Merge branch 'next' into for-linus

Prepare input updates for 4.15 merge window.

28 files changed, 805 insertions, 413 deletions

diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index 34b3fa2889d1..5f07333bb224 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -1,7 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0
 #
 # Arch-specific CryptoAPI modules.
 #
 
+OBJECT_FILES_NON_STANDARD := y
+
 avx_supported := $(call as-instr,vpxor %xmm0$(comma)%xmm0$(comma)%xmm0,yes,no)
 avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\
 				$(comma)4)$(comma)%ymm2,yes,no)
diff --git a/arch/x86/crypto/aes-x86_64-asm_64.S b/arch/x86/crypto/aes-x86_64-asm_64.S
index 910565547163..8739cf7795de 100644
--- a/arch/x86/crypto/aes-x86_64-asm_64.S
+++ b/arch/x86/crypto/aes-x86_64-asm_64.S
@@ -42,17 +42,15 @@
 #define R5E	%esi
 #define R6	%rdi
 #define R6E	%edi
-#define R7	%rbp
-#define R7E	%ebp
+#define R7	%r9	/* don't use %rbp; it breaks stack traces */
+#define R7E	%r9d
 #define R8	%r8
-#define R9	%r9
 #define R10	%r10
 #define R11	%r11
 
-#define prologue(FUNC,KEY,B128,B192,r1,r2,r3,r4,r5,r6,r7,r8,r9,r10,r11) \
+#define prologue(FUNC,KEY,B128,B192,r1,r2,r5,r6,r7,r8,r9,r10,r11) \
 	ENTRY(FUNC);			\
 	movq	r1,r2;			\
-	movq	r3,r4;			\
 	leaq	KEY+48(r8),r9;		\
 	movq	r10,r11;		\
 	movl	(r7),r5 ## E;		\
@@ -70,9 +68,8 @@
 	je	B192;			\
 	leaq	32(r9),r9;
 
-#define epilogue(FUNC,r1,r2,r3,r4,r5,r6,r7,r8,r9) \
+#define epilogue(FUNC,r1,r2,r5,r6,r7,r8,r9) \
 	movq	r1,r2;			\
-	movq	r3,r4;			\
 	movl	r5 ## E,(r9);		\
 	movl	r6 ## E,4(r9);		\
 	movl	r7 ## E,8(r9);		\
@@ -88,12 +85,12 @@
 	movl	TAB(,r6,4),r6 ## E;	\
 	roll	$16,r2 ## E;		\
 	shrl	$16,r4 ## E;		\
-	movzbl	r4 ## H,r7 ## E;	\
-	movzbl	r4 ## L,r4 ## E;	\
+	movzbl	r4 ## L,r7 ## E;	\
+	movzbl	r4 ## H,r4 ## E;	\
 	xorl	OFFSET(r8),ra ## E;	\
 	xorl	OFFSET+4(r8),rb ## E;	\
-	xorl	TAB+3072(,r7,4),r5 ## E;\
-	xorl	TAB+2048(,r4,4),r6 ## E;\
+	xorl	TAB+3072(,r4,4),r5 ## E;\
+	xorl	TAB+2048(,r7,4),r6 ## E;\
 	movzbl	r1 ## L,r7 ## E;	\
 	movzbl	r1 ## H,r4 ## E;	\
 	movl	TAB+1024(,r4,4),r4 ## E;\
@@ -101,19 +98,19 @@
 	roll	$16,r1 ## E;		\
 	shrl	$16,r3 ## E;		\
 	xorl	TAB(,r7,4),r5 ## E;	\
-	movzbl	r3 ## H,r7 ## E;	\
-	movzbl	r3 ## L,r3 ## E;	\
-	xorl	TAB+3072(,r7,4),r4 ## E;\
-	xorl	TAB+2048(,r3,4),r5 ## E;\
-	movzbl	r1 ## H,r7 ## E;	\
-	movzbl	r1 ## L,r3 ## E;	\
+	movzbl	r3 ## L,r7 ## E;	\
+	movzbl	r3 ## H,r3 ## E;	\
+	xorl	TAB+3072(,r3,4),r4 ## E;\
+	xorl	TAB+2048(,r7,4),r5 ## E;\
+	movzbl	r1 ## L,r7 ## E;	\
+	movzbl	r1 ## H,r3 ## E;	\
 	shrl	$16,r1 ## E;		\
-	xorl	TAB+3072(,r7,4),r6 ## E;\
-	movl	TAB+2048(,r3,4),r3 ## E;\
-	movzbl	r1 ## H,r7 ## E;	\
-	movzbl	r1 ## L,r1 ## E;	\
-	xorl	TAB+1024(,r7,4),r6 ## E;\
-	xorl	TAB(,r1,4),r3 ## E;	\
+	xorl	TAB+3072(,r3,4),r6 ## E;\
+	movl	TAB+2048(,r7,4),r3 ## E;\
+	movzbl	r1 ## L,r7 ## E;	\
+	movzbl	r1 ## H,r1 ## E;	\
+	xorl	TAB+1024(,r1,4),r6 ## E;\
+	xorl	TAB(,r7,4),r3 ## E;	\
 	movzbl	r2 ## H,r1 ## E;	\
 	movzbl	r2 ## L,r7 ## E;	\
 	shrl	$16,r2 ## E;		\
@@ -131,9 +128,9 @@
 	movl	r4 ## E,r2 ## E;
 
 #define entry(FUNC,KEY,B128,B192) \
-	prologue(FUNC,KEY,B128,B192,R2,R8,R7,R9,R1,R3,R4,R6,R10,R5,R11)
+	prologue(FUNC,KEY,B128,B192,R2,R8,R1,R3,R4,R6,R10,R5,R11)
 
-#define return(FUNC) epilogue(FUNC,R8,R2,R9,R7,R5,R6,R3,R4,R11)
+#define return(FUNC) epilogue(FUNC,R8,R2,R5,R6,R3,R4,R11)
 
 #define encrypt_round(TAB,OFFSET) \
 	round(TAB,OFFSET,R1,R2,R3,R4,R5,R6,R7,R10,R5,R6,R3,R4) \
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 3c465184ff8a..16627fec80b2 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -89,6 +89,29 @@ SHIFT_MASK: .octa 0x0f0e0d0c0b0a09080706050403020100
 ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
             .octa 0x00000000000000000000000000000000
 
+.section .rodata
+.align 16
+.type aad_shift_arr, @object
+.size aad_shift_arr, 272
+aad_shift_arr:
+        .octa     0xffffffffffffffffffffffffffffffff
+        .octa     0xffffffffffffffffffffffffffffff0C
+        .octa     0xffffffffffffffffffffffffffff0D0C
+        .octa     0xffffffffffffffffffffffffff0E0D0C
+        .octa     0xffffffffffffffffffffffff0F0E0D0C
+        .octa     0xffffffffffffffffffffff0C0B0A0908
+        .octa     0xffffffffffffffffffff0D0C0B0A0908
+        .octa     0xffffffffffffffffff0E0D0C0B0A0908
+        .octa     0xffffffffffffffff0F0E0D0C0B0A0908
+        .octa     0xffffffffffffff0C0B0A090807060504
+        .octa     0xffffffffffff0D0C0B0A090807060504
+        .octa     0xffffffffff0E0D0C0B0A090807060504
+        .octa     0xffffffff0F0E0D0C0B0A090807060504
+        .octa     0xffffff0C0B0A09080706050403020100
+        .octa     0xffff0D0C0B0A09080706050403020100
+        .octa     0xff0E0D0C0B0A09080706050403020100
+        .octa     0x0F0E0D0C0B0A09080706050403020100
+
 
 .text
 
@@ -252,32 +275,66 @@ XMM2 XMM3 XMM4 XMMDst TMP6 TMP7 i i_seq operation
 	mov	   arg8, %r12           # %r12 = aadLen
 	mov	   %r12, %r11
 	pxor	   %xmm\i, %xmm\i
+	pxor       \XMM2, \XMM2
 
-_get_AAD_loop\num_initial_blocks\operation:
-	movd	   (%r10), \TMP1
-	pslldq	   $12, \TMP1
-	psrldq	   $4, %xmm\i
+	cmp	   $16, %r11
+	jl	   _get_AAD_rest8\num_initial_blocks\operation
+_get_AAD_blocks\num_initial_blocks\operation:
+	movdqu	   (%r10), %xmm\i
+	PSHUFB_XMM %xmm14, %xmm\i # byte-reflect the AAD data
+	pxor	   %xmm\i, \XMM2
+	GHASH_MUL  \XMM2, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
+	add	   $16, %r10
+	sub	   $16, %r12
+	sub	   $16, %r11
+	cmp	   $16, %r11
+	jge	   _get_AAD_blocks\num_initial_blocks\operation
+
+	movdqu	   \XMM2, %xmm\i
+	cmp	   $0, %r11
+	je	   _get_AAD_done\num_initial_blocks\operation
+
+	pxor	   %xmm\i,%xmm\i
+
+	/* read the last <16B of AAD. since we have at least 4B of
+	data right after the AAD (the ICV, and maybe some CT), we can
+	read 4B/8B blocks safely, and then get rid of the extra stuff */
+_get_AAD_rest8\num_initial_blocks\operation:
+	cmp	   $4, %r11
+	jle	   _get_AAD_rest4\num_initial_blocks\operation
+	movq	   (%r10), \TMP1
+	add	   $8, %r10
+	sub	   $8, %r11
+	pslldq	   $8, \TMP1
+	psrldq	   $8, %xmm\i
 	pxor	   \TMP1, %xmm\i
+	jmp	   _get_AAD_rest8\num_initial_blocks\operation
+_get_AAD_rest4\num_initial_blocks\operation:
+	cmp	   $0, %r11
+	jle	   _get_AAD_rest0\num_initial_blocks\operation
+	mov	   (%r10), %eax
+	movq	   %rax, \TMP1
 	add	   $4, %r10
-	sub	   $4, %r12
-	jne	   _get_AAD_loop\num_initial_blocks\operation
-
-	cmp	   $16, %r11
-	je	   _get_AAD_loop2_done\num_initial_blocks\operation
-
-	mov	   $16, %r12
-_get_AAD_loop2\num_initial_blocks\operation:
+	sub	   $4, %r10
+	pslldq	   $12, \TMP1
 	psrldq	   $4, %xmm\i
-	sub	   $4, %r12
-	cmp	   %r11, %r12
-	jne	   _get_AAD_loop2\num_initial_blocks\operation
-
-_get_AAD_loop2_done\num_initial_blocks\operation:
+	pxor	   \TMP1, %xmm\i
+_get_AAD_rest0\num_initial_blocks\operation:
+	/* finalize: shift out the extra bytes we read, and align
+	left. since pslldq can only shift by an immediate, we use
+	vpshufb and an array of shuffle masks */
+	movq	   %r12, %r11
+	salq	   $4, %r11
+	movdqu	   aad_shift_arr(%r11), \TMP1
+	PSHUFB_XMM \TMP1, %xmm\i
+_get_AAD_rest_final\num_initial_blocks\operation:
 	PSHUFB_XMM   %xmm14, %xmm\i # byte-reflect the AAD data
+	pxor	   \XMM2, %xmm\i
+	GHASH_MUL  %xmm\i, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
 
+_get_AAD_done\num_initial_blocks\operation:
 	xor	   %r11, %r11 # initialise the data pointer offset as zero
-
-        # start AES for num_initial_blocks blocks
+	# start AES for num_initial_blocks blocks
 
 	mov	   %arg5, %rax                      # %rax = *Y0
 	movdqu	   (%rax), \XMM0                    # XMM0 = Y0
@@ -322,7 +379,7 @@ aes_loop_initial_dec\num_initial_blocks:
                 # prepare plaintext/ciphertext for GHASH computation
 .endr
 .endif
-	GHASH_MUL  %xmm\i, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
+
         # apply GHASH on num_initial_blocks blocks
 
 .if \i == 5
@@ -477,28 +534,66 @@ XMM2 XMM3 XMM4 XMMDst TMP6 TMP7 i i_seq operation
 	mov	   arg8, %r12           # %r12 = aadLen
 	mov	   %r12, %r11
 	pxor	   %xmm\i, %xmm\i
-_get_AAD_loop\num_initial_blocks\operation:
-	movd	   (%r10), \TMP1
-	pslldq	   $12, \TMP1
-	psrldq	   $4, %xmm\i
+	pxor	   \XMM2, \XMM2
+
+	cmp	   $16, %r11
+	jl	   _get_AAD_rest8\num_initial_blocks\operation
+_get_AAD_blocks\num_initial_blocks\operation:
+	movdqu	   (%r10), %xmm\i
+	PSHUFB_XMM   %xmm14, %xmm\i # byte-reflect the AAD data
+	pxor	   %xmm\i, \XMM2
+	GHASH_MUL  \XMM2, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
+	add	   $16, %r10
+	sub	   $16, %r12
+	sub	   $16, %r11
+	cmp	   $16, %r11
+	jge	   _get_AAD_blocks\num_initial_blocks\operation
+
+	movdqu	   \XMM2, %xmm\i
+	cmp	   $0, %r11
+	je	   _get_AAD_done\num_initial_blocks\operation
+
+	pxor	   %xmm\i,%xmm\i
+
+	/* read the last <16B of AAD. since we have at least 4B of
+	data right after the AAD (the ICV, and maybe some PT), we can
+	read 4B/8B blocks safely, and then get rid of the extra stuff */
+_get_AAD_rest8\num_initial_blocks\operation:
+	cmp	   $4, %r11
+	jle	   _get_AAD_rest4\num_initial_blocks\operation
+	movq	   (%r10), \TMP1
+	add	   $8, %r10
+	sub	   $8, %r11
+	pslldq	   $8, \TMP1
+	psrldq	   $8, %xmm\i
 	pxor	   \TMP1, %xmm\i
+	jmp	   _get_AAD_rest8\num_initial_blocks\operation
+_get_AAD_rest4\num_initial_blocks\operation:
+	cmp	   $0, %r11
+	jle	   _get_AAD_rest0\num_initial_blocks\operation
+	mov	   (%r10), %eax
+	movq	   %rax, \TMP1
 	add	   $4, %r10
-	sub	   $4, %r12
-	jne	   _get_AAD_loop\num_initial_blocks\operation
-	cmp	   $16, %r11
-	je	   _get_AAD_loop2_done\num_initial_blocks\operation
-	mov	   $16, %r12
-_get_AAD_loop2\num_initial_blocks\operation:
+	sub	   $4, %r10
+	pslldq	   $12, \TMP1
 	psrldq	   $4, %xmm\i
-	sub	   $4, %r12
-	cmp	   %r11, %r12
-	jne	   _get_AAD_loop2\num_initial_blocks\operation
-_get_AAD_loop2_done\num_initial_blocks\operation:
+	pxor	   \TMP1, %xmm\i
+_get_AAD_rest0\num_initial_blocks\operation:
+	/* finalize: shift out the extra bytes we read, and align
+	left. since pslldq can only shift by an immediate, we use
+	vpshufb and an array of shuffle masks */
+	movq	   %r12, %r11
+	salq	   $4, %r11
+	movdqu	   aad_shift_arr(%r11), \TMP1
+	PSHUFB_XMM \TMP1, %xmm\i
+_get_AAD_rest_final\num_initial_blocks\operation:
 	PSHUFB_XMM   %xmm14, %xmm\i # byte-reflect the AAD data
+	pxor	   \XMM2, %xmm\i
+	GHASH_MUL  %xmm\i, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
 
+_get_AAD_done\num_initial_blocks\operation:
 	xor	   %r11, %r11 # initialise the data pointer offset as zero
-
-        # start AES for num_initial_blocks blocks
+	# start AES for num_initial_blocks blocks
 
 	mov	   %arg5, %rax                      # %rax = *Y0
 	movdqu	   (%rax), \XMM0                    # XMM0 = Y0
@@ -543,7 +638,7 @@ aes_loop_initial_enc\num_initial_blocks:
 		# prepare plaintext/ciphertext for GHASH computation
 .endr
 .endif
-	GHASH_MUL  %xmm\i, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
+
         # apply GHASH on num_initial_blocks blocks
 
 .if \i == 5
@@ -1454,18 +1549,35 @@ _return_T_decrypt:
 	mov	arg10, %r11               # %r11 = auth_tag_len
 	cmp	$16, %r11
 	je	_T_16_decrypt
-	cmp	$12, %r11
-	je	_T_12_decrypt
+	cmp	$8, %r11
+	jl	_T_4_decrypt
 _T_8_decrypt:
 	MOVQ_R64_XMM	%xmm0, %rax
 	mov	%rax, (%r10)
-	jmp	_return_T_done_decrypt
-_T_12_decrypt:
-	MOVQ_R64_XMM	%xmm0, %rax
-	mov	%rax, (%r10)
+	add	$8, %r10
+	sub	$8, %r11
 	psrldq	$8, %xmm0
+	cmp	$0, %r11
+	je	_return_T_done_decrypt
+_T_4_decrypt:
+	movd	%xmm0, %eax
+	mov	%eax, (%r10)
+	add	$4, %r10
+	sub	$4, %r11
+	psrldq	$4, %xmm0
+	cmp	$0, %r11
+	je	_return_T_done_decrypt
+_T_123_decrypt:
 	movd	%xmm0, %eax
-	mov	%eax, 8(%r10)
+	cmp	$2, %r11
+	jl	_T_1_decrypt
+	mov	%ax, (%r10)
+	cmp	$2, %r11
+	je	_return_T_done_decrypt
+	add	$2, %r10
+	sar	$16, %eax
+_T_1_decrypt:
+	mov	%al, (%r10)
 	jmp	_return_T_done_decrypt
 _T_16_decrypt:
 	movdqu	%xmm0, (%r10)
@@ -1718,18 +1830,35 @@ _return_T_encrypt:
 	mov	arg10, %r11                    # %r11 = auth_tag_len
 	cmp	$16, %r11
 	je	_T_16_encrypt
-	cmp	$12, %r11
-	je	_T_12_encrypt
+	cmp	$8, %r11
+	jl	_T_4_encrypt
 _T_8_encrypt:
 	MOVQ_R64_XMM	%xmm0, %rax
 	mov	%rax, (%r10)
-	jmp	_return_T_done_encrypt
-_T_12_encrypt:
-	MOVQ_R64_XMM	%xmm0, %rax
-	mov	%rax, (%r10)
+	add	$8, %r10
+	sub	$8, %r11
 	psrldq	$8, %xmm0
+	cmp	$0, %r11
+	je	_return_T_done_encrypt
+_T_4_encrypt:
+	movd	%xmm0, %eax
+	mov	%eax, (%r10)
+	add	$4, %r10
+	sub	$4, %r11
+	psrldq	$4, %xmm0
+	cmp	$0, %r11
+	je	_return_T_done_encrypt
+_T_123_encrypt:
 	movd	%xmm0, %eax
-	mov	%eax, 8(%r10)
+	cmp	$2, %r11
+	jl	_T_1_encrypt
+	mov	%ax, (%r10)
+	cmp	$2, %r11
+	je	_return_T_done_encrypt
+	add	$2, %r10
+	sar	$16, %eax
+_T_1_encrypt:
+	mov	%al, (%r10)
 	jmp	_return_T_done_encrypt
 _T_16_encrypt:
 	movdqu	%xmm0, (%r10)
diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S
index d664382c6e56..faecb1518bf8 100644
--- a/arch/x86/crypto/aesni-intel_avx-x86_64.S
+++ b/arch/x86/crypto/aesni-intel_avx-x86_64.S
@@ -155,6 +155,30 @@ SHIFT_MASK:      .octa     0x0f0e0d0c0b0a09080706050403020100
 ALL_F:           .octa     0xffffffffffffffffffffffffffffffff
                  .octa     0x00000000000000000000000000000000
 
+.section .rodata
+.align 16
+.type aad_shift_arr, @object
+.size aad_shift_arr, 272
+aad_shift_arr:
+        .octa     0xffffffffffffffffffffffffffffffff
+        .octa     0xffffffffffffffffffffffffffffff0C
+        .octa     0xffffffffffffffffffffffffffff0D0C
+        .octa     0xffffffffffffffffffffffffff0E0D0C
+        .octa     0xffffffffffffffffffffffff0F0E0D0C
+        .octa     0xffffffffffffffffffffff0C0B0A0908
+        .octa     0xffffffffffffffffffff0D0C0B0A0908
+        .octa     0xffffffffffffffffff0E0D0C0B0A0908
+        .octa     0xffffffffffffffff0F0E0D0C0B0A0908
+        .octa     0xffffffffffffff0C0B0A090807060504
+        .octa     0xffffffffffff0D0C0B0A090807060504
+        .octa     0xffffffffff0E0D0C0B0A090807060504
+        .octa     0xffffffff0F0E0D0C0B0A090807060504
+        .octa     0xffffff0C0B0A09080706050403020100
+        .octa     0xffff0D0C0B0A09080706050403020100
+        .octa     0xff0E0D0C0B0A09080706050403020100
+        .octa     0x0F0E0D0C0B0A09080706050403020100
+
+
 .text
 
 
@@ -372,41 +396,72 @@ VARIABLE_OFFSET = 16*8
 
 .macro INITIAL_BLOCKS_AVX num_initial_blocks T1 T2 T3 T4 T5 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T6 T_key ENC_DEC
 	i = (8-\num_initial_blocks)
+	j = 0
 	setreg
 
-        mov     arg6, %r10                      # r10 = AAD
-        mov     arg7, %r12                      # r12 = aadLen
-
-
-        mov     %r12, %r11
-
-        vpxor   reg_i, reg_i, reg_i
-_get_AAD_loop\@:
-        vmovd   (%r10), \T1
-        vpslldq $12, \T1, \T1
-        vpsrldq $4, reg_i, reg_i
-        vpxor   \T1, reg_i, reg_i
-
-        add     $4, %r10
-        sub     $4, %r12
-        jg      _get_AAD_loop\@
-
-
-        cmp     $16, %r11
-        je      _get_AAD_loop2_done\@
-        mov     $16, %r12
-
-_get_AAD_loop2\@:
-        vpsrldq $4, reg_i, reg_i
-        sub     $4, %r12
-        cmp     %r11, %r12
-        jg      _get_AAD_loop2\@
-
-_get_AAD_loop2_done\@:
-
-        #byte-reflect the AAD data
-        vpshufb SHUF_MASK(%rip), reg_i, reg_i
-
+	mov     arg6, %r10                      # r10 = AAD
+	mov     arg7, %r12                      # r12 = aadLen
+
+
+	mov     %r12, %r11
+
+	vpxor   reg_j, reg_j, reg_j
+	vpxor   reg_i, reg_i, reg_i
+	cmp     $16, %r11
+	jl      _get_AAD_rest8\@
+_get_AAD_blocks\@:
+	vmovdqu (%r10), reg_i
+	vpshufb SHUF_MASK(%rip), reg_i, reg_i
+	vpxor   reg_i, reg_j, reg_j
+	GHASH_MUL_AVX       reg_j, \T2, \T1, \T3, \T4, \T5, \T6
+	add     $16, %r10
+	sub     $16, %r12
+	sub     $16, %r11
+	cmp     $16, %r11
+	jge     _get_AAD_blocks\@
+	vmovdqu reg_j, reg_i
+	cmp     $0, %r11
+	je      _get_AAD_done\@
+
+	vpxor   reg_i, reg_i, reg_i
+
+	/* read the last <16B of AAD. since we have at least 4B of
+	data right after the AAD (the ICV, and maybe some CT), we can
+	read 4B/8B blocks safely, and then get rid of the extra stuff */
+_get_AAD_rest8\@:
+	cmp     $4, %r11
+	jle     _get_AAD_rest4\@
+	movq    (%r10), \T1
+	add     $8, %r10
+	sub     $8, %r11
+	vpslldq $8, \T1, \T1
+	vpsrldq $8, reg_i, reg_i
+	vpxor   \T1, reg_i, reg_i
+	jmp     _get_AAD_rest8\@
+_get_AAD_rest4\@:
+	cmp     $0, %r11
+	jle      _get_AAD_rest0\@
+	mov     (%r10), %eax
+	movq    %rax, \T1
+	add     $4, %r10
+	sub     $4, %r11
+	vpslldq $12, \T1, \T1
+	vpsrldq $4, reg_i, reg_i
+	vpxor   \T1, reg_i, reg_i
+_get_AAD_rest0\@:
+	/* finalize: shift out the extra bytes we read, and align
+	left. since pslldq can only shift by an immediate, we use
+	vpshufb and an array of shuffle masks */
+	movq    %r12, %r11
+	salq    $4, %r11
+	movdqu  aad_shift_arr(%r11), \T1
+	vpshufb \T1, reg_i, reg_i
+_get_AAD_rest_final\@:
+	vpshufb SHUF_MASK(%rip), reg_i, reg_i
+	vpxor   reg_j, reg_i, reg_i
+	GHASH_MUL_AVX       reg_i, \T2, \T1, \T3, \T4, \T5, \T6
+
+_get_AAD_done\@:
 	# initialize the data pointer offset as zero
 	xor     %r11, %r11
 
@@ -480,7 +535,6 @@ _get_AAD_loop2_done\@:
 	i = (8-\num_initial_blocks)
 	j = (9-\num_initial_blocks)
 	setreg
-        GHASH_MUL_AVX       reg_i, \T2, \T1, \T3, \T4, \T5, \T6
 
 .rep \num_initial_blocks
         vpxor    reg_i, reg_j, reg_j
@@ -1427,19 +1481,36 @@ _return_T\@:
         cmp     $16, %r11
         je      _T_16\@
 
-        cmp     $12, %r11
-        je      _T_12\@
+        cmp     $8, %r11
+        jl      _T_4\@
 
 _T_8\@:
         vmovq   %xmm9, %rax
         mov     %rax, (%r10)
-        jmp     _return_T_done\@
-_T_12\@:
-        vmovq   %xmm9, %rax
-        mov     %rax, (%r10)
+        add     $8, %r10
+        sub     $8, %r11
         vpsrldq $8, %xmm9, %xmm9
+        cmp     $0, %r11
+        je     _return_T_done\@
+_T_4\@:
         vmovd   %xmm9, %eax
-        mov     %eax, 8(%r10)
+        mov     %eax, (%r10)
+        add     $4, %r10
+        sub     $4, %r11
+        vpsrldq     $4, %xmm9, %xmm9
+        cmp     $0, %r11
+        je     _return_T_done\@
+_T_123\@:
+        vmovd     %xmm9, %eax
+        cmp     $2, %r11
+        jl     _T_1\@
+        mov     %ax, (%r10)
+        cmp     $2, %r11
+        je     _return_T_done\@
+        add     $2, %r10
+        sar     $16, %eax
+_T_1\@:
+        mov     %al, (%r10)
         jmp     _return_T_done\@
 
 _T_16\@:
@@ -1631,41 +1702,73 @@ ENDPROC(aesni_gcm_dec_avx_gen2)
 
 .macro INITIAL_BLOCKS_AVX2 num_initial_blocks T1 T2 T3 T4 T5 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T6 T_key ENC_DEC VER
 	i = (8-\num_initial_blocks)
+	j = 0
 	setreg
 
-        mov     arg6, %r10                       # r10 = AAD
-        mov     arg7, %r12                       # r12 = aadLen
-
-
-        mov     %r12, %r11
-
-        vpxor   reg_i, reg_i, reg_i
-_get_AAD_loop\@:
-        vmovd   (%r10), \T1
-        vpslldq $12, \T1, \T1
-        vpsrldq $4, reg_i, reg_i
-        vpxor   \T1, reg_i, reg_i
-
-        add     $4, %r10
-        sub     $4, %r12
-        jg      _get_AAD_loop\@
-
-
-        cmp     $16, %r11
-        je      _get_AAD_loop2_done\@
-        mov     $16, %r12
-
-_get_AAD_loop2\@:
-        vpsrldq $4, reg_i, reg_i
-        sub     $4, %r12
-        cmp     %r11, %r12
-        jg      _get_AAD_loop2\@
-
-_get_AAD_loop2_done\@:
-
-        #byte-reflect the AAD data
-        vpshufb SHUF_MASK(%rip), reg_i, reg_i
-
+	mov     arg6, %r10                       # r10 = AAD
+	mov     arg7, %r12                       # r12 = aadLen
+
+
+	mov     %r12, %r11
+
+	vpxor   reg_j, reg_j, reg_j
+	vpxor   reg_i, reg_i, reg_i
+
+	cmp     $16, %r11
+	jl      _get_AAD_rest8\@
+_get_AAD_blocks\@:
+	vmovdqu (%r10), reg_i
+	vpshufb SHUF_MASK(%rip), reg_i, reg_i
+	vpxor   reg_i, reg_j, reg_j
+	GHASH_MUL_AVX2      reg_j, \T2, \T1, \T3, \T4, \T5, \T6
+	add     $16, %r10
+	sub     $16, %r12
+	sub     $16, %r11
+	cmp     $16, %r11
+	jge     _get_AAD_blocks\@
+	vmovdqu reg_j, reg_i
+	cmp     $0, %r11
+	je      _get_AAD_done\@
+
+	vpxor   reg_i, reg_i, reg_i
+
+	/* read the last <16B of AAD. since we have at least 4B of
+	data right after the AAD (the ICV, and maybe some CT), we can
+	read 4B/8B blocks safely, and then get rid of the extra stuff */
+_get_AAD_rest8\@:
+	cmp     $4, %r11
+	jle     _get_AAD_rest4\@
+	movq    (%r10), \T1
+	add     $8, %r10
+	sub     $8, %r11
+	vpslldq $8, \T1, \T1
+	vpsrldq $8, reg_i, reg_i
+	vpxor   \T1, reg_i, reg_i
+	jmp     _get_AAD_rest8\@
+_get_AAD_rest4\@:
+	cmp     $0, %r11
+	jle     _get_AAD_rest0\@
+	mov     (%r10), %eax
+	movq    %rax, \T1
+	add     $4, %r10
+	sub     $4, %r11
+	vpslldq $12, \T1, \T1
+	vpsrldq $4, reg_i, reg_i
+	vpxor   \T1, reg_i, reg_i
+_get_AAD_rest0\@:
+	/* finalize: shift out the extra bytes we read, and align
+	left. since pslldq can only shift by an immediate, we use
+	vpshufb and an array of shuffle masks */
+	movq    %r12, %r11
+	salq    $4, %r11
+	movdqu  aad_shift_arr(%r11), \T1
+	vpshufb \T1, reg_i, reg_i
+_get_AAD_rest_final\@:
+	vpshufb SHUF_MASK(%rip), reg_i, reg_i
+	vpxor   reg_j, reg_i, reg_i
+	GHASH_MUL_AVX2      reg_i, \T2, \T1, \T3, \T4, \T5, \T6
+
+_get_AAD_done\@:
 	# initialize the data pointer offset as zero
 	xor     %r11, %r11
 
@@ -1740,7 +1843,6 @@ _get_AAD_loop2_done\@:
 	i = (8-\num_initial_blocks)
 	j = (9-\num_initial_blocks)
 	setreg
-        GHASH_MUL_AVX2       reg_i, \T2, \T1, \T3, \T4, \T5, \T6
 
 .rep \num_initial_blocks
         vpxor    reg_i, reg_j, reg_j
@@ -2702,19 +2804,36 @@ _return_T\@:
         cmp     $16, %r11
         je      _T_16\@
 
-        cmp     $12, %r11
-        je      _T_12\@
+        cmp     $8, %r11
+        jl      _T_4\@
 
 _T_8\@:
         vmovq   %xmm9, %rax
         mov     %rax, (%r10)
-        jmp     _return_T_done\@
-_T_12\@:
-        vmovq   %xmm9, %rax
-        mov     %rax, (%r10)
+        add     $8, %r10
+        sub     $8, %r11
         vpsrldq $8, %xmm9, %xmm9
+        cmp     $0, %r11
+        je     _return_T_done\@
+_T_4\@:
         vmovd   %xmm9, %eax
-        mov     %eax, 8(%r10)
+        mov     %eax, (%r10)
+        add     $4, %r10
+        sub     $4, %r11
+        vpsrldq     $4, %xmm9, %xmm9
+        cmp     $0, %r11
+        je     _return_T_done\@
+_T_123\@:
+        vmovd     %xmm9, %eax
+        cmp     $2, %r11
+        jl     _T_1\@
+        mov     %ax, (%r10)
+        cmp     $2, %r11
+        je     _return_T_done\@
+        add     $2, %r10
+        sar     $16, %eax
+_T_1\@:
+        mov     %al, (%r10)
         jmp     _return_T_done\@
 
 _T_16\@:
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 93de8ea51548..5c15d6b57329 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -61,6 +61,11 @@ struct aesni_rfc4106_gcm_ctx {
 	u8 nonce[4];
 };
 
+struct generic_gcmaes_ctx {
+	u8 hash_subkey[16] AESNI_ALIGN_ATTR;
+	struct crypto_aes_ctx aes_key_expanded AESNI_ALIGN_ATTR;
+};
+
 struct aesni_xts_ctx {
 	u8 raw_tweak_ctx[sizeof(struct crypto_aes_ctx)] AESNI_ALIGN_ATTR;
 	u8 raw_crypt_ctx[sizeof(struct crypto_aes_ctx)] AESNI_ALIGN_ATTR;
@@ -102,13 +107,11 @@ asmlinkage void aesni_xts_crypt8(struct crypto_aes_ctx *ctx, u8 *out,
  * u8 *out, Ciphertext output. Encrypt in-place is allowed.
  * const u8 *in, Plaintext input
  * unsigned long plaintext_len, Length of data in bytes for encryption.
- * u8 *iv, Pre-counter block j0: 4 byte salt (from Security Association)
- *         concatenated with 8 byte Initialisation Vector (from IPSec ESP
- *         Payload) concatenated with 0x00000001. 16-byte aligned pointer.
+ * u8 *iv, Pre-counter block j0: 12 byte IV concatenated with 0x00000001.
+ *         16-byte aligned pointer.
  * u8 *hash_subkey, the Hash sub key input. Data starts on a 16-byte boundary.
  * const u8 *aad, Additional Authentication Data (AAD)
- * unsigned long aad_len, Length of AAD in bytes. With RFC4106 this
- *          is going to be 8 or 12 bytes
+ * unsigned long aad_len, Length of AAD in bytes.
  * u8 *auth_tag, Authenticated Tag output.
  * unsigned long auth_tag_len), Authenticated Tag Length in bytes.
  *          Valid values are 16 (most likely), 12 or 8.
@@ -123,9 +126,8 @@ asmlinkage void aesni_gcm_enc(void *ctx, u8 *out,
  * u8 *out, Plaintext output. Decrypt in-place is allowed.
  * const u8 *in, Ciphertext input
  * unsigned long ciphertext_len, Length of data in bytes for decryption.
- * u8 *iv, Pre-counter block j0: 4 byte salt (from Security Association)
- *         concatenated with 8 byte Initialisation Vector (from IPSec ESP
- *         Payload) concatenated with 0x00000001. 16-byte aligned pointer.
+ * u8 *iv, Pre-counter block j0: 12 byte IV concatenated with 0x00000001.
+ *         16-byte aligned pointer.
  * u8 *hash_subkey, the Hash sub key input. Data starts on a 16-byte boundary.
  * const u8 *aad, Additional Authentication Data (AAD)
  * unsigned long aad_len, Length of AAD in bytes. With RFC4106 this is going
@@ -275,6 +277,16 @@ aesni_rfc4106_gcm_ctx *aesni_rfc4106_gcm_ctx_get(struct crypto_aead *tfm)
 		align = 1;
 	return PTR_ALIGN(crypto_aead_ctx(tfm), align);
 }
+
+static inline struct
+generic_gcmaes_ctx *generic_gcmaes_ctx_get(struct crypto_aead *tfm)
+{
+	unsigned long align = AESNI_ALIGN;
+
+	if (align <= crypto_tfm_ctx_alignment())
+		align = 1;
+	return PTR_ALIGN(crypto_aead_ctx(tfm), align);
+}
 #endif
 
 static inline struct crypto_aes_ctx *aes_ctx(void *raw_ctx)
@@ -463,8 +475,8 @@ static void ctr_crypt_final(struct crypto_aes_ctx *ctx,
 	unsigned int nbytes = walk->nbytes;
 
 	aesni_enc(ctx, keystream, ctrblk);
-	crypto_xor(keystream, src, nbytes);
-	memcpy(dst, keystream, nbytes);
+	crypto_xor_cpy(dst, keystream, src, nbytes);
+
 	crypto_inc(ctrblk, AES_BLOCK_SIZE);
 }
 
@@ -712,32 +724,34 @@ static int rfc4106_set_authsize(struct crypto_aead *parent,
 	return crypto_aead_setauthsize(&cryptd_tfm->base, authsize);
 }
 
-static int helper_rfc4106_encrypt(struct aead_request *req)
+static int generic_gcmaes_set_authsize(struct crypto_aead *tfm,
+				       unsigned int authsize)
+{
+	switch (authsize) {
+	case 4:
+	case 8:
+	case 12:
+	case 13:
+	case 14:
+	case 15:
+	case 16:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int gcmaes_encrypt(struct aead_request *req, unsigned int assoclen,
+			  u8 *hash_subkey, u8 *iv, void *aes_ctx)
 {
 	u8 one_entry_in_sg = 0;
 	u8 *src, *dst, *assoc;
-	__be32 counter = cpu_to_be32(1);
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
-	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
-	void *aes_ctx = &(ctx->aes_key_expanded);
 	unsigned long auth_tag_len = crypto_aead_authsize(tfm);
-	u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN)));
 	struct scatter_walk src_sg_walk;
 	struct scatter_walk dst_sg_walk = {};
-	unsigned int i;
-
-	/* Assuming we are supporting rfc4106 64-bit extended */
-	/* sequence numbers We need to have the AAD length equal */
-	/* to 16 or 20 bytes */
-	if (unlikely(req->assoclen != 16 && req->assoclen != 20))
-		return -EINVAL;
-
-	/* IV below built */
-	for (i = 0; i < 4; i++)
-		*(iv+i) = ctx->nonce[i];
-	for (i = 0; i < 8; i++)
-		*(iv+4+i) = req->iv[i];
-	*((__be32 *)(iv+12)) = counter;
 
 	if (sg_is_last(req->src) &&
 	    (!PageHighMem(sg_page(req->src)) ||
@@ -768,7 +782,7 @@ static int helper_rfc4106_encrypt(struct aead_request *req)
 
 	kernel_fpu_begin();
 	aesni_gcm_enc_tfm(aes_ctx, dst, src, req->cryptlen, iv,
-			  ctx->hash_subkey, assoc, req->assoclen - 8,
+			  hash_subkey, assoc, assoclen,
 			  dst + req->cryptlen, auth_tag_len);
 	kernel_fpu_end();
 
@@ -791,37 +805,20 @@ static int helper_rfc4106_encrypt(struct aead_request *req)
 	return 0;
 }
 
-static int helper_rfc4106_decrypt(struct aead_request *req)
+static int gcmaes_decrypt(struct aead_request *req, unsigned int assoclen,
+			  u8 *hash_subkey, u8 *iv, void *aes_ctx)
 {
 	u8 one_entry_in_sg = 0;
 	u8 *src, *dst, *assoc;
 	unsigned long tempCipherLen = 0;
-	__be32 counter = cpu_to_be32(1);
-	int retval = 0;
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
-	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
-	void *aes_ctx = &(ctx->aes_key_expanded);
 	unsigned long auth_tag_len = crypto_aead_authsize(tfm);
-	u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN)));
 	u8 authTag[16];
 	struct scatter_walk src_sg_walk;
 	struct scatter_walk dst_sg_walk = {};
-	unsigned int i;
-
-	if (unlikely(req->assoclen != 16 && req->assoclen != 20))
-		return -EINVAL;
-
-	/* Assuming we are supporting rfc4106 64-bit extended */
-	/* sequence numbers We need to have the AAD length */
-	/* equal to 16 or 20 bytes */
+	int retval = 0;
 
 	tempCipherLen = (unsigned long)(req->cryptlen - auth_tag_len);
-	/* IV below built */
-	for (i = 0; i < 4; i++)
-		*(iv+i) = ctx->nonce[i];
-	for (i = 0; i < 8; i++)
-		*(iv+4+i) = req->iv[i];
-	*((__be32 *)(iv+12)) = counter;
 
 	if (sg_is_last(req->src) &&
 	    (!PageHighMem(sg_page(req->src)) ||
@@ -838,7 +835,6 @@ static int helper_rfc4106_decrypt(struct aead_request *req)
 			scatterwalk_start(&dst_sg_walk, req->dst);
 			dst = scatterwalk_map(&dst_sg_walk) + req->assoclen;
 		}
-
 	} else {
 		/* Allocate memory for src, dst, assoc */
 		assoc = kmalloc(req->cryptlen + req->assoclen, GFP_ATOMIC);
@@ -850,9 +846,10 @@ static int helper_rfc4106_decrypt(struct aead_request *req)
 		dst = src;
 	}
 
+
 	kernel_fpu_begin();
 	aesni_gcm_dec_tfm(aes_ctx, dst, src, tempCipherLen, iv,
-			  ctx->hash_subkey, assoc, req->assoclen - 8,
+			  hash_subkey, assoc, assoclen,
 			  authTag, auth_tag_len);
 	kernel_fpu_end();
 
@@ -875,6 +872,60 @@ static int helper_rfc4106_decrypt(struct aead_request *req)
 		kfree(assoc);
 	}
 	return retval;
+
+}
+
+static int helper_rfc4106_encrypt(struct aead_request *req)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
+	void *aes_ctx = &(ctx->aes_key_expanded);
+	u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN)));
+	unsigned int i;
+	__be32 counter = cpu_to_be32(1);
+
+	/* Assuming we are supporting rfc4106 64-bit extended */
+	/* sequence numbers We need to have the AAD length equal */
+	/* to 16 or 20 bytes */
+	if (unlikely(req->assoclen != 16 && req->assoclen != 20))
+		return -EINVAL;
+
+	/* IV below built */
+	for (i = 0; i < 4; i++)
+		*(iv+i) = ctx->nonce[i];
+	for (i = 0; i < 8; i++)
+		*(iv+4+i) = req->iv[i];
+	*((__be32 *)(iv+12)) = counter;
+
+	return gcmaes_encrypt(req, req->assoclen - 8, ctx->hash_subkey, iv,
+			      aes_ctx);
+}
+
+static int helper_rfc4106_decrypt(struct aead_request *req)
+{
+	__be32 counter = cpu_to_be32(1);
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
+	void *aes_ctx = &(ctx->aes_key_expanded);
+	u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN)));
+	unsigned int i;
+
+	if (unlikely(req->assoclen != 16 && req->assoclen != 20))
+		return -EINVAL;
+
+	/* Assuming we are supporting rfc4106 64-bit extended */
+	/* sequence numbers We need to have the AAD length */
+	/* equal to 16 or 20 bytes */
+
+	/* IV below built */
+	for (i = 0; i < 4; i++)
+		*(iv+i) = ctx->nonce[i];
+	for (i = 0; i < 8; i++)
+		*(iv+4+i) = req->iv[i];
+	*((__be32 *)(iv+12)) = counter;
+
+	return gcmaes_decrypt(req, req->assoclen - 8, ctx->hash_subkey, iv,
+			      aes_ctx);
 }
 
 static int rfc4106_encrypt(struct aead_request *req)
@@ -1035,6 +1086,46 @@ struct {
 };
 
 #ifdef CONFIG_X86_64
+static int generic_gcmaes_set_key(struct crypto_aead *aead, const u8 *key,
+				  unsigned int key_len)
+{
+	struct generic_gcmaes_ctx *ctx = generic_gcmaes_ctx_get(aead);
+
+	return aes_set_key_common(crypto_aead_tfm(aead),
+				  &ctx->aes_key_expanded, key, key_len) ?:
+	       rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len);
+}
+
+static int generic_gcmaes_encrypt(struct aead_request *req)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct generic_gcmaes_ctx *ctx = generic_gcmaes_ctx_get(tfm);
+	void *aes_ctx = &(ctx->aes_key_expanded);
+	u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN)));
+	__be32 counter = cpu_to_be32(1);
+
+	memcpy(iv, req->iv, 12);
+	*((__be32 *)(iv+12)) = counter;
+
+	return gcmaes_encrypt(req, req->assoclen, ctx->hash_subkey, iv,
+			      aes_ctx);
+}
+
+static int generic_gcmaes_decrypt(struct aead_request *req)
+{
+	__be32 counter = cpu_to_be32(1);
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
+	void *aes_ctx = &(ctx->aes_key_expanded);
+	u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN)));
+
+	memcpy(iv, req->iv, 12);
+	*((__be32 *)(iv+12)) = counter;
+
+	return gcmaes_decrypt(req, req->assoclen, ctx->hash_subkey, iv,
+			      aes_ctx);
+}
+
 static struct aead_alg aesni_aead_algs[] = { {
 	.setkey			= common_rfc4106_set_key,
 	.setauthsize		= common_rfc4106_set_authsize,
@@ -1069,6 +1160,23 @@ static struct aead_alg aesni_aead_algs[] = { {
 		.cra_ctxsize		= sizeof(struct cryptd_aead *),
 		.cra_module		= THIS_MODULE,
 	},
+}, {
+	.setkey			= generic_gcmaes_set_key,
+	.setauthsize		= generic_gcmaes_set_authsize,
+	.encrypt		= generic_gcmaes_encrypt,
+	.decrypt		= generic_gcmaes_decrypt,
+	.ivsize			= 12,
+	.maxauthsize		= 16,
+	.base = {
+		.cra_name		= "gcm(aes)",
+		.cra_driver_name	= "generic-gcm-aesni",
+		.cra_priority		= 400,
+		.cra_flags		= CRYPTO_ALG_ASYNC,
+		.cra_blocksize		= 1,
+		.cra_ctxsize		= sizeof(struct generic_gcmaes_ctx),
+		.cra_alignmask		= AESNI_ALIGN - 1,
+		.cra_module		= THIS_MODULE,
+	},
 } };
 #else
 static struct aead_alg aesni_aead_algs[0];
diff --git a/arch/x86/crypto/blowfish-x86_64-asm_64.S b/arch/x86/crypto/blowfish-x86_64-asm_64.S
index 246c67006ed0..8c1fcb6bad21 100644
--- a/arch/x86/crypto/blowfish-x86_64-asm_64.S
+++ b/arch/x86/crypto/blowfish-x86_64-asm_64.S
@@ -33,7 +33,7 @@
 #define s3	((16 + 2 + (3 * 256)) * 4)
 
 /* register macros */
-#define CTX %rdi
+#define CTX %r12
 #define RIO %rsi
 
 #define RX0 %rax
@@ -56,12 +56,12 @@
 #define RX2bh %ch
 #define RX3bh %dh
 
-#define RT0 %rbp
+#define RT0 %rdi
 #define RT1 %rsi
 #define RT2 %r8
 #define RT3 %r9
 
-#define RT0d %ebp
+#define RT0d %edi
 #define RT1d %esi
 #define RT2d %r8d
 #define RT3d %r9d
@@ -120,13 +120,14 @@
 
 ENTRY(__blowfish_enc_blk)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 *	%rcx: bool, if true: xor output
 	 */
-	movq %rbp, %r11;
+	movq %r12, %r11;
 
+	movq %rdi, CTX;
 	movq %rsi, %r10;
 	movq %rdx, RIO;
 
@@ -142,7 +143,7 @@ ENTRY(__blowfish_enc_blk)
 	round_enc(14);
 	add_roundkey_enc(16);
 
-	movq %r11, %rbp;
+	movq %r11, %r12;
 
 	movq %r10, RIO;
 	test %cl, %cl;
@@ -157,12 +158,13 @@ ENDPROC(__blowfish_enc_blk)
 
 ENTRY(blowfish_dec_blk)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
-	movq %rbp, %r11;
+	movq %r12, %r11;
 
+	movq %rdi, CTX;
 	movq %rsi, %r10;
 	movq %rdx, RIO;
 
@@ -181,7 +183,7 @@ ENTRY(blowfish_dec_blk)
 	movq %r10, RIO;
 	write_block();
 
-	movq %r11, %rbp;
+	movq %r11, %r12;
 
 	ret;
 ENDPROC(blowfish_dec_blk)
@@ -298,20 +300,21 @@ ENDPROC(blowfish_dec_blk)
 
 ENTRY(__blowfish_enc_blk_4way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 *	%rcx: bool, if true: xor output
 	 */
-	pushq %rbp;
+	pushq %r12;
 	pushq %rbx;
 	pushq %rcx;
 
-	preload_roundkey_enc(0);
-
+	movq %rdi, CTX
 	movq %rsi, %r11;
 	movq %rdx, RIO;
 
+	preload_roundkey_enc(0);
+
 	read_block4();
 
 	round_enc4(0);
@@ -324,39 +327,40 @@ ENTRY(__blowfish_enc_blk_4way)
 	round_enc4(14);
 	add_preloaded_roundkey4();
 
-	popq %rbp;
+	popq %r12;
 	movq %r11, RIO;
 
-	test %bpl, %bpl;
+	test %r12b, %r12b;
 	jnz .L__enc_xor4;
 
 	write_block4();
 
 	popq %rbx;
-	popq %rbp;
+	popq %r12;
 	ret;
 
 .L__enc_xor4:
 	xor_block4();
 
 	popq %rbx;
-	popq %rbp;
+	popq %r12;
 	ret;
 ENDPROC(__blowfish_enc_blk_4way)
 
 ENTRY(blowfish_dec_blk_4way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
-	pushq %rbp;
+	pushq %r12;
 	pushq %rbx;
-	preload_roundkey_dec(17);
 
-	movq %rsi, %r11;
+	movq %rdi, CTX;
+	movq %rsi, %r11
 	movq %rdx, RIO;
 
+	preload_roundkey_dec(17);
 	read_block4();
 
 	round_dec4(17);
@@ -373,7 +377,7 @@ ENTRY(blowfish_dec_blk_4way)
 	write_block4();
 
 	popq %rbx;
-	popq %rbp;
+	popq %r12;
 
 	ret;
 ENDPROC(blowfish_dec_blk_4way)
diff --git a/arch/x86/crypto/blowfish_glue.c b/arch/x86/crypto/blowfish_glue.c
index 17c05531dfd1..f9eca34301e2 100644
--- a/arch/x86/crypto/blowfish_glue.c
+++ b/arch/x86/crypto/blowfish_glue.c
@@ -271,8 +271,7 @@ static void ctr_crypt_final(struct bf_ctx *ctx, struct blkcipher_walk *walk)
 	unsigned int nbytes = walk->nbytes;
 
 	blowfish_enc_blk(ctx, keystream, ctrblk);
-	crypto_xor(keystream, src, nbytes);
-	memcpy(dst, keystream, nbytes);
+	crypto_xor_cpy(dst, keystream, src, nbytes);
 
 	crypto_inc(ctrblk, BF_BLOCK_SIZE);
 }
diff --git a/arch/x86/crypto/camellia-x86_64-asm_64.S b/arch/x86/crypto/camellia-x86_64-asm_64.S
index 310319c601ed..95ba6956a7f6 100644
--- a/arch/x86/crypto/camellia-x86_64-asm_64.S
+++ b/arch/x86/crypto/camellia-x86_64-asm_64.S
@@ -75,17 +75,17 @@
 #define RCD1bh %dh
 
 #define RT0 %rsi
-#define RT1 %rbp
+#define RT1 %r12
 #define RT2 %r8
 
 #define RT0d %esi
-#define RT1d %ebp
+#define RT1d %r12d
 #define RT2d %r8d
 
 #define RT2bl %r8b
 
 #define RXOR %r9
-#define RRBP %r10
+#define RR12 %r10
 #define RDST %r11
 
 #define RXORd %r9d
@@ -197,7 +197,7 @@ ENTRY(__camellia_enc_blk)
 	 *	%rdx: src
 	 *	%rcx: bool xor
 	 */
-	movq %rbp, RRBP;
+	movq %r12, RR12;
 
 	movq %rcx, RXOR;
 	movq %rsi, RDST;
@@ -227,13 +227,13 @@ ENTRY(__camellia_enc_blk)
 
 	enc_outunpack(mov, RT1);
 
-	movq RRBP, %rbp;
+	movq RR12, %r12;
 	ret;
 
 .L__enc_xor:
 	enc_outunpack(xor, RT1);
 
-	movq RRBP, %rbp;
+	movq RR12, %r12;
 	ret;
 ENDPROC(__camellia_enc_blk)
 
@@ -248,7 +248,7 @@ ENTRY(camellia_dec_blk)
 	movl $24, RXORd;
 	cmovel RXORd, RT2d; /* max */
 
-	movq %rbp, RRBP;
+	movq %r12, RR12;
 	movq %rsi, RDST;
 	movq %rdx, RIO;
 
@@ -271,7 +271,7 @@ ENTRY(camellia_dec_blk)
 
 	dec_outunpack();
 
-	movq RRBP, %rbp;
+	movq RR12, %r12;
 	ret;
 ENDPROC(camellia_dec_blk)
 
@@ -433,7 +433,7 @@ ENTRY(__camellia_enc_blk_2way)
 	 */
 	pushq %rbx;
 
-	movq %rbp, RRBP;
+	movq %r12, RR12;
 	movq %rcx, RXOR;
 	movq %rsi, RDST;
 	movq %rdx, RIO;
@@ -461,14 +461,14 @@ ENTRY(__camellia_enc_blk_2way)
 
 	enc_outunpack2(mov, RT2);
 
-	movq RRBP, %rbp;
+	movq RR12, %r12;
 	popq %rbx;
 	ret;
 
 .L__enc2_xor:
 	enc_outunpack2(xor, RT2);
 
-	movq RRBP, %rbp;
+	movq RR12, %r12;
 	popq %rbx;
 	ret;
 ENDPROC(__camellia_enc_blk_2way)
@@ -485,7 +485,7 @@ ENTRY(camellia_dec_blk_2way)
 	cmovel RXORd, RT2d; /* max */
 
 	movq %rbx, RXOR;
-	movq %rbp, RRBP;
+	movq %r12, RR12;
 	movq %rsi, RDST;
 	movq %rdx, RIO;
 
@@ -508,7 +508,7 @@ ENTRY(camellia_dec_blk_2way)
 
 	dec_outunpack2();
 
-	movq RRBP, %rbp;
+	movq RR12, %r12;
 	movq RXOR, %rbx;
 	ret;
 ENDPROC(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 b4a8806234ea..86107c961bb4 100644
--- a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
@@ -47,7 +47,7 @@
 /**********************************************************************
   16-way AVX cast5
  **********************************************************************/
-#define CTX %rdi
+#define CTX %r15
 
 #define RL1 %xmm0
 #define RR1 %xmm1
@@ -70,8 +70,8 @@
 
 #define RTMP %xmm15
 
-#define RID1  %rbp
-#define RID1d %ebp
+#define RID1  %rdi
+#define RID1d %edi
 #define RID2  %rsi
 #define RID2d %esi
 
@@ -226,7 +226,7 @@
 .align 16
 __cast5_enc_blk16:
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	RL1: blocks 1 and 2
 	 *	RR1: blocks 3 and 4
 	 *	RL2: blocks 5 and 6
@@ -246,9 +246,11 @@ __cast5_enc_blk16:
 	 *	RR4: encrypted blocks 15 and 16
 	 */
 
-	pushq %rbp;
+	pushq %r15;
 	pushq %rbx;
 
+	movq %rdi, CTX;
+
 	vmovdqa .Lbswap_mask, RKM;
 	vmovd .Lfirst_mask, R1ST;
 	vmovd .L32_mask, R32;
@@ -283,7 +285,7 @@ __cast5_enc_blk16:
 
 .L__skip_enc:
 	popq %rbx;
-	popq %rbp;
+	popq %r15;
 
 	vmovdqa .Lbswap_mask, RKM;
 
@@ -298,7 +300,7 @@ ENDPROC(__cast5_enc_blk16)
 .align 16
 __cast5_dec_blk16:
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	RL1: encrypted blocks 1 and 2
 	 *	RR1: encrypted blocks 3 and 4
 	 *	RL2: encrypted blocks 5 and 6
@@ -318,9 +320,11 @@ __cast5_dec_blk16:
 	 *	RR4: decrypted blocks 15 and 16
 	 */
 
-	pushq %rbp;
+	pushq %r15;
 	pushq %rbx;
 
+	movq %rdi, CTX;
+
 	vmovdqa .Lbswap_mask, RKM;
 	vmovd .Lfirst_mask, R1ST;
 	vmovd .L32_mask, R32;
@@ -356,7 +360,7 @@ __cast5_dec_blk16:
 
 	vmovdqa .Lbswap_mask, RKM;
 	popq %rbx;
-	popq %rbp;
+	popq %r15;
 
 	outunpack_blocks(RR1, RL1, RTMP, RX, RKM);
 	outunpack_blocks(RR2, RL2, RTMP, RX, RKM);
@@ -372,12 +376,14 @@ ENDPROC(__cast5_dec_blk16)
 
 ENTRY(cast5_ecb_enc_16way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
 	FRAME_BEGIN
+	pushq %r15;
 
+	movq %rdi, CTX;
 	movq %rsi, %r11;
 
 	vmovdqu (0*4*4)(%rdx), RL1;
@@ -400,18 +406,22 @@ ENTRY(cast5_ecb_enc_16way)
 	vmovdqu RR4, (6*4*4)(%r11);
 	vmovdqu RL4, (7*4*4)(%r11);
 
+	popq %r15;
 	FRAME_END
 	ret;
 ENDPROC(cast5_ecb_enc_16way)
 
 ENTRY(cast5_ecb_dec_16way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
 
 	FRAME_BEGIN
+	pushq %r15;
+
+	movq %rdi, CTX;
 	movq %rsi, %r11;
 
 	vmovdqu (0*4*4)(%rdx), RL1;
@@ -434,20 +444,22 @@ ENTRY(cast5_ecb_dec_16way)
 	vmovdqu RR4, (6*4*4)(%r11);
 	vmovdqu RL4, (7*4*4)(%r11);
 
+	popq %r15;
 	FRAME_END
 	ret;
 ENDPROC(cast5_ecb_dec_16way)
 
 ENTRY(cast5_cbc_dec_16way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
 	FRAME_BEGIN
-
 	pushq %r12;
+	pushq %r15;
 
+	movq %rdi, CTX;
 	movq %rsi, %r11;
 	movq %rdx, %r12;
 
@@ -483,23 +495,24 @@ ENTRY(cast5_cbc_dec_16way)
 	vmovdqu RR4, (6*16)(%r11);
 	vmovdqu RL4, (7*16)(%r11);
 
+	popq %r15;
 	popq %r12;
-
 	FRAME_END
 	ret;
 ENDPROC(cast5_cbc_dec_16way)
 
 ENTRY(cast5_ctr_16way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 *	%rcx: iv (big endian, 64bit)
 	 */
 	FRAME_BEGIN
-
 	pushq %r12;
+	pushq %r15;
 
+	movq %rdi, CTX;
 	movq %rsi, %r11;
 	movq %rdx, %r12;
 
@@ -558,8 +571,8 @@ ENTRY(cast5_ctr_16way)
 	vmovdqu RR4, (6*16)(%r11);
 	vmovdqu RL4, (7*16)(%r11);
 
+	popq %r15;
 	popq %r12;
-
 	FRAME_END
 	ret;
 ENDPROC(cast5_ctr_16way)
diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c
index 8648158f3916..dbea6020ffe7 100644
--- a/arch/x86/crypto/cast5_avx_glue.c
+++ b/arch/x86/crypto/cast5_avx_glue.c
@@ -256,8 +256,7 @@ static void ctr_crypt_final(struct blkcipher_desc *desc,
 	unsigned int nbytes = walk->nbytes;
 
 	__cast5_encrypt(ctx, keystream, ctrblk);
-	crypto_xor(keystream, src, nbytes);
-	memcpy(dst, keystream, nbytes);
+	crypto_xor_cpy(dst, keystream, src, nbytes);
 
 	crypto_inc(ctrblk, CAST5_BLOCK_SIZE);
 }
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 952d3156a933..7f30b6f0d72c 100644
--- a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
@@ -47,7 +47,7 @@
 /**********************************************************************
   8-way AVX cast6
  **********************************************************************/
-#define CTX %rdi
+#define CTX %r15
 
 #define RA1 %xmm0
 #define RB1 %xmm1
@@ -70,8 +70,8 @@
 
 #define RTMP %xmm15
 
-#define RID1  %rbp
-#define RID1d %ebp
+#define RID1  %rdi
+#define RID1d %edi
 #define RID2  %rsi
 #define RID2d %esi
 
@@ -264,15 +264,17 @@
 .align 8
 __cast6_enc_blk8:
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: blocks
 	 * output:
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks
 	 */
 
-	pushq %rbp;
+	pushq %r15;
 	pushq %rbx;
 
+	movq %rdi, CTX;
+
 	vmovdqa .Lbswap_mask, RKM;
 	vmovd .Lfirst_mask, R1ST;
 	vmovd .L32_mask, R32;
@@ -297,7 +299,7 @@ __cast6_enc_blk8:
 	QBAR(11);
 
 	popq %rbx;
-	popq %rbp;
+	popq %r15;
 
 	vmovdqa .Lbswap_mask, RKM;
 
@@ -310,15 +312,17 @@ ENDPROC(__cast6_enc_blk8)
 .align 8
 __cast6_dec_blk8:
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks
 	 * output:
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: decrypted blocks
 	 */
 
-	pushq %rbp;
+	pushq %r15;
 	pushq %rbx;
 
+	movq %rdi, CTX;
+
 	vmovdqa .Lbswap_mask, RKM;
 	vmovd .Lfirst_mask, R1ST;
 	vmovd .L32_mask, R32;
@@ -343,7 +347,7 @@ __cast6_dec_blk8:
 	QBAR(0);
 
 	popq %rbx;
-	popq %rbp;
+	popq %r15;
 
 	vmovdqa .Lbswap_mask, RKM;
 	outunpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
@@ -354,12 +358,14 @@ ENDPROC(__cast6_dec_blk8)
 
 ENTRY(cast6_ecb_enc_8way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
 	FRAME_BEGIN
+	pushq %r15;
 
+	movq %rdi, CTX;
 	movq %rsi, %r11;
 
 	load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
@@ -368,18 +374,21 @@ ENTRY(cast6_ecb_enc_8way)
 
 	store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	popq %r15;
 	FRAME_END
 	ret;
 ENDPROC(cast6_ecb_enc_8way)
 
 ENTRY(cast6_ecb_dec_8way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
 	FRAME_BEGIN
+	pushq %r15;
 
+	movq %rdi, CTX;
 	movq %rsi, %r11;
 
 	load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
@@ -388,20 +397,22 @@ ENTRY(cast6_ecb_dec_8way)
 
 	store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	popq %r15;
 	FRAME_END
 	ret;
 ENDPROC(cast6_ecb_dec_8way)
 
 ENTRY(cast6_cbc_dec_8way)
 	/* input:
-	 *	%rdi: ctx, CTX
+	 *	%rdi: ctx
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
 	FRAME_BEGIN
-
 	pushq %r12;
+	pushq %r15;
 
+	movq %rdi, CTX;
 	movq %rsi, %r11;
 	movq %rdx, %r12;
 
@@ -411,8 +422,8 @@ ENTRY(cast6_cbc_dec_8way)
 
 	store_cbc_8way(%r12, %r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	popq %r15;
 	popq %r12;
-
 	FRAME_END
 	ret;
 ENDPROC(cast6_cbc_dec_8way)
@@ -425,9 +436,10 @@ ENTRY(cast6_ctr_8way)
 	 *	%rcx: iv (little endian, 128bit)
 	 */
 	FRAME_BEGIN
-
 	pushq %r12;
+	pushq %r15
 
+	movq %rdi, CTX;
 	movq %rsi, %r11;
 	movq %rdx, %r12;
 
@@ -438,8 +450,8 @@ ENTRY(cast6_ctr_8way)
 
 	store_ctr_8way(%r12, %r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	popq %r15;
 	popq %r12;
-
 	FRAME_END
 	ret;
 ENDPROC(cast6_ctr_8way)
@@ -452,7 +464,9 @@ ENTRY(cast6_xts_enc_8way)
 	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
 	 */
 	FRAME_BEGIN
+	pushq %r15;
 
+	movq %rdi, CTX
 	movq %rsi, %r11;
 
 	/* regs <= src, dst <= IVs, regs <= regs xor IVs */
@@ -464,6 +478,7 @@ ENTRY(cast6_xts_enc_8way)
 	/* dst <= regs xor IVs(in dst) */
 	store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	popq %r15;
 	FRAME_END
 	ret;
 ENDPROC(cast6_xts_enc_8way)
@@ -476,7 +491,9 @@ ENTRY(cast6_xts_dec_8way)
 	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
 	 */
 	FRAME_BEGIN
+	pushq %r15;
 
+	movq %rdi, CTX
 	movq %rsi, %r11;
 
 	/* regs <= src, dst <= IVs, regs <= regs xor IVs */
@@ -488,6 +505,7 @@ ENTRY(cast6_xts_dec_8way)
 	/* dst <= regs xor IVs(in dst) */
 	store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
+	popq %r15;
 	FRAME_END
 	ret;
 ENDPROC(cast6_xts_dec_8way)
diff --git a/arch/x86/crypto/chacha20-avx2-x86_64.S b/arch/x86/crypto/chacha20-avx2-x86_64.S
index 3a2dc3dc6cac..f3cd26f48332 100644
--- a/arch/x86/crypto/chacha20-avx2-x86_64.S
+++ b/arch/x86/crypto/chacha20-avx2-x86_64.S
@@ -45,7 +45,7 @@ ENTRY(chacha20_8block_xor_avx2)
 
 	vzeroupper
 	# 4 * 32 byte stack, 32-byte aligned
-	mov		%rsp, %r8
+	lea		8(%rsp),%r10
 	and		$~31, %rsp
 	sub		$0x80, %rsp
 
@@ -443,6 +443,6 @@ ENTRY(chacha20_8block_xor_avx2)
 	vmovdqu		%ymm15,0x01e0(%rsi)
 
 	vzeroupper
-	mov		%r8,%rsp
+	lea		-8(%r10),%rsp
 	ret
 ENDPROC(chacha20_8block_xor_avx2)
diff --git a/arch/x86/crypto/chacha20-ssse3-x86_64.S b/arch/x86/crypto/chacha20-ssse3-x86_64.S
index 3f511a7d73b8..512a2b500fd1 100644
--- a/arch/x86/crypto/chacha20-ssse3-x86_64.S
+++ b/arch/x86/crypto/chacha20-ssse3-x86_64.S
@@ -160,7 +160,7 @@ ENTRY(chacha20_4block_xor_ssse3)
 	# done with the slightly better performing SSSE3 byte shuffling,
 	# 7/12-bit word rotation uses traditional shift+OR.
 
-	mov		%rsp,%r11
+	lea		8(%rsp),%r10
 	sub		$0x80,%rsp
 	and		$~63,%rsp
 
@@ -625,6 +625,6 @@ ENTRY(chacha20_4block_xor_ssse3)
 	pxor		%xmm1,%xmm15
 	movdqu		%xmm15,0xf0(%rsi)
 
-	mov		%r11,%rsp
+	lea		-8(%r10),%rsp
 	ret
 ENDPROC(chacha20_4block_xor_ssse3)
diff --git a/arch/x86/crypto/des3_ede-asm_64.S b/arch/x86/crypto/des3_ede-asm_64.S
index f3e91647ca27..8e49ce117494 100644
--- a/arch/x86/crypto/des3_ede-asm_64.S
+++ b/arch/x86/crypto/des3_ede-asm_64.S
@@ -64,12 +64,12 @@
 #define RW2bh %ch
 
 #define RT0 %r15
-#define RT1 %rbp
+#define RT1 %rsi
 #define RT2 %r14
 #define RT3 %rdx
 
 #define RT0d %r15d
-#define RT1d %ebp
+#define RT1d %esi
 #define RT2d %r14d
 #define RT3d %edx
 
@@ -177,13 +177,14 @@ ENTRY(des3_ede_x86_64_crypt_blk)
 	 *	%rsi: dst
 	 *	%rdx: src
 	 */
-	pushq %rbp;
 	pushq %rbx;
 	pushq %r12;
 	pushq %r13;
 	pushq %r14;
 	pushq %r15;
 
+	pushq %rsi; /* dst */
+
 	read_block(%rdx, RL0, RR0);
 	initial_permutation(RL0, RR0);
 
@@ -241,6 +242,8 @@ ENTRY(des3_ede_x86_64_crypt_blk)
 	round1(32+15, RL0, RR0, dummy2);
 
 	final_permutation(RR0, RL0);
+
+	popq %rsi /* dst */
 	write_block(%rsi, RR0, RL0);
 
 	popq %r15;
@@ -248,7 +251,6 @@ ENTRY(des3_ede_x86_64_crypt_blk)
 	popq %r13;
 	popq %r12;
 	popq %rbx;
-	popq %rbp;
 
 	ret;
 ENDPROC(des3_ede_x86_64_crypt_blk)
@@ -432,13 +434,14 @@ ENTRY(des3_ede_x86_64_crypt_blk_3way)
 	 *	%rdx: src (3 blocks)
 	 */
 
-	pushq %rbp;
 	pushq %rbx;
 	pushq %r12;
 	pushq %r13;
 	pushq %r14;
 	pushq %r15;
 
+	pushq %rsi /* dst */
+
 	/* load input */
 	movl 0 * 4(%rdx), RL0d;
 	movl 1 * 4(%rdx), RR0d;
@@ -520,6 +523,7 @@ ENTRY(des3_ede_x86_64_crypt_blk_3way)
 	bswapl RR2d;
 	bswapl RL2d;
 
+	popq %rsi /* dst */
 	movl RR0d, 0 * 4(%rsi);
 	movl RL0d, 1 * 4(%rsi);
 	movl RR1d, 2 * 4(%rsi);
@@ -532,7 +536,6 @@ ENTRY(des3_ede_x86_64_crypt_blk_3way)
 	popq %r13;
 	popq %r12;
 	popq %rbx;
-	popq %rbp;
 
 	ret;
 ENDPROC(des3_ede_x86_64_crypt_blk_3way)
diff --git a/arch/x86/crypto/des3_ede_glue.c b/arch/x86/crypto/des3_ede_glue.c
index d6fc59aaaadf..30c0a37f4882 100644
--- a/arch/x86/crypto/des3_ede_glue.c
+++ b/arch/x86/crypto/des3_ede_glue.c
@@ -277,8 +277,7 @@ static void ctr_crypt_final(struct des3_ede_x86_ctx *ctx,
 	unsigned int nbytes = walk->nbytes;
 
 	des3_ede_enc_blk(ctx, keystream, ctrblk);
-	crypto_xor(keystream, src, nbytes);
-	memcpy(dst, keystream, nbytes);
+	crypto_xor_cpy(dst, keystream, src, nbytes);
 
 	crypto_inc(ctrblk, DES3_EDE_BLOCK_SIZE);
 }
diff --git a/arch/x86/crypto/glue_helper.c b/arch/x86/crypto/glue_helper.c
index 24ac9fad832d..d61e57960fe0 100644
--- a/arch/x86/crypto/glue_helper.c
+++ b/arch/x86/crypto/glue_helper.c
@@ -176,9 +176,6 @@ __glue_cbc_decrypt_128bit(const struct common_glue_ctx *gctx,
 				src -= 1;
 				dst -= 1;
 			} while (nbytes >= func_bytes);
-
-			if (nbytes < bsize)
-				goto done;
 		}
 	}
 
diff --git a/arch/x86/crypto/salsa20-x86_64-asm_64.S b/arch/x86/crypto/salsa20-x86_64-asm_64.S
index 9279e0b2d60e..10db30d58006 100644
--- a/arch/x86/crypto/salsa20-x86_64-asm_64.S
+++ b/arch/x86/crypto/salsa20-x86_64-asm_64.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/linkage.h>
 
 # enter salsa20_encrypt_bytes
diff --git a/arch/x86/crypto/sha1-mb/Makefile b/arch/x86/crypto/sha1-mb/Makefile
index 2f8756375df5..815ded3ba90e 100644
--- a/arch/x86/crypto/sha1-mb/Makefile
+++ b/arch/x86/crypto/sha1-mb/Makefile
@@ -1,7 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0
 #
 # Arch-specific CryptoAPI modules.
 #
 
+OBJECT_FILES_NON_STANDARD := y
+
 avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\
                                 $(comma)4)$(comma)%ymm2,yes,no)
 ifeq ($(avx2_supported),yes)
diff --git a/arch/x86/crypto/sha1_avx2_x86_64_asm.S b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
index 1cd792db15ef..9f712a7dfd79 100644
--- a/arch/x86/crypto/sha1_avx2_x86_64_asm.S
+++ b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
@@ -89,7 +89,7 @@
 #define	REG_RE	%rdx
 #define	REG_RTA	%r12
 #define	REG_RTB	%rbx
-#define	REG_T1	%ebp
+#define	REG_T1	%r11d
 #define	xmm_mov	vmovups
 #define	avx2_zeroupper	vzeroupper
 #define	RND_F1	1
@@ -117,11 +117,10 @@
 	.set T1, REG_T1
 .endm
 
-#define K_BASE		%r8
 #define HASH_PTR	%r9
+#define BLOCKS_CTR	%r8
 #define BUFFER_PTR	%r10
 #define BUFFER_PTR2	%r13
-#define BUFFER_END	%r11
 
 #define PRECALC_BUF	%r14
 #define WK_BUF		%r15
@@ -205,14 +204,14 @@
 		 * blended AVX2 and ALU instruction scheduling
 		 * 1 vector iteration per 8 rounds
 		 */
-		vmovdqu ((i * 2) + PRECALC_OFFSET)(BUFFER_PTR), W_TMP
+		vmovdqu (i * 2)(BUFFER_PTR), W_TMP
 	.elseif ((i & 7) == 1)
-		vinsertf128 $1, (((i-1) * 2)+PRECALC_OFFSET)(BUFFER_PTR2),\
+		vinsertf128 $1, ((i-1) * 2)(BUFFER_PTR2),\
 			 WY_TMP, WY_TMP
 	.elseif ((i & 7) == 2)
 		vpshufb YMM_SHUFB_BSWAP, WY_TMP, WY
 	.elseif ((i & 7) == 4)
-		vpaddd  K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 	.elseif ((i & 7) == 7)
 		vmovdqu  WY_TMP, PRECALC_WK(i&~7)
 
@@ -255,7 +254,7 @@
 		vpxor	WY, WY_TMP, WY_TMP
 	.elseif ((i & 7) == 7)
 		vpxor	WY_TMP2, WY_TMP, WY
-		vpaddd	K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 		vmovdqu	WY_TMP, PRECALC_WK(i&~7)
 
 		PRECALC_ROTATE_WY
@@ -291,7 +290,7 @@
 		vpsrld	$30, WY, WY
 		vpor	WY, WY_TMP, WY
 	.elseif ((i & 7) == 7)
-		vpaddd	K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 		vmovdqu	WY_TMP, PRECALC_WK(i&~7)
 
 		PRECALC_ROTATE_WY
@@ -446,6 +445,16 @@
 
 .endm
 
+/* Add constant only if (%2 > %3) condition met (uses RTA as temp)
+ * %1 + %2 >= %3 ? %4 : 0
+ */
+.macro ADD_IF_GE a, b, c, d
+	mov     \a, RTA
+	add     $\d, RTA
+	cmp     $\c, \b
+	cmovge  RTA, \a
+.endm
+
 /*
  * macro implements 80 rounds of SHA-1, for multiple blocks with s/w pipelining
  */
@@ -463,13 +472,16 @@
 	lea	(2*4*80+32)(%rsp), WK_BUF
 
 	# Precalc WK for first 2 blocks
-	PRECALC_OFFSET = 0
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 2, 64
 	.set i, 0
 	.rept    160
 		PRECALC i
 		.set i, i + 1
 	.endr
-	PRECALC_OFFSET = 128
+
+	/* Go to next block if needed */
+	ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 3, 128
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128
 	xchg	WK_BUF, PRECALC_BUF
 
 	.align 32
@@ -479,8 +491,8 @@ _loop:
 	 * we use K_BASE value as a signal of a last block,
 	 * it is set below by: cmovae BUFFER_PTR, K_BASE
 	 */
-	cmp	K_BASE, BUFFER_PTR
-	jne	_begin
+	test BLOCKS_CTR, BLOCKS_CTR
+	jnz _begin
 	.align 32
 	jmp	_end
 	.align 32
@@ -512,10 +524,10 @@ _loop0:
 		.set j, j+2
 	.endr
 
-	add	$(2*64), BUFFER_PTR       /* move to next odd-64-byte block */
-	cmp	BUFFER_END, BUFFER_PTR    /* is current block the last one? */
-	cmovae	K_BASE, BUFFER_PTR	/* signal the last iteration smartly */
-
+	/* Update Counter */
+	sub $1, BLOCKS_CTR
+	/* Move to the next block only if needed*/
+	ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 4, 128
 	/*
 	 * rounds
 	 * 60,62,64,66,68
@@ -532,8 +544,8 @@ _loop0:
 	UPDATE_HASH	12(HASH_PTR), D
 	UPDATE_HASH	16(HASH_PTR), E
 
-	cmp	K_BASE, BUFFER_PTR	/* is current block the last one? */
-	je	_loop
+	test	BLOCKS_CTR, BLOCKS_CTR
+	jz	_loop
 
 	mov	TB, B
 
@@ -575,10 +587,10 @@ _loop2:
 		.set j, j+2
 	.endr
 
-	add	$(2*64), BUFFER_PTR2      /* move to next even-64-byte block */
-
-	cmp	BUFFER_END, BUFFER_PTR2   /* is current block the last one */
-	cmovae	K_BASE, BUFFER_PTR       /* signal the last iteration smartly */
+	/* update counter */
+	sub     $1, BLOCKS_CTR
+	/* Move to the next block only if needed*/
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128
 
 	jmp	_loop3
 _loop3:
@@ -625,7 +637,6 @@ _loop3:
 	ENTRY(\name)
 
 	push	%rbx
-	push	%rbp
 	push	%r12
 	push	%r13
 	push	%r14
@@ -641,19 +652,12 @@ _loop3:
 
 	avx2_zeroupper
 
-	lea	K_XMM_AR(%rip), K_BASE
-
+	/* Setup initial values */
 	mov	CTX, HASH_PTR
 	mov	BUF, BUFFER_PTR
-	lea	64(BUF), BUFFER_PTR2
-
-	shl	$6, CNT			/* mul by 64 */
-	add	BUF, CNT
-	add	$64, CNT
-	mov	CNT, BUFFER_END
 
-	cmp	BUFFER_END, BUFFER_PTR2
-	cmovae	K_BASE, BUFFER_PTR2
+	mov	BUF, BUFFER_PTR2
+	mov	CNT, BLOCKS_CTR
 
 	xmm_mov	BSWAP_SHUFB_CTL(%rip), YMM_SHUFB_BSWAP
 
@@ -668,7 +672,6 @@ _loop3:
 	pop	%r14
 	pop	%r13
 	pop	%r12
-	pop	%rbp
 	pop	%rbx
 
 	ret
diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S
index a4109506a5e8..6204bd53528c 100644
--- a/arch/x86/crypto/sha1_ssse3_asm.S
+++ b/arch/x86/crypto/sha1_ssse3_asm.S
@@ -37,7 +37,7 @@
 #define REG_A	%ecx
 #define REG_B	%esi
 #define REG_C	%edi
-#define REG_D	%ebp
+#define REG_D	%r12d
 #define REG_E	%edx
 
 #define REG_T1	%eax
@@ -74,10 +74,10 @@
 	ENTRY(\name)
 
 	push	%rbx
-	push	%rbp
 	push	%r12
+	push	%rbp
+	mov	%rsp, %rbp
 
-	mov	%rsp, %r12
 	sub	$64, %rsp		# allocate workspace
 	and	$~15, %rsp		# align stack
 
@@ -99,10 +99,9 @@
 	xor	%rax, %rax
 	rep stosq
 
-	mov	%r12, %rsp		# deallocate workspace
-
-	pop	%r12
+	mov	%rbp, %rsp		# deallocate workspace
 	pop	%rbp
+	pop	%r12
 	pop	%rbx
 	ret
 
diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/crypto/sha256-avx-asm.S
index e08888a1a5f2..001bbcf93c79 100644
--- a/arch/x86/crypto/sha256-avx-asm.S
+++ b/arch/x86/crypto/sha256-avx-asm.S
@@ -103,7 +103,7 @@ SRND = %rsi       # clobbers INP
 c = %ecx
 d = %r8d
 e = %edx
-TBL = %rbp
+TBL = %r12
 a = %eax
 b = %ebx
 
@@ -350,13 +350,13 @@ a = TMP_
 ENTRY(sha256_transform_avx)
 .align 32
 	pushq   %rbx
-	pushq   %rbp
+	pushq   %r12
 	pushq   %r13
 	pushq   %r14
 	pushq   %r15
-	pushq   %r12
+	pushq	%rbp
+	movq	%rsp, %rbp
 
-	mov	%rsp, %r12
 	subq    $STACK_SIZE, %rsp	# allocate stack space
 	and	$~15, %rsp		# align stack pointer
 
@@ -452,13 +452,12 @@ loop2:
 
 done_hash:
 
-	mov	%r12, %rsp
-
-	popq	%r12
+	mov	%rbp, %rsp
+	popq	%rbp
 	popq    %r15
 	popq    %r14
 	popq    %r13
-	popq    %rbp
+	popq	%r12
 	popq    %rbx
 	ret
 ENDPROC(sha256_transform_avx)
diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S
index 89c8f09787d2..1420db15dcdd 100644
--- a/arch/x86/crypto/sha256-avx2-asm.S
+++ b/arch/x86/crypto/sha256-avx2-asm.S
@@ -98,8 +98,6 @@ d	= %r8d
 e       = %edx	# clobbers NUM_BLKS
 y3	= %esi	# clobbers INP
 
-
-TBL	= %rbp
 SRND	= CTX	# SRND is same register as CTX
 
 a = %eax
@@ -531,7 +529,6 @@ STACK_SIZE	= _RSP      + _RSP_SIZE
 ENTRY(sha256_transform_rorx)
 .align 32
 	pushq	%rbx
-	pushq	%rbp
 	pushq	%r12
 	pushq	%r13
 	pushq	%r14
@@ -568,8 +565,6 @@ ENTRY(sha256_transform_rorx)
 	mov	CTX, _CTX(%rsp)
 
 loop0:
-	lea     K256(%rip), TBL
-
 	## Load first 16 dwords from two blocks
 	VMOVDQ	0*32(INP),XTMP0
 	VMOVDQ	1*32(INP),XTMP1
@@ -597,19 +592,19 @@ last_block_enter:
 
 .align 16
 loop1:
-	vpaddd	0*32(TBL, SRND), X0, XFER
+	vpaddd	K256+0*32(SRND), X0, XFER
 	vmovdqa XFER, 0*32+_XFER(%rsp, SRND)
 	FOUR_ROUNDS_AND_SCHED	_XFER + 0*32
 
-	vpaddd	1*32(TBL, SRND), X0, XFER
+	vpaddd	K256+1*32(SRND), X0, XFER
 	vmovdqa XFER, 1*32+_XFER(%rsp, SRND)
 	FOUR_ROUNDS_AND_SCHED	_XFER + 1*32
 
-	vpaddd	2*32(TBL, SRND), X0, XFER
+	vpaddd	K256+2*32(SRND), X0, XFER
 	vmovdqa XFER, 2*32+_XFER(%rsp, SRND)
 	FOUR_ROUNDS_AND_SCHED	_XFER + 2*32
 
-	vpaddd	3*32(TBL, SRND), X0, XFER
+	vpaddd	K256+3*32(SRND), X0, XFER
 	vmovdqa XFER, 3*32+_XFER(%rsp, SRND)
 	FOUR_ROUNDS_AND_SCHED	_XFER + 3*32
 
@@ -619,10 +614,11 @@ loop1:
 
 loop2:
 	## Do last 16 rounds with no scheduling
-	vpaddd	0*32(TBL, SRND), X0, XFER
+	vpaddd	K256+0*32(SRND), X0, XFER
 	vmovdqa XFER, 0*32+_XFER(%rsp, SRND)
 	DO_4ROUNDS	_XFER + 0*32
-	vpaddd	1*32(TBL, SRND), X1, XFER
+
+	vpaddd	K256+1*32(SRND), X1, XFER
 	vmovdqa XFER, 1*32+_XFER(%rsp, SRND)
 	DO_4ROUNDS	_XFER + 1*32
 	add	$2*32, SRND
@@ -676,9 +672,6 @@ loop3:
 	ja	done_hash
 
 do_last_block:
-	#### do last block
-	lea	K256(%rip), TBL
-
 	VMOVDQ	0*16(INP),XWORD0
 	VMOVDQ	1*16(INP),XWORD1
 	VMOVDQ	2*16(INP),XWORD2
@@ -718,7 +711,6 @@ done_hash:
 	popq	%r14
 	popq	%r13
 	popq	%r12
-	popq	%rbp
 	popq	%rbx
 	ret
 ENDPROC(sha256_transform_rorx)
diff --git a/arch/x86/crypto/sha256-mb/Makefile b/arch/x86/crypto/sha256-mb/Makefile
index 41089e7c400c..53ad6e7db747 100644
--- a/arch/x86/crypto/sha256-mb/Makefile
+++ b/arch/x86/crypto/sha256-mb/Makefile
@@ -1,7 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0
 #
 # Arch-specific CryptoAPI modules.
 #
 
+OBJECT_FILES_NON_STANDARD := y
+
 avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\
                                 $(comma)4)$(comma)%ymm2,yes,no)
 ifeq ($(avx2_supported),yes)
diff --git a/arch/x86/crypto/sha256-ssse3-asm.S b/arch/x86/crypto/sha256-ssse3-asm.S
index 39b83c93e7fd..c6c05ed2c16a 100644
--- a/arch/x86/crypto/sha256-ssse3-asm.S
+++ b/arch/x86/crypto/sha256-ssse3-asm.S
@@ -95,7 +95,7 @@ SRND = %rsi       # clobbers INP
 c = %ecx
 d = %r8d
 e = %edx
-TBL = %rbp
+TBL = %r12
 a = %eax
 b = %ebx
 
@@ -356,13 +356,13 @@ a = TMP_
 ENTRY(sha256_transform_ssse3)
 .align 32
 	pushq   %rbx
-	pushq   %rbp
+	pushq   %r12
 	pushq   %r13
 	pushq   %r14
 	pushq   %r15
-	pushq   %r12
+	pushq   %rbp
+	mov	%rsp, %rbp
 
-	mov	%rsp, %r12
 	subq    $STACK_SIZE, %rsp
 	and	$~15, %rsp
 
@@ -462,13 +462,12 @@ loop2:
 
 done_hash:
 
-	mov	%r12, %rsp
-
-	popq    %r12
+	mov	%rbp, %rsp
+	popq	%rbp
 	popq    %r15
 	popq    %r14
 	popq    %r13
-	popq    %rbp
+	popq    %r12
 	popq    %rbx
 
 	ret
diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S
index 7f5f6c6ec72e..b16d56005162 100644
--- a/arch/x86/crypto/sha512-avx2-asm.S
+++ b/arch/x86/crypto/sha512-avx2-asm.S
@@ -69,8 +69,9 @@ XFER  = YTMP0
 
 BYTE_FLIP_MASK  = %ymm9
 
-# 1st arg
-CTX         = %rdi
+# 1st arg is %rdi, which is saved to the stack and accessed later via %r12
+CTX1        = %rdi
+CTX2        = %r12
 # 2nd arg
 INP         = %rsi
 # 3rd arg
@@ -81,7 +82,7 @@ d           = %r8
 e           = %rdx
 y3          = %rsi
 
-TBL   = %rbp
+TBL   = %rdi # clobbers CTX1
 
 a     = %rax
 b     = %rbx
@@ -91,26 +92,26 @@ g     = %r10
 h     = %r11
 old_h = %r11
 
-T1    = %r12
+T1    = %r12 # clobbers CTX2
 y0    = %r13
 y1    = %r14
 y2    = %r15
 
-y4    = %r12
-
 # Local variables (stack frame)
 XFER_SIZE = 4*8
 SRND_SIZE = 1*8
 INP_SIZE = 1*8
 INPEND_SIZE = 1*8
+CTX_SIZE = 1*8
 RSPSAVE_SIZE = 1*8
-GPRSAVE_SIZE = 6*8
+GPRSAVE_SIZE = 5*8
 
 frame_XFER = 0
 frame_SRND = frame_XFER + XFER_SIZE
 frame_INP = frame_SRND + SRND_SIZE
 frame_INPEND = frame_INP + INP_SIZE
-frame_RSPSAVE = frame_INPEND + INPEND_SIZE
+frame_CTX = frame_INPEND + INPEND_SIZE
+frame_RSPSAVE = frame_CTX + CTX_SIZE
 frame_GPRSAVE = frame_RSPSAVE + RSPSAVE_SIZE
 frame_size = frame_GPRSAVE + GPRSAVE_SIZE
 
@@ -576,12 +577,11 @@ ENTRY(sha512_transform_rorx)
 	mov	%rax, frame_RSPSAVE(%rsp)
 
 	# Save GPRs
-	mov	%rbp, frame_GPRSAVE(%rsp)
-	mov	%rbx, 8*1+frame_GPRSAVE(%rsp)
-	mov	%r12, 8*2+frame_GPRSAVE(%rsp)
-	mov	%r13, 8*3+frame_GPRSAVE(%rsp)
-	mov	%r14, 8*4+frame_GPRSAVE(%rsp)
-	mov	%r15, 8*5+frame_GPRSAVE(%rsp)
+	mov	%rbx, 8*0+frame_GPRSAVE(%rsp)
+	mov	%r12, 8*1+frame_GPRSAVE(%rsp)
+	mov	%r13, 8*2+frame_GPRSAVE(%rsp)
+	mov	%r14, 8*3+frame_GPRSAVE(%rsp)
+	mov	%r15, 8*4+frame_GPRSAVE(%rsp)
 
 	shl	$7, NUM_BLKS	# convert to bytes
 	jz	done_hash
@@ -589,14 +589,17 @@ ENTRY(sha512_transform_rorx)
 	mov	NUM_BLKS, frame_INPEND(%rsp)
 
 	## load initial digest
-	mov	8*0(CTX),a
-	mov	8*1(CTX),b
-	mov	8*2(CTX),c
-	mov	8*3(CTX),d
-	mov	8*4(CTX),e
-	mov	8*5(CTX),f
-	mov	8*6(CTX),g
-	mov	8*7(CTX),h
+	mov	8*0(CTX1), a
+	mov	8*1(CTX1), b
+	mov	8*2(CTX1), c
+	mov	8*3(CTX1), d
+	mov	8*4(CTX1), e
+	mov	8*5(CTX1), f
+	mov	8*6(CTX1), g
+	mov	8*7(CTX1), h
+
+	# save %rdi (CTX) before it gets clobbered
+	mov	%rdi, frame_CTX(%rsp)
 
 	vmovdqa	PSHUFFLE_BYTE_FLIP_MASK(%rip), BYTE_FLIP_MASK
 
@@ -652,14 +655,15 @@ loop2:
 	subq	$1, frame_SRND(%rsp)
 	jne	loop2
 
-	addm	8*0(CTX),a
-	addm	8*1(CTX),b
-	addm	8*2(CTX),c
-	addm	8*3(CTX),d
-	addm	8*4(CTX),e
-	addm	8*5(CTX),f
-	addm	8*6(CTX),g
-	addm	8*7(CTX),h
+	mov	frame_CTX(%rsp), CTX2
+	addm	8*0(CTX2), a
+	addm	8*1(CTX2), b
+	addm	8*2(CTX2), c
+	addm	8*3(CTX2), d
+	addm	8*4(CTX2), e
+	addm	8*5(CTX2), f
+	addm	8*6(CTX2), g
+	addm	8*7(CTX2), h
 
 	mov	frame_INP(%rsp), INP
 	add	$128, INP
@@ -669,12 +673,11 @@ loop2:
 done_hash:
 
 # Restore GPRs
-	mov	frame_GPRSAVE(%rsp)     ,%rbp
-	mov	8*1+frame_GPRSAVE(%rsp) ,%rbx
-	mov	8*2+frame_GPRSAVE(%rsp) ,%r12
-	mov	8*3+frame_GPRSAVE(%rsp) ,%r13
-	mov	8*4+frame_GPRSAVE(%rsp) ,%r14
-	mov	8*5+frame_GPRSAVE(%rsp) ,%r15
+	mov	8*0+frame_GPRSAVE(%rsp), %rbx
+	mov	8*1+frame_GPRSAVE(%rsp), %r12
+	mov	8*2+frame_GPRSAVE(%rsp), %r13
+	mov	8*3+frame_GPRSAVE(%rsp), %r14
+	mov	8*4+frame_GPRSAVE(%rsp), %r15
 
 	# Restore Stack Pointer
 	mov	frame_RSPSAVE(%rsp), %rsp
diff --git a/arch/x86/crypto/sha512-mb/Makefile b/arch/x86/crypto/sha512-mb/Makefile
index 0a57e2103980..90f1ef69152e 100644
--- a/arch/x86/crypto/sha512-mb/Makefile
+++ b/arch/x86/crypto/sha512-mb/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 #
 # Arch-specific CryptoAPI modules.
 #
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb.c b/arch/x86/crypto/sha512-mb/sha512_mb.c
index 2dd3674b5a1e..458409b7568d 100644
--- a/arch/x86/crypto/sha512-mb/sha512_mb.c
+++ b/arch/x86/crypto/sha512-mb/sha512_mb.c
@@ -269,19 +269,19 @@ static struct sha512_hash_ctx
 		 * LAST
 		 */
 		ctx->error = HASH_CTX_ERROR_INVALID_FLAGS;
-		return ctx;
+		goto unlock;
 	}
 
 	if (ctx->status & HASH_CTX_STS_PROCESSING) {
 		/* Cannot submit to a currently processing job. */
 		ctx->error = HASH_CTX_ERROR_ALREADY_PROCESSING;
-		return ctx;
+		goto unlock;
 	}
 
 	if ((ctx->status & HASH_CTX_STS_COMPLETE) && !(flags & HASH_FIRST)) {
 		/* Cannot update a finished job. */
 		ctx->error = HASH_CTX_ERROR_ALREADY_COMPLETED;
-		return ctx;
+		goto unlock;
 	}
 
 
@@ -363,6 +363,7 @@ static struct sha512_hash_ctx
 	}
 
 	ctx = sha512_ctx_mgr_resubmit(mgr, ctx);
+unlock:
 	spin_unlock_irqrestore(&cstate->work_lock, irqflags);
 	return ctx;
 }
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 b3f49d286348..73b471da3622 100644
--- a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
@@ -76,8 +76,8 @@
 #define RT %xmm14
 #define RR %xmm15
 
-#define RID1  %rbp
-#define RID1d %ebp
+#define RID1  %r13
+#define RID1d %r13d
 #define RID2  %rsi
 #define RID2d %esi
 
@@ -259,7 +259,7 @@ __twofish_enc_blk8:
 
 	vmovdqu w(CTX), RK1;
 
-	pushq %rbp;
+	pushq %r13;
 	pushq %rbx;
 	pushq %rcx;
 
@@ -282,7 +282,7 @@ __twofish_enc_blk8:
 
 	popq %rcx;
 	popq %rbx;
-	popq %rbp;
+	popq %r13;
 
 	outunpack_blocks(RC1, RD1, RA1, RB1, RK1, RX0, RY0, RK2);
 	outunpack_blocks(RC2, RD2, RA2, RB2, RK1, RX0, RY0, RK2);
@@ -301,7 +301,7 @@ __twofish_dec_blk8:
 
 	vmovdqu (w+4*4)(CTX), RK1;
 
-	pushq %rbp;
+	pushq %r13;
 	pushq %rbx;
 
 	inpack_blocks(RC1, RD1, RA1, RB1, RK1, RX0, RY0, RK2);
@@ -322,7 +322,7 @@ __twofish_dec_blk8:
 	vmovdqu (w)(CTX), RK1;
 
 	popq %rbx;
-	popq %rbp;
+	popq %r13;
 
 	outunpack_blocks(RA1, RB1, RC1, RD1, RK1, RX0, RY0, RK2);
 	outunpack_blocks(RA2, RB2, RC2, RD2, RK1, RX0, RY0, RK2);