Merge tag 'x86_core_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 core updates from Borislav Petkov:

 - Get rid of all the .fixup sections because this generates
   misleading/wrong stacktraces and confuse RELIABLE_STACKTRACE and
   LIVEPATCH as the backtrace misses the function which is being fixed
   up.

 - Add Straight Line Speculation mitigation support which uses a new
   compiler switch -mharden-sls= which sticks an INT3 after a RET or an
   indirect branch in order to block speculation after them. Reportedly,
   CPUs do speculate behind such insns.

 - The usual set of cleanups and improvements

* tag 'x86_core_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (32 commits)
  x86/entry_32: Fix segment exceptions
  objtool: Remove .fixup handling
  x86: Remove .fixup section
  x86/word-at-a-time: Remove .fixup usage
  x86/usercopy: Remove .fixup usage
  x86/usercopy_32: Simplify __copy_user_intel_nocache()
  x86/sgx: Remove .fixup usage
  x86/checksum_32: Remove .fixup usage
  x86/vmx: Remove .fixup usage
  x86/kvm: Remove .fixup usage
  x86/segment: Remove .fixup usage
  x86/fpu: Remove .fixup usage
  x86/xen: Remove .fixup usage
  x86/uaccess: Remove .fixup usage
  x86/futex: Remove .fixup usage
  x86/msr: Remove .fixup usage
  x86/extable: Extend extable functionality
  x86/entry_32: Remove .fixup usage
  x86/entry_64: Remove .fixup usage
  x86/copy_mc_64: Remove .fixup usage
  ...

150 files changed, 991 insertions, 1316 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8910b09b5601..976dd6b532bf 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -473,6 +473,18 @@ config RETPOLINE
 	  branches. Requires a compiler with -mindirect-branch=thunk-extern
 	  support for full protection. The kernel may run slower.
 
+config CC_HAS_SLS
+	def_bool $(cc-option,-mharden-sls=all)
+
+config SLS
+	bool "Mitigate Straight-Line-Speculation"
+	depends on CC_HAS_SLS && X86_64
+	default n
+	help
+	  Compile the kernel with straight-line-speculation options to guard
+	  against straight line speculation. The kernel image might be slightly
+	  larger.
+
 config X86_CPU_RESCTRL
 	bool "x86 CPU resource control support"
 	depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD)
@@ -1952,7 +1964,7 @@ config EFI
 
 config EFI_STUB
 	bool "EFI stub support"
-	depends on EFI && !X86_USE_3DNOW
+	depends on EFI
 	depends on $(cc-option,-mabi=ms) || X86_32
 	select RELOCATABLE
 	help
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index eefc434351db..542377cd419d 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -342,10 +342,6 @@ config X86_USE_PPRO_CHECKSUM
 	def_bool y
 	depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MATOM
 
-config X86_USE_3DNOW
-	def_bool y
-	depends on (MCYRIXIII || MK7 || MGEODE_LX) && !UML
-
 #
 # P6_NOPs are a relatively minor optimization that require a family >=
 # 6 processor, except that it is broken on certain VIA chips.
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 42243869216d..e84cdd409b64 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -12,6 +12,18 @@ else
         KBUILD_DEFCONFIG := $(ARCH)_defconfig
 endif
 
+ifdef CONFIG_CC_IS_GCC
+RETPOLINE_CFLAGS	:= $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register)
+RETPOLINE_CFLAGS	+= $(call cc-option,-mindirect-branch-cs-prefix)
+RETPOLINE_VDSO_CFLAGS	:= $(call cc-option,-mindirect-branch=thunk-inline -mindirect-branch-register)
+endif
+ifdef CONFIG_CC_IS_CLANG
+RETPOLINE_CFLAGS	:= -mretpoline-external-thunk
+RETPOLINE_VDSO_CFLAGS	:= -mretpoline
+endif
+export RETPOLINE_CFLAGS
+export RETPOLINE_VDSO_CFLAGS
+
 # For gcc stack alignment is specified with -mpreferred-stack-boundary,
 # clang has the option -mstack-alignment for that purpose.
 ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
@@ -179,6 +191,10 @@ ifdef CONFIG_RETPOLINE
   endif
 endif
 
+ifdef CONFIG_SLS
+  KBUILD_CFLAGS += -mharden-sls=all
+endif
+
 KBUILD_LDFLAGS += -m elf_$(UTS_MACHINE)
 
 ifdef CONFIG_LTO_CLANG
diff --git a/arch/x86/boot/compressed/efi_thunk_64.S b/arch/x86/boot/compressed/efi_thunk_64.S
index d05f781d54f2..67e7edcdfea8 100644
--- a/arch/x86/boot/compressed/efi_thunk_64.S
+++ b/arch/x86/boot/compressed/efi_thunk_64.S
@@ -101,7 +101,7 @@ SYM_FUNC_START(__efi64_thunk)
 
 	pop	%rbx
 	pop	%rbp
-	ret
+	RET
 SYM_FUNC_END(__efi64_thunk)
 
 	.code32
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 572c535cf45b..fd9441f40457 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -813,7 +813,7 @@ SYM_FUNC_START(efi32_pe_entry)
 2:	popl	%edi				// restore callee-save registers
 	popl	%ebx
 	leave
-	ret
+	RET
 SYM_FUNC_END(efi32_pe_entry)
 
 	.section ".rodata"
@@ -868,7 +868,7 @@ SYM_FUNC_START(startup32_set_idt_entry)
 
 	pop     %ecx
 	pop     %ebx
-	ret
+	RET
 SYM_FUNC_END(startup32_set_idt_entry)
 #endif
 
@@ -884,7 +884,7 @@ SYM_FUNC_START(startup32_load_idt)
 	movl	%eax, rva(boot32_idt_desc+2)(%ebp)
 	lidt    rva(boot32_idt_desc)(%ebp)
 #endif
-	ret
+	RET
 SYM_FUNC_END(startup32_load_idt)
 
 /*
@@ -954,7 +954,7 @@ SYM_FUNC_START(startup32_check_sev_cbit)
 	popl	%ebx
 	popl	%eax
 #endif
-	ret
+	RET
 SYM_FUNC_END(startup32_check_sev_cbit)
 
 /*
diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S
index c1e81a848b2a..a63424d13627 100644
--- a/arch/x86/boot/compressed/mem_encrypt.S
+++ b/arch/x86/boot/compressed/mem_encrypt.S
@@ -58,7 +58,7 @@ SYM_FUNC_START(get_sev_encryption_bit)
 
 #endif	/* CONFIG_AMD_MEM_ENCRYPT */
 
-	ret
+	RET
 SYM_FUNC_END(get_sev_encryption_bit)
 
 /**
@@ -92,7 +92,7 @@ SYM_CODE_START_LOCAL(sev_es_req_cpuid)
 	/* All good - return success */
 	xorl	%eax, %eax
 1:
-	ret
+	RET
 2:
 	movl	$-1, %eax
 	jmp	1b
@@ -221,7 +221,7 @@ SYM_FUNC_START(set_sev_encryption_mask)
 #endif
 
 	xor	%rax, %rax
-	ret
+	RET
 SYM_FUNC_END(set_sev_encryption_mask)
 
 	.data
diff --git a/arch/x86/crypto/aegis128-aesni-asm.S b/arch/x86/crypto/aegis128-aesni-asm.S
index 51d46d93efbc..b48ddebb4748 100644
--- a/arch/x86/crypto/aegis128-aesni-asm.S
+++ b/arch/x86/crypto/aegis128-aesni-asm.S
@@ -122,7 +122,7 @@ SYM_FUNC_START_LOCAL(__load_partial)
 	pxor T0, MSG
 
 .Lld_partial_8:
-	ret
+	RET
 SYM_FUNC_END(__load_partial)
 
 /*
@@ -180,7 +180,7 @@ SYM_FUNC_START_LOCAL(__store_partial)
 	mov %r10b, (%r9)
 
 .Lst_partial_1:
-	ret
+	RET
 SYM_FUNC_END(__store_partial)
 
 /*
@@ -225,7 +225,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_init)
 	movdqu STATE4, 0x40(STATEP)
 
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(crypto_aegis128_aesni_init)
 
 /*
@@ -337,7 +337,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_ad)
 	movdqu STATE3, 0x30(STATEP)
 	movdqu STATE4, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Lad_out_1:
 	movdqu STATE4, 0x00(STATEP)
@@ -346,7 +346,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_ad)
 	movdqu STATE2, 0x30(STATEP)
 	movdqu STATE3, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Lad_out_2:
 	movdqu STATE3, 0x00(STATEP)
@@ -355,7 +355,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_ad)
 	movdqu STATE1, 0x30(STATEP)
 	movdqu STATE2, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Lad_out_3:
 	movdqu STATE2, 0x00(STATEP)
@@ -364,7 +364,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_ad)
 	movdqu STATE0, 0x30(STATEP)
 	movdqu STATE1, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Lad_out_4:
 	movdqu STATE1, 0x00(STATEP)
@@ -373,11 +373,11 @@ SYM_FUNC_START(crypto_aegis128_aesni_ad)
 	movdqu STATE4, 0x30(STATEP)
 	movdqu STATE0, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Lad_out:
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(crypto_aegis128_aesni_ad)
 
 .macro encrypt_block a s0 s1 s2 s3 s4 i
@@ -452,7 +452,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_enc)
 	movdqu STATE2, 0x30(STATEP)
 	movdqu STATE3, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Lenc_out_1:
 	movdqu STATE3, 0x00(STATEP)
@@ -461,7 +461,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_enc)
 	movdqu STATE1, 0x30(STATEP)
 	movdqu STATE2, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Lenc_out_2:
 	movdqu STATE2, 0x00(STATEP)
@@ -470,7 +470,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_enc)
 	movdqu STATE0, 0x30(STATEP)
 	movdqu STATE1, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Lenc_out_3:
 	movdqu STATE1, 0x00(STATEP)
@@ -479,7 +479,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_enc)
 	movdqu STATE4, 0x30(STATEP)
 	movdqu STATE0, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Lenc_out_4:
 	movdqu STATE0, 0x00(STATEP)
@@ -488,11 +488,11 @@ SYM_FUNC_START(crypto_aegis128_aesni_enc)
 	movdqu STATE3, 0x30(STATEP)
 	movdqu STATE4, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Lenc_out:
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(crypto_aegis128_aesni_enc)
 
 /*
@@ -532,7 +532,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_enc_tail)
 	movdqu STATE3, 0x40(STATEP)
 
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(crypto_aegis128_aesni_enc_tail)
 
 .macro decrypt_block a s0 s1 s2 s3 s4 i
@@ -606,7 +606,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_dec)
 	movdqu STATE2, 0x30(STATEP)
 	movdqu STATE3, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Ldec_out_1:
 	movdqu STATE3, 0x00(STATEP)
@@ -615,7 +615,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_dec)
 	movdqu STATE1, 0x30(STATEP)
 	movdqu STATE2, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Ldec_out_2:
 	movdqu STATE2, 0x00(STATEP)
@@ -624,7 +624,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_dec)
 	movdqu STATE0, 0x30(STATEP)
 	movdqu STATE1, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Ldec_out_3:
 	movdqu STATE1, 0x00(STATEP)
@@ -633,7 +633,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_dec)
 	movdqu STATE4, 0x30(STATEP)
 	movdqu STATE0, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Ldec_out_4:
 	movdqu STATE0, 0x00(STATEP)
@@ -642,11 +642,11 @@ SYM_FUNC_START(crypto_aegis128_aesni_dec)
 	movdqu STATE3, 0x30(STATEP)
 	movdqu STATE4, 0x40(STATEP)
 	FRAME_END
-	ret
+	RET
 
 .Ldec_out:
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(crypto_aegis128_aesni_dec)
 
 /*
@@ -696,7 +696,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_dec_tail)
 	movdqu STATE3, 0x40(STATEP)
 
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(crypto_aegis128_aesni_dec_tail)
 
 /*
@@ -743,5 +743,5 @@ SYM_FUNC_START(crypto_aegis128_aesni_final)
 	movdqu MSG, (%rsi)
 
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(crypto_aegis128_aesni_final)
diff --git a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
index 3f0fc7dd87d7..c799838242a6 100644
--- a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
+++ b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
@@ -525,7 +525,7 @@ ddq_add_8:
 	/* return updated IV */
 	vpshufb	xbyteswap, xcounter, xcounter
 	vmovdqu	xcounter, (p_iv)
-	ret
+	RET
 .endm
 
 /*
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 4e3972570916..363699dd7220 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -1594,7 +1594,7 @@ SYM_FUNC_START(aesni_gcm_dec)
 	GCM_ENC_DEC dec
 	GCM_COMPLETE arg10, arg11
 	FUNC_RESTORE
-	ret
+	RET
 SYM_FUNC_END(aesni_gcm_dec)
 
 
@@ -1683,7 +1683,7 @@ SYM_FUNC_START(aesni_gcm_enc)
 
 	GCM_COMPLETE arg10, arg11
 	FUNC_RESTORE
-	ret
+	RET
 SYM_FUNC_END(aesni_gcm_enc)
 
 /*****************************************************************************
@@ -1701,7 +1701,7 @@ SYM_FUNC_START(aesni_gcm_init)
 	FUNC_SAVE
 	GCM_INIT %arg3, %arg4,%arg5, %arg6
 	FUNC_RESTORE
-	ret
+	RET
 SYM_FUNC_END(aesni_gcm_init)
 
 /*****************************************************************************
@@ -1716,7 +1716,7 @@ SYM_FUNC_START(aesni_gcm_enc_update)
 	FUNC_SAVE
 	GCM_ENC_DEC enc
 	FUNC_RESTORE
-	ret
+	RET
 SYM_FUNC_END(aesni_gcm_enc_update)
 
 /*****************************************************************************
@@ -1731,7 +1731,7 @@ SYM_FUNC_START(aesni_gcm_dec_update)
 	FUNC_SAVE
 	GCM_ENC_DEC dec
 	FUNC_RESTORE
-	ret
+	RET
 SYM_FUNC_END(aesni_gcm_dec_update)
 
 /*****************************************************************************
@@ -1746,7 +1746,7 @@ SYM_FUNC_START(aesni_gcm_finalize)
 	FUNC_SAVE
 	GCM_COMPLETE %arg3 %arg4
 	FUNC_RESTORE
-	ret
+	RET
 SYM_FUNC_END(aesni_gcm_finalize)
 
 #endif
@@ -1762,7 +1762,7 @@ SYM_FUNC_START_LOCAL(_key_expansion_256a)
 	pxor %xmm1, %xmm0
 	movaps %xmm0, (TKEYP)
 	add $0x10, TKEYP
-	ret
+	RET
 SYM_FUNC_END(_key_expansion_256a)
 SYM_FUNC_END_ALIAS(_key_expansion_128)
 
@@ -1787,7 +1787,7 @@ SYM_FUNC_START_LOCAL(_key_expansion_192a)
 	shufps $0b01001110, %xmm2, %xmm1
 	movaps %xmm1, 0x10(TKEYP)
 	add $0x20, TKEYP
-	ret
+	RET
 SYM_FUNC_END(_key_expansion_192a)
 
 SYM_FUNC_START_LOCAL(_key_expansion_192b)
@@ -1806,7 +1806,7 @@ SYM_FUNC_START_LOCAL(_key_expansion_192b)
 
 	movaps %xmm0, (TKEYP)
 	add $0x10, TKEYP
-	ret
+	RET
 SYM_FUNC_END(_key_expansion_192b)
 
 SYM_FUNC_START_LOCAL(_key_expansion_256b)
@@ -1818,7 +1818,7 @@ SYM_FUNC_START_LOCAL(_key_expansion_256b)
 	pxor %xmm1, %xmm2
 	movaps %xmm2, (TKEYP)
 	add $0x10, TKEYP
-	ret
+	RET
 SYM_FUNC_END(_key_expansion_256b)
 
 /*
@@ -1933,7 +1933,7 @@ SYM_FUNC_START(aesni_set_key)
 	popl KEYP
 #endif
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(aesni_set_key)
 
 /*
@@ -1957,7 +1957,7 @@ SYM_FUNC_START(aesni_enc)
 	popl KEYP
 #endif
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(aesni_enc)
 
 /*
@@ -2014,7 +2014,7 @@ SYM_FUNC_START_LOCAL(_aesni_enc1)
 	aesenc KEY, STATE
 	movaps 0x70(TKEYP), KEY
 	aesenclast KEY, STATE
-	ret
+	RET
 SYM_FUNC_END(_aesni_enc1)
 
 /*
@@ -2122,7 +2122,7 @@ SYM_FUNC_START_LOCAL(_aesni_enc4)
 	aesenclast KEY, STATE2
 	aesenclast KEY, STATE3
 	aesenclast KEY, STATE4
-	ret
+	RET
 SYM_FUNC_END(_aesni_enc4)
 
 /*
@@ -2147,7 +2147,7 @@ SYM_FUNC_START(aesni_dec)
 	popl KEYP
 #endif
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(aesni_dec)
 
 /*
@@ -2204,7 +2204,7 @@ SYM_FUNC_START_LOCAL(_aesni_dec1)
 	aesdec KEY, STATE
 	movaps 0x70(TKEYP), KEY
 	aesdeclast KEY, STATE
-	ret
+	RET
 SYM_FUNC_END(_aesni_dec1)
 
 /*
@@ -2312,7 +2312,7 @@ SYM_FUNC_START_LOCAL(_aesni_dec4)
 	aesdeclast KEY, STATE2
 	aesdeclast KEY, STATE3
 	aesdeclast KEY, STATE4
-	ret
+	RET
 SYM_FUNC_END(_aesni_dec4)
 
 /*
@@ -2372,7 +2372,7 @@ SYM_FUNC_START(aesni_ecb_enc)
 	popl LEN
 #endif
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(aesni_ecb_enc)
 
 /*
@@ -2433,7 +2433,7 @@ SYM_FUNC_START(aesni_ecb_dec)
 	popl LEN
 #endif
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(aesni_ecb_dec)
 
 /*
@@ -2477,7 +2477,7 @@ SYM_FUNC_START(aesni_cbc_enc)
 	popl IVP
 #endif
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(aesni_cbc_enc)
 
 /*
@@ -2570,7 +2570,7 @@ SYM_FUNC_START(aesni_cbc_dec)
 	popl IVP
 #endif
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(aesni_cbc_dec)
 
 /*
@@ -2627,7 +2627,7 @@ SYM_FUNC_START(aesni_cts_cbc_enc)
 	popl IVP
 #endif
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(aesni_cts_cbc_enc)
 
 /*
@@ -2688,7 +2688,7 @@ SYM_FUNC_START(aesni_cts_cbc_dec)
 	popl IVP
 #endif
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(aesni_cts_cbc_dec)
 
 .pushsection .rodata
@@ -2725,7 +2725,7 @@ SYM_FUNC_START_LOCAL(_aesni_inc_init)
 	mov $1, TCTR_LOW
 	movq TCTR_LOW, INC
 	movq CTR, TCTR_LOW
-	ret
+	RET
 SYM_FUNC_END(_aesni_inc_init)
 
 /*
@@ -2753,7 +2753,7 @@ SYM_FUNC_START_LOCAL(_aesni_inc)
 .Linc_low:
 	movaps CTR, IV
 	pshufb BSWAP_MASK, IV
-	ret
+	RET
 SYM_FUNC_END(_aesni_inc)
 
 /*
@@ -2816,7 +2816,7 @@ SYM_FUNC_START(aesni_ctr_enc)
 	movups IV, (IVP)
 .Lctr_enc_just_ret:
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(aesni_ctr_enc)
 
 #endif
@@ -2932,7 +2932,7 @@ SYM_FUNC_START(aesni_xts_encrypt)
 	popl IVP
 #endif
 	FRAME_END
-	ret
+	RET
 
 .Lxts_enc_1x:
 	add $64, LEN
@@ -3092,7 +3092,7 @@ SYM_FUNC_START(aesni_xts_decrypt)
 	popl IVP
 #endif
 	FRAME_END
-	ret
+	RET
 
 .Lxts_dec_1x:
 	add $64, LEN
diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S
index 98e3552b6e03..0852ab573fd3 100644
--- a/arch/x86/crypto/aesni-intel_avx-x86_64.S
+++ b/arch/x86/crypto/aesni-intel_avx-x86_64.S
@@ -1767,7 +1767,7 @@ SYM_FUNC_START(aesni_gcm_init_avx_gen2)
         FUNC_SAVE
         INIT GHASH_MUL_AVX, PRECOMPUTE_AVX
         FUNC_RESTORE
-        ret
+        RET
 SYM_FUNC_END(aesni_gcm_init_avx_gen2)
 
 ###############################################################################
@@ -1788,15 +1788,15 @@ SYM_FUNC_START(aesni_gcm_enc_update_avx_gen2)
         # must be 192
         GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, ENC, 11
         FUNC_RESTORE
-        ret
+        RET
 key_128_enc_update:
         GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, ENC, 9
         FUNC_RESTORE
-        ret
+        RET
 key_256_enc_update:
         GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, ENC, 13
         FUNC_RESTORE
-        ret
+        RET
 SYM_FUNC_END(aesni_gcm_enc_update_avx_gen2)
 
 ###############################################################################
@@ -1817,15 +1817,15 @@ SYM_FUNC_START(aesni_gcm_dec_update_avx_gen2)
         # must be 192
         GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, DEC, 11
         FUNC_RESTORE
-        ret
+        RET
 key_128_dec_update:
         GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, DEC, 9
         FUNC_RESTORE
-        ret
+        RET
 key_256_dec_update:
         GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, DEC, 13
         FUNC_RESTORE
-        ret
+        RET
 SYM_FUNC_END(aesni_gcm_dec_update_avx_gen2)
 
 ###############################################################################
@@ -1846,15 +1846,15 @@ SYM_FUNC_START(aesni_gcm_finalize_avx_gen2)
         # must be 192
         GCM_COMPLETE GHASH_MUL_AVX, 11, arg3, arg4
         FUNC_RESTORE
-        ret
+        RET
 key_128_finalize:
         GCM_COMPLETE GHASH_MUL_AVX, 9, arg3, arg4
         FUNC_RESTORE
-        ret
+        RET
 key_256_finalize:
         GCM_COMPLETE GHASH_MUL_AVX, 13, arg3, arg4
         FUNC_RESTORE
-        ret
+        RET
 SYM_FUNC_END(aesni_gcm_finalize_avx_gen2)
 
 ###############################################################################
@@ -2735,7 +2735,7 @@ SYM_FUNC_START(aesni_gcm_init_avx_gen4)
         FUNC_SAVE
         INIT GHASH_MUL_AVX2, PRECOMPUTE_AVX2
         FUNC_RESTORE
-        ret
+        RET
 SYM_FUNC_END(aesni_gcm_init_avx_gen4)
 
 ###############################################################################
@@ -2756,15 +2756,15 @@ SYM_FUNC_START(aesni_gcm_enc_update_avx_gen4)
         # must be 192
         GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, ENC, 11
         FUNC_RESTORE
-	ret
+	RET
 key_128_enc_update4:
         GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, ENC, 9
         FUNC_RESTORE
-	ret
+	RET
 key_256_enc_update4:
         GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, ENC, 13
         FUNC_RESTORE
-	ret
+	RET
 SYM_FUNC_END(aesni_gcm_enc_update_avx_gen4)
 
 ###############################################################################
@@ -2785,15 +2785,15 @@ SYM_FUNC_START(aesni_gcm_dec_update_avx_gen4)
         # must be 192
         GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, DEC, 11
         FUNC_RESTORE
-        ret
+        RET
 key_128_dec_update4:
         GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, DEC, 9
         FUNC_RESTORE
-        ret
+        RET
 key_256_dec_update4:
         GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, DEC, 13
         FUNC_RESTORE
-        ret
+        RET
 SYM_FUNC_END(aesni_gcm_dec_update_avx_gen4)
 
 ###############################################################################
@@ -2814,13 +2814,13 @@ SYM_FUNC_START(aesni_gcm_finalize_avx_gen4)
         # must be 192
         GCM_COMPLETE GHASH_MUL_AVX2, 11, arg3, arg4
         FUNC_RESTORE
-        ret
+        RET
 key_128_finalize4:
         GCM_COMPLETE GHASH_MUL_AVX2, 9, arg3, arg4
         FUNC_RESTORE
-        ret
+        RET
 key_256_finalize4:
         GCM_COMPLETE GHASH_MUL_AVX2, 13, arg3, arg4
         FUNC_RESTORE
-        ret
+        RET
 SYM_FUNC_END(aesni_gcm_finalize_avx_gen4)
diff --git a/arch/x86/crypto/blake2s-core.S b/arch/x86/crypto/blake2s-core.S
index 2ca79974f819..b50b35ff1fdb 100644
--- a/arch/x86/crypto/blake2s-core.S
+++ b/arch/x86/crypto/blake2s-core.S
@@ -171,7 +171,7 @@ SYM_FUNC_START(blake2s_compress_ssse3)
 	movdqu		%xmm1,0x10(%rdi)
 	movdqu		%xmm14,0x20(%rdi)
 .Lendofloop:
-	ret
+	RET
 SYM_FUNC_END(blake2s_compress_ssse3)
 
 #ifdef CONFIG_AS_AVX512
@@ -251,6 +251,6 @@ SYM_FUNC_START(blake2s_compress_avx512)
 	vmovdqu		%xmm1,0x10(%rdi)
 	vmovdqu		%xmm4,0x20(%rdi)
 	vzeroupper
-	retq
+	RET
 SYM_FUNC_END(blake2s_compress_avx512)
 #endif /* CONFIG_AS_AVX512 */
diff --git a/arch/x86/crypto/blowfish-x86_64-asm_64.S b/arch/x86/crypto/blowfish-x86_64-asm_64.S
index 4222ac6d6584..802d71582689 100644
--- a/arch/x86/crypto/blowfish-x86_64-asm_64.S
+++ b/arch/x86/crypto/blowfish-x86_64-asm_64.S
@@ -135,10 +135,10 @@ SYM_FUNC_START(__blowfish_enc_blk)
 	jnz .L__enc_xor;
 
 	write_block();
-	ret;
+	RET;
 .L__enc_xor:
 	xor_block();
-	ret;
+	RET;
 SYM_FUNC_END(__blowfish_enc_blk)
 
 SYM_FUNC_START(blowfish_dec_blk)
@@ -170,7 +170,7 @@ SYM_FUNC_START(blowfish_dec_blk)
 
 	movq %r11, %r12;
 
-	ret;
+	RET;
 SYM_FUNC_END(blowfish_dec_blk)
 
 /**********************************************************************
@@ -322,14 +322,14 @@ SYM_FUNC_START(__blowfish_enc_blk_4way)
 
 	popq %rbx;
 	popq %r12;
-	ret;
+	RET;
 
 .L__enc_xor4:
 	xor_block4();
 
 	popq %rbx;
 	popq %r12;
-	ret;
+	RET;
 SYM_FUNC_END(__blowfish_enc_blk_4way)
 
 SYM_FUNC_START(blowfish_dec_blk_4way)
@@ -364,5 +364,5 @@ SYM_FUNC_START(blowfish_dec_blk_4way)
 	popq %rbx;
 	popq %r12;
 
-	ret;
+	RET;
 SYM_FUNC_END(blowfish_dec_blk_4way)
diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
index e2a0e0f4bf9d..2e1658ddbe1a 100644
--- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
@@ -192,7 +192,7 @@ SYM_FUNC_START_LOCAL(roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_c
 	roundsm16(%xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7,
 		  %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm15,
 		  %rcx, (%r9));
-	ret;
+	RET;
 SYM_FUNC_END(roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
 
 .align 8
@@ -200,7 +200,7 @@ SYM_FUNC_START_LOCAL(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_a
 	roundsm16(%xmm4, %xmm5, %xmm6, %xmm7, %xmm0, %xmm1, %xmm2, %xmm3,
 		  %xmm12, %xmm13, %xmm14, %xmm15, %xmm8, %xmm9, %xmm10, %xmm11,
 		  %rax, (%r9));
-	ret;
+	RET;
 SYM_FUNC_END(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 
 /*
@@ -778,7 +778,7 @@ SYM_FUNC_START_LOCAL(__camellia_enc_blk16)
 		    %xmm15, (key_table)(CTX, %r8, 8), (%rax), 1 * 16(%rax));
 
 	FRAME_END
-	ret;
+	RET;
 
 .align 8
 .Lenc_max32:
@@ -865,7 +865,7 @@ SYM_FUNC_START_LOCAL(__camellia_dec_blk16)
 		    %xmm15, (key_table)(CTX), (%rax), 1 * 16(%rax));
 
 	FRAME_END
-	ret;
+	RET;
 
 .align 8
 .Ldec_max32:
@@ -906,7 +906,7 @@ SYM_FUNC_START(camellia_ecb_enc_16way)
 		     %xmm8, %rsi);
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(camellia_ecb_enc_16way)
 
 SYM_FUNC_START(camellia_ecb_dec_16way)
@@ -936,7 +936,7 @@ SYM_FUNC_START(camellia_ecb_dec_16way)
 		     %xmm8, %rsi);
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(camellia_ecb_dec_16way)
 
 SYM_FUNC_START(camellia_cbc_dec_16way)
@@ -987,5 +987,5 @@ SYM_FUNC_START(camellia_cbc_dec_16way)
 		     %xmm8, %rsi);
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(camellia_cbc_dec_16way)
diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
index 706f70829a07..0e4e9abbf4de 100644
--- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
@@ -226,7 +226,7 @@ SYM_FUNC_START_LOCAL(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_c
 	roundsm32(%ymm0, %ymm1, %ymm2, %ymm3, %ymm4, %ymm5, %ymm6, %ymm7,
 		  %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, %ymm15,
 		  %rcx, (%r9));
-	ret;
+	RET;
 SYM_FUNC_END(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
 
 .align 8
@@ -234,7 +234,7 @@ SYM_FUNC_START_LOCAL(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_a
 	roundsm32(%ymm4, %ymm5, %ymm6, %ymm7, %ymm0, %ymm1, %ymm2, %ymm3,
 		  %ymm12, %ymm13, %ymm14, %ymm15, %ymm8, %ymm9, %ymm10, %ymm11,
 		  %rax, (%r9));
-	ret;
+	RET;
 SYM_FUNC_END(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 
 /*
@@ -814,7 +814,7 @@ SYM_FUNC_START_LOCAL(__camellia_enc_blk32)
 		    %ymm15, (key_table)(CTX, %r8, 8), (%rax), 1 * 32(%rax));
 
 	FRAME_END
-	ret;
+	RET;
 
 .align 8
 .Lenc_max32:
@@ -901,7 +901,7 @@ SYM_FUNC_START_LOCAL(__camellia_dec_blk32)
 		    %ymm15, (key_table)(CTX), (%rax), 1 * 32(%rax));
 
 	FRAME_END
-	ret;
+	RET;
 
 .align 8
 .Ldec_max32:
@@ -946,7 +946,7 @@ SYM_FUNC_START(camellia_ecb_enc_32way)
 	vzeroupper;
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(camellia_ecb_enc_32way)
 
 SYM_FUNC_START(camellia_ecb_dec_32way)
@@ -980,7 +980,7 @@ SYM_FUNC_START(camellia_ecb_dec_32way)
 	vzeroupper;
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(camellia_ecb_dec_32way)
 
 SYM_FUNC_START(camellia_cbc_dec_32way)
@@ -1047,5 +1047,5 @@ SYM_FUNC_START(camellia_cbc_dec_32way)
 
 	addq $(16 * 32), %rsp;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(camellia_cbc_dec_32way)
diff --git a/arch/x86/crypto/camellia-x86_64-asm_64.S b/arch/x86/crypto/camellia-x86_64-asm_64.S
index 1372e6408850..347c059f5940 100644
--- a/arch/x86/crypto/camellia-x86_64-asm_64.S
+++ b/arch/x86/crypto/camellia-x86_64-asm_64.S
@@ -213,13 +213,13 @@ SYM_FUNC_START(__camellia_enc_blk)
 	enc_outunpack(mov, RT1);
 
 	movq RR12, %r12;
-	ret;
+	RET;
 
 .L__enc_xor:
 	enc_outunpack(xor, RT1);
 
 	movq RR12, %r12;
-	ret;
+	RET;
 SYM_FUNC_END(__camellia_enc_blk)
 
 SYM_FUNC_START(camellia_dec_blk)
@@ -257,7 +257,7 @@ SYM_FUNC_START(camellia_dec_blk)
 	dec_outunpack();
 
 	movq RR12, %r12;
-	ret;
+	RET;
 SYM_FUNC_END(camellia_dec_blk)
 
 /**********************************************************************
@@ -448,14 +448,14 @@ SYM_FUNC_START(__camellia_enc_blk_2way)
 
 	movq RR12, %r12;
 	popq %rbx;
-	ret;
+	RET;
 
 .L__enc2_xor:
 	enc_outunpack2(xor, RT2);
 
 	movq RR12, %r12;
 	popq %rbx;
-	ret;
+	RET;
 SYM_FUNC_END(__camellia_enc_blk_2way)
 
 SYM_FUNC_START(camellia_dec_blk_2way)
@@ -495,5 +495,5 @@ SYM_FUNC_START(camellia_dec_blk_2way)
 
 	movq RR12, %r12;
 	movq RXOR, %rbx;
-	ret;
+	RET;
 SYM_FUNC_END(camellia_dec_blk_2way)
diff --git a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
index 8a6181b08b59..b258af420c92 100644
--- a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
@@ -279,7 +279,7 @@ SYM_FUNC_START_LOCAL(__cast5_enc_blk16)
 	outunpack_blocks(RR3, RL3, RTMP, RX, RKM);
 	outunpack_blocks(RR4, RL4, RTMP, RX, RKM);
 
-	ret;
+	RET;
 SYM_FUNC_END(__cast5_enc_blk16)
 
 .align 16
@@ -352,7 +352,7 @@ SYM_FUNC_START_LOCAL(__cast5_dec_blk16)
 	outunpack_blocks(RR3, RL3, RTMP, RX, RKM);
 	outunpack_blocks(RR4, RL4, RTMP, RX, RKM);
 
-	ret;
+	RET;
 
 .L__skip_dec:
 	vpsrldq $4, RKR, RKR;
@@ -393,7 +393,7 @@ SYM_FUNC_START(cast5_ecb_enc_16way)
 
 	popq %r15;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(cast5_ecb_enc_16way)
 
 SYM_FUNC_START(cast5_ecb_dec_16way)
@@ -431,7 +431,7 @@ SYM_FUNC_START(cast5_ecb_dec_16way)
 
 	popq %r15;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(cast5_ecb_dec_16way)
 
 SYM_FUNC_START(cast5_cbc_dec_16way)
@@ -483,7 +483,7 @@ SYM_FUNC_START(cast5_cbc_dec_16way)
 	popq %r15;
 	popq %r12;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(cast5_cbc_dec_16way)
 
 SYM_FUNC_START(cast5_ctr_16way)
@@ -559,5 +559,5 @@ SYM_FUNC_START(cast5_ctr_16way)
 	popq %r15;
 	popq %r12;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(cast5_ctr_16way)
diff --git a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
index fbddcecc3e3f..82b716fd5dba 100644
--- a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
@@ -289,7 +289,7 @@ SYM_FUNC_START_LOCAL(__cast6_enc_blk8)
 	outunpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
 	outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
 
-	ret;
+	RET;
 SYM_FUNC_END(__cast6_enc_blk8)
 
 .align 8
@@ -336,7 +336,7 @@ SYM_FUNC_START_LOCAL(__cast6_dec_blk8)
 	outunpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
 	outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
 
-	ret;
+	RET;
 SYM_FUNC_END(__cast6_dec_blk8)
 
 SYM_FUNC_START(cast6_ecb_enc_8way)
@@ -359,7 +359,7 @@ SYM_FUNC_START(cast6_ecb_enc_8way)
 
 	popq %r15;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(cast6_ecb_enc_8way)
 
 SYM_FUNC_START(cast6_ecb_dec_8way)
@@ -382,7 +382,7 @@ SYM_FUNC_START(cast6_ecb_dec_8way)
 
 	popq %r15;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(cast6_ecb_dec_8way)
 
 SYM_FUNC_START(cast6_cbc_dec_8way)
@@ -408,5 +408,5 @@ SYM_FUNC_START(cast6_cbc_dec_8way)
 	popq %r15;
 	popq %r12;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(cast6_cbc_dec_8way)
diff --git a/arch/x86/crypto/chacha-avx2-x86_64.S b/arch/x86/crypto/chacha-avx2-x86_64.S
index ee9a40ab4109..f3d8fc018249 100644
--- a/arch/x86/crypto/chacha-avx2-x86_64.S
+++ b/arch/x86/crypto/chacha-avx2-x86_64.S
@@ -193,7 +193,7 @@ SYM_FUNC_START(chacha_2block_xor_avx2)
 
 .Ldone2:
 	vzeroupper
-	ret
+	RET
 
 .Lxorpart2:
 	# xor remaining bytes from partial register into output
@@ -498,7 +498,7 @@ SYM_FUNC_START(chacha_4block_xor_avx2)
 
 .Ldone4:
 	vzeroupper
-	ret
+	RET
 
 .Lxorpart4:
 	# xor remaining bytes from partial register into output
@@ -992,7 +992,7 @@ SYM_FUNC_START(chacha_8block_xor_avx2)
 .Ldone8:
 	vzeroupper
 	lea		-8(%r10),%rsp
-	ret
+	RET
 
 .Lxorpart8:
 	# xor remaining bytes from partial register into output
diff --git a/arch/x86/crypto/chacha-avx512vl-x86_64.S b/arch/x86/crypto/chacha-avx512vl-x86_64.S
index bb193fde123a..946f74dd6fba 100644
--- a/arch/x86/crypto/chacha-avx512vl-x86_64.S
+++ b/arch/x86/crypto/chacha-avx512vl-x86_64.S
@@ -166,7 +166,7 @@ SYM_FUNC_START(chacha_2block_xor_avx512vl)
 
 .Ldone2:
 	vzeroupper
-	ret
+	RET
 
 .Lxorpart2:
 	# xor remaining bytes from partial register into output
@@ -432,7 +432,7 @@ SYM_FUNC_START(chacha_4block_xor_avx512vl)
 
 .Ldone4:
 	vzeroupper
-	ret
+	RET
 
 .Lxorpart4:
 	# xor remaining bytes from partial register into output
@@ -812,7 +812,7 @@ SYM_FUNC_START(chacha_8block_xor_avx512vl)
 
 .Ldone8:
 	vzeroupper
-	ret
+	RET
 
 .Lxorpart8:
 	# xor remaining bytes from partial register into output
diff --git a/arch/x86/crypto/chacha-ssse3-x86_64.S b/arch/x86/crypto/chacha-ssse3-x86_64.S
index ca1788bfee16..7111949cd5b9 100644
--- a/arch/x86/crypto/chacha-ssse3-x86_64.S
+++ b/arch/x86/crypto/chacha-ssse3-x86_64.S
@@ -108,7 +108,7 @@ SYM_FUNC_START_LOCAL(chacha_permute)
 	sub		$2,%r8d
 	jnz		.Ldoubleround
 
-	ret
+	RET
 SYM_FUNC_END(chacha_permute)
 
 SYM_FUNC_START(chacha_block_xor_ssse3)
@@ -166,7 +166,7 @@ SYM_FUNC_START(chacha_block_xor_ssse3)
 
 .Ldone:
 	FRAME_END
-	ret
+	RET
 
 .Lxorpart:
 	# xor remaining bytes from partial register into output
@@ -217,7 +217,7 @@ SYM_FUNC_START(hchacha_block_ssse3)
 	movdqu		%xmm3,0x10(%rsi)
 
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(hchacha_block_ssse3)
 
 SYM_FUNC_START(chacha_4block_xor_ssse3)
@@ -762,7 +762,7 @@ SYM_FUNC_START(chacha_4block_xor_ssse3)
 
 .Ldone4:
 	lea		-8(%r10),%rsp
-	ret
+	RET
 
 .Lxorpart4:
 	# xor remaining bytes from partial register into output
diff --git a/arch/x86/crypto/crc32-pclmul_asm.S b/arch/x86/crypto/crc32-pclmul_asm.S
index 6e7d4c4d3208..c392a6edbfff 100644
--- a/arch/x86/crypto/crc32-pclmul_asm.S
+++ b/arch/x86/crypto/crc32-pclmul_asm.S
@@ -236,5 +236,5 @@ fold_64:
 	pxor    %xmm2, %xmm1
 	pextrd  $0x01, %xmm1, %eax
 
-	ret
+	RET
 SYM_FUNC_END(crc32_pclmul_le_16)
diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
index ac1f303eed0f..80c0d22fc42c 100644
--- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
+++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
@@ -306,7 +306,7 @@ do_return:
 	popq    %rsi
 	popq    %rdi
 	popq    %rbx
-        ret
+        RET
 SYM_FUNC_END(crc_pcl)
 
 .section	.rodata, "a", @progbits
diff --git a/arch/x86/crypto/crct10dif-pcl-asm_64.S b/arch/x86/crypto/crct10dif-pcl-asm_64.S
index b2533d63030e..721474abfb71 100644
--- a/arch/x86/crypto/crct10dif-pcl-asm_64.S
+++ b/arch/x86/crypto/crct10dif-pcl-asm_64.S
@@ -257,7 +257,7 @@ SYM_FUNC_START(crc_t10dif_pcl)
 	# Final CRC value (x^16 * M(x)) mod G(x) is in low 16 bits of xmm0.
 
 	pextrw	$0, %xmm0, %eax
-	ret
+	RET
 
 .align 16
 .Lless_than_256_bytes:
diff --git a/arch/x86/crypto/des3_ede-asm_64.S b/arch/x86/crypto/des3_ede-asm_64.S
index fac0fdc3f25d..f4c760f4cade 100644
--- a/arch/x86/crypto/des3_ede-asm_64.S
+++ b/arch/x86/crypto/des3_ede-asm_64.S
@@ -243,7 +243,7 @@ SYM_FUNC_START(des3_ede_x86_64_crypt_blk)
 	popq %r12;
 	popq %rbx;
 
-	ret;
+	RET;
 SYM_FUNC_END(des3_ede_x86_64_crypt_blk)
 
 /***********************************************************************
@@ -528,7 +528,7 @@ SYM_FUNC_START(des3_ede_x86_64_crypt_blk_3way)
 	popq %r12;
 	popq %rbx;
 
-	ret;
+	RET;
 SYM_FUNC_END(des3_ede_x86_64_crypt_blk_3way)
 
 .section	.rodata, "a", @progbits
diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S
index 99ac25e18e09..2bf871899920 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_asm.S
+++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S
@@ -85,7 +85,7 @@ SYM_FUNC_START_LOCAL(__clmul_gf128mul_ble)
 	psrlq $1, T2
 	pxor T2, T1
 	pxor T1, DATA
-	ret
+	RET
 SYM_FUNC_END(__clmul_gf128mul_ble)
 
 /* void clmul_ghash_mul(char *dst, const u128 *shash) */
@@ -99,7 +99,7 @@ SYM_FUNC_START(clmul_ghash_mul)
 	pshufb BSWAP, DATA
 	movups DATA, (%rdi)
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(clmul_ghash_mul)
 
 /*
@@ -128,5 +128,5 @@ SYM_FUNC_START(clmul_ghash_update)
 	movups DATA, (%rdi)
 .Lupdate_just_ret:
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(clmul_ghash_update)
diff --git a/arch/x86/crypto/nh-avx2-x86_64.S b/arch/x86/crypto/nh-avx2-x86_64.S
index b22c7b936272..6a0b15e7196a 100644
--- a/arch/x86/crypto/nh-avx2-x86_64.S
+++ b/arch/x86/crypto/nh-avx2-x86_64.S
@@ -153,5 +153,5 @@ SYM_FUNC_START(nh_avx2)
 	vpaddq		T1, T0, T0
 	vpaddq		T4, T0, T0
 	vmovdqu		T0, (HASH)
-	ret
+	RET
 SYM_FUNC_END(nh_avx2)
diff --git a/arch/x86/crypto/nh-sse2-x86_64.S b/arch/x86/crypto/nh-sse2-x86_64.S
index d7ae22dd6683..34c567bbcb4f 100644
--- a/arch/x86/crypto/nh-sse2-x86_64.S
+++ b/arch/x86/crypto/nh-sse2-x86_64.S
@@ -119,5 +119,5 @@ SYM_FUNC_START(nh_sse2)
 	paddq		PASS2_SUMS, T1
 	movdqu		T0, 0x00(HASH)
 	movdqu		T1, 0x10(HASH)
-	ret
+	RET
 SYM_FUNC_END(nh_sse2)
diff --git a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
index b7ee24df7fba..82f2313f512b 100644
--- a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
@@ -601,7 +601,7 @@ SYM_FUNC_START_LOCAL(__serpent_enc_blk8_avx)
 	write_blocks(RA1, RB1, RC1, RD1, RK0, RK1, RK2);
 	write_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2);
 
-	ret;
+	RET;
 SYM_FUNC_END(__serpent_enc_blk8_avx)
 
 .align 8
@@ -655,7 +655,7 @@ SYM_FUNC_START_LOCAL(__serpent_dec_blk8_avx)
 	write_blocks(RC1, RD1, RB1, RE1, RK0, RK1, RK2);
 	write_blocks(RC2, RD2, RB2, RE2, RK0, RK1, RK2);
 
-	ret;
+	RET;
 SYM_FUNC_END(__serpent_dec_blk8_avx)
 
 SYM_FUNC_START(serpent_ecb_enc_8way_avx)
@@ -673,7 +673,7 @@ SYM_FUNC_START(serpent_ecb_enc_8way_avx)
 	store_8way(%rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(serpent_ecb_enc_8way_avx)
 
 SYM_FUNC_START(serpent_ecb_dec_8way_avx)
@@ -691,7 +691,7 @@ SYM_FUNC_START(serpent_ecb_dec_8way_avx)
 	store_8way(%rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2);
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(serpent_ecb_dec_8way_avx)
 
 SYM_FUNC_START(serpent_cbc_dec_8way_avx)
@@ -709,5 +709,5 @@ SYM_FUNC_START(serpent_cbc_dec_8way_avx)
 	store_cbc_8way(%rdx, %rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2);
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(serpent_cbc_dec_8way_avx)
diff --git a/arch/x86/crypto/serpent-avx2-asm_64.S b/arch/x86/crypto/serpent-avx2-asm_64.S
index 9161b6e441f3..8ea34c9b9316 100644
--- a/arch/x86/crypto/serpent-avx2-asm_64.S
+++ b/arch/x86/crypto/serpent-avx2-asm_64.S
@@ -601,7 +601,7 @@ SYM_FUNC_START_LOCAL(__serpent_enc_blk16)
 	write_blocks(RA1, RB1, RC1, RD1, RK0, RK1, RK2);
 	write_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2);
 
-	ret;
+	RET;
 SYM_FUNC_END(__serpent_enc_blk16)
 
 .align 8
@@ -655,7 +655,7 @@ SYM_FUNC_START_LOCAL(__serpent_dec_blk16)
 	write_blocks(RC1, RD1, RB1, RE1, RK0, RK1, RK2);
 	write_blocks(RC2, RD2, RB2, RE2, RK0, RK1, RK2);
 
-	ret;
+	RET;
 SYM_FUNC_END(__serpent_dec_blk16)
 
 SYM_FUNC_START(serpent_ecb_enc_16way)
@@ -677,7 +677,7 @@ SYM_FUNC_START(serpent_ecb_enc_16way)
 	vzeroupper;
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(serpent_ecb_enc_16way)
 
 SYM_FUNC_START(serpent_ecb_dec_16way)
@@ -699,7 +699,7 @@ SYM_FUNC_START(serpent_ecb_dec_16way)
 	vzeroupper;
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(serpent_ecb_dec_16way)
 
 SYM_FUNC_START(serpent_cbc_dec_16way)
@@ -722,5 +722,5 @@ SYM_FUNC_START(serpent_cbc_dec_16way)
 	vzeroupper;
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(serpent_cbc_dec_16way)
diff --git a/arch/x86/crypto/serpent-sse2-i586-asm_32.S b/arch/x86/crypto/serpent-sse2-i586-asm_32.S
index 6379b99cb722..8ccb03ad7cef 100644
--- a/arch/x86/crypto/serpent-sse2-i586-asm_32.S
+++ b/arch/x86/crypto/serpent-sse2-i586-asm_32.S
@@ -553,12 +553,12 @@ SYM_FUNC_START(__serpent_enc_blk_4way)
 
 	write_blocks(%eax, RA, RB, RC, RD, RT0, RT1, RE);
 
-	ret;
+	RET;
 
 .L__enc_xor4:
 	xor_blocks(%eax, RA, RB, RC, RD, RT0, RT1, RE);
 
-	ret;
+	RET;
 SYM_FUNC_END(__serpent_enc_blk_4way)
 
 SYM_FUNC_START(serpent_dec_blk_4way)
@@ -612,5 +612,5 @@ SYM_FUNC_START(serpent_dec_blk_4way)
 	movl arg_dst(%esp), %eax;
 	write_blocks(%eax, RC, RD, RB, RE, RT0, RT1, RA);
 
-	ret;
+	RET;
 SYM_FUNC_END(serpent_dec_blk_4way)
diff --git a/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S b/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S
index efb6dc17dc90..e0998a011d1d 100644
--- a/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S
+++ b/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S
@@ -675,13 +675,13 @@ SYM_FUNC_START(__serpent_enc_blk_8way)
 	write_blocks(%rsi, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
 	write_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);
 
-	ret;
+	RET;
 
 .L__enc_xor8:
 	xor_blocks(%rsi, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
 	xor_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);
 
-	ret;
+	RET;
 SYM_FUNC_END(__serpent_enc_blk_8way)
 
 SYM_FUNC_START(serpent_dec_blk_8way)
@@ -735,5 +735,5 @@ SYM_FUNC_START(serpent_dec_blk_8way)
 	write_blocks(%rsi, RC1, RD1, RB1, RE1, RK0, RK1, RK2);
 	write_blocks(%rax, RC2, RD2, RB2, RE2, RK0, RK1, RK2);
 
-	ret;
+	RET;
 SYM_FUNC_END(serpent_dec_blk_8way)
diff --git a/arch/x86/crypto/sha1_avx2_x86_64_asm.S b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
index 5eed620f4676..a96b2fd26dab 100644
--- a/arch/x86/crypto/sha1_avx2_x86_64_asm.S
+++ b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
@@ -674,7 +674,7 @@ _loop3:
 	pop	%r12
 	pop	%rbx
 
-	ret
+	RET
 
 	SYM_FUNC_END(\name)
 .endm
diff --git a/arch/x86/crypto/sha1_ni_asm.S b/arch/x86/crypto/sha1_ni_asm.S
index 5d8415f482bd..2f94ec0e763b 100644
--- a/arch/x86/crypto/sha1_ni_asm.S
+++ b/arch/x86/crypto/sha1_ni_asm.S
@@ -290,7 +290,7 @@ SYM_FUNC_START(sha1_ni_transform)
 	mov		%rbp, %rsp
 	pop		%rbp
 
-	ret
+	RET
 SYM_FUNC_END(sha1_ni_transform)
 
 .section	.rodata.cst16.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 16
diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S
index d25668d2a1e9..263f916362e0 100644
--- a/arch/x86/crypto/sha1_ssse3_asm.S
+++ b/arch/x86/crypto/sha1_ssse3_asm.S
@@ -99,7 +99,7 @@
 	pop	%rbp
 	pop	%r12
 	pop	%rbx
-	ret
+	RET
 
 	SYM_FUNC_END(\name)
 .endm
diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/crypto/sha256-avx-asm.S
index 4739cd31b9db..3baa1ec39097 100644
--- a/arch/x86/crypto/sha256-avx-asm.S
+++ b/arch/x86/crypto/sha256-avx-asm.S
@@ -458,7 +458,7 @@ done_hash:
 	popq    %r13
 	popq	%r12
 	popq    %rbx
-	ret
+	RET
 SYM_FUNC_END(sha256_transform_avx)
 
 .section	.rodata.cst256.K256, "aM", @progbits, 256
diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S
index 4087f7432a7e..9bcdbc47b8b4 100644
--- a/arch/x86/crypto/sha256-avx2-asm.S
+++ b/arch/x86/crypto/sha256-avx2-asm.S
@@ -710,7 +710,7 @@ done_hash:
 	popq	%r13
 	popq	%r12
 	popq	%rbx
-	ret
+	RET
 SYM_FUNC_END(sha256_transform_rorx)
 
 .section	.rodata.cst512.K256, "aM", @progbits, 512
diff --git a/arch/x86/crypto/sha256-ssse3-asm.S b/arch/x86/crypto/sha256-ssse3-asm.S
index ddfa863b4ee3..c4a5db612c32 100644
--- a/arch/x86/crypto/sha256-ssse3-asm.S
+++ b/arch/x86/crypto/sha256-ssse3-asm.S
@@ -472,7 +472,7 @@ done_hash:
 	popq    %r12
 	popq    %rbx
 
-	ret
+	RET
 SYM_FUNC_END(sha256_transform_ssse3)
 
 .section	.rodata.cst256.K256, "aM", @progbits, 256
diff --git a/arch/x86/crypto/sha256_ni_asm.S b/arch/x86/crypto/sha256_ni_asm.S
index 7abade04a3a3..94d50dd27cb5 100644
--- a/arch/x86/crypto/sha256_ni_asm.S
+++ b/arch/x86/crypto/sha256_ni_asm.S
@@ -326,7 +326,7 @@ SYM_FUNC_START(sha256_ni_transform)
 
 .Ldone_hash:
 
-	ret
+	RET
 SYM_FUNC_END(sha256_ni_transform)
 
 .section	.rodata.cst256.K256, "aM", @progbits, 256
diff --git a/arch/x86/crypto/sha512-avx-asm.S b/arch/x86/crypto/sha512-avx-asm.S
index 3d8f0fd4eea8..1fefe6dd3a9e 100644
--- a/arch/x86/crypto/sha512-avx-asm.S
+++ b/arch/x86/crypto/sha512-avx-asm.S
@@ -361,7 +361,7 @@ updateblock:
 	pop	%rbx
 
 nowork:
-	ret
+	RET
 SYM_FUNC_END(sha512_transform_avx)
 
 ########################################################################
diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S
index 072cb0f0deae..5cdaab7d6901 100644
--- a/arch/x86/crypto/sha512-avx2-asm.S
+++ b/arch/x86/crypto/sha512-avx2-asm.S
@@ -679,7 +679,7 @@ done_hash:
 	pop	%r12
 	pop	%rbx
 
-	ret
+	RET
 SYM_FUNC_END(sha512_transform_rorx)
 
 ########################################################################
diff --git a/arch/x86/crypto/sha512-ssse3-asm.S b/arch/x86/crypto/sha512-ssse3-asm.S
index bd51c9070bed..b84c22e06c5f 100644
--- a/arch/x86/crypto/sha512-ssse3-asm.S
+++ b/arch/x86/crypto/sha512-ssse3-asm.S
@@ -363,7 +363,7 @@ updateblock:
 	pop	%rbx
 
 nowork:
-	ret
+	RET
 SYM_FUNC_END(sha512_transform_ssse3)
 
 ########################################################################
diff --git a/arch/x86/crypto/sm4-aesni-avx-asm_64.S b/arch/x86/crypto/sm4-aesni-avx-asm_64.S
index 1cc72b4804fa..4767ab61ff48 100644
--- a/arch/x86/crypto/sm4-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/sm4-aesni-avx-asm_64.S
@@ -246,7 +246,7 @@ SYM_FUNC_START(sm4_aesni_avx_crypt4)
 .Lblk4_store_output_done:
 	vzeroall;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(sm4_aesni_avx_crypt4)
 
 .align 8
@@ -356,7 +356,7 @@ SYM_FUNC_START_LOCAL(__sm4_crypt_blk8)
 	vpshufb RTMP2, RB3, RB3;
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(__sm4_crypt_blk8)
 
 /*
@@ -412,7 +412,7 @@ SYM_FUNC_START(sm4_aesni_avx_crypt8)
 .Lblk8_store_output_done:
 	vzeroall;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(sm4_aesni_avx_crypt8)
 
 /*
@@ -487,7 +487,7 @@ SYM_FUNC_START(sm4_aesni_avx_ctr_enc_blk8)
 
 	vzeroall;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(sm4_aesni_avx_ctr_enc_blk8)
 
 /*
@@ -537,7 +537,7 @@ SYM_FUNC_START(sm4_aesni_avx_cbc_dec_blk8)
 
 	vzeroall;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(sm4_aesni_avx_cbc_dec_blk8)
 
 /*
@@ -590,5 +590,5 @@ SYM_FUNC_START(sm4_aesni_avx_cfb_dec_blk8)
 
 	vzeroall;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(sm4_aesni_avx_cfb_dec_blk8)
diff --git a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S
index 9c5d3f3ad45a..4732fe8bb65b 100644
--- a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S
@@ -268,7 +268,7 @@ SYM_FUNC_START_LOCAL(__sm4_crypt_blk16)
 	vpshufb RTMP2, RB3, RB3;
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(__sm4_crypt_blk16)
 
 #define inc_le128(x, minus_one, tmp) \
@@ -387,7 +387,7 @@ SYM_FUNC_START(sm4_aesni_avx2_ctr_enc_blk16)
 
 	vzeroall;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(sm4_aesni_avx2_ctr_enc_blk16)
 
 /*
@@ -441,7 +441,7 @@ SYM_FUNC_START(sm4_aesni_avx2_cbc_dec_blk16)
 
 	vzeroall;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(sm4_aesni_avx2_cbc_dec_blk16)
 
 /*
@@ -497,5 +497,5 @@ SYM_FUNC_START(sm4_aesni_avx2_cfb_dec_blk16)
 
 	vzeroall;
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(sm4_aesni_avx2_cfb_dec_blk16)
diff --git a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
index 37e63b3c664e..31f9b2ec3857 100644
--- a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
@@ -267,7 +267,7 @@ SYM_FUNC_START_LOCAL(__twofish_enc_blk8)
 	outunpack_blocks(RC1, RD1, RA1, RB1, RK1, RX0, RY0, RK2);
 	outunpack_blocks(RC2, RD2, RA2, RB2, RK1, RX0, RY0, RK2);
 
-	ret;
+	RET;
 SYM_FUNC_END(__twofish_enc_blk8)
 
 .align 8
@@ -307,7 +307,7 @@ SYM_FUNC_START_LOCAL(__twofish_dec_blk8)
 	outunpack_blocks(RA1, RB1, RC1, RD1, RK1, RX0, RY0, RK2);
 	outunpack_blocks(RA2, RB2, RC2, RD2, RK1, RX0, RY0, RK2);
 
-	ret;
+	RET;
 SYM_FUNC_END(__twofish_dec_blk8)
 
 SYM_FUNC_START(twofish_ecb_enc_8way)
@@ -327,7 +327,7 @@ SYM_FUNC_START(twofish_ecb_enc_8way)
 	store_8way(%r11, RC1, RD1, RA1, RB1, RC2, RD2, RA2, RB2);
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(twofish_ecb_enc_8way)
 
 SYM_FUNC_START(twofish_ecb_dec_8way)
@@ -347,7 +347,7 @@ SYM_FUNC_START(twofish_ecb_dec_8way)
 	store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(twofish_ecb_dec_8way)
 
 SYM_FUNC_START(twofish_cbc_dec_8way)
@@ -372,5 +372,5 @@ SYM_FUNC_START(twofish_cbc_dec_8way)
 	popq %r12;
 
 	FRAME_END
-	ret;
+	RET;
 SYM_FUNC_END(twofish_cbc_dec_8way)
diff --git a/arch/x86/crypto/twofish-i586-asm_32.S b/arch/x86/crypto/twofish-i586-asm_32.S
index a6f09e4f2e46..3abcad661884 100644
--- a/arch/x86/crypto/twofish-i586-asm_32.S
+++ b/arch/x86/crypto/twofish-i586-asm_32.S
@@ -260,7 +260,7 @@ SYM_FUNC_START(twofish_enc_blk)
 	pop	%ebx
 	pop	%ebp
 	mov	$1,	%eax
-	ret
+	RET
 SYM_FUNC_END(twofish_enc_blk)
 
 SYM_FUNC_START(twofish_dec_blk)
@@ -317,5 +317,5 @@ SYM_FUNC_START(twofish_dec_blk)
 	pop	%ebx
 	pop	%ebp
 	mov	$1,	%eax
-	ret
+	RET
 SYM_FUNC_END(twofish_dec_blk)
diff --git a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
index bca4cea757ce..d2288bf38a8a 100644
--- a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
+++ b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
@@ -258,7 +258,7 @@ SYM_FUNC_START(__twofish_enc_blk_3way)
 	popq %rbx;
 	popq %r12;
 	popq %r13;
-	ret;
+	RET;
 
 .L__enc_xor3:
 	outunpack_enc3(xor);
@@ -266,7 +266,7 @@ SYM_FUNC_START(__twofish_enc_blk_3way)
 	popq %rbx;
 	popq %r12;
 	popq %r13;
-	ret;
+	RET;
 SYM_FUNC_END(__twofish_enc_blk_3way)
 
 SYM_FUNC_START(twofish_dec_blk_3way)
@@ -301,5 +301,5 @@ SYM_FUNC_START(twofish_dec_blk_3way)
 	popq %rbx;
 	popq %r12;
 	popq %r13;
-	ret;
+	RET;
 SYM_FUNC_END(twofish_dec_blk_3way)
diff --git a/arch/x86/crypto/twofish-x86_64-asm_64.S b/arch/x86/crypto/twofish-x86_64-asm_64.S
index d2e56232494a..775af290cd19 100644
--- a/arch/x86/crypto/twofish-x86_64-asm_64.S
+++ b/arch/x86/crypto/twofish-x86_64-asm_64.S
@@ -252,7 +252,7 @@ SYM_FUNC_START(twofish_enc_blk)
 
 	popq	R1
 	movl	$1,%eax
-	ret
+	RET
 SYM_FUNC_END(twofish_enc_blk)
 
 SYM_FUNC_START(twofish_dec_blk)
@@ -304,5 +304,5 @@ SYM_FUNC_START(twofish_dec_blk)
 
 	popq	R1
 	movl	$1,%eax
-	ret
+	RET
 SYM_FUNC_END(twofish_dec_blk)
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index ccb9d32768f3..a7ec22b1d06c 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -268,19 +268,16 @@
 1:	popl	%ds
 2:	popl	%es
 3:	popl	%fs
-	addl	$(4 + \pop), %esp	/* pop the unused "gs" slot */
+4:	addl	$(4 + \pop), %esp	/* pop the unused "gs" slot */
 	IRET_FRAME
-.pushsection .fixup, "ax"
-4:	movl	$0, (%esp)
-	jmp	1b
-5:	movl	$0, (%esp)
-	jmp	2b
-6:	movl	$0, (%esp)
-	jmp	3b
-.popsection
-	_ASM_EXTABLE(1b, 4b)
-	_ASM_EXTABLE(2b, 5b)
-	_ASM_EXTABLE(3b, 6b)
+
+	/*
+	 * There is no _ASM_EXTABLE_TYPE_REG() for ASM, however since this is
+	 * ASM the registers are known and we can trivially hard-code them.
+	 */
+	_ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_POP_ZERO|EX_REG_DS)
+	_ASM_EXTABLE_TYPE(2b, 3b, EX_TYPE_POP_ZERO|EX_REG_ES)
+	_ASM_EXTABLE_TYPE(3b, 4b, EX_TYPE_POP_ZERO|EX_REG_FS)
 .endm
 
 .macro RESTORE_ALL_NMI cr3_reg:req pop=0
@@ -740,7 +737,7 @@ SYM_FUNC_START(schedule_tail_wrapper)
 	popl	%eax
 
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(schedule_tail_wrapper)
 .popsection
 
@@ -925,10 +922,8 @@ SYM_FUNC_START(entry_SYSENTER_32)
 	sti
 	sysexit
 
-.pushsection .fixup, "ax"
-2:	movl	$0, PT_FS(%esp)
-	jmp	1b
-.popsection
+2:	movl    $0, PT_FS(%esp)
+	jmp     1b
 	_ASM_EXTABLE(1b, 2b)
 
 .Lsysenter_fix_flags:
@@ -996,8 +991,7 @@ restore_all_switch_stack:
 	 */
 	iret
 
-.section .fixup, "ax"
-SYM_CODE_START(asm_iret_error)
+.Lasm_iret_error:
 	pushl	$0				# no error code
 	pushl	$iret_error
 
@@ -1014,9 +1008,8 @@ SYM_CODE_START(asm_iret_error)
 #endif
 
 	jmp	handle_exception
-SYM_CODE_END(asm_iret_error)
-.previous
-	_ASM_EXTABLE(.Lirq_return, asm_iret_error)
+
+	_ASM_EXTABLE(.Lirq_return, .Lasm_iret_error)
 SYM_FUNC_END(entry_INT80_32)
 
 .macro FIXUP_ESPFIX_STACK
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 97b1f84bb53f..1ffdbfaad2e2 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -738,14 +738,10 @@ SYM_FUNC_START(asm_load_gs_index)
 2:	ALTERNATIVE "", "mfence", X86_BUG_SWAPGS_FENCE
 	swapgs
 	FRAME_END
-	ret
-SYM_FUNC_END(asm_load_gs_index)
-EXPORT_SYMBOL(asm_load_gs_index)
+	RET
 
-	_ASM_EXTABLE(.Lgs_change, .Lbad_gs)
-	.section .fixup, "ax"
 	/* running with kernelgs */
-SYM_CODE_START_LOCAL_NOALIGN(.Lbad_gs)
+.Lbad_gs:
 	swapgs					/* switch back to user gs */
 .macro ZAP_GS
 	/* This can't be a string because the preprocessor needs to see it. */
@@ -756,8 +752,11 @@ SYM_CODE_START_LOCAL_NOALIGN(.Lbad_gs)
 	xorl	%eax, %eax
 	movl	%eax, %gs
 	jmp	2b
-SYM_CODE_END(.Lbad_gs)
-	.previous
+
+	_ASM_EXTABLE(.Lgs_change, .Lbad_gs)
+
+SYM_FUNC_END(asm_load_gs_index)
+EXPORT_SYMBOL(asm_load_gs_index)
 
 #ifdef CONFIG_XEN_PV
 /*
@@ -889,7 +888,7 @@ SYM_CODE_START_LOCAL(paranoid_entry)
 	 * is needed here.
 	 */
 	SAVE_AND_SET_GSBASE scratch_reg=%rax save_reg=%rbx
-	ret
+	RET
 
 .Lparanoid_entry_checkgs:
 	/* EBX = 1 -> kernel GSBASE active, no restore required */
@@ -910,7 +909,7 @@ SYM_CODE_START_LOCAL(paranoid_entry)
 .Lparanoid_kernel_gsbase:
 
 	FENCE_SWAPGS_KERNEL_ENTRY
-	ret
+	RET
 SYM_CODE_END(paranoid_entry)
 
 /*
@@ -989,7 +988,7 @@ SYM_CODE_START_LOCAL(error_entry)
 	movq	%rax, %rsp			/* switch stack */
 	ENCODE_FRAME_POINTER
 	pushq	%r12
-	ret
+	RET
 
 	/*
 	 * There are two places in the kernel that can potentially fault with
@@ -1020,7 +1019,7 @@ SYM_CODE_START_LOCAL(error_entry)
 	 */
 .Lerror_entry_done_lfence:
 	FENCE_SWAPGS_KERNEL_ENTRY
-	ret
+	RET
 
 .Lbstep_iret:
 	/* Fix truncated RIP */
diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S
index f1f96d4d8cd6..7591bab060f7 100644
--- a/arch/x86/entry/thunk_32.S
+++ b/arch/x86/entry/thunk_32.S
@@ -24,7 +24,7 @@ SYM_CODE_START_NOALIGN(\name)
 	popl %edx
 	popl %ecx
 	popl %eax
-	ret
+	RET
 	_ASM_NOKPROBE(\name)
 SYM_CODE_END(\name)
 	.endm
diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S
index 496b11ec469d..505b488fcc65 100644
--- a/arch/x86/entry/thunk_64.S
+++ b/arch/x86/entry/thunk_64.S
@@ -50,7 +50,7 @@ SYM_CODE_START_LOCAL_NOALIGN(__thunk_restore)
 	popq %rsi
 	popq %rdi
 	popq %rbp
-	ret
+	RET
 	_ASM_NOKPROBE(__thunk_restore)
 SYM_CODE_END(__thunk_restore)
 #endif
diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S
index dc8da7695859..bafa73f09e92 100644
--- a/arch/x86/entry/vdso/vdso-layout.lds.S
+++ b/arch/x86/entry/vdso/vdso-layout.lds.S
@@ -77,7 +77,6 @@ SECTIONS
 
 	.text		: {
 		*(.text*)
-		*(.fixup)
 	}						:text	=0x90909090,
 
 
diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S
index 6ddd7a937b3e..d33c6513fd2c 100644
--- a/arch/x86/entry/vdso/vdso32/system_call.S
+++ b/arch/x86/entry/vdso/vdso32/system_call.S
@@ -78,7 +78,7 @@ SYM_INNER_LABEL(int80_landing_pad, SYM_L_GLOBAL)
 	popl	%ecx
 	CFI_RESTORE		ecx
 	CFI_ADJUST_CFA_OFFSET	-4
-	ret
+	RET
 	CFI_ENDPROC
 
 	.size __kernel_vsyscall,.-__kernel_vsyscall
diff --git a/arch/x86/entry/vdso/vsgx.S b/arch/x86/entry/vdso/vsgx.S
index 99dafac992e2..d77d278ee9dd 100644
--- a/arch/x86/entry/vdso/vsgx.S
+++ b/arch/x86/entry/vdso/vsgx.S
@@ -81,7 +81,7 @@ SYM_FUNC_START(__vdso_sgx_enter_enclave)
 	pop	%rbx
 	leave
 	.cfi_def_cfa		%rsp, 8
-	ret
+	RET
 
 	/* The out-of-line code runs with the pre-leave stack frame. */
 	.cfi_def_cfa		%rbp, 16
diff --git a/arch/x86/entry/vsyscall/vsyscall_emu_64.S b/arch/x86/entry/vsyscall/vsyscall_emu_64.S
index 2e203f3a25a7..15e35159ebb6 100644
--- a/arch/x86/entry/vsyscall/vsyscall_emu_64.S
+++ b/arch/x86/entry/vsyscall/vsyscall_emu_64.S
@@ -19,17 +19,17 @@ __vsyscall_page:
 
 	mov $__NR_gettimeofday, %rax
 	syscall
-	ret
+	RET
 
 	.balign 1024, 0xcc
 	mov $__NR_time, %rax
 	syscall
-	ret
+	RET
 
 	.balign 1024, 0xcc
 	mov $__NR_getcpu, %rax
 	syscall
-	ret
+	RET
 
 	.balign 4096, 0xcc
 
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 3a168483bc8e..c878fed3056f 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -152,6 +152,33 @@
 
 #else /* ! __ASSEMBLY__ */
 
+# define DEFINE_EXTABLE_TYPE_REG \
+	".macro extable_type_reg type:req reg:req\n"						\
+	".set found, 0\n"									\
+	".set regnr, 0\n"									\
+	".irp rs,rax,rcx,rdx,rbx,rsp,rbp,rsi,rdi,r8,r9,r10,r11,r12,r13,r14,r15\n"		\
+	".ifc \\reg, %%\\rs\n"									\
+	".set found, found+1\n"									\
+	".long \\type + (regnr << 8)\n"								\
+	".endif\n"										\
+	".set regnr, regnr+1\n"									\
+	".endr\n"										\
+	".set regnr, 0\n"									\
+	".irp rs,eax,ecx,edx,ebx,esp,ebp,esi,edi,r8d,r9d,r10d,r11d,r12d,r13d,r14d,r15d\n"	\
+	".ifc \\reg, %%\\rs\n"									\
+	".set found, found+1\n"									\
+	".long \\type + (regnr << 8)\n"								\
+	".endif\n"										\
+	".set regnr, regnr+1\n"									\
+	".endr\n"										\
+	".if (found != 1)\n"									\
+	".error \"extable_type_reg: bad register argument\"\n"					\
+	".endif\n"										\
+	".endm\n"
+
+# define UNDEFINE_EXTABLE_TYPE_REG \
+	".purgem extable_type_reg\n"
+
 # define _ASM_EXTABLE_TYPE(from, to, type)			\
 	" .pushsection \"__ex_table\",\"a\"\n"			\
 	" .balign 4\n"						\
@@ -160,6 +187,16 @@
 	" .long " __stringify(type) " \n"			\
 	" .popsection\n"
 
+# define _ASM_EXTABLE_TYPE_REG(from, to, type, reg)				\
+	" .pushsection \"__ex_table\",\"a\"\n"					\
+	" .balign 4\n"								\
+	" .long (" #from ") - .\n"						\
+	" .long (" #to ") - .\n"						\
+	DEFINE_EXTABLE_TYPE_REG							\
+	"extable_type_reg reg=" __stringify(reg) ", type=" __stringify(type) " \n"\
+	UNDEFINE_EXTABLE_TYPE_REG						\
+	" .popsection\n"
+
 /* For C file, we already have NOKPROBE_SYMBOL macro */
 
 /*
diff --git a/arch/x86/include/asm/extable.h b/arch/x86/include/asm/extable.h
index 93f400eb728f..155c991ba95e 100644
--- a/arch/x86/include/asm/extable.h
+++ b/arch/x86/include/asm/extable.h
@@ -21,7 +21,7 @@
  */
 
 struct exception_table_entry {
-	int insn, fixup, type;
+	int insn, fixup, data;
 };
 struct pt_regs;
 
@@ -31,8 +31,8 @@ struct pt_regs;
 	do {							\
 		(a)->fixup = (b)->fixup + (delta);		\
 		(b)->fixup = (tmp).fixup - (delta);		\
-		(a)->type = (b)->type;				\
-		(b)->type = (tmp).type;				\
+		(a)->data = (b)->data;				\
+		(b)->data = (tmp).data;				\
 	} while (0)
 
 extern int fixup_exception(struct pt_regs *regs, int trapnr,
diff --git a/arch/x86/include/asm/extable_fixup_types.h b/arch/x86/include/asm/extable_fixup_types.h
index 409524d5d2eb..503622627400 100644
--- a/arch/x86/include/asm/extable_fixup_types.h
+++ b/arch/x86/include/asm/extable_fixup_types.h
@@ -2,6 +2,36 @@
 #ifndef _ASM_X86_EXTABLE_FIXUP_TYPES_H
 #define _ASM_X86_EXTABLE_FIXUP_TYPES_H
 
+/*
+ * Our IMM is signed, as such it must live at the top end of the word. Also,
+ * since C99 hex constants are of ambigious type, force cast the mask to 'int'
+ * so that FIELD_GET() will DTRT and sign extend the value when it extracts it.
+ */
+#define EX_DATA_TYPE_MASK		((int)0x000000FF)
+#define EX_DATA_REG_MASK		((int)0x00000F00)
+#define EX_DATA_FLAG_MASK		((int)0x0000F000)
+#define EX_DATA_IMM_MASK		((int)0xFFFF0000)
+
+#define EX_DATA_REG_SHIFT		8
+#define EX_DATA_FLAG_SHIFT		12
+#define EX_DATA_IMM_SHIFT		16
+
+#define EX_DATA_REG(reg)		((reg) << EX_DATA_REG_SHIFT)
+#define EX_DATA_FLAG(flag)		((flag) << EX_DATA_FLAG_SHIFT)
+#define EX_DATA_IMM(imm)		((imm) << EX_DATA_IMM_SHIFT)
+
+/* segment regs */
+#define EX_REG_DS			EX_DATA_REG(8)
+#define EX_REG_ES			EX_DATA_REG(9)
+#define EX_REG_FS			EX_DATA_REG(10)
+#define EX_REG_GS			EX_DATA_REG(11)
+
+/* flags */
+#define EX_FLAG_CLEAR_AX		EX_DATA_FLAG(1)
+#define EX_FLAG_CLEAR_DX		EX_DATA_FLAG(2)
+#define EX_FLAG_CLEAR_AX_DX		EX_DATA_FLAG(3)
+
+/* types */
 #define	EX_TYPE_NONE			 0
 #define	EX_TYPE_DEFAULT			 1
 #define	EX_TYPE_FAULT			 2
@@ -9,14 +39,29 @@
 #define	EX_TYPE_COPY			 4
 #define	EX_TYPE_CLEAR_FS		 5
 #define	EX_TYPE_FPU_RESTORE		 6
-#define	EX_TYPE_WRMSR			 7
-#define	EX_TYPE_RDMSR			 8
-#define	EX_TYPE_BPF			 9
+#define	EX_TYPE_BPF			 7
+#define	EX_TYPE_WRMSR			 8
+#define	EX_TYPE_RDMSR			 9
+#define	EX_TYPE_WRMSR_SAFE		10 /* reg := -EIO */
+#define	EX_TYPE_RDMSR_SAFE		11 /* reg := -EIO */
+#define	EX_TYPE_WRMSR_IN_MCE		12
+#define	EX_TYPE_RDMSR_IN_MCE		13
+#define	EX_TYPE_DEFAULT_MCE_SAFE	14
+#define	EX_TYPE_FAULT_MCE_SAFE		15
+
+#define	EX_TYPE_POP_REG			16 /* sp += sizeof(long) */
+#define EX_TYPE_POP_ZERO		(EX_TYPE_POP_REG | EX_DATA_IMM(0))
+
+#define	EX_TYPE_IMM_REG			17 /* reg := (long)imm */
+#define	EX_TYPE_EFAULT_REG		(EX_TYPE_IMM_REG | EX_DATA_IMM(-EFAULT))
+#define	EX_TYPE_ZERO_REG		(EX_TYPE_IMM_REG | EX_DATA_IMM(0))
+#define	EX_TYPE_ONE_REG			(EX_TYPE_IMM_REG | EX_DATA_IMM(1))
 
-#define	EX_TYPE_WRMSR_IN_MCE		10
-#define	EX_TYPE_RDMSR_IN_MCE		11
+#define	EX_TYPE_FAULT_SGX		18
 
-#define	EX_TYPE_DEFAULT_MCE_SAFE	12
-#define	EX_TYPE_FAULT_MCE_SAFE		13
+#define	EX_TYPE_UCOPY_LEN		19 /* cx := reg + imm*cx */
+#define	EX_TYPE_UCOPY_LEN1		(EX_TYPE_UCOPY_LEN | EX_DATA_IMM(1))
+#define	EX_TYPE_UCOPY_LEN4		(EX_TYPE_UCOPY_LEN | EX_DATA_IMM(4))
+#define	EX_TYPE_UCOPY_LEN8		(EX_TYPE_UCOPY_LEN | EX_DATA_IMM(8))
 
 #endif
diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h
index f9c00110a69a..99d345b686fa 100644
--- a/arch/x86/include/asm/futex.h
+++ b/arch/x86/include/asm/futex.h
@@ -17,13 +17,9 @@ do {								\
 	int oldval = 0, ret;					\
 	asm volatile("1:\t" insn "\n"				\
 		     "2:\n"					\
-		     "\t.section .fixup,\"ax\"\n"		\
-		     "3:\tmov\t%3, %1\n"			\
-		     "\tjmp\t2b\n"				\
-		     "\t.previous\n"				\
-		     _ASM_EXTABLE_UA(1b, 3b)			\
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %1) \
 		     : "=r" (oldval), "=r" (ret), "+m" (*uaddr)	\
-		     : "i" (-EFAULT), "0" (oparg), "1" (0));	\
+		     : "0" (oparg), "1" (0));	\
 	if (ret)						\
 		goto label;					\
 	*oval = oldval;						\
@@ -39,15 +35,11 @@ do {								\
 		     "3:\t" LOCK_PREFIX "cmpxchgl %3, %2\n"	\
 		     "\tjnz\t2b\n"				\
 		     "4:\n"					\
-		     "\t.section .fixup,\"ax\"\n"		\
-		     "5:\tmov\t%5, %1\n"			\
-		     "\tjmp\t4b\n"				\
-		     "\t.previous\n"				\
-		     _ASM_EXTABLE_UA(1b, 5b)			\
-		     _ASM_EXTABLE_UA(3b, 5b)			\
+		     _ASM_EXTABLE_TYPE_REG(1b, 4b, EX_TYPE_EFAULT_REG, %1) \
+		     _ASM_EXTABLE_TYPE_REG(3b, 4b, EX_TYPE_EFAULT_REG, %1) \
 		     : "=&a" (oldval), "=&r" (ret),		\
 		       "+m" (*uaddr), "=&r" (tem)		\
-		     : "r" (oparg), "i" (-EFAULT), "1" (0));	\
+		     : "r" (oparg), "1" (0));			\
 	if (ret)						\
 		goto label;					\
 	*oval = oldval;						\
@@ -95,15 +87,11 @@ static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	if (!user_access_begin(uaddr, sizeof(u32)))
 		return -EFAULT;
 	asm volatile("\n"
-		"1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n"
+		"1:\t" LOCK_PREFIX "cmpxchgl %3, %2\n"
 		"2:\n"
-		"\t.section .fixup, \"ax\"\n"
-		"3:\tmov     %3, %0\n"
-		"\tjmp     2b\n"
-		"\t.previous\n"
-		_ASM_EXTABLE_UA(1b, 3b)
+		_ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %0) \
 		: "+r" (ret), "=a" (oldval), "+m" (*uaddr)
-		: "i" (-EFAULT), "r" (newval), "1" (oldval)
+		: "r" (newval), "1" (oldval)
 		: "memory"
 	);
 	user_access_end();
diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h
index 43785ee363f1..f07faa61c7f3 100644
--- a/arch/x86/include/asm/insn-eval.h
+++ b/arch/x86/include/asm/insn-eval.h
@@ -15,6 +15,8 @@
 #define INSN_CODE_SEG_OPND_SZ(params) (params & 0xf)
 #define INSN_CODE_SEG_PARAMS(oper_sz, addr_sz) (oper_sz | (addr_sz << 4))
 
+int pt_regs_offset(struct pt_regs *regs, int regno);
+
 bool insn_has_rep_prefix(struct insn *insn);
 void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs);
 int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs);
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index 365111789cc6..030907922bd0 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -18,6 +18,20 @@
 #define __ALIGN_STR	__stringify(__ALIGN)
 #endif
 
+#ifdef CONFIG_SLS
+#define RET	ret; int3
+#else
+#define RET	ret
+#endif
+
+#else /* __ASSEMBLY__ */
+
+#ifdef CONFIG_SLS
+#define ASM_RET	"ret; int3\n\t"
+#else
+#define ASM_RET	"ret\n\t"
+#endif
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_LINKAGE_H */
diff --git a/arch/x86/include/asm/mmx.h b/arch/x86/include/asm/mmx.h
index f572d0f944bb..e69de29bb2d1 100644
--- a/arch/x86/include/asm/mmx.h
+++ b/arch/x86/include/asm/mmx.h
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_MMX_H
-#define _ASM_X86_MMX_H
-
-/*
- *	MMX 3Dnow! helper operations
- */
-
-#include <linux/types.h>
-
-extern void *_mmx_memcpy(void *to, const void *from, size_t size);
-extern void mmx_clear_page(void *page);
-extern void mmx_copy_page(void *to, void *from);
-
-#endif /* _ASM_X86_MMX_H */
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 6b52182e178a..d42e6c6b47b1 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -137,17 +137,11 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr,
 {
 	DECLARE_ARGS(val, low, high);
 
-	asm volatile("2: rdmsr ; xor %[err],%[err]\n"
-		     "1:\n\t"
-		     ".section .fixup,\"ax\"\n\t"
-		     "3: mov %[fault],%[err]\n\t"
-		     "xorl %%eax, %%eax\n\t"
-		     "xorl %%edx, %%edx\n\t"
-		     "jmp 1b\n\t"
-		     ".previous\n\t"
-		     _ASM_EXTABLE(2b, 3b)
+	asm volatile("1: rdmsr ; xor %[err],%[err]\n"
+		     "2:\n\t"
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_RDMSR_SAFE, %[err])
 		     : [err] "=r" (*err), EAX_EDX_RET(val, low, high)
-		     : "c" (msr), [fault] "i" (-EIO));
+		     : "c" (msr));
 	if (tracepoint_enabled(read_msr))
 		do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), *err);
 	return EAX_EDX_VAL(val, low, high);
@@ -169,15 +163,11 @@ native_write_msr_safe(unsigned int msr, u32 low, u32 high)
 {
 	int err;
 
-	asm volatile("2: wrmsr ; xor %[err],%[err]\n"
-		     "1:\n\t"
-		     ".section .fixup,\"ax\"\n\t"
-		     "3:  mov %[fault],%[err] ; jmp 1b\n\t"
-		     ".previous\n\t"
-		     _ASM_EXTABLE(2b, 3b)
+	asm volatile("1: wrmsr ; xor %[err],%[err]\n"
+		     "2:\n\t"
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_WRMSR_SAFE, %[err])
 		     : [err] "=a" (err)
-		     : "c" (msr), "0" (low), "d" (high),
-		       [fault] "i" (-EIO)
+		     : "c" (msr), "0" (low), "d" (high)
 		     : "memory");
 	if (tracepoint_enabled(write_msr))
 		do_trace_write_msr(msr, ((u64)high << 32 | low), err);
diff --git a/arch/x86/include/asm/page_32.h b/arch/x86/include/asm/page_32.h
index b13f8488ac85..df42f8aa99e4 100644
--- a/arch/x86/include/asm/page_32.h
+++ b/arch/x86/include/asm/page_32.h
@@ -19,19 +19,6 @@ extern unsigned long __phys_addr(unsigned long);
 #define pfn_valid(pfn)		((pfn) < max_mapnr)
 #endif /* CONFIG_FLATMEM */
 
-#ifdef CONFIG_X86_USE_3DNOW
-#include <asm/mmx.h>
-
-static inline void clear_page(void *page)
-{
-	mmx_clear_page(page);
-}
-
-static inline void copy_page(void *to, void *from)
-{
-	mmx_copy_page(to, from);
-}
-#else  /* !CONFIG_X86_USE_3DNOW */
 #include <linux/string.h>
 
 static inline void clear_page(void *page)
@@ -43,7 +30,6 @@ static inline void copy_page(void *to, void *from)
 {
 	memcpy(to, from, PAGE_SIZE);
 }
-#endif	/* CONFIG_X86_USE_3DNOW */
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* _ASM_X86_PAGE_32_H */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 27d276232c80..0d76502cc6f5 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -671,7 +671,7 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
 	    "call " #func ";"						\
 	    PV_RESTORE_ALL_CALLER_REGS					\
 	    FRAME_END							\
-	    "ret;"							\
+	    ASM_RET							\
 	    ".size " PV_THUNK_NAME(func) ", .-" PV_THUNK_NAME(func) ";"	\
 	    ".popsection")
 
diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
index 159622ee0674..1474cf96251d 100644
--- a/arch/x86/include/asm/qspinlock_paravirt.h
+++ b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -48,7 +48,7 @@ asm    (".pushsection .text;"
 	"jne   .slowpath;"
 	"pop   %rdx;"
 	FRAME_END
-	"ret;"
+	ASM_RET
 	".slowpath: "
 	"push   %rsi;"
 	"movzbl %al,%esi;"
@@ -56,7 +56,7 @@ asm    (".pushsection .text;"
 	"pop    %rsi;"
 	"pop    %rdx;"
 	FRAME_END
-	"ret;"
+	ASM_RET
 	".size " PV_UNLOCK ", .-" PV_UNLOCK ";"
 	".popsection");
 
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index b2d504f11937..aff774775c67 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -35,11 +35,7 @@
 # define NEED_CMOV	0
 #endif
 
-#ifdef CONFIG_X86_USE_3DNOW
-# define NEED_3DNOW	(1<<(X86_FEATURE_3DNOW & 31))
-#else
 # define NEED_3DNOW	0
-#endif
 
 #if defined(CONFIG_X86_P6_NOP) || defined(CONFIG_X86_64)
 # define NEED_NOPL	(1<<(X86_FEATURE_NOPL & 31))
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 8dd8e8ec9fa5..b228c9d44ee7 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -307,14 +307,7 @@ do {									\
 									\
 	asm volatile("						\n"	\
 		     "1:	movl %k0,%%" #seg "		\n"	\
-									\
-		     ".section .fixup,\"ax\"			\n"	\
-		     "2:	xorl %k0,%k0			\n"	\
-		     "		jmp 1b				\n"	\
-		     ".previous					\n"	\
-									\
-		     _ASM_EXTABLE(1b, 2b)				\
-									\
+		     _ASM_EXTABLE_TYPE_REG(1b, 1b, EX_TYPE_ZERO_REG, %k0)\
 		     : "+r" (__val) : : "memory");			\
 } while (0)
 
diff --git a/arch/x86/include/asm/sgx.h b/arch/x86/include/asm/sgx.h
index 05f3e21f01a7..3f9334ef67cd 100644
--- a/arch/x86/include/asm/sgx.h
+++ b/arch/x86/include/asm/sgx.h
@@ -46,6 +46,24 @@ enum sgx_encls_function {
 };
 
 /**
+ * SGX_ENCLS_FAULT_FLAG - flag signifying an ENCLS return code is a trapnr
+ *
+ * ENCLS has its own (positive value) error codes and also generates
+ * ENCLS specific #GP and #PF faults.  And the ENCLS values get munged
+ * with system error codes as everything percolates back up the stack.
+ * Unfortunately (for us), we need to precisely identify each unique
+ * error code, e.g. the action taken if EWB fails varies based on the
+ * type of fault and on the exact SGX error code, i.e. we can't simply
+ * convert all faults to -EFAULT.
+ *
+ * To make all three error types coexist, we set bit 30 to identify an
+ * ENCLS fault.  Bit 31 (technically bits N:31) is used to differentiate
+ * between positive (faults and SGX error codes) and negative (system
+ * error codes) values.
+ */
+#define SGX_ENCLS_FAULT_FLAG 0x40000000
+
+/**
  * enum sgx_return_code - The return code type for ENCLS, ENCLU and ENCLV
  * %SGX_NOT_TRACKED:		Previous ETRACK's shootdown sequence has not
  *				been completed yet.
diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h
index 39ebe0511869..ed4f8bb6c2d9 100644
--- a/arch/x86/include/asm/static_call.h
+++ b/arch/x86/include/asm/static_call.h
@@ -36,7 +36,7 @@
 	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, ".byte 0xe9; .long " #func " - (. + 4)")
 
 #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)			\
-	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; nop; nop; nop; nop")
+	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; int3; nop; nop; nop")
 
 
 #define ARCH_ADD_TRAMP_KEY(name)					\
diff --git a/arch/x86/include/asm/string_32.h b/arch/x86/include/asm/string_32.h
index f74362b05619..32c0d981a82a 100644
--- a/arch/x86/include/asm/string_32.h
+++ b/arch/x86/include/asm/string_32.h
@@ -146,42 +146,9 @@ static __always_inline void *__constant_memcpy(void *to, const void *from,
 extern void *memcpy(void *, const void *, size_t);
 
 #ifndef CONFIG_FORTIFY_SOURCE
-#ifdef CONFIG_X86_USE_3DNOW
-
-#include <asm/mmx.h>
-
-/*
- *	This CPU favours 3DNow strongly (eg AMD Athlon)
- */
-
-static inline void *__constant_memcpy3d(void *to, const void *from, size_t len)
-{
-	if (len < 512)
-		return __constant_memcpy(to, from, len);
-	return _mmx_memcpy(to, from, len);
-}
-
-static inline void *__memcpy3d(void *to, const void *from, size_t len)
-{
-	if (len < 512)
-		return __memcpy(to, from, len);
-	return _mmx_memcpy(to, from, len);
-}
-
-#define memcpy(t, f, n)				\
-	(__builtin_constant_p((n))		\
-	 ? __constant_memcpy3d((t), (f), (n))	\
-	 : __memcpy3d((t), (f), (n)))
-
-#else
-
-/*
- *	No 3D Now!
- */
 
 #define memcpy(t, f, n) __builtin_memcpy(t, f, n)
 
-#endif
 #endif /* !CONFIG_FORTIFY_SOURCE */
 
 #define __HAVE_ARCH_MEMMOVE
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 8ab9e79abb2b..ac96f9b2d64b 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -352,24 +352,22 @@ do {									\
 		     "1:	movl %[lowbits],%%eax\n"		\
 		     "2:	movl %[highbits],%%edx\n"		\
 		     "3:\n"						\
-		     ".section .fixup,\"ax\"\n"				\
-		     "4:	mov %[efault],%[errout]\n"		\
-		     "	xorl %%eax,%%eax\n"				\
-		     "	xorl %%edx,%%edx\n"				\
-		     "	jmp 3b\n"					\
-		     ".previous\n"					\
-		     _ASM_EXTABLE_UA(1b, 4b)				\
-		     _ASM_EXTABLE_UA(2b, 4b)				\
+		     _ASM_EXTABLE_TYPE_REG(1b, 3b, EX_TYPE_EFAULT_REG |	\
+					   EX_FLAG_CLEAR_AX_DX,		\
+					   %[errout])			\
+		     _ASM_EXTABLE_TYPE_REG(2b, 3b, EX_TYPE_EFAULT_REG |	\
+					   EX_FLAG_CLEAR_AX_DX,		\
+					   %[errout])			\
 		     : [errout] "=r" (retval),				\
 		       [output] "=&A"(x)				\
 		     : [lowbits] "m" (__m(__ptr)),			\
 		       [highbits] "m" __m(((u32 __user *)(__ptr)) + 1),	\
-		       [efault] "i" (-EFAULT), "0" (retval));		\
+		       "0" (retval));					\
 })
 
 #else
 #define __get_user_asm_u64(x, ptr, retval) \
-	 __get_user_asm(x, ptr, retval, "q", "=r")
+	 __get_user_asm(x, ptr, retval, "q")
 #endif
 
 #define __get_user_size(x, ptr, size, retval)				\
@@ -380,14 +378,14 @@ do {									\
 	__chk_user_ptr(ptr);						\
 	switch (size) {							\
 	case 1:								\
-		__get_user_asm(x_u8__, ptr, retval, "b", "=q");		\
+		__get_user_asm(x_u8__, ptr, retval, "b");		\
 		(x) = x_u8__;						\
 		break;							\
 	case 2:								\
-		__get_user_asm(x, ptr, retval, "w", "=r");		\
+		__get_user_asm(x, ptr, retval, "w");			\
 		break;							\
 	case 4:								\
-		__get_user_asm(x, ptr, retval, "l", "=r");		\
+		__get_user_asm(x, ptr, retval, "l");			\
 		break;							\
 	case 8:								\
 		__get_user_asm_u64(x, ptr, retval);			\
@@ -397,20 +395,17 @@ do {									\
 	}								\
 } while (0)
 
-#define __get_user_asm(x, addr, err, itype, ltype)			\
+#define __get_user_asm(x, addr, err, itype)				\
 	asm volatile("\n"						\
 		     "1:	mov"itype" %[umem],%[output]\n"		\
 		     "2:\n"						\
-		     ".section .fixup,\"ax\"\n"				\
-		     "3:	mov %[efault],%[errout]\n"		\
-		     "	xorl %k[output],%k[output]\n"			\
-		     "	jmp 2b\n"					\
-		     ".previous\n"					\
-		     _ASM_EXTABLE_UA(1b, 3b)				\
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG | \
+					   EX_FLAG_CLEAR_AX,		\
+					   %[errout])			\
 		     : [errout] "=r" (err),				\
-		       [output] ltype(x)				\
+		       [output] "=a" (x)				\
 		     : [umem] "m" (__m(addr)),				\
-		       [efault] "i" (-EFAULT), "0" (err))
+		       "0" (err))
 
 #endif // CONFIG_CC_HAS_ASM_GOTO_OUTPUT
 
diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h
index 06006b0351f3..8338b0432b50 100644
--- a/arch/x86/include/asm/word-at-a-time.h
+++ b/arch/x86/include/asm/word-at-a-time.h
@@ -77,30 +77,58 @@ static inline unsigned long find_zero(unsigned long mask)
  * and the next page not being mapped, take the exception and
  * return zeroes in the non-existing part.
  */
+#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
+
 static inline unsigned long load_unaligned_zeropad(const void *addr)
 {
-	unsigned long ret, dummy;
+	unsigned long offset, data;
+	unsigned long ret;
+
+	asm_volatile_goto(
+		"1:	mov %[mem], %[ret]\n"
+
+		_ASM_EXTABLE(1b, %l[do_exception])
+
+		: [ret] "=r" (ret)
+		: [mem] "m" (*(unsigned long *)addr)
+		: : do_exception);
+
+	return ret;
+
+do_exception:
+	offset = (unsigned long)addr & (sizeof(long) - 1);
+	addr = (void *)((unsigned long)addr & ~(sizeof(long) - 1));
+	data = *(unsigned long *)addr;
+	ret = data >> offset * 8;
+
+	return ret;
+}
 
-	asm(
-		"1:\tmov %2,%0\n"
+#else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
+
+static inline unsigned long load_unaligned_zeropad(const void *addr)
+{
+	unsigned long offset, data;
+	unsigned long ret, err = 0;
+
+	asm(	"1:	mov %[mem], %[ret]\n"
 		"2:\n"
-		".section .fixup,\"ax\"\n"
-		"3:\t"
-		"lea %2,%1\n\t"
-		"and %3,%1\n\t"
-		"mov (%1),%0\n\t"
-		"leal %2,%%ecx\n\t"
-		"andl %4,%%ecx\n\t"
-		"shll $3,%%ecx\n\t"
-		"shr %%cl,%0\n\t"
-		"jmp 2b\n"
-		".previous\n"
-		_ASM_EXTABLE(1b, 3b)
-		:"=&r" (ret),"=&c" (dummy)
-		:"m" (*(unsigned long *)addr),
-		 "i" (-sizeof(unsigned long)),
-		 "i" (sizeof(unsigned long)-1));
+
+		_ASM_EXTABLE_FAULT(1b, 2b)
+
+		: [ret] "=&r" (ret), "+a" (err)
+		: [mem] "m" (*(unsigned long *)addr));
+
+	if (unlikely(err)) {
+		offset = (unsigned long)addr & (sizeof(long) - 1);
+		addr = (void *)((unsigned long)addr & ~(sizeof(long) - 1));
+		data = *(unsigned long *)addr;
+		ret = data >> offset * 8;
+	}
+
 	return ret;
 }
 
+#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
+
 #endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 1a162e559753..e989bc2269f5 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -96,11 +96,7 @@ static inline int xen_safe_write_ulong(unsigned long *addr, unsigned long val)
 
 	asm volatile("1: mov %[val], %[ptr]\n"
 		     "2:\n"
-		     ".section .fixup, \"ax\"\n"
-		     "3: sub $1, %[ret]\n"
-		     "   jmp 2b\n"
-		     ".previous\n"
-		     _ASM_EXTABLE(1b, 3b)
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %[ret])
 		     : [ret] "+r" (ret), [ptr] "=m" (*addr)
 		     : [val] "r" (val));
 
@@ -110,16 +106,12 @@ static inline int xen_safe_write_ulong(unsigned long *addr, unsigned long val)
 static inline int xen_safe_read_ulong(const unsigned long *addr,
 				      unsigned long *val)
 {
-	int ret = 0;
 	unsigned long rval = ~0ul;
+	int ret = 0;
 
 	asm volatile("1: mov %[ptr], %[rval]\n"
 		     "2:\n"
-		     ".section .fixup, \"ax\"\n"
-		     "3: sub $1, %[ret]\n"
-		     "   jmp 2b\n"
-		     ".previous\n"
-		     _ASM_EXTABLE(1b, 3b)
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %[ret])
 		     : [ret] "+r" (ret), [rval] "+r" (rval)
 		     : [ptr] "m" (*addr));
 	*val = rval;
diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S
index daf88f8143c5..cf69081073b5 100644
--- a/arch/x86/kernel/acpi/wakeup_32.S
+++ b/arch/x86/kernel/acpi/wakeup_32.S
@@ -60,7 +60,7 @@ save_registers:
 	popl	saved_context_eflags
 
 	movl	$ret_point, saved_eip
-	ret
+	RET
 
 
 restore_registers:
@@ -70,7 +70,7 @@ restore_registers:
 	movl	saved_context_edi, %edi
 	pushl	saved_context_eflags
 	popfl
-	ret
+	RET
 
 SYM_CODE_START(do_suspend_lowlevel)
 	call	save_processor_state
@@ -86,7 +86,7 @@ SYM_CODE_START(do_suspend_lowlevel)
 ret_point:
 	call	restore_registers
 	call	restore_processor_state
-	ret
+	RET
 SYM_CODE_END(do_suspend_lowlevel)
 
 .data
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 23fb4d51a5da..5007c3ffe96f 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -714,7 +714,7 @@ asm (
 "	.type		int3_magic, @function\n"
 "int3_magic:\n"
 "	movl	$1, (%" _ASM_ARG1 ")\n"
-"	ret\n"
+	ASM_RET
 "	.size		int3_magic, .-int3_magic\n"
 "	.popsection\n"
 );
@@ -1113,10 +1113,13 @@ void text_poke_sync(void)
 }
 
 struct text_poke_loc {
-	s32 rel_addr; /* addr := _stext + rel_addr */
-	s32 rel32;
+	/* addr := _stext + rel_addr */
+	s32 rel_addr;
+	s32 disp;
+	u8 len;
 	u8 opcode;
 	const u8 text[POKE_MAX_OPCODE_SIZE];
+	/* see text_poke_bp_batch() */
 	u8 old;
 };
 
@@ -1131,7 +1134,8 @@ static struct bp_patching_desc *bp_desc;
 static __always_inline
 struct bp_patching_desc *try_get_desc(struct bp_patching_desc **descp)
 {
-	struct bp_patching_desc *desc = __READ_ONCE(*descp); /* rcu_dereference */
+	/* rcu_dereference */
+	struct bp_patching_desc *desc = __READ_ONCE(*descp);
 
 	if (!desc || !arch_atomic_inc_not_zero(&desc->refs))
 		return NULL;
@@ -1165,7 +1169,7 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
 {
 	struct bp_patching_desc *desc;
 	struct text_poke_loc *tp;
-	int len, ret = 0;
+	int ret = 0;
 	void *ip;
 
 	if (user_mode(regs))
@@ -1205,8 +1209,7 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
 			goto out_put;
 	}
 
-	len = text_opcode_size(tp->opcode);
-	ip += len;
+	ip += tp->len;
 
 	switch (tp->opcode) {
 	case INT3_INSN_OPCODE:
@@ -1221,12 +1224,12 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
 		break;
 
 	case CALL_INSN_OPCODE:
-		int3_emulate_call(regs, (long)ip + tp->rel32);
+		int3_emulate_call(regs, (long)ip + tp->disp);
 		break;
 
 	case JMP32_INSN_OPCODE:
 	case JMP8_INSN_OPCODE:
-		int3_emulate_jmp(regs, (long)ip + tp->rel32);
+		int3_emulate_jmp(regs, (long)ip + tp->disp);
 		break;
 
 	default:
@@ -1301,7 +1304,7 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
 	 */
 	for (do_sync = 0, i = 0; i < nr_entries; i++) {
 		u8 old[POKE_MAX_OPCODE_SIZE] = { tp[i].old, };
-		int len = text_opcode_size(tp[i].opcode);
+		int len = tp[i].len;
 
 		if (len - INT3_INSN_SIZE > 0) {
 			memcpy(old + INT3_INSN_SIZE,
@@ -1378,21 +1381,37 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
 			       const void *opcode, size_t len, const void *emulate)
 {
 	struct insn insn;
-	int ret;
+	int ret, i;
 
 	memcpy((void *)tp->text, opcode, len);
 	if (!emulate)
 		emulate = opcode;
 
 	ret = insn_decode_kernel(&insn, emulate);
-
 	BUG_ON(ret < 0);
-	BUG_ON(len != insn.length);
 
 	tp->rel_addr = addr - (void *)_stext;
+	tp->len = len;
 	tp->opcode = insn.opcode.bytes[0];
 
 	switch (tp->opcode) {
+	case RET_INSN_OPCODE:
+	case JMP32_INSN_OPCODE:
+	case JMP8_INSN_OPCODE:
+		/*
+		 * Control flow instructions without implied execution of the
+		 * next instruction can be padded with INT3.
+		 */
+		for (i = insn.length; i < len; i++)
+			BUG_ON(tp->text[i] != INT3_INSN_OPCODE);
+		break;
+
+	default:
+		BUG_ON(len != insn.length);
+	};
+
+
+	switch (tp->opcode) {
 	case INT3_INSN_OPCODE:
 	case RET_INSN_OPCODE:
 		break;
@@ -1400,7 +1419,7 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
 	case CALL_INSN_OPCODE:
 	case JMP32_INSN_OPCODE:
 	case JMP8_INSN_OPCODE:
-		tp->rel32 = insn.immediate.value;
+		tp->disp = insn.immediate.value;
 		break;
 
 	default: /* assume NOP */
@@ -1408,13 +1427,13 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
 		case 2: /* NOP2 -- emulate as JMP8+0 */
 			BUG_ON(memcmp(emulate, x86_nops[len], len));
 			tp->opcode = JMP8_INSN_OPCODE;
-			tp->rel32 = 0;
+			tp->disp = 0;
 			break;
 
 		case 5: /* NOP5 -- emulate as JMP32+0 */
 			BUG_ON(memcmp(emulate, x86_nops[len], len));
 			tp->opcode = JMP32_INSN_OPCODE;
-			tp->rel32 = 0;
+			tp->disp = 0;
 			break;
 
 		default: /* unknown instruction */
diff --git a/arch/x86/kernel/cpu/sgx/encls.h b/arch/x86/kernel/cpu/sgx/encls.h
index 9b204843b78d..fa04a73daf9c 100644
--- a/arch/x86/kernel/cpu/sgx/encls.h
+++ b/arch/x86/kernel/cpu/sgx/encls.h
@@ -11,26 +11,8 @@
 #include <asm/traps.h>
 #include "sgx.h"
 
-/**
- * ENCLS_FAULT_FLAG - flag signifying an ENCLS return code is a trapnr
- *
- * ENCLS has its own (positive value) error codes and also generates
- * ENCLS specific #GP and #PF faults.  And the ENCLS values get munged
- * with system error codes as everything percolates back up the stack.
- * Unfortunately (for us), we need to precisely identify each unique
- * error code, e.g. the action taken if EWB fails varies based on the
- * type of fault and on the exact SGX error code, i.e. we can't simply
- * convert all faults to -EFAULT.
- *
- * To make all three error types coexist, we set bit 30 to identify an
- * ENCLS fault.  Bit 31 (technically bits N:31) is used to differentiate
- * between positive (faults and SGX error codes) and negative (system
- * error codes) values.
- */
-#define ENCLS_FAULT_FLAG 0x40000000
-
 /* Retrieve the encoded trapnr from the specified return code. */
-#define ENCLS_TRAPNR(r) ((r) & ~ENCLS_FAULT_FLAG)
+#define ENCLS_TRAPNR(r) ((r) & ~SGX_ENCLS_FAULT_FLAG)
 
 /* Issue a WARN() about an ENCLS function. */
 #define ENCLS_WARN(r, name) {						  \
@@ -50,7 +32,7 @@
  */
 static inline bool encls_faulted(int ret)
 {
-	return ret & ENCLS_FAULT_FLAG;
+	return ret & SGX_ENCLS_FAULT_FLAG;
 }
 
 /**
@@ -88,11 +70,7 @@ static inline bool encls_failed(int ret)
 	asm volatile(						\
 	"1: .byte 0x0f, 0x01, 0xcf;\n\t"			\
 	"2:\n"							\
-	".section .fixup,\"ax\"\n"				\
-	"3: orl $"__stringify(ENCLS_FAULT_FLAG)",%%eax\n"	\
-	"   jmp 2b\n"						\
-	".previous\n"						\
-	_ASM_EXTABLE_FAULT(1b, 3b)				\
+	_ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_SGX)		\
 	: "=a"(ret)						\
 	: "a"(rax), inputs					\
 	: "memory", "cc");					\
@@ -127,7 +105,7 @@ static inline bool encls_failed(int ret)
  *
  * Return:
  *   0 on success,
- *   trapnr with ENCLS_FAULT_FLAG set on fault
+ *   trapnr with SGX_ENCLS_FAULT_FLAG set on fault
  */
 #define __encls_N(rax, rbx_out, inputs...)			\
 	({							\
@@ -136,11 +114,7 @@ static inline bool encls_failed(int ret)
 	"1: .byte 0x0f, 0x01, 0xcf;\n\t"			\
 	"   xor %%eax,%%eax;\n"					\
 	"2:\n"							\
-	".section .fixup,\"ax\"\n"				\
-	"3: orl $"__stringify(ENCLS_FAULT_FLAG)",%%eax\n"	\
-	"   jmp 2b\n"						\
-	".previous\n"						\
-	_ASM_EXTABLE_FAULT(1b, 3b)				\
+	_ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_SGX)		\
 	: "=a"(ret), "=b"(rbx_out)				\
 	: "a"(rax), inputs					\
 	: "memory");						\
diff --git a/arch/x86/kernel/fpu/legacy.h b/arch/x86/kernel/fpu/legacy.h
index 17c26b164c63..098f367bb8a7 100644
--- a/arch/x86/kernel/fpu/legacy.h
+++ b/arch/x86/kernel/fpu/legacy.h
@@ -35,11 +35,7 @@ static inline void ldmxcsr(u32 mxcsr)
 	int err;							\
 	asm volatile("1:" #insn "\n\t"					\
 		     "2:\n"						\
-		     ".section .fixup,\"ax\"\n"				\
-		     "3:  movl $-1,%[err]\n"				\
-		     "    jmp  2b\n"					\
-		     ".previous\n"					\
-		     _ASM_EXTABLE(1b, 3b)				\
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %[err]) \
 		     : [err] "=r" (err), output				\
 		     : "0"(0), input);					\
 	err;								\
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
index 86ea7c0fa2f6..e0c9264b1dd0 100644
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -108,11 +108,7 @@ static inline u64 xfeatures_mask_independent(void)
 		     "\n"						\
 		     "xor %[err], %[err]\n"				\
 		     "3:\n"						\
-		     ".pushsection .fixup,\"ax\"\n"			\
-		     "4: movl $-2, %[err]\n"				\
-		     "jmp 3b\n"						\
-		     ".popsection\n"					\
-		     _ASM_EXTABLE(661b, 4b)				\
+		     _ASM_EXTABLE_TYPE_REG(661b, 3b, EX_TYPE_EFAULT_REG, %[err]) \
 		     : [err] "=r" (err)					\
 		     : "D" (st), "m" (*st), "a" (lmask), "d" (hmask)	\
 		     : "memory")
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index c39f906cdc4e..7cc540e6de0c 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -303,7 +303,7 @@ union ftrace_op_code_union {
 	} __attribute__((packed));
 };
 
-#define RET_SIZE		1
+#define RET_SIZE		1 + IS_ENABLED(CONFIG_SLS)
 
 static unsigned long
 create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S
index e405fe1a8bf4..a0ed0e4a2c0c 100644
--- a/arch/x86/kernel/ftrace_32.S
+++ b/arch/x86/kernel/ftrace_32.S
@@ -19,7 +19,7 @@
 #endif
 
 SYM_FUNC_START(__fentry__)
-	ret
+	RET
 SYM_FUNC_END(__fentry__)
 EXPORT_SYMBOL(__fentry__)
 
@@ -84,7 +84,7 @@ ftrace_graph_call:
 
 /* This is weak to keep gas from relaxing the jumps */
 SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK)
-	ret
+	RET
 SYM_CODE_END(ftrace_caller)
 
 SYM_CODE_START(ftrace_regs_caller)
@@ -177,7 +177,7 @@ SYM_CODE_START(ftrace_graph_caller)
 	popl	%edx
 	popl	%ecx
 	popl	%eax
-	ret
+	RET
 SYM_CODE_END(ftrace_graph_caller)
 
 .globl return_to_handler
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index 7a879901f103..11ac028e30e4 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -132,7 +132,7 @@
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 SYM_FUNC_START(__fentry__)
-	retq
+	RET
 SYM_FUNC_END(__fentry__)
 EXPORT_SYMBOL(__fentry__)
 
@@ -176,11 +176,11 @@ SYM_FUNC_END(ftrace_caller);
 SYM_FUNC_START(ftrace_epilogue)
 /*
  * This is weak to keep gas from relaxing the jumps.
- * It is also used to copy the retq for trampolines.
+ * It is also used to copy the RET for trampolines.
  */
 SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK)
 	UNWIND_HINT_FUNC
-	retq
+	RET
 SYM_FUNC_END(ftrace_epilogue)
 
 SYM_FUNC_START(ftrace_regs_caller)
@@ -284,7 +284,7 @@ SYM_FUNC_START(__fentry__)
 	jnz trace
 
 SYM_INNER_LABEL(ftrace_stub, SYM_L_GLOBAL)
-	retq
+	RET
 
 trace:
 	/* save_mcount_regs fills in first two parameters */
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index d8c64dab0efe..eb8656bac99b 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -340,7 +340,7 @@ SYM_FUNC_END(startup_32_smp)
 __INIT
 setup_once:
 	andl $0,setup_once_ref	/* Once is enough, thanks */
-	ret
+	RET
 
 SYM_FUNC_START(early_idt_handler_array)
 	# 36(%esp) %eflags
diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S
index 760e1f293093..aaf9e776f323 100644
--- a/arch/x86/kernel/irqflags.S
+++ b/arch/x86/kernel/irqflags.S
@@ -11,7 +11,7 @@
 SYM_FUNC_START(native_save_fl)
 	pushf
 	pop %_ASM_AX
-	ret
+	RET
 SYM_FUNC_END(native_save_fl)
 .popsection
 EXPORT_SYMBOL(native_save_fl)
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index fce99e249d61..6290712cb36d 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -1051,7 +1051,7 @@ asm(
 	"	addl $4, %esp\n"
 	"	popfl\n"
 #endif
-	"	ret\n"
+	ASM_RET
 	".size __kretprobe_trampoline, .-__kretprobe_trampoline\n"
 );
 NOKPROBE_SYMBOL(__kretprobe_trampoline);
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 7f7636aac620..4420499f7bb4 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -41,7 +41,7 @@ extern void _paravirt_nop(void);
 asm (".pushsection .entry.text, \"ax\"\n"
      ".global _paravirt_nop\n"
      "_paravirt_nop:\n\t"
-     "ret\n\t"
+     ASM_RET
      ".size _paravirt_nop, . - _paravirt_nop\n\t"
      ".type _paravirt_nop, @function\n\t"
      ".popsection");
@@ -51,7 +51,7 @@ asm (".pushsection .entry.text, \"ax\"\n"
      ".global paravirt_ret0\n"
      "paravirt_ret0:\n\t"
      "xor %" _ASM_AX ", %" _ASM_AX ";\n\t"
-     "ret\n\t"
+     ASM_RET
      ".size paravirt_ret0, . - paravirt_ret0\n\t"
      ".type paravirt_ret0, @function\n\t"
      ".popsection");
diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S
index f469153eca8a..fcc8a7699103 100644
--- a/arch/x86/kernel/relocate_kernel_32.S
+++ b/arch/x86/kernel/relocate_kernel_32.S
@@ -91,7 +91,7 @@ SYM_CODE_START_NOALIGN(relocate_kernel)
 	movl    %edi, %eax
 	addl    $(identity_mapped - relocate_kernel), %eax
 	pushl   %eax
-	ret
+	RET
 SYM_CODE_END(relocate_kernel)
 
 SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
@@ -159,7 +159,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
 	xorl    %edx, %edx
 	xorl    %esi, %esi
 	xorl    %ebp, %ebp
-	ret
+	RET
 1:
 	popl	%edx
 	movl	CP_PA_SWAP_PAGE(%edi), %esp
@@ -190,7 +190,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
 	movl	%edi, %eax
 	addl	$(virtual_mapped - relocate_kernel), %eax
 	pushl	%eax
-	ret
+	RET
 SYM_CODE_END(identity_mapped)
 
 SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped)
@@ -208,7 +208,7 @@ SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped)
 	popl	%edi
 	popl	%esi
 	popl	%ebx
-	ret
+	RET
 SYM_CODE_END(virtual_mapped)
 
 	/* Do the copies */
@@ -271,7 +271,7 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages)
 	popl	%edi
 	popl	%ebx
 	popl	%ebp
-	ret
+	RET
 SYM_CODE_END(swap_pages)
 
 	.globl kexec_control_code_size
diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S
index c8fe74a28143..399f075ccdc4 100644
--- a/arch/x86/kernel/relocate_kernel_64.S
+++ b/arch/x86/kernel/relocate_kernel_64.S
@@ -104,7 +104,7 @@ SYM_CODE_START_NOALIGN(relocate_kernel)
 	/* jump to identity mapped page */
 	addq	$(identity_mapped - relocate_kernel), %r8
 	pushq	%r8
-	ret
+	RET
 SYM_CODE_END(relocate_kernel)
 
 SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
@@ -191,7 +191,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
 	xorl	%r14d, %r14d
 	xorl	%r15d, %r15d
 
-	ret
+	RET
 
 1:
 	popq	%rdx
@@ -210,7 +210,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
 	call	swap_pages
 	movq	$virtual_mapped, %rax
 	pushq	%rax
-	ret
+	RET
 SYM_CODE_END(identity_mapped)
 
 SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped)
@@ -231,7 +231,7 @@ SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped)
 	popq	%r12
 	popq	%rbp
 	popq	%rbx
-	ret
+	RET
 SYM_CODE_END(virtual_mapped)
 
 	/* Do the copies */
@@ -288,7 +288,7 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages)
 	lea	PAGE_SIZE(%rax), %rsi
 	jmp	0b
 3:
-	ret
+	RET
 SYM_CODE_END(swap_pages)
 
 	.globl kexec_control_code_size
diff --git a/arch/x86/kernel/sev_verify_cbit.S b/arch/x86/kernel/sev_verify_cbit.S
index ee04941a6546..3355e27c69eb 100644
--- a/arch/x86/kernel/sev_verify_cbit.S
+++ b/arch/x86/kernel/sev_verify_cbit.S
@@ -85,5 +85,5 @@ SYM_FUNC_START(sev_verify_cbit)
 #endif
 	/* Return page-table pointer */
 	movq	%rdi, %rax
-	ret
+	RET
 SYM_FUNC_END(sev_verify_cbit)
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index 9c407a33a774..531fb4cbb63f 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -17,6 +17,8 @@ enum insn_type {
  */
 static const u8 xor5rax[] = { 0x66, 0x66, 0x48, 0x31, 0xc0 };
 
+static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc };
+
 static void __ref __static_call_transform(void *insn, enum insn_type type, void *func)
 {
 	const void *emulate = NULL;
@@ -42,8 +44,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, void
 		break;
 
 	case RET:
-		code = text_gen_insn(RET_INSN_OPCODE, insn, func);
-		size = RET_INSN_SIZE;
+		code = &retinsn;
 		break;
 	}
 
diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S
index 641f0fe1e5b4..1258a5872d12 100644
--- a/arch/x86/kernel/verify_cpu.S
+++ b/arch/x86/kernel/verify_cpu.S
@@ -132,9 +132,9 @@ SYM_FUNC_START_LOCAL(verify_cpu)
 .Lverify_cpu_no_longmode:
 	popf				# Restore caller passed flags
 	movl $1,%eax
-	ret
+	RET
 .Lverify_cpu_sse_ok:
 	popf				# Restore caller passed flags
 	xorl %eax, %eax
-	ret
+	RET
 SYM_FUNC_END(verify_cpu)
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 3d6dc12d198f..27f830345b6f 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -137,7 +137,6 @@ SECTIONS
 		ALIGN_ENTRY_TEXT_END
 		SOFTIRQENTRY_TEXT
 		STATIC_CALL_TEXT
-		*(.fixup)
 		*(.gnu.warning)
 
 #ifdef CONFIG_RETPOLINE
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 28b1a4e57827..1e19a4de441f 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -315,7 +315,7 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
 	__FOP_FUNC(#name)
 
 #define __FOP_RET(name) \
-	"ret \n\t" \
+	"11: " ASM_RET \
 	".size " name ", .-" name "\n\t"
 
 #define FOP_RET(name) \
@@ -344,7 +344,7 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
 	__FOP_RET(#op "_" #dst)
 
 #define FOP1EEX(op,  dst) \
-	FOP1E(op, dst) _ASM_EXTABLE(10b, kvm_fastop_exception)
+	FOP1E(op, dst) _ASM_EXTABLE_TYPE_REG(10b, 11b, EX_TYPE_ZERO_REG, %%esi)
 
 #define FASTOP1(op) \
 	FOP_START(op) \
@@ -434,10 +434,6 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
 	#op " %al \n\t" \
 	__FOP_RET(#op)
 
-asm(".pushsection .fixup, \"ax\"\n"
-    "kvm_fastop_exception: xor %esi, %esi; ret\n"
-    ".popsection");
-
 FOP_START(setcc)
 FOP_SETCC(seto)
 FOP_SETCC(setno)
@@ -473,12 +469,8 @@ FOP_END;
  \
 	asm volatile("1:" insn "\n" \
 	             "2:\n" \
-	             ".pushsection .fixup, \"ax\"\n" \
-	             "3: movl $1, %[_fault]\n" \
-	             "   jmp  2b\n" \
-	             ".popsection\n" \
-	             _ASM_EXTABLE(1b, 3b) \
-	             : [_fault] "+qm"(_fault) inoutclob ); \
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_ONE_REG, %[_fault]) \
+	             : [_fault] "+r"(_fault) inoutclob ); \
  \
 	_fault ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE; \
 })
diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S
index 4fa17df123cd..dfaeb47fcf2a 100644
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -148,7 +148,7 @@ SYM_FUNC_START(__svm_vcpu_run)
 	pop %edi
 #endif
 	pop %_ASM_BP
-	ret
+	RET
 
 3:	cmpb $0, kvm_rebooting
 	jne 2b
@@ -202,7 +202,7 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run)
 	pop %edi
 #endif
 	pop %_ASM_BP
-	ret
+	RET
 
 3:	cmpb $0, kvm_rebooting
 	jne 2b
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 3a6461694fc2..435c187927c4 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -49,14 +49,14 @@ SYM_FUNC_START_LOCAL(vmx_vmenter)
 	je 2f
 
 1:	vmresume
-	ret
+	RET
 
 2:	vmlaunch
-	ret
+	RET
 
 3:	cmpb $0, kvm_rebooting
 	je 4f
-	ret
+	RET
 4:	ud2
 
 	_ASM_EXTABLE(1b, 3b)
@@ -89,7 +89,7 @@ SYM_FUNC_START(vmx_vmexit)
 	pop %_ASM_AX
 .Lvmexit_skip_rsb:
 #endif
-	ret
+	RET
 SYM_FUNC_END(vmx_vmexit)
 
 /**
@@ -228,7 +228,7 @@ SYM_FUNC_START(__vmx_vcpu_run)
 	pop %edi
 #endif
 	pop %_ASM_BP
-	ret
+	RET
 
 	/* VM-Fail.  Out-of-line to avoid a taken Jcc after VM-Exit. */
 2:	mov $1, %eax
@@ -293,7 +293,7 @@ SYM_FUNC_START(vmread_error_trampoline)
 	pop %_ASM_AX
 	pop %_ASM_BP
 
-	ret
+	RET
 SYM_FUNC_END(vmread_error_trampoline)
 
 SYM_FUNC_START(vmx_do_interrupt_nmi_irqoff)
@@ -326,5 +326,5 @@ SYM_FUNC_START(vmx_do_interrupt_nmi_irqoff)
 	 */
 	mov %_ASM_BP, %_ASM_SP
 	pop %_ASM_BP
-	ret
+	RET
 SYM_FUNC_END(vmx_do_interrupt_nmi_irqoff)
diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h
index 9e9ef47e988c..35d9324c2f2a 100644
--- a/arch/x86/kvm/vmx/vmx_ops.h
+++ b/arch/x86/kvm/vmx/vmx_ops.h
@@ -80,9 +80,11 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field)
 		      * @field, and bounce through the trampoline to preserve
 		      * volatile registers.
 		      */
-		     "push $0\n\t"
+		     "xorl %k1, %k1\n\t"
+		     "2:\n\t"
+		     "push %1\n\t"
 		     "push %2\n\t"
-		     "2:call vmread_error_trampoline\n\t"
+		     "call vmread_error_trampoline\n\t"
 
 		     /*
 		      * Unwind the stack.  Note, the trampoline zeros out the
@@ -93,13 +95,9 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field)
 		     "3:\n\t"
 
 		     /* VMREAD faulted.  As above, except push '1' for @fault. */
-		     ".pushsection .fixup, \"ax\"\n\t"
-		     "4: push $1\n\t"
-		     "push %2\n\t"
-		     "jmp 2b\n\t"
-		     ".popsection\n\t"
-		     _ASM_EXTABLE(1b, 4b)
-		     : ASM_CALL_CONSTRAINT, "=r"(value) : "r"(field) : "cc");
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_ONE_REG, %1)
+
+		     : ASM_CALL_CONSTRAINT, "=&r"(value) : "r"(field) : "cc");
 	return value;
 }
 
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index c6506c6a7092..f76747862bd2 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -63,7 +63,6 @@ ifeq ($(CONFIG_X86_32),y)
 ifneq ($(CONFIG_X86_CMPXCHG64),y)
         lib-y += cmpxchg8b_emu.o atomic64_386_32.o
 endif
-        lib-$(CONFIG_X86_USE_3DNOW) += mmx_32.o
 else
         obj-y += iomap_copy_64.o
         lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o
diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S
index 16bc9130e7a5..e768815e58ae 100644
--- a/arch/x86/lib/atomic64_386_32.S
+++ b/arch/x86/lib/atomic64_386_32.S
@@ -9,81 +9,83 @@
 #include <asm/alternative.h>
 
 /* if you want SMP support, implement these with real spinlocks */
-.macro LOCK reg
+.macro IRQ_SAVE reg
 	pushfl
 	cli
 .endm
 
-.macro UNLOCK reg
+.macro IRQ_RESTORE reg
 	popfl
 .endm
 
-#define BEGIN(op) \
+#define BEGIN_IRQ_SAVE(op) \
 .macro endp; \
 SYM_FUNC_END(atomic64_##op##_386); \
 .purgem endp; \
 .endm; \
 SYM_FUNC_START(atomic64_##op##_386); \
-	LOCK v;
+	IRQ_SAVE v;
 
 #define ENDP endp
 
-#define RET \
-	UNLOCK v; \
-	ret
-
-#define RET_ENDP \
-	RET; \
-	ENDP
+#define RET_IRQ_RESTORE \
+	IRQ_RESTORE v; \
+	RET
 
 #define v %ecx
-BEGIN(read)
+BEGIN_IRQ_SAVE(read)
 	movl  (v), %eax
 	movl 4(v), %edx
-RET_ENDP
+	RET_IRQ_RESTORE
+ENDP
 #undef v
 
 #define v %esi
-BEGIN(set)
+BEGIN_IRQ_SAVE(set)
 	movl %ebx,  (v)
 	movl %ecx, 4(v)
-RET_ENDP
+	RET_IRQ_RESTORE
+ENDP
 #undef v
 
 #define v  %esi
-BEGIN(xchg)
+BEGIN_IRQ_SAVE(xchg)
 	movl  (v), %eax
 	movl 4(v), %edx
 	movl %ebx,  (v)
 	movl %ecx, 4(v)
-RET_ENDP
+	RET_IRQ_RESTORE
+ENDP
 #undef v
 
 #define v %ecx
-BEGIN(add)
+BEGIN_IRQ_SAVE(add)
 	addl %eax,  (v)
 	adcl %edx, 4(v)
-RET_ENDP
+	RET_IRQ_RESTORE
+ENDP
 #undef v
 
 #define v %ecx
-BEGIN(add_return)
+BEGIN_IRQ_SAVE(add_return)
 	addl  (v), %eax
 	adcl 4(v), %edx
 	movl %eax,  (v)
 	movl %edx, 4(v)
-RET_ENDP
+	RET_IRQ_RESTORE
+ENDP
 #undef v
 
 #define v %ecx
-BEGIN(sub)
+BEGIN_IRQ_SAVE(sub)
 	subl %eax,  (v)
 	sbbl %edx, 4(v)
-RET_ENDP
+	RET_IRQ_RESTORE
+ENDP
 #undef v
 
 #define v %ecx
-BEGIN(sub_return)
+BEGIN_IRQ_SAVE(sub_return)
 	negl %edx
 	negl %eax
 	sbbl $0, %edx
@@ -91,47 +93,52 @@ BEGIN(sub_return)
 	adcl 4(v), %edx
 	movl %eax,  (v)
 	movl %edx, 4(v)
-RET_ENDP
+	RET_IRQ_RESTORE
+ENDP
 #undef v
 
 #define v %esi
-BEGIN(inc)
+BEGIN_IRQ_SAVE(inc)
 	addl $1,  (v)
 	adcl $0, 4(v)
-RET_ENDP
+	RET_IRQ_RESTORE
+ENDP
 #undef v
 
 #define v %esi
-BEGIN(inc_return)
+BEGIN_IRQ_SAVE(inc_return)
 	movl  (v), %eax
 	movl 4(v), %edx
 	addl $1, %eax
 	adcl $0, %edx
 	movl %eax,  (v)
 	movl %edx, 4(v)
-RET_ENDP
+	RET_IRQ_RESTORE
+ENDP
 #undef v
 
 #define v %esi
-BEGIN(dec)
+BEGIN_IRQ_SAVE(dec)
 	subl $1,  (v)
 	sbbl $0, 4(v)
-RET_ENDP
+	RET_IRQ_RESTORE
+ENDP
 #undef v
 
 #define v %esi
-BEGIN(dec_return)
+BEGIN_IRQ_SAVE(dec_return)
 	movl  (v), %eax
 	movl 4(v), %edx
 	subl $1, %eax
 	sbbl $0, %edx
 	movl %eax,  (v)
 	movl %edx, 4(v)
-RET_ENDP
+	RET_IRQ_RESTORE
+ENDP
 #undef v
 
 #define v %esi
-BEGIN(add_unless)
+BEGIN_IRQ_SAVE(add_unless)
 	addl %eax, %ecx
 	adcl %edx, %edi
 	addl  (v), %eax
@@ -143,7 +150,7 @@ BEGIN(add_unless)
 	movl %edx, 4(v)
 	movl $1, %eax
 2:
-	RET
+	RET_IRQ_RESTORE
 3:
 	cmpl %edx, %edi
 	jne 1b
@@ -153,7 +160,7 @@ ENDP
 #undef v
 
 #define v %esi
-BEGIN(inc_not_zero)
+BEGIN_IRQ_SAVE(inc_not_zero)
 	movl  (v), %eax
 	movl 4(v), %edx
 	testl %eax, %eax
@@ -165,7 +172,7 @@ BEGIN(inc_not_zero)
 	movl %edx, 4(v)
 	movl $1, %eax
 2:
-	RET
+	RET_IRQ_RESTORE
 3:
 	testl %edx, %edx
 	jne 1b
@@ -174,7 +181,7 @@ ENDP
 #undef v
 
 #define v %esi
-BEGIN(dec_if_positive)
+BEGIN_IRQ_SAVE(dec_if_positive)
 	movl  (v), %eax
 	movl 4(v), %edx
 	subl $1, %eax
@@ -183,5 +190,6 @@ BEGIN(dec_if_positive)
 	movl %eax,  (v)
 	movl %edx, 4(v)
 1:
-RET_ENDP
+	RET_IRQ_RESTORE
+ENDP
 #undef v
diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S
index ce6935690766..90afb488b396 100644
--- a/arch/x86/lib/atomic64_cx8_32.S
+++ b/arch/x86/lib/atomic64_cx8_32.S
@@ -18,7 +18,7 @@
 
 SYM_FUNC_START(atomic64_read_cx8)
 	read64 %ecx
-	ret
+	RET
 SYM_FUNC_END(atomic64_read_cx8)
 
 SYM_FUNC_START(atomic64_set_cx8)
@@ -28,7 +28,7 @@ SYM_FUNC_START(atomic64_set_cx8)
 	cmpxchg8b (%esi)
 	jne 1b
 
-	ret
+	RET
 SYM_FUNC_END(atomic64_set_cx8)
 
 SYM_FUNC_START(atomic64_xchg_cx8)
@@ -37,7 +37,7 @@ SYM_FUNC_START(atomic64_xchg_cx8)
 	cmpxchg8b (%esi)
 	jne 1b
 
-	ret
+	RET
 SYM_FUNC_END(atomic64_xchg_cx8)
 
 .macro addsub_return func ins insc
@@ -68,7 +68,7 @@ SYM_FUNC_START(atomic64_\func\()_return_cx8)
 	popl %esi
 	popl %ebx
 	popl %ebp
-	ret
+	RET
 SYM_FUNC_END(atomic64_\func\()_return_cx8)
 .endm
 
@@ -93,7 +93,7 @@ SYM_FUNC_START(atomic64_\func\()_return_cx8)
 	movl %ebx, %eax
 	movl %ecx, %edx
 	popl %ebx
-	ret
+	RET
 SYM_FUNC_END(atomic64_\func\()_return_cx8)
 .endm
 
@@ -118,7 +118,7 @@ SYM_FUNC_START(atomic64_dec_if_positive_cx8)
 	movl %ebx, %eax
 	movl %ecx, %edx
 	popl %ebx
-	ret
+	RET
 SYM_FUNC_END(atomic64_dec_if_positive_cx8)
 
 SYM_FUNC_START(atomic64_add_unless_cx8)
@@ -149,7 +149,7 @@ SYM_FUNC_START(atomic64_add_unless_cx8)
 	addl $8, %esp
 	popl %ebx
 	popl %ebp
-	ret
+	RET
 4:
 	cmpl %edx, 4(%esp)
 	jne 2b
@@ -176,5 +176,5 @@ SYM_FUNC_START(atomic64_inc_not_zero_cx8)
 	movl $1, %eax
 3:
 	popl %ebx
-	ret
+	RET
 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 4304320e51f4..23318c338db0 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -127,7 +127,7 @@ SYM_FUNC_START(csum_partial)
 8:
 	popl %ebx
 	popl %esi
-	ret
+	RET
 SYM_FUNC_END(csum_partial)
 
 #else
@@ -245,7 +245,7 @@ SYM_FUNC_START(csum_partial)
 90: 
 	popl %ebx
 	popl %esi
-	ret
+	RET
 SYM_FUNC_END(csum_partial)
 				
 #endif
@@ -260,9 +260,9 @@ unsigned int csum_partial_copy_generic (const char *src, char *dst,
  * Copy from ds while checksumming, otherwise like csum_partial
  */
 
-#define EXC(y...)			\
-	9999: y;			\
-	_ASM_EXTABLE_UA(9999b, 6001f)
+#define EXC(y...)						\
+	9999: y;						\
+	_ASM_EXTABLE_TYPE(9999b, 7f, EX_TYPE_UACCESS | EX_FLAG_CLEAR_AX)
 
 #ifndef CONFIG_X86_USE_PPRO_CHECKSUM
 
@@ -358,20 +358,11 @@ EXC(	movb %cl, (%edi)	)
 	adcl $0, %eax
 7:
 
-# Exception handler:
-.section .fixup, "ax"							
-
-6001:
-	xorl %eax, %eax
-	jmp 7b
-
-.previous
-
 	popl %ebx
 	popl %esi
 	popl %edi
 	popl %ecx			# equivalent to addl $4,%esp
-	ret	
+	RET
 SYM_FUNC_END(csum_partial_copy_generic)
 
 #else
@@ -439,15 +430,11 @@ EXC(	movb %dl, (%edi)         )
 6:	addl %edx, %eax
 	adcl $0, %eax
 7:
-.section .fixup, "ax"
-6001:	xorl %eax, %eax
-	jmp  7b			
-.previous				
 
 	popl %esi
 	popl %edi
 	popl %ebx
-	ret
+	RET
 SYM_FUNC_END(csum_partial_copy_generic)
 				
 #undef ROUND
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index c4c7dd115953..fe59b8ac4fcc 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -17,7 +17,7 @@ SYM_FUNC_START(clear_page_rep)
 	movl $4096/8,%ecx
 	xorl %eax,%eax
 	rep stosq
-	ret
+	RET
 SYM_FUNC_END(clear_page_rep)
 EXPORT_SYMBOL_GPL(clear_page_rep)
 
@@ -39,7 +39,7 @@ SYM_FUNC_START(clear_page_orig)
 	leaq	64(%rdi),%rdi
 	jnz	.Lloop
 	nop
-	ret
+	RET
 SYM_FUNC_END(clear_page_orig)
 EXPORT_SYMBOL_GPL(clear_page_orig)
 
@@ -47,6 +47,6 @@ SYM_FUNC_START(clear_page_erms)
 	movl $4096,%ecx
 	xorl %eax,%eax
 	rep stosb
-	ret
+	RET
 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 3542502faa3b..33c70c0160ea 100644
--- a/arch/x86/lib/cmpxchg16b_emu.S
+++ b/arch/x86/lib/cmpxchg16b_emu.S
@@ -37,11 +37,11 @@ SYM_FUNC_START(this_cpu_cmpxchg16b_emu)
 
 	popfq
 	mov $1, %al
-	ret
+	RET
 
 .Lnot_same:
 	popfq
 	xor %al,%al
-	ret
+	RET
 
 SYM_FUNC_END(this_cpu_cmpxchg16b_emu)
diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S
index ca01ed6029f4..6a912d58fecc 100644
--- a/arch/x86/lib/cmpxchg8b_emu.S
+++ b/arch/x86/lib/cmpxchg8b_emu.S
@@ -32,7 +32,7 @@ SYM_FUNC_START(cmpxchg8b_emu)
 	movl %ecx, 4(%esi)
 
 	popfl
-	ret
+	RET
 
 .Lnot_same:
 	movl  (%esi), %eax
@@ -40,7 +40,7 @@ SYM_FUNC_START(cmpxchg8b_emu)
 	movl 4(%esi), %edx
 
 	popfl
-	ret
+	RET
 
 SYM_FUNC_END(cmpxchg8b_emu)
 EXPORT_SYMBOL(cmpxchg8b_emu)
diff --git a/arch/x86/lib/copy_mc_64.S b/arch/x86/lib/copy_mc_64.S
index 7334055157ba..c859a8a09860 100644
--- a/arch/x86/lib/copy_mc_64.S
+++ b/arch/x86/lib/copy_mc_64.S
@@ -77,10 +77,8 @@ SYM_FUNC_START(copy_mc_fragile)
 .L_done_memcpy_trap:
 	xorl %eax, %eax
 .L_done:
-	ret
-SYM_FUNC_END(copy_mc_fragile)
+	RET
 
-	.section .fixup, "ax"
 	/*
 	 * Return number of bytes not copied for any failure. Note that
 	 * there is no "tail" handling since the source buffer is 8-byte
@@ -105,14 +103,14 @@ SYM_FUNC_END(copy_mc_fragile)
 	movl	%ecx, %edx
 	jmp copy_mc_fragile_handle_tail
 
-	.previous
-
 	_ASM_EXTABLE_TYPE(.L_read_leading_bytes, .E_leading_bytes, EX_TYPE_DEFAULT_MCE_SAFE)
 	_ASM_EXTABLE_TYPE(.L_read_words, .E_read_words, EX_TYPE_DEFAULT_MCE_SAFE)
 	_ASM_EXTABLE_TYPE(.L_read_trailing_bytes, .E_trailing_bytes, EX_TYPE_DEFAULT_MCE_SAFE)
 	_ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes)
 	_ASM_EXTABLE(.L_write_words, .E_write_words)
 	_ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes)
+
+SYM_FUNC_END(copy_mc_fragile)
 #endif /* CONFIG_X86_MCE */
 
 /*
@@ -132,10 +130,8 @@ SYM_FUNC_START(copy_mc_enhanced_fast_string)
 	rep movsb
 	/* Copy successful. Return zero */
 	xorl %eax, %eax
-	ret
-SYM_FUNC_END(copy_mc_enhanced_fast_string)
+	RET
 
-	.section .fixup, "ax"
 .E_copy:
 	/*
 	 * On fault %rcx is updated such that the copy instruction could
@@ -145,9 +141,9 @@ SYM_FUNC_END(copy_mc_enhanced_fast_string)
 	 * user-copy routines.
 	 */
 	movq %rcx, %rax
-	ret
-
-	.previous
+	RET
 
 	_ASM_EXTABLE_TYPE(.L_copy, .E_copy, EX_TYPE_DEFAULT_MCE_SAFE)
+
+SYM_FUNC_END(copy_mc_enhanced_fast_string)
 #endif /* !CONFIG_UML */
diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S
index db4b4f9197c7..30ea644bf446 100644
--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -17,7 +17,7 @@ SYM_FUNC_START(copy_page)
 	ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD
 	movl	$4096/8, %ecx
 	rep	movsq
-	ret
+	RET
 SYM_FUNC_END(copy_page)
 EXPORT_SYMBOL(copy_page)
 
@@ -85,5 +85,5 @@ SYM_FUNC_START_LOCAL(copy_page_regs)
 	movq	(%rsp), %rbx
 	movq	1*8(%rsp), %r12
 	addq	$2*8, %rsp
-	ret
+	RET
 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 a2cbeae4b180..8ca5ecf16dc4 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -32,14 +32,10 @@
 	decl %ecx
 	jnz 100b
 102:
-	.section .fixup,"ax"
-103:	addl %ecx,%edx			/* ecx is zerorest also */
-	jmp .Lcopy_user_handle_tail
-	.previous
 
-	_ASM_EXTABLE_CPY(100b, 103b)
-	_ASM_EXTABLE_CPY(101b, 103b)
-	.endm
+	_ASM_EXTABLE_CPY(100b, .Lcopy_user_handle_align)
+	_ASM_EXTABLE_CPY(101b, .Lcopy_user_handle_align)
+.endm
 
 /*
  * copy_user_generic_unrolled - memory copy with exception handling.
@@ -105,9 +101,8 @@ SYM_FUNC_START(copy_user_generic_unrolled)
 	jnz 21b
 23:	xor %eax,%eax
 	ASM_CLAC
-	ret
+	RET
 
-	.section .fixup,"ax"
 30:	shll $6,%ecx
 	addl %ecx,%edx
 	jmp 60f
@@ -115,7 +110,6 @@ SYM_FUNC_START(copy_user_generic_unrolled)
 	jmp 60f
 50:	movl %ecx,%edx
 60:	jmp .Lcopy_user_handle_tail /* ecx is zerorest also */
-	.previous
 
 	_ASM_EXTABLE_CPY(1b, 30b)
 	_ASM_EXTABLE_CPY(2b, 30b)
@@ -166,20 +160,16 @@ SYM_FUNC_START(copy_user_generic_string)
 	movl %edx,%ecx
 	shrl $3,%ecx
 	andl $7,%edx
-1:	rep
-	movsq
+1:	rep movsq
 2:	movl %edx,%ecx
-3:	rep
-	movsb
+3:	rep movsb
 	xorl %eax,%eax
 	ASM_CLAC
-	ret
+	RET
 
-	.section .fixup,"ax"
 11:	leal (%rdx,%rcx,8),%ecx
 12:	movl %ecx,%edx		/* ecx is zerorest also */
 	jmp .Lcopy_user_handle_tail
-	.previous
 
 	_ASM_EXTABLE_CPY(1b, 11b)
 	_ASM_EXTABLE_CPY(3b, 12b)
@@ -203,16 +193,13 @@ SYM_FUNC_START(copy_user_enhanced_fast_string)
 	/* CPUs without FSRM should avoid rep movsb for short copies */
 	ALTERNATIVE "cmpl $64, %edx; jb .L_copy_short_string", "", X86_FEATURE_FSRM
 	movl %edx,%ecx
-1:	rep
-	movsb
+1:	rep movsb
 	xorl %eax,%eax
 	ASM_CLAC
-	ret
+	RET
 
-	.section .fixup,"ax"
 12:	movl %ecx,%edx		/* ecx is zerorest also */
 	jmp .Lcopy_user_handle_tail
-	.previous
 
 	_ASM_EXTABLE_CPY(1b, 12b)
 SYM_FUNC_END(copy_user_enhanced_fast_string)
@@ -241,7 +228,7 @@ SYM_CODE_START_LOCAL(.Lcopy_user_handle_tail)
 1:	rep movsb
 2:	mov %ecx,%eax
 	ASM_CLAC
-	ret
+	RET
 
 3:
 	movl %edx,%eax
@@ -249,6 +236,11 @@ SYM_CODE_START_LOCAL(.Lcopy_user_handle_tail)
 	RET
 
 	_ASM_EXTABLE_CPY(1b, 2b)
+
+.Lcopy_user_handle_align:
+	addl %ecx,%edx			/* ecx is zerorest also */
+	jmp .Lcopy_user_handle_tail
+
 SYM_CODE_END(.Lcopy_user_handle_tail)
 
 /*
@@ -357,9 +349,8 @@ SYM_FUNC_START(__copy_user_nocache)
 	xorl %eax,%eax
 	ASM_CLAC
 	sfence
-	ret
+	RET
 
-	.section .fixup,"ax"
 .L_fixup_4x8b_copy:
 	shll $6,%ecx
 	addl %ecx,%edx
@@ -375,7 +366,6 @@ SYM_FUNC_START(__copy_user_nocache)
 .L_fixup_handle_tail:
 	sfence
 	jmp .Lcopy_user_handle_tail
-	.previous
 
 	_ASM_EXTABLE_CPY(1b, .L_fixup_4x8b_copy)
 	_ASM_EXTABLE_CPY(2b, .L_fixup_4x8b_copy)
diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S
index 1fbd8ee9642d..d9e16a2cf285 100644
--- a/arch/x86/lib/csum-copy_64.S
+++ b/arch/x86/lib/csum-copy_64.S
@@ -201,7 +201,7 @@ SYM_FUNC_START(csum_partial_copy_generic)
 	movq 3*8(%rsp), %r13
 	movq 4*8(%rsp), %r15
 	addq $5*8, %rsp
-	ret
+	RET
 .Lshort:
 	movl %ecx, %r10d
 	jmp  .L1
diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c
index e7925d668b68..1f8a8f895173 100644
--- a/arch/x86/lib/csum-partial_64.c
+++ b/arch/x86/lib/csum-partial_64.c
@@ -9,6 +9,7 @@
 #include <linux/compiler.h>
 #include <linux/export.h>
 #include <asm/checksum.h>
+#include <asm/word-at-a-time.h>
 
 static inline unsigned short from32to16(unsigned a) 
 {
@@ -21,120 +22,119 @@ static inline unsigned short from32to16(unsigned a)
 }
 
 /*
- * Do a 64-bit checksum on an arbitrary memory area.
+ * Do a checksum on an arbitrary memory area.
  * Returns a 32bit checksum.
  *
  * This isn't as time critical as it used to be because many NICs
  * do hardware checksumming these days.
- * 
- * Things tried and found to not make it faster:
- * Manual Prefetching
- * Unrolling to an 128 bytes inner loop.
- * Using interleaving with more registers to break the carry chains.
+ *
+ * Still, with CHECKSUM_COMPLETE this is called to compute
+ * checksums on IPv6 headers (40 bytes) and other small parts.
+ * it's best to have buff aligned on a 64-bit boundary
  */
-static unsigned do_csum(const unsigned char *buff, unsigned len)
+__wsum csum_partial(const void *buff, int len, __wsum sum)
 {
-	unsigned odd, count;
-	unsigned long result = 0;
+	u64 temp64 = (__force u64)sum;
+	unsigned odd, result;
 
-	if (unlikely(len == 0))
-		return result; 
 	odd = 1 & (unsigned long) buff;
 	if (unlikely(odd)) {
-		result = *buff << 8;
+		if (unlikely(len == 0))
+			return sum;
+		temp64 = ror32((__force u32)sum, 8);
+		temp64 += (*(unsigned char *)buff << 8);
 		len--;
 		buff++;
 	}
-	count = len >> 1;		/* nr of 16-bit words.. */
-	if (count) {
-		if (2 & (unsigned long) buff) {
-			result += *(unsigned short *)buff;
-			count--;
-			len -= 2;
-			buff += 2;
-		}
-		count >>= 1;		/* nr of 32-bit words.. */
-		if (count) {
-			unsigned long zero;
-			unsigned count64;
-			if (4 & (unsigned long) buff) {
-				result += *(unsigned int *) buff;
-				count--;
-				len -= 4;
-				buff += 4;
-			}
-			count >>= 1;	/* nr of 64-bit words.. */
 
-			/* main loop using 64byte blocks */
-			zero = 0;
-			count64 = count >> 3;
-			while (count64) { 
-				asm("addq 0*8(%[src]),%[res]\n\t"
-				    "adcq 1*8(%[src]),%[res]\n\t"
-				    "adcq 2*8(%[src]),%[res]\n\t"
-				    "adcq 3*8(%[src]),%[res]\n\t"
-				    "adcq 4*8(%[src]),%[res]\n\t"
-				    "adcq 5*8(%[src]),%[res]\n\t"
-				    "adcq 6*8(%[src]),%[res]\n\t"
-				    "adcq 7*8(%[src]),%[res]\n\t"
-				    "adcq %[zero],%[res]"
-				    : [res] "=r" (result)
-				    : [src] "r" (buff), [zero] "r" (zero),
-				    "[res]" (result));
-				buff += 64;
-				count64--;
-			}
+	while (unlikely(len >= 64)) {
+		asm("addq 0*8(%[src]),%[res]\n\t"
+		    "adcq 1*8(%[src]),%[res]\n\t"
+		    "adcq 2*8(%[src]),%[res]\n\t"
+		    "adcq 3*8(%[src]),%[res]\n\t"
+		    "adcq 4*8(%[src]),%[res]\n\t"
+		    "adcq 5*8(%[src]),%[res]\n\t"
+		    "adcq 6*8(%[src]),%[res]\n\t"
+		    "adcq 7*8(%[src]),%[res]\n\t"
+		    "adcq $0,%[res]"
+		    : [res] "+r" (temp64)
+		    : [src] "r" (buff)
+		    : "memory");
+		buff += 64;
+		len -= 64;
+	}
+
+	if (len & 32) {
+		asm("addq 0*8(%[src]),%[res]\n\t"
+		    "adcq 1*8(%[src]),%[res]\n\t"
+		    "adcq 2*8(%[src]),%[res]\n\t"
+		    "adcq 3*8(%[src]),%[res]\n\t"
+		    "adcq $0,%[res]"
+			: [res] "+r" (temp64)
+			: [src] "r" (buff)
+			: "memory");
+		buff += 32;
+	}
+	if (len & 16) {
+		asm("addq 0*8(%[src]),%[res]\n\t"
+		    "adcq 1*8(%[src]),%[res]\n\t"
+		    "adcq $0,%[res]"
+			: [res] "+r" (temp64)
+			: [src] "r" (buff)
+			: "memory");
+		buff += 16;
+	}
+	if (len & 8) {
+		asm("addq 0*8(%[src]),%[res]\n\t"
+		    "adcq $0,%[res]"
+			: [res] "+r" (temp64)
+			: [src] "r" (buff)
+			: "memory");
+		buff += 8;
+	}
+	if (len & 7) {
+#ifdef CONFIG_DCACHE_WORD_ACCESS
+		unsigned int shift = (8 - (len & 7)) * 8;
+		unsigned long trail;
 
-			/* last up to 7 8byte blocks */
-			count %= 8; 
-			while (count) { 
-				asm("addq %1,%0\n\t"
-				    "adcq %2,%0\n" 
-					    : "=r" (result)
-				    : "m" (*(unsigned long *)buff), 
-				    "r" (zero),  "0" (result));
-				--count; 
-				buff += 8;
-			}
-			result = add32_with_carry(result>>32,
-						  result&0xffffffff); 
+		trail = (load_unaligned_zeropad(buff) << shift) >> shift;
 
-			if (len & 4) {
-				result += *(unsigned int *) buff;
-				buff += 4;
-			}
+		asm("addq %[trail],%[res]\n\t"
+		    "adcq $0,%[res]"
+			: [res] "+r" (temp64)
+			: [trail] "r" (trail));
+#else
+		if (len & 4) {
+			asm("addq %[val],%[res]\n\t"
+			    "adcq $0,%[res]"
+				: [res] "+r" (temp64)
+				: [val] "r" ((u64)*(u32 *)buff)
+				: "memory");
+			buff += 4;
 		}
 		if (len & 2) {
-			result += *(unsigned short *) buff;
+			asm("addq %[val],%[res]\n\t"
+			    "adcq $0,%[res]"
+				: [res] "+r" (temp64)
+				: [val] "r" ((u64)*(u16 *)buff)
+				: "memory");
 			buff += 2;
 		}
+		if (len & 1) {
+			asm("addq %[val],%[res]\n\t"
+			    "adcq $0,%[res]"
+				: [res] "+r" (temp64)
+				: [val] "r" ((u64)*(u8 *)buff)
+				: "memory");
+		}
+#endif
 	}
-	if (len & 1)
-		result += *buff;
-	result = add32_with_carry(result>>32, result & 0xffffffff); 
-	if (unlikely(odd)) { 
+	result = add32_with_carry(temp64 >> 32, temp64 & 0xffffffff);
+	if (unlikely(odd)) {
 		result = from32to16(result);
 		result = ((result >> 8) & 0xff) | ((result & 0xff) << 8);
 	}
-	return result;
-}
-
-/*
- * computes the checksum of a memory block at buff, length len,
- * and adds in "sum" (32-bit)
- *
- * returns a 32-bit number suitable for feeding into itself
- * or csum_tcpudp_magic
- *
- * this function must be called with even lengths, except
- * for the last fragment, which may be odd
- *
- * it's best to have buff aligned on a 64-bit boundary
- */
-__wsum csum_partial(const void *buff, int len, __wsum sum)
-{
-	return (__force __wsum)add32_with_carry(do_csum(buff, len),
-						(__force u32)sum);
+	return (__force __wsum)result;
 }
 EXPORT_SYMBOL(csum_partial);
 
@@ -147,4 +147,3 @@ __sum16 ip_compute_csum(const void *buff, int len)
 	return csum_fold(csum_partial(buff,len,0));
 }
 EXPORT_SYMBOL(ip_compute_csum);
-
diff --git a/arch/x86/lib/error-inject.c b/arch/x86/lib/error-inject.c
index be5b5fb1598b..520897061ee0 100644
--- a/arch/x86/lib/error-inject.c
+++ b/arch/x86/lib/error-inject.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 
+#include <linux/linkage.h>
 #include <linux/error-injection.h>
 #include <linux/kprobes.h>
 
@@ -10,7 +11,7 @@ asm(
 	".type just_return_func, @function\n"
 	".globl just_return_func\n"
 	"just_return_func:\n"
-	"	ret\n"
+		ASM_RET
 	".size just_return_func, .-just_return_func\n"
 );
 
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index fa1bc2104b32..b70d98d79a9d 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -57,7 +57,7 @@ SYM_FUNC_START(__get_user_1)
 1:	movzbl (%_ASM_AX),%edx
 	xor %eax,%eax
 	ASM_CLAC
-	ret
+	RET
 SYM_FUNC_END(__get_user_1)
 EXPORT_SYMBOL(__get_user_1)
 
@@ -71,7 +71,7 @@ SYM_FUNC_START(__get_user_2)
 2:	movzwl (%_ASM_AX),%edx
 	xor %eax,%eax
 	ASM_CLAC
-	ret
+	RET
 SYM_FUNC_END(__get_user_2)
 EXPORT_SYMBOL(__get_user_2)
 
@@ -85,7 +85,7 @@ SYM_FUNC_START(__get_user_4)
 3:	movl (%_ASM_AX),%edx
 	xor %eax,%eax
 	ASM_CLAC
-	ret
+	RET
 SYM_FUNC_END(__get_user_4)
 EXPORT_SYMBOL(__get_user_4)
 
@@ -100,7 +100,7 @@ SYM_FUNC_START(__get_user_8)
 4:	movq (%_ASM_AX),%rdx
 	xor %eax,%eax
 	ASM_CLAC
-	ret
+	RET
 #else
 	LOAD_TASK_SIZE_MINUS_N(7)
 	cmp %_ASM_DX,%_ASM_AX
@@ -112,7 +112,7 @@ SYM_FUNC_START(__get_user_8)
 5:	movl 4(%_ASM_AX),%ecx
 	xor %eax,%eax
 	ASM_CLAC
-	ret
+	RET
 #endif
 SYM_FUNC_END(__get_user_8)
 EXPORT_SYMBOL(__get_user_8)
@@ -124,7 +124,7 @@ SYM_FUNC_START(__get_user_nocheck_1)
 6:	movzbl (%_ASM_AX),%edx
 	xor %eax,%eax
 	ASM_CLAC
-	ret
+	RET
 SYM_FUNC_END(__get_user_nocheck_1)
 EXPORT_SYMBOL(__get_user_nocheck_1)
 
@@ -134,7 +134,7 @@ SYM_FUNC_START(__get_user_nocheck_2)
 7:	movzwl (%_ASM_AX),%edx
 	xor %eax,%eax
 	ASM_CLAC
-	ret
+	RET
 SYM_FUNC_END(__get_user_nocheck_2)
 EXPORT_SYMBOL(__get_user_nocheck_2)
 
@@ -144,7 +144,7 @@ SYM_FUNC_START(__get_user_nocheck_4)
 8:	movl (%_ASM_AX),%edx
 	xor %eax,%eax
 	ASM_CLAC
-	ret
+	RET
 SYM_FUNC_END(__get_user_nocheck_4)
 EXPORT_SYMBOL(__get_user_nocheck_4)
 
@@ -159,7 +159,7 @@ SYM_FUNC_START(__get_user_nocheck_8)
 #endif
 	xor %eax,%eax
 	ASM_CLAC
-	ret
+	RET
 SYM_FUNC_END(__get_user_nocheck_8)
 EXPORT_SYMBOL(__get_user_nocheck_8)
 
@@ -169,7 +169,7 @@ SYM_CODE_START_LOCAL(.Lbad_get_user_clac)
 bad_get_user:
 	xor %edx,%edx
 	mov $(-EFAULT),%_ASM_AX
-	ret
+	RET
 SYM_CODE_END(.Lbad_get_user_clac)
 
 #ifdef CONFIG_X86_32
@@ -179,7 +179,7 @@ bad_get_user_8:
 	xor %edx,%edx
 	xor %ecx,%ecx
 	mov $(-EFAULT),%_ASM_AX
-	ret
+	RET
 SYM_CODE_END(.Lbad_get_user_8_clac)
 #endif
 
diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S
index dbf8cc97b7f5..12c16c6aa44a 100644
--- a/arch/x86/lib/hweight.S
+++ b/arch/x86/lib/hweight.S
@@ -32,7 +32,7 @@ SYM_FUNC_START(__sw_hweight32)
 	imull $0x01010101, %eax, %eax		# w_tmp *= 0x01010101
 	shrl $24, %eax				# w = w_tmp >> 24
 	__ASM_SIZE(pop,) %__ASM_REG(dx)
-	ret
+	RET
 SYM_FUNC_END(__sw_hweight32)
 EXPORT_SYMBOL(__sw_hweight32)
 
@@ -65,7 +65,7 @@ SYM_FUNC_START(__sw_hweight64)
 
 	popq    %rdx
 	popq    %rdi
-	ret
+	RET
 #else /* CONFIG_X86_32 */
 	/* We're getting an u64 arg in (%eax,%edx): unsigned long hweight64(__u64 w) */
 	pushl   %ecx
@@ -77,7 +77,7 @@ SYM_FUNC_START(__sw_hweight64)
 	addl    %ecx, %eax                      # result
 
 	popl    %ecx
-	ret
+	RET
 #endif
 SYM_FUNC_END(__sw_hweight64)
 EXPORT_SYMBOL(__sw_hweight64)
diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c
index 53e57ef5925c..b781d324211b 100644
--- a/arch/x86/lib/insn-eval.c
+++ b/arch/x86/lib/insn-eval.c
@@ -410,32 +410,44 @@ static short get_segment_selector(struct pt_regs *regs, int seg_reg_idx)
 #endif /* CONFIG_X86_64 */
 }
 
-static int get_reg_offset(struct insn *insn, struct pt_regs *regs,
-			  enum reg_type type)
+static const int pt_regoff[] = {
+	offsetof(struct pt_regs, ax),
+	offsetof(struct pt_regs, cx),
+	offsetof(struct pt_regs, dx),
+	offsetof(struct pt_regs, bx),
+	offsetof(struct pt_regs, sp),
+	offsetof(struct pt_regs, bp),
+	offsetof(struct pt_regs, si),
+	offsetof(struct pt_regs, di),
+#ifdef CONFIG_X86_64
+	offsetof(struct pt_regs, r8),
+	offsetof(struct pt_regs, r9),
+	offsetof(struct pt_regs, r10),
+	offsetof(struct pt_regs, r11),
+	offsetof(struct pt_regs, r12),
+	offsetof(struct pt_regs, r13),
+	offsetof(struct pt_regs, r14),
+	offsetof(struct pt_regs, r15),
+#else
+	offsetof(struct pt_regs, ds),
+	offsetof(struct pt_regs, es),
+	offsetof(struct pt_regs, fs),
+	offsetof(struct pt_regs, gs),
+#endif
+};
+
+int pt_regs_offset(struct pt_regs *regs, int regno)
+{
+	if ((unsigned)regno < ARRAY_SIZE(pt_regoff))
+		return pt_regoff[regno];
+	return -EDOM;
+}
+
+static int get_regno(struct insn *insn, enum reg_type type)
 {
+	int nr_registers = ARRAY_SIZE(pt_regoff);
 	int regno = 0;
 
-	static const int regoff[] = {
-		offsetof(struct pt_regs, ax),
-		offsetof(struct pt_regs, cx),
-		offsetof(struct pt_regs, dx),
-		offsetof(struct pt_regs, bx),
-		offsetof(struct pt_regs, sp),
-		offsetof(struct pt_regs, bp),
-		offsetof(struct pt_regs, si),
-		offsetof(struct pt_regs, di),
-#ifdef CONFIG_X86_64
-		offsetof(struct pt_regs, r8),
-		offsetof(struct pt_regs, r9),
-		offsetof(struct pt_regs, r10),
-		offsetof(struct pt_regs, r11),
-		offsetof(struct pt_regs, r12),
-		offsetof(struct pt_regs, r13),
-		offsetof(struct pt_regs, r14),
-		offsetof(struct pt_regs, r15),
-#endif
-	};
-	int nr_registers = ARRAY_SIZE(regoff);
 	/*
 	 * Don't possibly decode a 32-bit instructions as
 	 * reading a 64-bit-only register.
@@ -503,7 +515,18 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs,
 		WARN_ONCE(1, "decoded an instruction with an invalid register");
 		return -EINVAL;
 	}
-	return regoff[regno];
+	return regno;
+}
+
+static int get_reg_offset(struct insn *insn, struct pt_regs *regs,
+			  enum reg_type type)
+{
+	int regno = get_regno(insn, type);
+
+	if (regno < 0)
+		return regno;
+
+	return pt_regs_offset(regs, regno);
 }
 
 /**
diff --git a/arch/x86/lib/iomap_copy_64.S b/arch/x86/lib/iomap_copy_64.S
index cb5a1964506b..a1f9416bf67a 100644
--- a/arch/x86/lib/iomap_copy_64.S
+++ b/arch/x86/lib/iomap_copy_64.S
@@ -11,5 +11,5 @@
 SYM_FUNC_START(__iowrite32_copy)
 	movl %edx,%ecx
 	rep movsd
-	ret
+	RET
 SYM_FUNC_END(__iowrite32_copy)
diff --git a/arch/x86/lib/memcpy_32.c b/arch/x86/lib/memcpy_32.c
index e565d1c9019e..3a6e6cfe8c35 100644
--- a/arch/x86/lib/memcpy_32.c
+++ b/arch/x86/lib/memcpy_32.c
@@ -7,11 +7,7 @@
 
 __visible void *memcpy(void *to, const void *from, size_t n)
 {
-#if defined(CONFIG_X86_USE_3DNOW) && !defined(CONFIG_FORTIFY_SOURCE)
-	return __memcpy3d(to, from, n);
-#else
 	return __memcpy(to, from, n);
-#endif
 }
 EXPORT_SYMBOL(memcpy);
 
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 1cc9da6e29c7..59cf2343f3d9 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -39,7 +39,7 @@ SYM_FUNC_START_WEAK(memcpy)
 	rep movsq
 	movl %edx, %ecx
 	rep movsb
-	ret
+	RET
 SYM_FUNC_END(memcpy)
 SYM_FUNC_END_ALIAS(__memcpy)
 EXPORT_SYMBOL(memcpy)
@@ -53,7 +53,7 @@ SYM_FUNC_START_LOCAL(memcpy_erms)
 	movq %rdi, %rax
 	movq %rdx, %rcx
 	rep movsb
-	ret
+	RET
 SYM_FUNC_END(memcpy_erms)
 
 SYM_FUNC_START_LOCAL(memcpy_orig)
@@ -137,7 +137,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig)
 	movq %r9,	1*8(%rdi)
 	movq %r10,	-2*8(%rdi, %rdx)
 	movq %r11,	-1*8(%rdi, %rdx)
-	retq
+	RET
 	.p2align 4
 .Lless_16bytes:
 	cmpl $8,	%edx
@@ -149,7 +149,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig)
 	movq -1*8(%rsi, %rdx),	%r9
 	movq %r8,	0*8(%rdi)
 	movq %r9,	-1*8(%rdi, %rdx)
-	retq
+	RET
 	.p2align 4
 .Lless_8bytes:
 	cmpl $4,	%edx
@@ -162,7 +162,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig)
 	movl -4(%rsi, %rdx), %r8d
 	movl %ecx, (%rdi)
 	movl %r8d, -4(%rdi, %rdx)
-	retq
+	RET
 	.p2align 4
 .Lless_3bytes:
 	subl $1, %edx
@@ -180,7 +180,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig)
 	movb %cl, (%rdi)
 
 .Lend:
-	retq
+	RET
 SYM_FUNC_END(memcpy_orig)
 
 .popsection
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 64801010d312..50ea390df712 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -40,7 +40,7 @@ SYM_FUNC_START(__memmove)
 	/* FSRM implies ERMS => no length checks, do the copy directly */
 .Lmemmove_begin_forward:
 	ALTERNATIVE "cmp $0x20, %rdx; jb 1f", "", X86_FEATURE_FSRM
-	ALTERNATIVE "", "movq %rdx, %rcx; rep movsb; retq", X86_FEATURE_ERMS
+	ALTERNATIVE "", __stringify(movq %rdx, %rcx; rep movsb; RET), X86_FEATURE_ERMS
 
 	/*
 	 * movsq instruction have many startup latency
@@ -205,7 +205,7 @@ SYM_FUNC_START(__memmove)
 	movb (%rsi), %r11b
 	movb %r11b, (%rdi)
 13:
-	retq
+	RET
 SYM_FUNC_END(__memmove)
 SYM_FUNC_END_ALIAS(memmove)
 EXPORT_SYMBOL(__memmove)
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 9827ae267f96..d624f2bc42f1 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -40,7 +40,7 @@ SYM_FUNC_START(__memset)
 	movl %edx,%ecx
 	rep stosb
 	movq %r9,%rax
-	ret
+	RET
 SYM_FUNC_END(__memset)
 SYM_FUNC_END_ALIAS(memset)
 EXPORT_SYMBOL(memset)
@@ -63,7 +63,7 @@ SYM_FUNC_START_LOCAL(memset_erms)
 	movq %rdx,%rcx
 	rep stosb
 	movq %r9,%rax
-	ret
+	RET
 SYM_FUNC_END(memset_erms)
 
 SYM_FUNC_START_LOCAL(memset_orig)
@@ -125,7 +125,7 @@ SYM_FUNC_START_LOCAL(memset_orig)
 
 .Lende:
 	movq	%r10,%rax
-	ret
+	RET
 
 .Lbad_alignment:
 	cmpq $7,%rdx
diff --git a/arch/x86/lib/mmx_32.c b/arch/x86/lib/mmx_32.c
index cc5f4ea943d3..e69de29bb2d1 100644
--- a/arch/x86/lib/mmx_32.c
+++ b/arch/x86/lib/mmx_32.c
@@ -1,388 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- *	MMX 3DNow! library helper functions
- *
- *	To do:
- *	We can use MMX just for prefetch in IRQ's. This may be a win.
- *		(reported so on K6-III)
- *	We should use a better code neutral filler for the short jump
- *		leal ebx. [ebx] is apparently best for K6-2, but Cyrix ??
- *	We also want to clobber the filler register so we don't get any
- *		register forwarding stalls on the filler.
- *
- *	Add *user handling. Checksums are not a win with MMX on any CPU
- *	tested so far for any MMX solution figured.
- *
- *	22/09/2000 - Arjan van de Ven
- *		Improved for non-engineering-sample Athlons
- *
- */
-#include <linux/hardirq.h>
-#include <linux/string.h>
-#include <linux/export.h>
-#include <linux/sched.h>
-#include <linux/types.h>
-
-#include <asm/fpu/api.h>
-#include <asm/asm.h>
-
-/*
- * Use KFPU_387.  MMX instructions are not affected by MXCSR,
- * but both AMD and Intel documentation states that even integer MMX
- * operations will result in #MF if an exception is pending in FCW.
- *
- * EMMS is not needed afterwards because, after calling kernel_fpu_end(),
- * any subsequent user of the 387 stack will reinitialize it using
- * KFPU_387.
- */
-
-void *_mmx_memcpy(void *to, const void *from, size_t len)
-{
-	void *p;
-	int i;
-
-	if (unlikely(in_interrupt()))
-		return __memcpy(to, from, len);
-
-	p = to;
-	i = len >> 6; /* len/64 */
-
-	kernel_fpu_begin_mask(KFPU_387);
-
-	__asm__ __volatile__ (
-		"1: prefetch (%0)\n"		/* This set is 28 bytes */
-		"   prefetch 64(%0)\n"
-		"   prefetch 128(%0)\n"
-		"   prefetch 192(%0)\n"
-		"   prefetch 256(%0)\n"
-		"2:  \n"
-		".section .fixup, \"ax\"\n"
-		"3: movw $0x1AEB, 1b\n"	/* jmp on 26 bytes */
-		"   jmp 2b\n"
-		".previous\n"
-			_ASM_EXTABLE(1b, 3b)
-			: : "r" (from));
-
-	for ( ; i > 5; i--) {
-		__asm__ __volatile__ (
-		"1:  prefetch 320(%0)\n"
-		"2:  movq (%0), %%mm0\n"
-		"  movq 8(%0), %%mm1\n"
-		"  movq 16(%0), %%mm2\n"
-		"  movq 24(%0), %%mm3\n"
-		"  movq %%mm0, (%1)\n"
-		"  movq %%mm1, 8(%1)\n"
-		"  movq %%mm2, 16(%1)\n"
-		"  movq %%mm3, 24(%1)\n"
-		"  movq 32(%0), %%mm0\n"
-		"  movq 40(%0), %%mm1\n"
-		"  movq 48(%0), %%mm2\n"
-		"  movq 56(%0), %%mm3\n"
-		"  movq %%mm0, 32(%1)\n"
-		"  movq %%mm1, 40(%1)\n"
-		"  movq %%mm2, 48(%1)\n"
-		"  movq %%mm3, 56(%1)\n"
-		".section .fixup, \"ax\"\n"
-		"3: movw $0x05EB, 1b\n"	/* jmp on 5 bytes */
-		"   jmp 2b\n"
-		".previous\n"
-			_ASM_EXTABLE(1b, 3b)
-			: : "r" (from), "r" (to) : "memory");
-
-		from += 64;
-		to += 64;
-	}
-
-	for ( ; i > 0; i--) {
-		__asm__ __volatile__ (
-		"  movq (%0), %%mm0\n"
-		"  movq 8(%0), %%mm1\n"
-		"  movq 16(%0), %%mm2\n"
-		"  movq 24(%0), %%mm3\n"
-		"  movq %%mm0, (%1)\n"
-		"  movq %%mm1, 8(%1)\n"
-		"  movq %%mm2, 16(%1)\n"
-		"  movq %%mm3, 24(%1)\n"
-		"  movq 32(%0), %%mm0\n"
-		"  movq 40(%0), %%mm1\n"
-		"  movq 48(%0), %%mm2\n"
-		"  movq 56(%0), %%mm3\n"
-		"  movq %%mm0, 32(%1)\n"
-		"  movq %%mm1, 40(%1)\n"
-		"  movq %%mm2, 48(%1)\n"
-		"  movq %%mm3, 56(%1)\n"
-			: : "r" (from), "r" (to) : "memory");
-
-		from += 64;
-		to += 64;
-	}
-	/*
-	 * Now do the tail of the block:
-	 */
-	__memcpy(to, from, len & 63);
-	kernel_fpu_end();
-
-	return p;
-}
-EXPORT_SYMBOL(_mmx_memcpy);
-
-#ifdef CONFIG_MK7
-
-/*
- *	The K7 has streaming cache bypass load/store. The Cyrix III, K6 and
- *	other MMX using processors do not.
- */
-
-static void fast_clear_page(void *page)
-{
-	int i;
-
-	kernel_fpu_begin_mask(KFPU_387);
-
-	__asm__ __volatile__ (
-		"  pxor %%mm0, %%mm0\n" : :
-	);
-
-	for (i = 0; i < 4096/64; i++) {
-		__asm__ __volatile__ (
-		"  movntq %%mm0, (%0)\n"
-		"  movntq %%mm0, 8(%0)\n"
-		"  movntq %%mm0, 16(%0)\n"
-		"  movntq %%mm0, 24(%0)\n"
-		"  movntq %%mm0, 32(%0)\n"
-		"  movntq %%mm0, 40(%0)\n"
-		"  movntq %%mm0, 48(%0)\n"
-		"  movntq %%mm0, 56(%0)\n"
-		: : "r" (page) : "memory");
-		page += 64;
-	}
-
-	/*
-	 * Since movntq is weakly-ordered, a "sfence" is needed to become
-	 * ordered again:
-	 */
-	__asm__ __volatile__("sfence\n"::);
-
-	kernel_fpu_end();
-}
-
-static void fast_copy_page(void *to, void *from)
-{
-	int i;
-
-	kernel_fpu_begin_mask(KFPU_387);
-
-	/*
-	 * maybe the prefetch stuff can go before the expensive fnsave...
-	 * but that is for later. -AV
-	 */
-	__asm__ __volatile__(
-		"1: prefetch (%0)\n"
-		"   prefetch 64(%0)\n"
-		"   prefetch 128(%0)\n"
-		"   prefetch 192(%0)\n"
-		"   prefetch 256(%0)\n"
-		"2:  \n"
-		".section .fixup, \"ax\"\n"
-		"3: movw $0x1AEB, 1b\n"	/* jmp on 26 bytes */
-		"   jmp 2b\n"
-		".previous\n"
-			_ASM_EXTABLE(1b, 3b) : : "r" (from));
-
-	for (i = 0; i < (4096-320)/64; i++) {
-		__asm__ __volatile__ (
-		"1: prefetch 320(%0)\n"
-		"2: movq (%0), %%mm0\n"
-		"   movntq %%mm0, (%1)\n"
-		"   movq 8(%0), %%mm1\n"
-		"   movntq %%mm1, 8(%1)\n"
-		"   movq 16(%0), %%mm2\n"
-		"   movntq %%mm2, 16(%1)\n"
-		"   movq 24(%0), %%mm3\n"
-		"   movntq %%mm3, 24(%1)\n"
-		"   movq 32(%0), %%mm4\n"
-		"   movntq %%mm4, 32(%1)\n"
-		"   movq 40(%0), %%mm5\n"
-		"   movntq %%mm5, 40(%1)\n"
-		"   movq 48(%0), %%mm6\n"
-		"   movntq %%mm6, 48(%1)\n"
-		"   movq 56(%0), %%mm7\n"
-		"   movntq %%mm7, 56(%1)\n"
-		".section .fixup, \"ax\"\n"
-		"3: movw $0x05EB, 1b\n"	/* jmp on 5 bytes */
-		"   jmp 2b\n"
-		".previous\n"
-		_ASM_EXTABLE(1b, 3b) : : "r" (from), "r" (to) : "memory");
-
-		from += 64;
-		to += 64;
-	}
-
-	for (i = (4096-320)/64; i < 4096/64; i++) {
-		__asm__ __volatile__ (
-		"2: movq (%0), %%mm0\n"
-		"   movntq %%mm0, (%1)\n"
-		"   movq 8(%0), %%mm1\n"
-		"   movntq %%mm1, 8(%1)\n"
-		"   movq 16(%0), %%mm2\n"
-		"   movntq %%mm2, 16(%1)\n"
-		"   movq 24(%0), %%mm3\n"
-		"   movntq %%mm3, 24(%1)\n"
-		"   movq 32(%0), %%mm4\n"
-		"   movntq %%mm4, 32(%1)\n"
-		"   movq 40(%0), %%mm5\n"
-		"   movntq %%mm5, 40(%1)\n"
-		"   movq 48(%0), %%mm6\n"
-		"   movntq %%mm6, 48(%1)\n"
-		"   movq 56(%0), %%mm7\n"
-		"   movntq %%mm7, 56(%1)\n"
-			: : "r" (from), "r" (to) : "memory");
-		from += 64;
-		to += 64;
-	}
-	/*
-	 * Since movntq is weakly-ordered, a "sfence" is needed to become
-	 * ordered again:
-	 */
-	__asm__ __volatile__("sfence \n"::);
-	kernel_fpu_end();
-}
-
-#else /* CONFIG_MK7 */
-
-/*
- *	Generic MMX implementation without K7 specific streaming
- */
-static void fast_clear_page(void *page)
-{
-	int i;
-
-	kernel_fpu_begin_mask(KFPU_387);
-
-	__asm__ __volatile__ (
-		"  pxor %%mm0, %%mm0\n" : :
-	);
-
-	for (i = 0; i < 4096/128; i++) {
-		__asm__ __volatile__ (
-		"  movq %%mm0, (%0)\n"
-		"  movq %%mm0, 8(%0)\n"
-		"  movq %%mm0, 16(%0)\n"
-		"  movq %%mm0, 24(%0)\n"
-		"  movq %%mm0, 32(%0)\n"
-		"  movq %%mm0, 40(%0)\n"
-		"  movq %%mm0, 48(%0)\n"
-		"  movq %%mm0, 56(%0)\n"
-		"  movq %%mm0, 64(%0)\n"
-		"  movq %%mm0, 72(%0)\n"
-		"  movq %%mm0, 80(%0)\n"
-		"  movq %%mm0, 88(%0)\n"
-		"  movq %%mm0, 96(%0)\n"
-		"  movq %%mm0, 104(%0)\n"
-		"  movq %%mm0, 112(%0)\n"
-		"  movq %%mm0, 120(%0)\n"
-			: : "r" (page) : "memory");
-		page += 128;
-	}
-
-	kernel_fpu_end();
-}
-
-static void fast_copy_page(void *to, void *from)
-{
-	int i;
-
-	kernel_fpu_begin_mask(KFPU_387);
-
-	__asm__ __volatile__ (
-		"1: prefetch (%0)\n"
-		"   prefetch 64(%0)\n"
-		"   prefetch 128(%0)\n"
-		"   prefetch 192(%0)\n"
-		"   prefetch 256(%0)\n"
-		"2:  \n"
-		".section .fixup, \"ax\"\n"
-		"3: movw $0x1AEB, 1b\n"	/* jmp on 26 bytes */
-		"   jmp 2b\n"
-		".previous\n"
-			_ASM_EXTABLE(1b, 3b) : : "r" (from));
-
-	for (i = 0; i < 4096/64; i++) {
-		__asm__ __volatile__ (
-		"1: prefetch 320(%0)\n"
-		"2: movq (%0), %%mm0\n"
-		"   movq 8(%0), %%mm1\n"
-		"   movq 16(%0), %%mm2\n"
-		"   movq 24(%0), %%mm3\n"
-		"   movq %%mm0, (%1)\n"
-		"   movq %%mm1, 8(%1)\n"
-		"   movq %%mm2, 16(%1)\n"
-		"   movq %%mm3, 24(%1)\n"
-		"   movq 32(%0), %%mm0\n"
-		"   movq 40(%0), %%mm1\n"
-		"   movq 48(%0), %%mm2\n"
-		"   movq 56(%0), %%mm3\n"
-		"   movq %%mm0, 32(%1)\n"
-		"   movq %%mm1, 40(%1)\n"
-		"   movq %%mm2, 48(%1)\n"
-		"   movq %%mm3, 56(%1)\n"
-		".section .fixup, \"ax\"\n"
-		"3: movw $0x05EB, 1b\n"	/* jmp on 5 bytes */
-		"   jmp 2b\n"
-		".previous\n"
-			_ASM_EXTABLE(1b, 3b)
-			: : "r" (from), "r" (to) : "memory");
-
-		from += 64;
-		to += 64;
-	}
-	kernel_fpu_end();
-}
-
-#endif /* !CONFIG_MK7 */
-
-/*
- * Favour MMX for page clear and copy:
- */
-static void slow_zero_page(void *page)
-{
-	int d0, d1;
-
-	__asm__ __volatile__(
-		"cld\n\t"
-		"rep ; stosl"
-
-			: "=&c" (d0), "=&D" (d1)
-			:"a" (0), "1" (page), "0" (1024)
-			:"memory");
-}
-
-void mmx_clear_page(void *page)
-{
-	if (unlikely(in_interrupt()))
-		slow_zero_page(page);
-	else
-		fast_clear_page(page);
-}
-EXPORT_SYMBOL(mmx_clear_page);
-
-static void slow_copy_page(void *to, void *from)
-{
-	int d0, d1, d2;
-
-	__asm__ __volatile__(
-		"cld\n\t"
-		"rep ; movsl"
-		: "=&c" (d0), "=&D" (d1), "=&S" (d2)
-		: "0" (1024), "1" ((long) to), "2" ((long) from)
-		: "memory");
-}
-
-void mmx_copy_page(void *to, void *from)
-{
-	if (unlikely(in_interrupt()))
-		slow_copy_page(to, from);
-	else
-		fast_copy_page(to, from);
-}
-EXPORT_SYMBOL(mmx_copy_page);
diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S
index a2b9caa5274c..ebd259f31496 100644
--- a/arch/x86/lib/msr-reg.S
+++ b/arch/x86/lib/msr-reg.S
@@ -35,7 +35,7 @@ SYM_FUNC_START(\op\()_safe_regs)
 	movl    %edi, 28(%r10)
 	popq %r12
 	popq %rbx
-	ret
+	RET
 3:
 	movl    $-EIO, %r11d
 	jmp     2b
@@ -77,7 +77,7 @@ SYM_FUNC_START(\op\()_safe_regs)
 	popl %esi
 	popl %ebp
 	popl %ebx
-	ret
+	RET
 3:
 	movl    $-EIO, 4(%esp)
 	jmp     2b
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index 0ea344c5ea43..ecb2049c1273 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -52,7 +52,7 @@ SYM_INNER_LABEL(__put_user_nocheck_1, SYM_L_GLOBAL)
 1:	movb %al,(%_ASM_CX)
 	xor %ecx,%ecx
 	ASM_CLAC
-	ret
+	RET
 SYM_FUNC_END(__put_user_1)
 EXPORT_SYMBOL(__put_user_1)
 EXPORT_SYMBOL(__put_user_nocheck_1)
@@ -66,7 +66,7 @@ SYM_INNER_LABEL(__put_user_nocheck_2, SYM_L_GLOBAL)
 2:	movw %ax,(%_ASM_CX)
 	xor %ecx,%ecx
 	ASM_CLAC
-	ret
+	RET
 SYM_FUNC_END(__put_user_2)
 EXPORT_SYMBOL(__put_user_2)
 EXPORT_SYMBOL(__put_user_nocheck_2)
@@ -80,7 +80,7 @@ SYM_INNER_LABEL(__put_user_nocheck_4, SYM_L_GLOBAL)
 3:	movl %eax,(%_ASM_CX)
 	xor %ecx,%ecx
 	ASM_CLAC
-	ret
+	RET
 SYM_FUNC_END(__put_user_4)
 EXPORT_SYMBOL(__put_user_4)
 EXPORT_SYMBOL(__put_user_nocheck_4)
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index cf0b39f97adc..89b3fb244e15 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -23,7 +23,7 @@
 .Ldo_rop_\@:
 	mov     %\reg, (%_ASM_SP)
 	UNWIND_HINT_FUNC
-	ret
+	RET
 .endm
 
 .macro THUNK reg
@@ -34,7 +34,7 @@ SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL)
 
 	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \
 		      __stringify(RETPOLINE \reg), X86_FEATURE_RETPOLINE, \
-		      __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_AMD
+		      __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg; int3), X86_FEATURE_RETPOLINE_AMD
 
 .endm
 
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 7d290777246d..422257c350c6 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -8,7 +8,6 @@
  */
 #include <linux/export.h>
 #include <linux/uaccess.h>
-#include <asm/mmx.h>
 #include <asm/asm.h>
 
 #ifdef CONFIG_X86_INTEL_USERCOPY
@@ -43,11 +42,7 @@ do {									\
 		"	movl %2,%0\n"					\
 		"1:	rep; stosb\n"					\
 		"2: " ASM_CLAC "\n"					\
-		".section .fixup,\"ax\"\n"				\
-		"3:	lea 0(%2,%0,4),%0\n"				\
-		"	jmp 2b\n"					\
-		".previous\n"						\
-		_ASM_EXTABLE_UA(0b, 3b)					\
+		_ASM_EXTABLE_TYPE_REG(0b, 2b, EX_TYPE_UCOPY_LEN4, %2)	\
 		_ASM_EXTABLE_UA(1b, 2b)					\
 		: "=&c"(size), "=&D" (__d0)				\
 		: "r"(size & 3), "0"(size / 4), "1"(addr), "a"(0));	\
@@ -149,10 +144,6 @@ __copy_user_intel(void __user *to, const void *from, unsigned long size)
 		       "36:    movl %%eax, %0\n"
 		       "37:    rep; movsb\n"
 		       "100:\n"
-		       ".section .fixup,\"ax\"\n"
-		       "101:   lea 0(%%eax,%0,4),%0\n"
-		       "       jmp 100b\n"
-		       ".previous\n"
 		       _ASM_EXTABLE_UA(1b, 100b)
 		       _ASM_EXTABLE_UA(2b, 100b)
 		       _ASM_EXTABLE_UA(3b, 100b)
@@ -190,7 +181,7 @@ __copy_user_intel(void __user *to, const void *from, unsigned long size)
 		       _ASM_EXTABLE_UA(35b, 100b)
 		       _ASM_EXTABLE_UA(36b, 100b)
 		       _ASM_EXTABLE_UA(37b, 100b)
-		       _ASM_EXTABLE_UA(99b, 101b)
+		       _ASM_EXTABLE_TYPE_REG(99b, 100b, EX_TYPE_UCOPY_LEN4, %%eax)
 		       : "=&c"(size), "=&D" (d0), "=&S" (d1)
 		       :  "1"(to), "2"(from), "0"(size)
 		       : "eax", "edx", "memory");
@@ -255,30 +246,26 @@ static unsigned long __copy_user_intel_nocache(void *to,
 	       "        movl %%eax,%0\n"
 	       "7:      rep; movsb\n"
 	       "8:\n"
-	       ".section .fixup,\"ax\"\n"
-	       "9:      lea 0(%%eax,%0,4),%0\n"
-	       "16:     jmp 8b\n"
-	       ".previous\n"
-	       _ASM_EXTABLE_UA(0b, 16b)
-	       _ASM_EXTABLE_UA(1b, 16b)
-	       _ASM_EXTABLE_UA(2b, 16b)
-	       _ASM_EXTABLE_UA(21b, 16b)
-	       _ASM_EXTABLE_UA(3b, 16b)
-	       _ASM_EXTABLE_UA(31b, 16b)
-	       _ASM_EXTABLE_UA(4b, 16b)
-	       _ASM_EXTABLE_UA(41b, 16b)
-	       _ASM_EXTABLE_UA(10b, 16b)
-	       _ASM_EXTABLE_UA(51b, 16b)
-	       _ASM_EXTABLE_UA(11b, 16b)
-	       _ASM_EXTABLE_UA(61b, 16b)
-	       _ASM_EXTABLE_UA(12b, 16b)
-	       _ASM_EXTABLE_UA(71b, 16b)
-	       _ASM_EXTABLE_UA(13b, 16b)
-	       _ASM_EXTABLE_UA(81b, 16b)
-	       _ASM_EXTABLE_UA(14b, 16b)
-	       _ASM_EXTABLE_UA(91b, 16b)
-	       _ASM_EXTABLE_UA(6b, 9b)
-	       _ASM_EXTABLE_UA(7b, 16b)
+	       _ASM_EXTABLE_UA(0b, 8b)
+	       _ASM_EXTABLE_UA(1b, 8b)
+	       _ASM_EXTABLE_UA(2b, 8b)
+	       _ASM_EXTABLE_UA(21b, 8b)
+	       _ASM_EXTABLE_UA(3b, 8b)
+	       _ASM_EXTABLE_UA(31b, 8b)
+	       _ASM_EXTABLE_UA(4b, 8b)
+	       _ASM_EXTABLE_UA(41b, 8b)
+	       _ASM_EXTABLE_UA(10b, 8b)
+	       _ASM_EXTABLE_UA(51b, 8b)
+	       _ASM_EXTABLE_UA(11b, 8b)
+	       _ASM_EXTABLE_UA(61b, 8b)
+	       _ASM_EXTABLE_UA(12b, 8b)
+	       _ASM_EXTABLE_UA(71b, 8b)
+	       _ASM_EXTABLE_UA(13b, 8b)
+	       _ASM_EXTABLE_UA(81b, 8b)
+	       _ASM_EXTABLE_UA(14b, 8b)
+	       _ASM_EXTABLE_UA(91b, 8b)
+	       _ASM_EXTABLE_TYPE_REG(6b, 8b, EX_TYPE_UCOPY_LEN4, %%eax)
+	       _ASM_EXTABLE_UA(7b, 8b)
 	       : "=&c"(size), "=&D" (d0), "=&S" (d1)
 	       :  "1"(to), "2"(from), "0"(size)
 	       : "eax", "edx", "memory");
@@ -315,14 +302,8 @@ do {									\
 		"	movl %3,%0\n"					\
 		"1:	rep; movsb\n"					\
 		"2:\n"							\
-		".section .fixup,\"ax\"\n"				\
-		"5:	addl %3,%0\n"					\
-		"	jmp 2b\n"					\
-		"3:	lea 0(%3,%0,4),%0\n"				\
-		"	jmp 2b\n"					\
-		".previous\n"						\
-		_ASM_EXTABLE_UA(4b, 5b)					\
-		_ASM_EXTABLE_UA(0b, 3b)					\
+		_ASM_EXTABLE_TYPE_REG(4b, 2b, EX_TYPE_UCOPY_LEN1, %3)	\
+		_ASM_EXTABLE_TYPE_REG(0b, 2b, EX_TYPE_UCOPY_LEN4, %3)	\
 		_ASM_EXTABLE_UA(1b, 2b)					\
 		: "=&c"(size), "=&D" (__d0), "=&S" (__d1), "=r"(__d2)	\
 		: "3"(size), "0"(size), "1"(to), "2"(from)		\
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index 508c81e97ab1..0402a749f3a0 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -35,12 +35,10 @@ unsigned long __clear_user(void __user *addr, unsigned long size)
 		"	incq   %[dst]\n"
 		"	decl %%ecx ; jnz  1b\n"
 		"2:\n"
-		".section .fixup,\"ax\"\n"
-		"3:	lea 0(%[size1],%[size8],8),%[size8]\n"
-		"	jmp 2b\n"
-		".previous\n"
-		_ASM_EXTABLE_UA(0b, 3b)
+
+		_ASM_EXTABLE_TYPE_REG(0b, 2b, EX_TYPE_UCOPY_LEN8, %[size1])
 		_ASM_EXTABLE_UA(1b, 2b)
+
 		: [size8] "=&c"(size), [dst] "=&D" (__d0)
 		: [size1] "r"(size & 7), "[size8]" (size / 8), "[dst]"(addr));
 	clac();
diff --git a/arch/x86/math-emu/div_Xsig.S b/arch/x86/math-emu/div_Xsig.S
index 951da2ad54bb..8c270ab415be 100644
--- a/arch/x86/math-emu/div_Xsig.S
+++ b/arch/x86/math-emu/div_Xsig.S
@@ -341,7 +341,7 @@ L_exit:
 	popl	%esi
 
 	leave
-	ret
+	RET
 
 
 #ifdef PARANOID
diff --git a/arch/x86/math-emu/div_small.S b/arch/x86/math-emu/div_small.S
index d047d1816abe..637439bfefa4 100644
--- a/arch/x86/math-emu/div_small.S
+++ b/arch/x86/math-emu/div_small.S
@@ -44,5 +44,5 @@ SYM_FUNC_START(FPU_div_small)
 	popl	%esi
 
 	leave
-	ret
+	RET
 SYM_FUNC_END(FPU_div_small)
diff --git a/arch/x86/math-emu/mul_Xsig.S b/arch/x86/math-emu/mul_Xsig.S
index 4afc7b1fa6e9..54a031b66142 100644
--- a/arch/x86/math-emu/mul_Xsig.S
+++ b/arch/x86/math-emu/mul_Xsig.S
@@ -62,7 +62,7 @@ SYM_FUNC_START(mul32_Xsig)
 
 	popl %esi
 	leave
-	ret
+	RET
 SYM_FUNC_END(mul32_Xsig)
 
 
@@ -115,7 +115,7 @@ SYM_FUNC_START(mul64_Xsig)
 
 	popl %esi
 	leave
-	ret
+	RET
 SYM_FUNC_END(mul64_Xsig)
 
 
@@ -175,5 +175,5 @@ SYM_FUNC_START(mul_Xsig_Xsig)
 
 	popl %esi
 	leave
-	ret
+	RET
 SYM_FUNC_END(mul_Xsig_Xsig)
diff --git a/arch/x86/math-emu/polynom_Xsig.S b/arch/x86/math-emu/polynom_Xsig.S
index 702315eecb86..35fd723fc0df 100644
--- a/arch/x86/math-emu/polynom_Xsig.S
+++ b/arch/x86/math-emu/polynom_Xsig.S
@@ -133,5 +133,5 @@ L_accum_done:
 	popl	%edi
 	popl	%esi
 	leave
-	ret
+	RET
 SYM_FUNC_END(polynomial_Xsig)
diff --git a/arch/x86/math-emu/reg_norm.S b/arch/x86/math-emu/reg_norm.S
index cad1d60b1e84..594936eeed67 100644
--- a/arch/x86/math-emu/reg_norm.S
+++ b/arch/x86/math-emu/reg_norm.S
@@ -72,7 +72,7 @@ L_exit_valid:
 L_exit:
 	popl	%ebx
 	leave
-	ret
+	RET
 
 
 L_zero:
@@ -138,7 +138,7 @@ L_exit_nuo_valid:
 
 	popl	%ebx
 	leave
-	ret
+	RET
 
 L_exit_nuo_zero:
 	movl	TAG_Zero,%eax
@@ -146,5 +146,5 @@ L_exit_nuo_zero:
 
 	popl	%ebx
 	leave
-	ret
+	RET
 SYM_FUNC_END(FPU_normalize_nuo)
diff --git a/arch/x86/math-emu/reg_round.S b/arch/x86/math-emu/reg_round.S
index 4a9fc3cc5a4d..0bb2a092161a 100644
--- a/arch/x86/math-emu/reg_round.S
+++ b/arch/x86/math-emu/reg_round.S
@@ -437,7 +437,7 @@ fpu_Arith_exit:
 	popl	%edi
 	popl	%esi
 	leave
-	ret
+	RET
 
 
 /*
diff --git a/arch/x86/math-emu/reg_u_add.S b/arch/x86/math-emu/reg_u_add.S
index 9c9e2c810afe..07247287a3af 100644
--- a/arch/x86/math-emu/reg_u_add.S
+++ b/arch/x86/math-emu/reg_u_add.S
@@ -164,6 +164,6 @@ L_exit:
 	popl	%edi
 	popl	%esi
 	leave
-	ret
+	RET
 #endif /* PARANOID */
 SYM_FUNC_END(FPU_u_add)
diff --git a/arch/x86/math-emu/reg_u_div.S b/arch/x86/math-emu/reg_u_div.S
index e2fb5c2644c5..b5a41e2fc484 100644
--- a/arch/x86/math-emu/reg_u_div.S
+++ b/arch/x86/math-emu/reg_u_div.S
@@ -468,7 +468,7 @@ L_exit:
 	popl	%esi
 
 	leave
-	ret
+	RET
 #endif /* PARANOID */ 
 
 SYM_FUNC_END(FPU_u_div)
diff --git a/arch/x86/math-emu/reg_u_mul.S b/arch/x86/math-emu/reg_u_mul.S
index 0c779c87ac5b..e2588b24b8c2 100644
--- a/arch/x86/math-emu/reg_u_mul.S
+++ b/arch/x86/math-emu/reg_u_mul.S
@@ -144,7 +144,7 @@ L_exit:
 	popl	%edi
 	popl	%esi
 	leave
-	ret
+	RET
 #endif /* PARANOID */ 
 
 SYM_FUNC_END(FPU_u_mul)
diff --git a/arch/x86/math-emu/reg_u_sub.S b/arch/x86/math-emu/reg_u_sub.S
index e9bb7c248649..4c900c29e4ff 100644
--- a/arch/x86/math-emu/reg_u_sub.S
+++ b/arch/x86/math-emu/reg_u_sub.S
@@ -270,5 +270,5 @@ L_exit:
 	popl	%edi
 	popl	%esi
 	leave
-	ret
+	RET
 SYM_FUNC_END(FPU_u_sub)
diff --git a/arch/x86/math-emu/round_Xsig.S b/arch/x86/math-emu/round_Xsig.S
index d9d7de8dbd7b..126c40473bad 100644
--- a/arch/x86/math-emu/round_Xsig.S
+++ b/arch/x86/math-emu/round_Xsig.S
@@ -78,7 +78,7 @@ L_exit:
 	popl	%esi
 	popl	%ebx
 	leave
-	ret
+	RET
 SYM_FUNC_END(round_Xsig)
 
 
@@ -138,5 +138,5 @@ L_n_exit:
 	popl	%esi
 	popl	%ebx
 	leave
-	ret
+	RET
 SYM_FUNC_END(norm_Xsig)
diff --git a/arch/x86/math-emu/shr_Xsig.S b/arch/x86/math-emu/shr_Xsig.S
index 726af985f758..f726bf6f6396 100644
--- a/arch/x86/math-emu/shr_Xsig.S
+++ b/arch/x86/math-emu/shr_Xsig.S
@@ -45,7 +45,7 @@ SYM_FUNC_START(shr_Xsig)
 	popl	%ebx
 	popl	%esi
 	leave
-	ret
+	RET
 
 L_more_than_31:
 	cmpl	$64,%ecx
@@ -61,7 +61,7 @@ L_more_than_31:
 	movl	$0,8(%esi)
 	popl	%esi
 	leave
-	ret
+	RET
 
 L_more_than_63:
 	cmpl	$96,%ecx
@@ -76,7 +76,7 @@ L_more_than_63:
 	movl	%edx,8(%esi)
 	popl	%esi
 	leave
-	ret
+	RET
 
 L_more_than_95:
 	xorl	%eax,%eax
@@ -85,5 +85,5 @@ L_more_than_95:
 	movl	%eax,8(%esi)
 	popl	%esi
 	leave
-	ret
+	RET
 SYM_FUNC_END(shr_Xsig)
diff --git a/arch/x86/math-emu/wm_shrx.S b/arch/x86/math-emu/wm_shrx.S
index 4fc89174caf0..f608a28a4c43 100644
--- a/arch/x86/math-emu/wm_shrx.S
+++ b/arch/x86/math-emu/wm_shrx.S
@@ -55,7 +55,7 @@ SYM_FUNC_START(FPU_shrx)
 	popl	%ebx
 	popl	%esi
 	leave
-	ret
+	RET
 
 L_more_than_31:
 	cmpl	$64,%ecx
@@ -70,7 +70,7 @@ L_more_than_31:
 	movl	$0,4(%esi)
 	popl	%esi
 	leave
-	ret
+	RET
 
 L_more_than_63:
 	cmpl	$96,%ecx
@@ -84,7 +84,7 @@ L_more_than_63:
 	movl	%edx,4(%esi)
 	popl	%esi
 	leave
-	ret
+	RET
 
 L_more_than_95:
 	xorl	%eax,%eax
@@ -92,7 +92,7 @@ L_more_than_95:
 	movl	%eax,4(%esi)
 	popl	%esi
 	leave
-	ret
+	RET
 SYM_FUNC_END(FPU_shrx)
 
 
@@ -146,7 +146,7 @@ SYM_FUNC_START(FPU_shrxs)
 	popl	%ebx
 	popl	%esi
 	leave
-	ret
+	RET
 
 /* Shift by [0..31] bits */
 Ls_less_than_32:
@@ -163,7 +163,7 @@ Ls_less_than_32:
 	popl	%ebx
 	popl	%esi
 	leave
-	ret
+	RET
 
 /* Shift by [64..95] bits */
 Ls_more_than_63:
@@ -189,7 +189,7 @@ Ls_more_than_63:
 	popl	%ebx
 	popl	%esi
 	leave
-	ret
+	RET
 
 Ls_more_than_95:
 /* Shift by [96..inf) bits */
@@ -203,5 +203,5 @@ Ls_more_than_95:
 	popl	%ebx
 	popl	%esi
 	leave
-	ret
+	RET
 SYM_FUNC_END(FPU_shrxs)
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 5cd2a88930a9..dba2197c05c3 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -2,12 +2,26 @@
 #include <linux/extable.h>
 #include <linux/uaccess.h>
 #include <linux/sched/debug.h>
+#include <linux/bitfield.h>
 #include <xen/xen.h>
 
 #include <asm/fpu/api.h>
 #include <asm/sev.h>
 #include <asm/traps.h>
 #include <asm/kdebug.h>
+#include <asm/insn-eval.h>
+#include <asm/sgx.h>
+
+static inline unsigned long *pt_regs_nr(struct pt_regs *regs, int nr)
+{
+	int reg_offset = pt_regs_offset(regs, nr);
+	static unsigned long __dummy;
+
+	if (WARN_ON_ONCE(reg_offset < 0))
+		return &__dummy;
+
+	return (unsigned long *)((unsigned long)regs + reg_offset);
+}
 
 static inline unsigned long
 ex_fixup_addr(const struct exception_table_entry *x)
@@ -15,10 +29,15 @@ ex_fixup_addr(const struct exception_table_entry *x)
 	return (unsigned long)&x->fixup + x->fixup;
 }
 
-static bool ex_handler_default(const struct exception_table_entry *fixup,
+static bool ex_handler_default(const struct exception_table_entry *e,
 			       struct pt_regs *regs)
 {
-	regs->ip = ex_fixup_addr(fixup);
+	if (e->data & EX_FLAG_CLEAR_AX)
+		regs->ax = 0;
+	if (e->data & EX_FLAG_CLEAR_DX)
+		regs->dx = 0;
+
+	regs->ip = ex_fixup_addr(e);
 	return true;
 }
 
@@ -29,6 +48,13 @@ static bool ex_handler_fault(const struct exception_table_entry *fixup,
 	return ex_handler_default(fixup, regs);
 }
 
+static bool ex_handler_sgx(const struct exception_table_entry *fixup,
+			   struct pt_regs *regs, int trapnr)
+{
+	regs->ax = trapnr | SGX_ENCLS_FAULT_FLAG;
+	return ex_handler_default(fixup, regs);
+}
+
 /*
  * Handler for when we fail to restore a task's FPU state.  We should never get
  * here because the FPU state of a task using the FPU (task->thread.fpu.state)
@@ -65,28 +91,29 @@ static bool ex_handler_copy(const struct exception_table_entry *fixup,
 	return ex_handler_fault(fixup, regs, trapnr);
 }
 
-static bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup,
-				    struct pt_regs *regs)
+static bool ex_handler_msr(const struct exception_table_entry *fixup,
+			   struct pt_regs *regs, bool wrmsr, bool safe, int reg)
 {
-	if (pr_warn_once("unchecked MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n",
+	if (!safe && wrmsr &&
+	    pr_warn_once("unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n",
+			 (unsigned int)regs->cx, (unsigned int)regs->dx,
+			 (unsigned int)regs->ax,  regs->ip, (void *)regs->ip))
+		show_stack_regs(regs);
+
+	if (!safe && !wrmsr &&
+	    pr_warn_once("unchecked MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n",
 			 (unsigned int)regs->cx, regs->ip, (void *)regs->ip))
 		show_stack_regs(regs);
 
-	/* Pretend that the read succeeded and returned 0. */
-	regs->ax = 0;
-	regs->dx = 0;
-	return ex_handler_default(fixup, regs);
-}
+	if (!wrmsr) {
+		/* Pretend that the read succeeded and returned 0. */
+		regs->ax = 0;
+		regs->dx = 0;
+	}
 
-static bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup,
-				    struct pt_regs *regs)
-{
-	if (pr_warn_once("unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n",
-			 (unsigned int)regs->cx, (unsigned int)regs->dx,
-			 (unsigned int)regs->ax,  regs->ip, (void *)regs->ip))
-		show_stack_regs(regs);
+	if (safe)
+		*pt_regs_nr(regs, reg) = -EIO;
 
-	/* Pretend that the write succeeded. */
 	return ex_handler_default(fixup, regs);
 }
 
@@ -99,17 +126,32 @@ static bool ex_handler_clear_fs(const struct exception_table_entry *fixup,
 	return ex_handler_default(fixup, regs);
 }
 
+static bool ex_handler_imm_reg(const struct exception_table_entry *fixup,
+			       struct pt_regs *regs, int reg, int imm)
+{
+	*pt_regs_nr(regs, reg) = (long)imm;
+	return ex_handler_default(fixup, regs);
+}
+
+static bool ex_handler_ucopy_len(const struct exception_table_entry *fixup,
+				  struct pt_regs *regs, int trapnr, int reg, int imm)
+{
+	regs->cx = imm * regs->cx + *pt_regs_nr(regs, reg);
+	return ex_handler_uaccess(fixup, regs, trapnr);
+}
+
 int ex_get_fixup_type(unsigned long ip)
 {
 	const struct exception_table_entry *e = search_exception_tables(ip);
 
-	return e ? e->type : EX_TYPE_NONE;
+	return e ? FIELD_GET(EX_DATA_TYPE_MASK, e->data) : EX_TYPE_NONE;
 }
 
 int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code,
 		    unsigned long fault_addr)
 {
 	const struct exception_table_entry *e;
+	int type, reg, imm;
 
 #ifdef CONFIG_PNPBIOS
 	if (unlikely(SEGMENT_IS_PNP_CODE(regs->cs))) {
@@ -129,7 +171,11 @@ int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code,
 	if (!e)
 		return 0;
 
-	switch (e->type) {
+	type = FIELD_GET(EX_DATA_TYPE_MASK, e->data);
+	reg  = FIELD_GET(EX_DATA_REG_MASK,  e->data);
+	imm  = FIELD_GET(EX_DATA_IMM_MASK,  e->data);
+
+	switch (type) {
 	case EX_TYPE_DEFAULT:
 	case EX_TYPE_DEFAULT_MCE_SAFE:
 		return ex_handler_default(e, regs);
@@ -144,18 +190,31 @@ int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code,
 		return ex_handler_clear_fs(e, regs);
 	case EX_TYPE_FPU_RESTORE:
 		return ex_handler_fprestore(e, regs);
-	case EX_TYPE_RDMSR:
-		return ex_handler_rdmsr_unsafe(e, regs);
-	case EX_TYPE_WRMSR:
-		return ex_handler_wrmsr_unsafe(e, regs);
 	case EX_TYPE_BPF:
 		return ex_handler_bpf(e, regs);
-	case EX_TYPE_RDMSR_IN_MCE:
-		ex_handler_msr_mce(regs, false);
-		break;
+	case EX_TYPE_WRMSR:
+		return ex_handler_msr(e, regs, true, false, reg);
+	case EX_TYPE_RDMSR:
+		return ex_handler_msr(e, regs, false, false, reg);
+	case EX_TYPE_WRMSR_SAFE:
+		return ex_handler_msr(e, regs, true, true, reg);
+	case EX_TYPE_RDMSR_SAFE:
+		return ex_handler_msr(e, regs, false, true, reg);
 	case EX_TYPE_WRMSR_IN_MCE:
 		ex_handler_msr_mce(regs, true);
 		break;
+	case EX_TYPE_RDMSR_IN_MCE:
+		ex_handler_msr_mce(regs, false);
+		break;
+	case EX_TYPE_POP_REG:
+		regs->sp += sizeof(long);
+		fallthrough;
+	case EX_TYPE_IMM_REG:
+		return ex_handler_imm_reg(e, regs, reg, imm);
+	case EX_TYPE_FAULT_SGX:
+		return ex_handler_sgx(e, regs, trapnr);
+	case EX_TYPE_UCOPY_LEN:
+		return ex_handler_ucopy_len(e, regs, trapnr, reg, imm);
 	}
 	BUG();
 }
diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S
index 17d292b7072f..3d1dba05fce4 100644
--- a/arch/x86/mm/mem_encrypt_boot.S
+++ b/arch/x86/mm/mem_encrypt_boot.S
@@ -65,7 +65,7 @@ SYM_FUNC_START(sme_encrypt_execute)
 	movq	%rbp, %rsp		/* Restore original stack pointer */
 	pop	%rbp
 
-	ret
+	RET
 SYM_FUNC_END(sme_encrypt_execute)
 
 SYM_FUNC_START(__enc_copy)
@@ -151,6 +151,6 @@ SYM_FUNC_START(__enc_copy)
 	pop	%r12
 	pop	%r15
 
-	ret
+	RET
 .L__enc_copy_end:
 SYM_FUNC_END(__enc_copy)
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index ce1f86f245c9..2b1e266ff95c 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1326,7 +1326,7 @@ st:			if (is_imm8(insn->off))
 				}
 				ex->insn = delta;
 
-				ex->type = EX_TYPE_BPF;
+				ex->data = EX_TYPE_BPF;
 
 				if (dst_reg > BPF_REG_9) {
 					pr_err("verifier error\n");
diff --git a/arch/x86/platform/efi/efi_stub_32.S b/arch/x86/platform/efi/efi_stub_32.S
index 09ec84f6ef51..f3cfdb1c9a35 100644
--- a/arch/x86/platform/efi/efi_stub_32.S
+++ b/arch/x86/platform/efi/efi_stub_32.S
@@ -56,5 +56,5 @@ SYM_FUNC_START(efi_call_svam)
 
 	movl	16(%esp), %ebx
 	leave
-	ret
+	RET
 SYM_FUNC_END(efi_call_svam)
diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S
index 90380a17ab23..2206b8bc47b8 100644
--- a/arch/x86/platform/efi/efi_stub_64.S
+++ b/arch/x86/platform/efi/efi_stub_64.S
@@ -23,5 +23,5 @@ SYM_FUNC_START(__efi_call)
 	mov %rsi, %rcx
 	CALL_NOSPEC rdi
 	leave
-	ret
+	RET
 SYM_FUNC_END(__efi_call)
diff --git a/arch/x86/platform/efi/efi_thunk_64.S b/arch/x86/platform/efi/efi_thunk_64.S
index 5b7c6e09954e..25799d768624 100644
--- a/arch/x86/platform/efi/efi_thunk_64.S
+++ b/arch/x86/platform/efi/efi_thunk_64.S
@@ -73,7 +73,7 @@ SYM_CODE_START(__efi64_thunk)
 1:	movq	0x20(%rsp), %rsp
 	pop	%rbx
 	pop	%rbp
-	retq
+	RET
 
 	.code32
 2:	pushl	$__KERNEL_CS
diff --git a/arch/x86/platform/olpc/xo1-wakeup.S b/arch/x86/platform/olpc/xo1-wakeup.S
index 75f4faff8468..3a5abffe5660 100644
--- a/arch/x86/platform/olpc/xo1-wakeup.S
+++ b/arch/x86/platform/olpc/xo1-wakeup.S
@@ -77,7 +77,7 @@ save_registers:
 	pushfl
 	popl saved_context_eflags
 
-	ret
+	RET
 
 restore_registers:
 	movl saved_context_ebp, %ebp
@@ -88,7 +88,7 @@ restore_registers:
 	pushl saved_context_eflags
 	popfl
 
-	ret
+	RET
 
 SYM_CODE_START(do_olpc_suspend_lowlevel)
 	call	save_processor_state
@@ -109,7 +109,7 @@ ret_point:
 
 	call	restore_registers
 	call	restore_processor_state
-	ret
+	RET
 SYM_CODE_END(do_olpc_suspend_lowlevel)
 
 .data
diff --git a/arch/x86/power/hibernate_asm_32.S b/arch/x86/power/hibernate_asm_32.S
index 8786653ad3c0..5606a15cf9a1 100644
--- a/arch/x86/power/hibernate_asm_32.S
+++ b/arch/x86/power/hibernate_asm_32.S
@@ -32,7 +32,7 @@ SYM_FUNC_START(swsusp_arch_suspend)
 	FRAME_BEGIN
 	call swsusp_save
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(swsusp_arch_suspend)
 
 SYM_CODE_START(restore_image)
@@ -108,5 +108,5 @@ SYM_FUNC_START(restore_registers)
 	/* tell the hibernation core that we've just restored the memory */
 	movl	%eax, in_suspend
 
-	ret
+	RET
 SYM_FUNC_END(restore_registers)
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index d9bed596d849..0a0539e1cc81 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -66,7 +66,7 @@ SYM_FUNC_START(restore_registers)
 	/* tell the hibernation core that we've just restored the memory */
 	movq	%rax, in_suspend(%rip)
 
-	ret
+	RET
 SYM_FUNC_END(restore_registers)
 
 SYM_FUNC_START(swsusp_arch_suspend)
@@ -96,7 +96,7 @@ SYM_FUNC_START(swsusp_arch_suspend)
 	FRAME_BEGIN
 	call swsusp_save
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(swsusp_arch_suspend)
 
 SYM_FUNC_START(restore_image)
diff --git a/arch/x86/um/checksum_32.S b/arch/x86/um/checksum_32.S
index 13f118dec74f..aed782ab7721 100644
--- a/arch/x86/um/checksum_32.S
+++ b/arch/x86/um/checksum_32.S
@@ -110,7 +110,7 @@ csum_partial:
 7:	
 	popl %ebx
 	popl %esi
-	ret
+	RET
 
 #else
 
@@ -208,7 +208,7 @@ csum_partial:
 80: 
 	popl %ebx
 	popl %esi
-	ret
+	RET
 				
 #endif
 	EXPORT_SYMBOL(csum_partial)
diff --git a/arch/x86/um/setjmp_32.S b/arch/x86/um/setjmp_32.S
index 62eaf8c80e04..2d991ddbcca5 100644
--- a/arch/x86/um/setjmp_32.S
+++ b/arch/x86/um/setjmp_32.S
@@ -34,7 +34,7 @@ kernel_setjmp:
 	movl %esi,12(%edx)
 	movl %edi,16(%edx)
 	movl %ecx,20(%edx)		# Return address
-	ret
+	RET
 
 	.size kernel_setjmp,.-kernel_setjmp
 
diff --git a/arch/x86/um/setjmp_64.S b/arch/x86/um/setjmp_64.S
index 1b5d40d4ff46..b46acb6a8ebd 100644
--- a/arch/x86/um/setjmp_64.S
+++ b/arch/x86/um/setjmp_64.S
@@ -33,7 +33,7 @@ kernel_setjmp:
 	movq %r14,40(%rdi)
 	movq %r15,48(%rdi)
 	movq %rsi,56(%rdi)		# Return address
-	ret
+	RET
 
 	.size kernel_setjmp,.-kernel_setjmp
 
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 444d824775f6..e730e6200e64 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -29,7 +29,7 @@
  */
 SYM_FUNC_START(xen_irq_disable_direct)
 	movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
-	ret
+	RET
 SYM_FUNC_END(xen_irq_disable_direct)
 
 /*
@@ -58,7 +58,7 @@ SYM_FUNC_START(check_events)
 	pop %rcx
 	pop %rax
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(check_events)
 
 /*
@@ -84,7 +84,7 @@ SYM_FUNC_START(xen_irq_enable_direct)
 	call check_events
 1:
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(xen_irq_enable_direct)
 
 /*
@@ -100,7 +100,7 @@ SYM_FUNC_START(xen_save_fl_direct)
 	testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
 	setz %ah
 	addb %ah, %ah
-	ret
+	RET
 SYM_FUNC_END(xen_save_fl_direct)
 
 SYM_FUNC_START(xen_read_cr2)
@@ -108,14 +108,14 @@ SYM_FUNC_START(xen_read_cr2)
 	_ASM_MOV PER_CPU_VAR(xen_vcpu), %_ASM_AX
 	_ASM_MOV XEN_vcpu_info_arch_cr2(%_ASM_AX), %_ASM_AX
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(xen_read_cr2);
 
 SYM_FUNC_START(xen_read_cr2_direct)
 	FRAME_BEGIN
 	_ASM_MOV PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_arch_cr2, %_ASM_AX
 	FRAME_END
-	ret
+	RET
 SYM_FUNC_END(xen_read_cr2_direct);
 .popsection
 
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 6a64496edefb..11d286529fe5 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -26,7 +26,7 @@ SYM_CODE_START(hypercall_page)
 	.rept (PAGE_SIZE / 32)
 		UNWIND_HINT_FUNC
 		.skip 31, 0x90
-		ret
+		RET
 	.endr
 
 #define HYPERCALL(n) \