CET_ENDBR
 	movl	20(%esi),%eax
 	sbbl	20(%edx),%eax
 	movl	%eax,20(%edi)
-	_CET_ENDBR
 	movl	24(%esi),%eax
 	sbbl	24(%edx),%eax
 	movl	%eax,24(%edi)
-	_CET_ENDBR
 	movl	28(%esi),%eax
 	sbbl	28(%edx),%eax
 	movl	%eax,28(%edi)
@@ -120,11 +100,6 @@ L(oop):	movl	(%esi),%eax
 	sbbl	%eax,%eax
 	negl	%eax
 
-#if defined __CET__ && (__CET__ & 1) != 0
-	popl	%ebx
-	cfi_adjust_cfa_offset (-4)
-	cfi_restore (ebx)
-#endif
 	popl %esi
 	cfi_adjust_cfa_offset (-4)
 	cfi_restore (esi)
diff --git a/sysdeps/i386/sysdep.h b/sysdeps/i386/sysdep.h
index 69c8b51..86b5fdd 100644
--- a/sysdeps/i386/sysdep.h
+++ b/sysdeps/i386/sysdep.h
@@ -18,6 +18,8 @@
 
 #include <sysdeps/x86/sysdep.h>
 
+#define CET_ENABLED     0
+
 /* It is desirable that the names of PIC thunks match those used by
    GCC so that multiple copies are eliminated by the linker.  Because
    GCC 4.6 and earlier use __i686 in the names, it is necessary to
@@ -37,6 +39,15 @@
 
 /* Syntactic details of assembler.  */
 
+/* Define an entry point visible from C.  */
+#define	ENTRY_P2ALIGN(name, alignment)					      \
+  .globl C_SYMBOL_NAME(name);						      \
+  .type C_SYMBOL_NAME(name),@function;					      \
+  .align ALIGNARG(alignment);						      \
+  C_LABEL(name)								      \
+  cfi_startproc;							      \
+  CALL_MCOUNT
+
 /* If compiled for profiling, call `mcount' at the start of each function.  */
 #ifdef	PROF
 /* The mcount code relies on a normal frame pointer being on the stack