21 files changed, 188 insertions, 126 deletions

diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S
index e0788bade5ab..3b6544111ac9 100644
--- a/arch/x86/lib/atomic64_386_32.S
+++ b/arch/x86/lib/atomic64_386_32.S
@@ -20,10 +20,10 @@
 
 #define BEGIN(op) \
 .macro endp; \
-ENDPROC(atomic64_##op##_386); \
+SYM_FUNC_END(atomic64_##op##_386); \
 .purgem endp; \
 .endm; \
-ENTRY(atomic64_##op##_386); \
+SYM_FUNC_START(atomic64_##op##_386); \
 	LOCK v;
 
 #define ENDP endp
diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S
index 843d978ee341..1c5c81c16b06 100644
--- a/arch/x86/lib/atomic64_cx8_32.S
+++ b/arch/x86/lib/atomic64_cx8_32.S
@@ -16,12 +16,12 @@
 	cmpxchg8b (\reg)
 .endm
 
-ENTRY(atomic64_read_cx8)
+SYM_FUNC_START(atomic64_read_cx8)
 	read64 %ecx
 	ret
-ENDPROC(atomic64_read_cx8)
+SYM_FUNC_END(atomic64_read_cx8)
 
-ENTRY(atomic64_set_cx8)
+SYM_FUNC_START(atomic64_set_cx8)
 1:
 /* we don't need LOCK_PREFIX since aligned 64-bit writes
  * are atomic on 586 and newer */
@@ -29,19 +29,19 @@ ENTRY(atomic64_set_cx8)
 	jne 1b
 
 	ret
-ENDPROC(atomic64_set_cx8)
+SYM_FUNC_END(atomic64_set_cx8)
 
-ENTRY(atomic64_xchg_cx8)
+SYM_FUNC_START(atomic64_xchg_cx8)
 1:
 	LOCK_PREFIX
 	cmpxchg8b (%esi)
 	jne 1b
 
 	ret
-ENDPROC(atomic64_xchg_cx8)
+SYM_FUNC_END(atomic64_xchg_cx8)
 
 .macro addsub_return func ins insc
-ENTRY(atomic64_\func\()_return_cx8)
+SYM_FUNC_START(atomic64_\func\()_return_cx8)
 	pushl %ebp
 	pushl %ebx
 	pushl %esi
@@ -69,14 +69,14 @@ ENTRY(atomic64_\func\()_return_cx8)
 	popl %ebx
 	popl %ebp
 	ret
-ENDPROC(atomic64_\func\()_return_cx8)
+SYM_FUNC_END(atomic64_\func\()_return_cx8)
 .endm
 
 addsub_return add add adc
 addsub_return sub sub sbb
 
 .macro incdec_return func ins insc
-ENTRY(atomic64_\func\()_return_cx8)
+SYM_FUNC_START(atomic64_\func\()_return_cx8)
 	pushl %ebx
 
 	read64 %esi
@@ -94,13 +94,13 @@ ENTRY(atomic64_\func\()_return_cx8)
 	movl %ecx, %edx
 	popl %ebx
 	ret
-ENDPROC(atomic64_\func\()_return_cx8)
+SYM_FUNC_END(atomic64_\func\()_return_cx8)
 .endm
 
 incdec_return inc add adc
 incdec_return dec sub sbb
 
-ENTRY(atomic64_dec_if_positive_cx8)
+SYM_FUNC_START(atomic64_dec_if_positive_cx8)
 	pushl %ebx
 
 	read64 %esi
@@ -119,9 +119,9 @@ ENTRY(atomic64_dec_if_positive_cx8)
 	movl %ecx, %edx
 	popl %ebx
 	ret
-ENDPROC(atomic64_dec_if_positive_cx8)
+SYM_FUNC_END(atomic64_dec_if_positive_cx8)
 
-ENTRY(atomic64_add_unless_cx8)
+SYM_FUNC_START(atomic64_add_unless_cx8)
 	pushl %ebp
 	pushl %ebx
 /* these just push these two parameters on the stack */
@@ -155,9 +155,9 @@ ENTRY(atomic64_add_unless_cx8)
 	jne 2b
 	xorl %eax, %eax
 	jmp 3b
-ENDPROC(atomic64_add_unless_cx8)
+SYM_FUNC_END(atomic64_add_unless_cx8)
 
-ENTRY(atomic64_inc_not_zero_cx8)
+SYM_FUNC_START(atomic64_inc_not_zero_cx8)
 	pushl %ebx
 
 	read64 %esi
@@ -177,4 +177,4 @@ ENTRY(atomic64_inc_not_zero_cx8)
 3:
 	popl %ebx
 	ret
-ENDPROC(atomic64_inc_not_zero_cx8)
+SYM_FUNC_END(atomic64_inc_not_zero_cx8)
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index 4df90c9ea383..4742e8fa7ee7 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -46,7 +46,7 @@ unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum)
 	   * Fortunately, it is easy to convert 2-byte alignment to 4-byte
 	   * alignment for the unrolled loop.
 	   */		
-ENTRY(csum_partial)
+SYM_FUNC_START(csum_partial)
 	pushl %esi
 	pushl %ebx
 	movl 20(%esp),%eax	# Function arg: unsigned int sum
@@ -128,13 +128,13 @@ ENTRY(csum_partial)
 	popl %ebx
 	popl %esi
 	ret
-ENDPROC(csum_partial)
+SYM_FUNC_END(csum_partial)
 
 #else
 
 /* Version for PentiumII/PPro */
 
-ENTRY(csum_partial)
+SYM_FUNC_START(csum_partial)
 	pushl %esi
 	pushl %ebx
 	movl 20(%esp),%eax	# Function arg: unsigned int sum
@@ -246,7 +246,7 @@ ENTRY(csum_partial)
 	popl %ebx
 	popl %esi
 	ret
-ENDPROC(csum_partial)
+SYM_FUNC_END(csum_partial)
 				
 #endif
 EXPORT_SYMBOL(csum_partial)
@@ -280,7 +280,7 @@ unsigned int csum_partial_copy_generic (const char *src, char *dst,
 #define ARGBASE 16		
 #define FP		12
 		
-ENTRY(csum_partial_copy_generic)
+SYM_FUNC_START(csum_partial_copy_generic)
 	subl  $4,%esp	
 	pushl %edi
 	pushl %esi
@@ -398,7 +398,7 @@ DST(	movb %cl, (%edi)	)
 	popl %edi
 	popl %ecx			# equivalent to addl $4,%esp
 	ret	
-ENDPROC(csum_partial_copy_generic)
+SYM_FUNC_END(csum_partial_copy_generic)
 
 #else
 
@@ -416,7 +416,7 @@ ENDPROC(csum_partial_copy_generic)
 
 #define ARGBASE 12
 		
-ENTRY(csum_partial_copy_generic)
+SYM_FUNC_START(csum_partial_copy_generic)
 	pushl %ebx
 	pushl %edi
 	pushl %esi
@@ -483,7 +483,7 @@ DST(	movb %dl, (%edi)         )
 	popl %edi
 	popl %ebx
 	ret
-ENDPROC(csum_partial_copy_generic)
+SYM_FUNC_END(csum_partial_copy_generic)
 				
 #undef ROUND
 #undef ROUND1		
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index 75a5a4515fa7..c4c7dd115953 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -13,15 +13,15 @@
  * Zero a page.
  * %rdi	- page
  */
-ENTRY(clear_page_rep)
+SYM_FUNC_START(clear_page_rep)
 	movl $4096/8,%ecx
 	xorl %eax,%eax
 	rep stosq
 	ret
-ENDPROC(clear_page_rep)
+SYM_FUNC_END(clear_page_rep)
 EXPORT_SYMBOL_GPL(clear_page_rep)
 
-ENTRY(clear_page_orig)
+SYM_FUNC_START(clear_page_orig)
 	xorl   %eax,%eax
 	movl   $4096/64,%ecx
 	.p2align 4
@@ -40,13 +40,13 @@ ENTRY(clear_page_orig)
 	jnz	.Lloop
 	nop
 	ret
-ENDPROC(clear_page_orig)
+SYM_FUNC_END(clear_page_orig)
 EXPORT_SYMBOL_GPL(clear_page_orig)
 
-ENTRY(clear_page_erms)
+SYM_FUNC_START(clear_page_erms)
 	movl $4096,%ecx
 	xorl %eax,%eax
 	rep stosb
 	ret
-ENDPROC(clear_page_erms)
+SYM_FUNC_END(clear_page_erms)
 EXPORT_SYMBOL_GPL(clear_page_erms)
diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S
index d63185698a23..3542502faa3b 100644
--- a/arch/x86/lib/cmpxchg16b_emu.S
+++ b/arch/x86/lib/cmpxchg16b_emu.S
@@ -13,7 +13,7 @@
  * %rcx : high 64 bits of new value
  * %al  : Operation successful
  */
-ENTRY(this_cpu_cmpxchg16b_emu)
+SYM_FUNC_START(this_cpu_cmpxchg16b_emu)
 
 #
 # Emulate 'cmpxchg16b %gs:(%rsi)' except we return the result in %al not
@@ -44,4 +44,4 @@ ENTRY(this_cpu_cmpxchg16b_emu)
 	xor %al,%al
 	ret
 
-ENDPROC(this_cpu_cmpxchg16b_emu)
+SYM_FUNC_END(this_cpu_cmpxchg16b_emu)
diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S
index 691d80e97488..ca01ed6029f4 100644
--- a/arch/x86/lib/cmpxchg8b_emu.S
+++ b/arch/x86/lib/cmpxchg8b_emu.S
@@ -13,7 +13,7 @@
  * %ebx : low 32 bits of new value
  * %ecx : high 32 bits of new value
  */
-ENTRY(cmpxchg8b_emu)
+SYM_FUNC_START(cmpxchg8b_emu)
 
 #
 # Emulate 'cmpxchg8b (%esi)' on UP except we don't
@@ -42,5 +42,5 @@ ENTRY(cmpxchg8b_emu)
 	popfl
 	ret
 
-ENDPROC(cmpxchg8b_emu)
+SYM_FUNC_END(cmpxchg8b_emu)
 EXPORT_SYMBOL(cmpxchg8b_emu)
diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S
index fd2d09afa097..2402d4c489d2 100644
--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -13,15 +13,15 @@
  * prefetch distance based on SMP/UP.
  */
 	ALIGN
-ENTRY(copy_page)
+SYM_FUNC_START(copy_page)
 	ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD
 	movl	$4096/8, %ecx
 	rep	movsq
 	ret
-ENDPROC(copy_page)
+SYM_FUNC_END(copy_page)
 EXPORT_SYMBOL(copy_page)
 
-ENTRY(copy_page_regs)
+SYM_FUNC_START_LOCAL(copy_page_regs)
 	subq	$2*8,	%rsp
 	movq	%rbx,	(%rsp)
 	movq	%r12,	1*8(%rsp)
@@ -86,4 +86,4 @@ ENTRY(copy_page_regs)
 	movq	1*8(%rsp), %r12
 	addq	$2*8, %rsp
 	ret
-ENDPROC(copy_page_regs)
+SYM_FUNC_END(copy_page_regs)
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 86976b55ae74..816f128a6d52 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -53,7 +53,7 @@
  * Output:
  * eax uncopied bytes or 0 if successful.
  */
-ENTRY(copy_user_generic_unrolled)
+SYM_FUNC_START(copy_user_generic_unrolled)
 	ASM_STAC
 	cmpl $8,%edx
 	jb 20f		/* less then 8 bytes, go to byte copy loop */
@@ -136,7 +136,7 @@ ENTRY(copy_user_generic_unrolled)
 	_ASM_EXTABLE_UA(19b, 40b)
 	_ASM_EXTABLE_UA(21b, 50b)
 	_ASM_EXTABLE_UA(22b, 50b)
-ENDPROC(copy_user_generic_unrolled)
+SYM_FUNC_END(copy_user_generic_unrolled)
 EXPORT_SYMBOL(copy_user_generic_unrolled)
 
 /* Some CPUs run faster using the string copy instructions.
@@ -157,7 +157,7 @@ EXPORT_SYMBOL(copy_user_generic_unrolled)
  * Output:
  * eax uncopied bytes or 0 if successful.
  */
-ENTRY(copy_user_generic_string)
+SYM_FUNC_START(copy_user_generic_string)
 	ASM_STAC
 	cmpl $8,%edx
 	jb 2f		/* less than 8 bytes, go to byte copy loop */
@@ -182,7 +182,7 @@ ENTRY(copy_user_generic_string)
 
 	_ASM_EXTABLE_UA(1b, 11b)
 	_ASM_EXTABLE_UA(3b, 12b)
-ENDPROC(copy_user_generic_string)
+SYM_FUNC_END(copy_user_generic_string)
 EXPORT_SYMBOL(copy_user_generic_string)
 
 /*
@@ -197,7 +197,7 @@ EXPORT_SYMBOL(copy_user_generic_string)
  * Output:
  * eax uncopied bytes or 0 if successful.
  */
-ENTRY(copy_user_enhanced_fast_string)
+SYM_FUNC_START(copy_user_enhanced_fast_string)
 	ASM_STAC
 	cmpl $64,%edx
 	jb .L_copy_short_string	/* less then 64 bytes, avoid the costly 'rep' */
@@ -214,7 +214,7 @@ ENTRY(copy_user_enhanced_fast_string)
 	.previous
 
 	_ASM_EXTABLE_UA(1b, 12b)
-ENDPROC(copy_user_enhanced_fast_string)
+SYM_FUNC_END(copy_user_enhanced_fast_string)
 EXPORT_SYMBOL(copy_user_enhanced_fast_string)
 
 /*
@@ -230,8 +230,7 @@ EXPORT_SYMBOL(copy_user_enhanced_fast_string)
  * Output:
  * eax uncopied bytes or 0 if successful.
  */
-ALIGN;
-.Lcopy_user_handle_tail:
+SYM_CODE_START_LOCAL(.Lcopy_user_handle_tail)
 	movl %edx,%ecx
 1:	rep movsb
 2:	mov %ecx,%eax
@@ -239,7 +238,7 @@ ALIGN;
 	ret
 
 	_ASM_EXTABLE_UA(1b, 2b)
-END(.Lcopy_user_handle_tail)
+SYM_CODE_END(.Lcopy_user_handle_tail)
 
 /*
  * copy_user_nocache - Uncached memory copy with exception handling
@@ -250,7 +249,7 @@ END(.Lcopy_user_handle_tail)
  *  - Require 8-byte alignment when size is 8 bytes or larger.
  *  - Require 4-byte alignment when size is 4 bytes.
  */
-ENTRY(__copy_user_nocache)
+SYM_FUNC_START(__copy_user_nocache)
 	ASM_STAC
 
 	/* If size is less than 8 bytes, go to 4-byte copy */
@@ -389,5 +388,5 @@ ENTRY(__copy_user_nocache)
 	_ASM_EXTABLE_UA(31b, .L_fixup_4b_copy)
 	_ASM_EXTABLE_UA(40b, .L_fixup_1b_copy)
 	_ASM_EXTABLE_UA(41b, .L_fixup_1b_copy)
-ENDPROC(__copy_user_nocache)
+SYM_FUNC_END(__copy_user_nocache)
 EXPORT_SYMBOL(__copy_user_nocache)
diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S
index a4a379e79259..3394a8ff7fd0 100644
--- a/arch/x86/lib/csum-copy_64.S
+++ b/arch/x86/lib/csum-copy_64.S
@@ -49,7 +49,7 @@
 	.endm
 
 
-ENTRY(csum_partial_copy_generic)
+SYM_FUNC_START(csum_partial_copy_generic)
 	cmpl	$3*64, %edx
 	jle	.Lignore
 
@@ -225,4 +225,4 @@ ENTRY(csum_partial_copy_generic)
 	jz   .Lende
 	movl $-EFAULT, (%rax)
 	jmp .Lende
-ENDPROC(csum_partial_copy_generic)
+SYM_FUNC_END(csum_partial_copy_generic)
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index b7375dc6898f..c126571e5e2e 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -113,8 +113,8 @@ static void delay_mwaitx(unsigned long __loops)
 		__monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0);
 
 		/*
-		 * AMD, like Intel, supports the EAX hint and EAX=0xf
-		 * means, do not enter any deep C-state and we use it
+		 * AMD, like Intel's MWAIT version, supports the EAX hint and
+		 * EAX=0xf0 means, do not enter any deep C-state and we use it
 		 * here in delay() to minimize wakeup latency.
 		 */
 		__mwaitx(MWAITX_DISABLE_CSTATES, delay, MWAITX_ECX_TIMER_ENABLE);
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 9578eb88fc87..c8a85b512796 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -36,7 +36,7 @@
 #include <asm/export.h>
 
 	.text
-ENTRY(__get_user_1)
+SYM_FUNC_START(__get_user_1)
 	mov PER_CPU_VAR(current_task), %_ASM_DX
 	cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user
@@ -47,10 +47,10 @@ ENTRY(__get_user_1)
 	xor %eax,%eax
 	ASM_CLAC
 	ret
-ENDPROC(__get_user_1)
+SYM_FUNC_END(__get_user_1)
 EXPORT_SYMBOL(__get_user_1)
 
-ENTRY(__get_user_2)
+SYM_FUNC_START(__get_user_2)
 	add $1,%_ASM_AX
 	jc bad_get_user
 	mov PER_CPU_VAR(current_task), %_ASM_DX
@@ -63,10 +63,10 @@ ENTRY(__get_user_2)
 	xor %eax,%eax
 	ASM_CLAC
 	ret
-ENDPROC(__get_user_2)
+SYM_FUNC_END(__get_user_2)
 EXPORT_SYMBOL(__get_user_2)
 
-ENTRY(__get_user_4)
+SYM_FUNC_START(__get_user_4)
 	add $3,%_ASM_AX
 	jc bad_get_user
 	mov PER_CPU_VAR(current_task), %_ASM_DX
@@ -79,10 +79,10 @@ ENTRY(__get_user_4)
 	xor %eax,%eax
 	ASM_CLAC
 	ret
-ENDPROC(__get_user_4)
+SYM_FUNC_END(__get_user_4)
 EXPORT_SYMBOL(__get_user_4)
 
-ENTRY(__get_user_8)
+SYM_FUNC_START(__get_user_8)
 #ifdef CONFIG_X86_64
 	add $7,%_ASM_AX
 	jc bad_get_user
@@ -111,25 +111,27 @@ ENTRY(__get_user_8)
 	ASM_CLAC
 	ret
 #endif
-ENDPROC(__get_user_8)
+SYM_FUNC_END(__get_user_8)
 EXPORT_SYMBOL(__get_user_8)
 
 
-.Lbad_get_user_clac:
+SYM_CODE_START_LOCAL(.Lbad_get_user_clac)
 	ASM_CLAC
 bad_get_user:
 	xor %edx,%edx
 	mov $(-EFAULT),%_ASM_AX
 	ret
+SYM_CODE_END(.Lbad_get_user_clac)
 
 #ifdef CONFIG_X86_32
-.Lbad_get_user_8_clac:
+SYM_CODE_START_LOCAL(.Lbad_get_user_8_clac)
 	ASM_CLAC
 bad_get_user_8:
 	xor %edx,%edx
 	xor %ecx,%ecx
 	mov $(-EFAULT),%_ASM_AX
 	ret
+SYM_CODE_END(.Lbad_get_user_8_clac)
 #endif
 
 	_ASM_EXTABLE_UA(1b, .Lbad_get_user_clac)
diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S
index a14f9939c365..dbf8cc97b7f5 100644
--- a/arch/x86/lib/hweight.S
+++ b/arch/x86/lib/hweight.S
@@ -8,7 +8,7 @@
  * unsigned int __sw_hweight32(unsigned int w)
  * %rdi: w
  */
-ENTRY(__sw_hweight32)
+SYM_FUNC_START(__sw_hweight32)
 
 #ifdef CONFIG_X86_64
 	movl %edi, %eax				# w
@@ -33,10 +33,10 @@ ENTRY(__sw_hweight32)
 	shrl $24, %eax				# w = w_tmp >> 24
 	__ASM_SIZE(pop,) %__ASM_REG(dx)
 	ret
-ENDPROC(__sw_hweight32)
+SYM_FUNC_END(__sw_hweight32)
 EXPORT_SYMBOL(__sw_hweight32)
 
-ENTRY(__sw_hweight64)
+SYM_FUNC_START(__sw_hweight64)
 #ifdef CONFIG_X86_64
 	pushq   %rdi
 	pushq   %rdx
@@ -79,5 +79,5 @@ ENTRY(__sw_hweight64)
 	popl    %ecx
 	ret
 #endif
-ENDPROC(__sw_hweight64)
+SYM_FUNC_END(__sw_hweight64)
 EXPORT_SYMBOL(__sw_hweight64)
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 0b5862ba6a75..404279563891 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -13,6 +13,8 @@
 #include <asm/inat.h>
 #include <asm/insn.h>
 
+#include <asm/emulate_prefix.h>
+
 /* Verify next sizeof(t) bytes can be on the same instruction */
 #define validate_next(t, insn, n)	\
 	((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr)
@@ -58,6 +60,36 @@ void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64)
 		insn->addr_bytes = 4;
 }
 
+static const insn_byte_t xen_prefix[] = { __XEN_EMULATE_PREFIX };
+static const insn_byte_t kvm_prefix[] = { __KVM_EMULATE_PREFIX };
+
+static int __insn_get_emulate_prefix(struct insn *insn,
+				     const insn_byte_t *prefix, size_t len)
+{
+	size_t i;
+
+	for (i = 0; i < len; i++) {
+		if (peek_nbyte_next(insn_byte_t, insn, i) != prefix[i])
+			goto err_out;
+	}
+
+	insn->emulate_prefix_size = len;
+	insn->next_byte += len;
+
+	return 1;
+
+err_out:
+	return 0;
+}
+
+static void insn_get_emulate_prefix(struct insn *insn)
+{
+	if (__insn_get_emulate_prefix(insn, xen_prefix, sizeof(xen_prefix)))
+		return;
+
+	__insn_get_emulate_prefix(insn, kvm_prefix, sizeof(kvm_prefix));
+}
+
 /**
  * insn_get_prefixes - scan x86 instruction prefix bytes
  * @insn:	&struct insn containing instruction
@@ -76,6 +108,8 @@ void insn_get_prefixes(struct insn *insn)
 	if (prefixes->got)
 		return;
 
+	insn_get_emulate_prefix(insn);
+
 	nb = 0;
 	lb = 0;
 	b = peek_next(insn_byte_t, insn);
diff --git a/arch/x86/lib/iomap_copy_64.S b/arch/x86/lib/iomap_copy_64.S
index a9bdf0805be0..cb5a1964506b 100644
--- a/arch/x86/lib/iomap_copy_64.S
+++ b/arch/x86/lib/iomap_copy_64.S
@@ -8,8 +8,8 @@
 /*
  * override generic version in lib/iomap_copy.c
  */
-ENTRY(__iowrite32_copy)
+SYM_FUNC_START(__iowrite32_copy)
 	movl %edx,%ecx
 	rep movsd
 	ret
-ENDPROC(__iowrite32_copy)
+SYM_FUNC_END(__iowrite32_copy)
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 92748660ba51..56b243b14c3a 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -28,8 +28,8 @@
  * Output:
  * rax original destination
  */
-ENTRY(__memcpy)
-ENTRY(memcpy)
+SYM_FUNC_START_ALIAS(__memcpy)
+SYM_FUNC_START_LOCAL(memcpy)
 	ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
 		      "jmp memcpy_erms", X86_FEATURE_ERMS
 
@@ -41,8 +41,8 @@ ENTRY(memcpy)
 	movl %edx, %ecx
 	rep movsb
 	ret
-ENDPROC(memcpy)
-ENDPROC(__memcpy)
+SYM_FUNC_END(memcpy)
+SYM_FUNC_END_ALIAS(__memcpy)
 EXPORT_SYMBOL(memcpy)
 EXPORT_SYMBOL(__memcpy)
 
@@ -50,14 +50,14 @@ EXPORT_SYMBOL(__memcpy)
  * memcpy_erms() - enhanced fast string memcpy. This is faster and
  * simpler than memcpy. Use memcpy_erms when possible.
  */
-ENTRY(memcpy_erms)
+SYM_FUNC_START_LOCAL(memcpy_erms)
 	movq %rdi, %rax
 	movq %rdx, %rcx
 	rep movsb
 	ret
-ENDPROC(memcpy_erms)
+SYM_FUNC_END(memcpy_erms)
 
-ENTRY(memcpy_orig)
+SYM_FUNC_START_LOCAL(memcpy_orig)
 	movq %rdi, %rax
 
 	cmpq $0x20, %rdx
@@ -182,7 +182,7 @@ ENTRY(memcpy_orig)
 
 .Lend:
 	retq
-ENDPROC(memcpy_orig)
+SYM_FUNC_END(memcpy_orig)
 
 #ifndef CONFIG_UML
 
@@ -193,7 +193,7 @@ MCSAFE_TEST_CTL
  * Note that we only catch machine checks when reading the source addresses.
  * Writes to target are posted and don't generate machine checks.
  */
-ENTRY(__memcpy_mcsafe)
+SYM_FUNC_START(__memcpy_mcsafe)
 	cmpl $8, %edx
 	/* Less than 8 bytes? Go to byte copy loop */
 	jb .L_no_whole_words
@@ -260,7 +260,7 @@ ENTRY(__memcpy_mcsafe)
 	xorl %eax, %eax
 .L_done:
 	ret
-ENDPROC(__memcpy_mcsafe)
+SYM_FUNC_END(__memcpy_mcsafe)
 EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
 
 	.section .fixup, "ax"
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index bbec69d8223b..337830d7a59c 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -26,8 +26,8 @@
  */
 .weak memmove
 
-ENTRY(memmove)
-ENTRY(__memmove)
+SYM_FUNC_START_ALIAS(memmove)
+SYM_FUNC_START(__memmove)
 
 	/* Handle more 32 bytes in loop */
 	mov %rdi, %rax
@@ -207,7 +207,7 @@ ENTRY(__memmove)
 	movb %r11b, (%rdi)
 13:
 	retq
-ENDPROC(__memmove)
-ENDPROC(memmove)
+SYM_FUNC_END(__memmove)
+SYM_FUNC_END_ALIAS(memmove)
 EXPORT_SYMBOL(__memmove)
 EXPORT_SYMBOL(memmove)
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 9bc861c71e75..9ff15ee404a4 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -19,8 +19,8 @@
  *
  * rax   original destination
  */
-ENTRY(memset)
-ENTRY(__memset)
+SYM_FUNC_START_ALIAS(memset)
+SYM_FUNC_START(__memset)
 	/*
 	 * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended
 	 * to use it when possible. If not available, use fast string instructions.
@@ -43,8 +43,8 @@ ENTRY(__memset)
 	rep stosb
 	movq %r9,%rax
 	ret
-ENDPROC(memset)
-ENDPROC(__memset)
+SYM_FUNC_END(__memset)
+SYM_FUNC_END_ALIAS(memset)
 EXPORT_SYMBOL(memset)
 EXPORT_SYMBOL(__memset)
 
@@ -59,16 +59,16 @@ EXPORT_SYMBOL(__memset)
  *
  * rax   original destination
  */
-ENTRY(memset_erms)
+SYM_FUNC_START_LOCAL(memset_erms)
 	movq %rdi,%r9
 	movb %sil,%al
 	movq %rdx,%rcx
 	rep stosb
 	movq %r9,%rax
 	ret
-ENDPROC(memset_erms)
+SYM_FUNC_END(memset_erms)
 
-ENTRY(memset_orig)
+SYM_FUNC_START_LOCAL(memset_orig)
 	movq %rdi,%r10
 
 	/* expand byte value  */
@@ -139,4 +139,4 @@ ENTRY(memset_orig)
 	subq %r8,%rdx
 	jmp .Lafter_bad_alignment
 .Lfinal:
-ENDPROC(memset_orig)
+SYM_FUNC_END(memset_orig)
diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S
index ed33cbab3958..a2b9caa5274c 100644
--- a/arch/x86/lib/msr-reg.S
+++ b/arch/x86/lib/msr-reg.S
@@ -12,7 +12,7 @@
  *
  */
 .macro op_safe_regs op
-ENTRY(\op\()_safe_regs)
+SYM_FUNC_START(\op\()_safe_regs)
 	pushq %rbx
 	pushq %r12
 	movq	%rdi, %r10	/* Save pointer */
@@ -41,13 +41,13 @@ ENTRY(\op\()_safe_regs)
 	jmp     2b
 
 	_ASM_EXTABLE(1b, 3b)
-ENDPROC(\op\()_safe_regs)
+SYM_FUNC_END(\op\()_safe_regs)
 .endm
 
 #else /* X86_32 */
 
 .macro op_safe_regs op
-ENTRY(\op\()_safe_regs)
+SYM_FUNC_START(\op\()_safe_regs)
 	pushl %ebx
 	pushl %ebp
 	pushl %esi
@@ -83,7 +83,7 @@ ENTRY(\op\()_safe_regs)
 	jmp     2b
 
 	_ASM_EXTABLE(1b, 3b)
-ENDPROC(\op\()_safe_regs)
+SYM_FUNC_END(\op\()_safe_regs)
 .endm
 
 #endif
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index 126dd6a9ec9b..7c7c92db8497 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -34,7 +34,7 @@
 #define ENTER	mov PER_CPU_VAR(current_task), %_ASM_BX
 
 .text
-ENTRY(__put_user_1)
+SYM_FUNC_START(__put_user_1)
 	ENTER
 	cmp TASK_addr_limit(%_ASM_BX),%_ASM_CX
 	jae .Lbad_put_user
@@ -43,10 +43,10 @@ ENTRY(__put_user_1)
 	xor %eax,%eax
 	ASM_CLAC
 	ret
-ENDPROC(__put_user_1)
+SYM_FUNC_END(__put_user_1)
 EXPORT_SYMBOL(__put_user_1)
 
-ENTRY(__put_user_2)
+SYM_FUNC_START(__put_user_2)
 	ENTER
 	mov TASK_addr_limit(%_ASM_BX),%_ASM_BX
 	sub $1,%_ASM_BX
@@ -57,10 +57,10 @@ ENTRY(__put_user_2)
 	xor %eax,%eax
 	ASM_CLAC
 	ret
-ENDPROC(__put_user_2)
+SYM_FUNC_END(__put_user_2)
 EXPORT_SYMBOL(__put_user_2)
 
-ENTRY(__put_user_4)
+SYM_FUNC_START(__put_user_4)
 	ENTER
 	mov TASK_addr_limit(%_ASM_BX),%_ASM_BX
 	sub $3,%_ASM_BX
@@ -71,10 +71,10 @@ ENTRY(__put_user_4)
 	xor %eax,%eax
 	ASM_CLAC
 	ret
-ENDPROC(__put_user_4)
+SYM_FUNC_END(__put_user_4)
 EXPORT_SYMBOL(__put_user_4)
 
-ENTRY(__put_user_8)
+SYM_FUNC_START(__put_user_8)
 	ENTER
 	mov TASK_addr_limit(%_ASM_BX),%_ASM_BX
 	sub $7,%_ASM_BX
@@ -88,14 +88,15 @@ ENTRY(__put_user_8)
 	xor %eax,%eax
 	ASM_CLAC
 	RET
-ENDPROC(__put_user_8)
+SYM_FUNC_END(__put_user_8)
 EXPORT_SYMBOL(__put_user_8)
 
-.Lbad_put_user_clac:
+SYM_CODE_START_LOCAL(.Lbad_put_user_clac)
 	ASM_CLAC
 .Lbad_put_user:
 	movl $-EFAULT,%eax
 	RET
+SYM_CODE_END(.Lbad_put_user_clac)
 
 	_ASM_EXTABLE_UA(1b, .Lbad_put_user_clac)
 	_ASM_EXTABLE_UA(2b, .Lbad_put_user_clac)
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index c909961e678a..363ec132df7e 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -11,11 +11,11 @@
 .macro THUNK reg
 	.section .text.__x86.indirect_thunk
 
-ENTRY(__x86_indirect_thunk_\reg)
+SYM_FUNC_START(__x86_indirect_thunk_\reg)
 	CFI_STARTPROC
 	JMP_NOSPEC %\reg
 	CFI_ENDPROC
-ENDPROC(__x86_indirect_thunk_\reg)
+SYM_FUNC_END(__x86_indirect_thunk_\reg)
 .endm
 
 /*
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index e0b85930dd77..8908c58bd6cd 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -333,7 +333,7 @@ AVXcode: 1
 06: CLTS
 07: SYSRET (o64)
 08: INVD
-09: WBINVD
+09: WBINVD | WBNOINVD (F3)
 0a:
 0b: UD2 (1B)
 0c:
@@ -364,7 +364,7 @@ AVXcode: 1
 # a ModR/M byte.
 1a: BNDCL Gv,Ev (F3) | BNDCU Gv,Ev (F2) | BNDMOV Gv,Ev (66) | BNDLDX Gv,Ev
 1b: BNDCN Gv,Ev (F2) | BNDMOV Ev,Gv (66) | BNDMK Gv,Ev (F3) | BNDSTX Ev,Gv
-1c:
+1c: Grp20 (1A),(1C)
 1d:
 1e:
 1f: NOP Ev
@@ -695,16 +695,28 @@ AVXcode: 2
 4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev)
 4e: vrsqrt14ps/d Vpd,Wpd (66),(ev)
 4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev)
-# Skip 0x50-0x57
+50: vpdpbusd Vx,Hx,Wx (66),(ev)
+51: vpdpbusds Vx,Hx,Wx (66),(ev)
+52: vdpbf16ps Vx,Hx,Wx (F3),(ev) | vpdpwssd Vx,Hx,Wx (66),(ev) | vp4dpwssd Vdqq,Hdqq,Wdq (F2),(ev)
+53: vpdpwssds Vx,Hx,Wx (66),(ev) | vp4dpwssds Vdqq,Hdqq,Wdq (F2),(ev)
+54: vpopcntb/w Vx,Wx (66),(ev)
+55: vpopcntd/q Vx,Wx (66),(ev)
 58: vpbroadcastd Vx,Wx (66),(v)
 59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo)
 5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo)
 5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev)
-# Skip 0x5c-0x63
+# Skip 0x5c-0x61
+62: vpexpandb/w Vx,Wx (66),(ev)
+63: vpcompressb/w Wx,Vx (66),(ev)
 64: vpblendmd/q Vx,Hx,Wx (66),(ev)
 65: vblendmps/d Vx,Hx,Wx (66),(ev)
 66: vpblendmb/w Vx,Hx,Wx (66),(ev)
-# Skip 0x67-0x74
+68: vp2intersectd/q Kx,Hx,Wx (F2),(ev)
+# Skip 0x69-0x6f
+70: vpshldvw Vx,Hx,Wx (66),(ev)
+71: vpshldvd/q Vx,Hx,Wx (66),(ev)
+72: vcvtne2ps2bf16 Vx,Hx,Wx (F2),(ev) | vcvtneps2bf16 Vx,Wx (F3),(ev) | vpshrdvw Vx,Hx,Wx (66),(ev)
+73: vpshrdvd/q Vx,Hx,Wx (66),(ev)
 75: vpermi2b/w Vx,Hx,Wx (66),(ev)
 76: vpermi2d/q Vx,Hx,Wx (66),(ev)
 77: vpermi2ps/d Vx,Hx,Wx (66),(ev)
@@ -727,6 +739,7 @@ AVXcode: 2
 8c: vpmaskmovd/q Vx,Hx,Mx (66),(v)
 8d: vpermb/w Vx,Hx,Wx (66),(ev)
 8e: vpmaskmovd/q Mx,Vx,Hx (66),(v)
+8f: vpshufbitqmb Kx,Hx,Wx (66),(ev)
 # 0x0f 0x38 0x90-0xbf (FMA)
 90: vgatherdd/q Vx,Hx,Wx (66),(v) | vpgatherdd/q Vx,Wx (66),(evo)
 91: vgatherqd/q Vx,Hx,Wx (66),(v) | vpgatherqd/q Vx,Wx (66),(evo)
@@ -738,8 +751,8 @@ AVXcode: 2
 97: vfmsubadd132ps/d Vx,Hx,Wx (66),(v)
 98: vfmadd132ps/d Vx,Hx,Wx (66),(v)
 99: vfmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
-9a: vfmsub132ps/d Vx,Hx,Wx (66),(v)
-9b: vfmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
+9a: vfmsub132ps/d Vx,Hx,Wx (66),(v) | v4fmaddps Vdqq,Hdqq,Wdq (F2),(ev)
+9b: vfmsub132ss/d Vx,Hx,Wx (66),(v),(v1) | v4fmaddss Vdq,Hdq,Wdq (F2),(ev)
 9c: vfnmadd132ps/d Vx,Hx,Wx (66),(v)
 9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
 9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v)
@@ -752,8 +765,8 @@ a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v)
 a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v)
 a8: vfmadd213ps/d Vx,Hx,Wx (66),(v)
 a9: vfmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
-aa: vfmsub213ps/d Vx,Hx,Wx (66),(v)
-ab: vfmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
+aa: vfmsub213ps/d Vx,Hx,Wx (66),(v) | v4fnmaddps Vdqq,Hdqq,Wdq (F2),(ev)
+ab: vfmsub213ss/d Vx,Hx,Wx (66),(v),(v1) | v4fnmaddss Vdq,Hdq,Wdq (F2),(ev)
 ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v)
 ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
 ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v)
@@ -780,11 +793,12 @@ ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev)
 cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev)
 cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev)
 cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev)
+cf: vgf2p8mulb Vx,Wx (66)
 db: VAESIMC Vdq,Wdq (66),(v1)
-dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
-dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
-de: VAESDEC Vdq,Hdq,Wdq (66),(v1)
-df: VAESDECLAST Vdq,Hdq,Wdq (66),(v1)
+dc: vaesenc Vx,Hx,Wx (66)
+dd: vaesenclast Vx,Hx,Wx (66)
+de: vaesdec Vx,Hx,Wx (66)
+df: vaesdeclast Vx,Hx,Wx (66)
 f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) | CRC32 Gd,Eb (66&F2)
 f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) | CRC32 Gd,Ew (66&F2)
 f2: ANDN Gy,By,Ey (v)
@@ -792,6 +806,8 @@ f3: Grp17 (1A)
 f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v)
 f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v)
 f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v)
+f8: MOVDIR64B Gv,Mdqq (66) | ENQCMD Gv,Mdqq (F2) | ENQCMDS Gv,Mdqq (F3)
+f9: MOVDIRI My,Gy
 EndTable
 
 Table: 3-byte opcode 2 (0x0f 0x3a)
@@ -846,7 +862,7 @@ AVXcode: 3
 41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1)
 42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) | vdbpsadbw Vx,Hx,Wx,Ib (66),(evo)
 43: vshufi32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
-44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1)
+44: vpclmulqdq Vx,Hx,Wx,Ib (66)
 46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v)
 4a: vblendvps Vx,Hx,Wx,Lx (66),(v)
 4b: vblendvpd Vx,Hx,Wx,Lx (66),(v)
@@ -863,7 +879,13 @@ AVXcode: 3
 63: vpcmpistri Vdq,Wdq,Ib (66),(v1)
 66: vfpclassps/d Vk,Wx,Ib (66),(ev)
 67: vfpclassss/d Vk,Wx,Ib (66),(ev)
+70: vpshldw Vx,Hx,Wx,Ib (66),(ev)
+71: vpshldd/q Vx,Hx,Wx,Ib (66),(ev)
+72: vpshrdw Vx,Hx,Wx,Ib (66),(ev)
+73: vpshrdd/q Vx,Hx,Wx,Ib (66),(ev)
 cc: sha1rnds4 Vdq,Wdq,Ib
+ce: vgf2p8affineqb Vx,Wx,Ib (66)
+cf: vgf2p8affineinvqb Vx,Wx,Ib (66)
 df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
 f0: RORX Gy,Ey,Ib (F2),(v)
 EndTable
@@ -943,9 +965,9 @@ GrpTable: Grp6
 EndTable
 
 GrpTable: Grp7
-0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B)
-1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B)
-2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B)
+0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B)
+1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B)
+2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B)
 3: LIDT Ms
 4: SMSW Mw/Rv
 5: rdpkru (110),(11B) | wrpkru (111),(11B)
@@ -1020,7 +1042,7 @@ GrpTable: Grp15
 3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B)
 4: XSAVE | ptwrite Ey (F3),(11B)
 5: XRSTOR | lfence (11B)
-6: XSAVEOPT | clwb (66) | mfence (11B)
+6: XSAVEOPT | clwb (66) | mfence (11B) | TPAUSE Rd (66),(11B) | UMONITOR Rv (F3),(11B) | UMWAIT Rd (F2),(11B)
 7: clflush | clflushopt (66) | sfence (11B)
 EndTable
 
@@ -1051,6 +1073,10 @@ GrpTable: Grp19
 6: vscatterpf1qps/d Wx (66),(ev)
 EndTable
 
+GrpTable: Grp20
+0: cldemote Mb
+EndTable
+
 # AMD's Prefetch Group
 GrpTable: GrpP
 0: PREFETCH