Merge tag 'v6.10-p1' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto updates from Herbert Xu:
 "API:
   - Remove crypto stats interface

  Algorithms:
   - Add faster AES-XTS on modern x86_64 CPUs
   - Forbid curves with order less than 224 bits in ecc (FIPS 186-5)
   - Add ECDSA NIST P521

  Drivers:
   - Expose otp zone in atmel
   - Add dh fallback for primes > 4K in qat
   - Add interface for live migration in qat
   - Use dma for aes requests in starfive
   - Add full DMA support for stm32mpx in stm32
   - Add Tegra Security Engine driver

  Others:
   - Introduce scope-based x509_certificate allocation"

* tag 'v6.10-p1' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (123 commits)
  crypto: atmel-sha204a - provide the otp content
  crypto: atmel-sha204a - add reading from otp zone
  crypto: atmel-i2c - rename read function
  crypto: atmel-i2c - add missing arg description
  crypto: iaa - Use kmemdup() instead of kzalloc() and memcpy()
  crypto: sahara - use 'time_left' variable with wait_for_completion_timeout()
  crypto: api - use 'time_left' variable with wait_for_completion_killable_timeout()
  crypto: caam - i.MX8ULP donot have CAAM page0 access
  crypto: caam - init-clk based on caam-page0-access
  crypto: starfive - Use fallback for unaligned dma access
  crypto: starfive - Do not free stack buffer
  crypto: starfive - Skip unneeded fallback allocation
  crypto: starfive - Skip dma setup for zeroed message
  crypto: hisilicon/sec2 - fix for register offset
  crypto: hisilicon/debugfs - mask the unnecessary info from the dump
  crypto: qat - specify firmware files for 402xx
  crypto: x86/aes-gcm - simplify GCM hash subkey derivation
  crypto: x86/aes-gcm - delete unused GCM assembly code
  crypto: x86/aes-xts - simplify loop in xts_crypt_slowpath()
  hwrng: stm32 - repair clock handling
  ...

9 files changed, 1283 insertions, 698 deletions

diff --git a/arch/x86/Kconfig.assembler b/arch/x86/Kconfig.assembler
index 8ad41da301e5..59aedf32c4ea 100644
--- a/arch/x86/Kconfig.assembler
+++ b/arch/x86/Kconfig.assembler
@@ -25,6 +25,16 @@ config AS_GFNI
 	help
 	  Supported by binutils >= 2.30 and LLVM integrated assembler
 
+config AS_VAES
+	def_bool $(as-instr,vaesenc %ymm0$(comma)%ymm1$(comma)%ymm2)
+	help
+	  Supported by binutils >= 2.30 and LLVM integrated assembler
+
+config AS_VPCLMULQDQ
+	def_bool $(as-instr,vpclmulqdq \$0x10$(comma)%ymm0$(comma)%ymm1$(comma)%ymm2)
+	help
+	  Supported by binutils >= 2.30 and LLVM integrated assembler
+
 config AS_WRUSS
 	def_bool $(as-instr,wrussq %rax$(comma)(%rbx))
 	help
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index 9aa46093c91b..9c5ce5613738 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -48,7 +48,8 @@ chacha-x86_64-$(CONFIG_AS_AVX512) += chacha-avx512vl-x86_64.o
 
 obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o
 aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o
-aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o aes_ctrby8_avx-x86_64.o
+aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o \
+	aes_ctrby8_avx-x86_64.o aes-xts-avx-x86_64.o
 
 obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o
 sha1-ssse3-y := sha1_avx2_x86_64_asm.o sha1_ssse3_asm.o sha1_ssse3_glue.o
diff --git a/arch/x86/crypto/aes-xts-avx-x86_64.S b/arch/x86/crypto/aes-xts-avx-x86_64.S
new file mode 100644
index 000000000000..48f97b79f7a9
--- /dev/null
+++ b/arch/x86/crypto/aes-xts-avx-x86_64.S
@@ -0,0 +1,845 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * AES-XTS for modern x86_64 CPUs
+ *
+ * Copyright 2024 Google LLC
+ *
+ * Author: Eric Biggers <ebiggers@google.com>
+ */
+
+/*
+ * This file implements AES-XTS for modern x86_64 CPUs.  To handle the
+ * complexities of coding for x86 SIMD, e.g. where every vector length needs
+ * different code, it uses a macro to generate several implementations that
+ * share similar source code but are targeted at different CPUs, listed below:
+ *
+ * AES-NI + AVX
+ *    - 128-bit vectors (1 AES block per vector)
+ *    - VEX-coded instructions
+ *    - xmm0-xmm15
+ *    - This is for older CPUs that lack VAES but do have AVX.
+ *
+ * VAES + VPCLMULQDQ + AVX2
+ *    - 256-bit vectors (2 AES blocks per vector)
+ *    - VEX-coded instructions
+ *    - ymm0-ymm15
+ *    - This is for CPUs that have VAES but lack AVX512 or AVX10,
+ *      e.g. Intel's Alder Lake and AMD's Zen 3.
+ *
+ * VAES + VPCLMULQDQ + AVX10/256 + BMI2
+ *    - 256-bit vectors (2 AES blocks per vector)
+ *    - EVEX-coded instructions
+ *    - ymm0-ymm31
+ *    - This is for CPUs that have AVX512 but where using zmm registers causes
+ *      downclocking, and for CPUs that have AVX10/256 but not AVX10/512.
+ *    - By "AVX10/256" we really mean (AVX512BW + AVX512VL) || AVX10/256.
+ *      To avoid confusion with 512-bit, we just write AVX10/256.
+ *
+ * VAES + VPCLMULQDQ + AVX10/512 + BMI2
+ *    - Same as the previous one, but upgrades to 512-bit vectors
+ *      (4 AES blocks per vector) in zmm0-zmm31.
+ *    - This is for CPUs that have good AVX512 or AVX10/512 support.
+ *
+ * This file doesn't have an implementation for AES-NI alone (without AVX), as
+ * the lack of VEX would make all the assembly code different.
+ *
+ * When we use VAES, we also use VPCLMULQDQ to parallelize the computation of
+ * the XTS tweaks.  This avoids a bottleneck.  Currently there don't seem to be
+ * any CPUs that support VAES but not VPCLMULQDQ.  If that changes, we might
+ * need to start also providing an implementation using VAES alone.
+ *
+ * The AES-XTS implementations in this file support everything required by the
+ * crypto API, including support for arbitrary input lengths and multi-part
+ * processing.  However, they are most heavily optimized for the common case of
+ * power-of-2 length inputs that are processed in a single part (disk sectors).
+ */
+
+#include <linux/linkage.h>
+#include <linux/cfi_types.h>
+
+.section .rodata
+.p2align 4
+.Lgf_poly:
+	// The low 64 bits of this value represent the polynomial x^7 + x^2 + x
+	// + 1.  It is the value that must be XOR'd into the low 64 bits of the
+	// tweak each time a 1 is carried out of the high 64 bits.
+	//
+	// The high 64 bits of this value is just the internal carry bit that
+	// exists when there's a carry out of the low 64 bits of the tweak.
+	.quad	0x87, 1
+
+	// This table contains constants for vpshufb and vpblendvb, used to
+	// handle variable byte shifts and blending during ciphertext stealing
+	// on CPUs that don't support AVX10-style masking.
+.Lcts_permute_table:
+	.byte	0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80
+	.byte	0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80
+	.byte	0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07
+	.byte	0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f
+	.byte	0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80
+	.byte	0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80
+.text
+
+// Function parameters
+.set	KEY,		%rdi	// Initially points to crypto_aes_ctx, then is
+				// advanced to point to 7th-from-last round key
+.set	SRC,		%rsi	// Pointer to next source data
+.set	DST,		%rdx	// Pointer to next destination data
+.set	LEN,		%ecx	// Remaining length in bytes
+.set	LEN8,		%cl
+.set	LEN64,		%rcx
+.set	TWEAK,		%r8	// Pointer to next tweak
+
+// %rax holds the AES key length in bytes.
+.set	KEYLEN,		%eax
+.set	KEYLEN64,	%rax
+
+// %r9-r11 are available as temporaries.
+
+.macro	_define_Vi	i
+.if VL == 16
+	.set	V\i,		%xmm\i
+.elseif VL == 32
+	.set	V\i,		%ymm\i
+.elseif VL == 64
+	.set	V\i,		%zmm\i
+.else
+	.error "Unsupported Vector Length (VL)"
+.endif
+.endm
+
+.macro _define_aliases
+	// Define register aliases V0-V15, or V0-V31 if all 32 SIMD registers
+	// are available, that map to the xmm, ymm, or zmm registers according
+	// to the selected Vector Length (VL).
+	_define_Vi	0
+	_define_Vi	1
+	_define_Vi	2
+	_define_Vi	3
+	_define_Vi	4
+	_define_Vi	5
+	_define_Vi	6
+	_define_Vi	7
+	_define_Vi	8
+	_define_Vi	9
+	_define_Vi	10
+	_define_Vi	11
+	_define_Vi	12
+	_define_Vi	13
+	_define_Vi	14
+	_define_Vi	15
+.if USE_AVX10
+	_define_Vi	16
+	_define_Vi	17
+	_define_Vi	18
+	_define_Vi	19
+	_define_Vi	20
+	_define_Vi	21
+	_define_Vi	22
+	_define_Vi	23
+	_define_Vi	24
+	_define_Vi	25
+	_define_Vi	26
+	_define_Vi	27
+	_define_Vi	28
+	_define_Vi	29
+	_define_Vi	30
+	_define_Vi	31
+.endif
+
+	// V0-V3 hold the data blocks during the main loop, or temporary values
+	// otherwise.  V4-V5 hold temporary values.
+
+	// V6-V9 hold XTS tweaks.  Each 128-bit lane holds one tweak.
+	.set	TWEAK0_XMM,	%xmm6
+	.set	TWEAK0,		V6
+	.set	TWEAK1_XMM,	%xmm7
+	.set	TWEAK1,		V7
+	.set	TWEAK2,		V8
+	.set	TWEAK3,		V9
+
+	// V10-V13 are used for computing the next values of TWEAK[0-3].
+	.set	NEXT_TWEAK0,	V10
+	.set	NEXT_TWEAK1,	V11
+	.set	NEXT_TWEAK2,	V12
+	.set	NEXT_TWEAK3,	V13
+
+	// V14 holds the constant from .Lgf_poly, copied to all 128-bit lanes.
+	.set	GF_POLY_XMM,	%xmm14
+	.set	GF_POLY,	V14
+
+	// V15 holds the key for AES "round 0", copied to all 128-bit lanes.
+	.set	KEY0_XMM,	%xmm15
+	.set	KEY0,		V15
+
+	// If 32 SIMD registers are available, then V16-V29 hold the remaining
+	// AES round keys, copied to all 128-bit lanes.
+	//
+	// AES-128, AES-192, and AES-256 use different numbers of round keys.
+	// To allow handling all three variants efficiently, we align the round
+	// keys to the *end* of this register range.  I.e., AES-128 uses
+	// KEY5-KEY14, AES-192 uses KEY3-KEY14, and AES-256 uses KEY1-KEY14.
+	// (All also use KEY0 for the XOR-only "round" at the beginning.)
+.if USE_AVX10
+	.set	KEY1_XMM,	%xmm16
+	.set	KEY1,		V16
+	.set	KEY2_XMM,	%xmm17
+	.set	KEY2,		V17
+	.set	KEY3_XMM,	%xmm18
+	.set	KEY3,		V18
+	.set	KEY4_XMM,	%xmm19
+	.set	KEY4,		V19
+	.set	KEY5_XMM,	%xmm20
+	.set	KEY5,		V20
+	.set	KEY6_XMM,	%xmm21
+	.set	KEY6,		V21
+	.set	KEY7_XMM,	%xmm22
+	.set	KEY7,		V22
+	.set	KEY8_XMM,	%xmm23
+	.set	KEY8,		V23
+	.set	KEY9_XMM,	%xmm24
+	.set	KEY9,		V24
+	.set	KEY10_XMM,	%xmm25
+	.set	KEY10,		V25
+	.set	KEY11_XMM,	%xmm26
+	.set	KEY11,		V26
+	.set	KEY12_XMM,	%xmm27
+	.set	KEY12,		V27
+	.set	KEY13_XMM,	%xmm28
+	.set	KEY13,		V28
+	.set	KEY14_XMM,	%xmm29
+	.set	KEY14,		V29
+.endif
+	// V30-V31 are currently unused.
+.endm
+
+// Move a vector between memory and a register.
+.macro	_vmovdqu	src, dst
+.if VL < 64
+	vmovdqu		\src, \dst
+.else
+	vmovdqu8	\src, \dst
+.endif
+.endm
+
+// Broadcast a 128-bit value into a vector.
+.macro	_vbroadcast128	src, dst
+.if VL == 16 && !USE_AVX10
+	vmovdqu		\src, \dst
+.elseif VL == 32 && !USE_AVX10
+	vbroadcasti128	\src, \dst
+.else
+	vbroadcasti32x4	\src, \dst
+.endif
+.endm
+
+// XOR two vectors together.
+.macro	_vpxor	src1, src2, dst
+.if USE_AVX10
+	vpxord		\src1, \src2, \dst
+.else
+	vpxor		\src1, \src2, \dst
+.endif
+.endm
+
+// XOR three vectors together.
+.macro	_xor3	src1, src2, src3_and_dst
+.if USE_AVX10
+	// vpternlogd with immediate 0x96 is a three-argument XOR.
+	vpternlogd	$0x96, \src1, \src2, \src3_and_dst
+.else
+	vpxor		\src1, \src3_and_dst, \src3_and_dst
+	vpxor		\src2, \src3_and_dst, \src3_and_dst
+.endif
+.endm
+
+// Given a 128-bit XTS tweak in the xmm register \src, compute the next tweak
+// (by multiplying by the polynomial 'x') and write it to \dst.
+.macro	_next_tweak	src, tmp, dst
+	vpshufd		$0x13, \src, \tmp
+	vpaddq		\src, \src, \dst
+	vpsrad		$31, \tmp, \tmp
+	vpand		GF_POLY_XMM, \tmp, \tmp
+	vpxor		\tmp, \dst, \dst
+.endm
+
+// Given the XTS tweak(s) in the vector \src, compute the next vector of
+// tweak(s) (by multiplying by the polynomial 'x^(VL/16)') and write it to \dst.
+//
+// If VL > 16, then there are multiple tweaks, and we use vpclmulqdq to compute
+// all tweaks in the vector in parallel.  If VL=16, we just do the regular
+// computation without vpclmulqdq, as it's the faster method for a single tweak.
+.macro	_next_tweakvec	src, tmp1, tmp2, dst
+.if VL == 16
+	_next_tweak	\src, \tmp1, \dst
+.else
+	vpsrlq		$64 - VL/16, \src, \tmp1
+	vpclmulqdq	$0x01, GF_POLY, \tmp1, \tmp2
+	vpslldq		$8, \tmp1, \tmp1
+	vpsllq		$VL/16, \src, \dst
+	_xor3		\tmp1, \tmp2, \dst
+.endif
+.endm
+
+// Given the first XTS tweak at (TWEAK), compute the first set of tweaks and
+// store them in the vector registers TWEAK0-TWEAK3.  Clobbers V0-V5.
+.macro	_compute_first_set_of_tweaks
+	vmovdqu		(TWEAK), TWEAK0_XMM
+	_vbroadcast128	.Lgf_poly(%rip), GF_POLY
+.if VL == 16
+	// With VL=16, multiplying by x serially is fastest.
+	_next_tweak	TWEAK0, %xmm0, TWEAK1
+	_next_tweak	TWEAK1, %xmm0, TWEAK2
+	_next_tweak	TWEAK2, %xmm0, TWEAK3
+.else
+.if VL == 32
+	// Compute the second block of TWEAK0.
+	_next_tweak	TWEAK0_XMM, %xmm0, %xmm1
+	vinserti128	$1, %xmm1, TWEAK0, TWEAK0
+.elseif VL == 64
+	// Compute the remaining blocks of TWEAK0.
+	_next_tweak	TWEAK0_XMM, %xmm0, %xmm1
+	_next_tweak	%xmm1, %xmm0, %xmm2
+	_next_tweak	%xmm2, %xmm0, %xmm3
+	vinserti32x4	$1, %xmm1, TWEAK0, TWEAK0
+	vinserti32x4	$2, %xmm2, TWEAK0, TWEAK0
+	vinserti32x4	$3, %xmm3, TWEAK0, TWEAK0
+.endif
+	// Compute TWEAK[1-3] from TWEAK0.
+	vpsrlq		$64 - 1*VL/16, TWEAK0, V0
+	vpsrlq		$64 - 2*VL/16, TWEAK0, V2
+	vpsrlq		$64 - 3*VL/16, TWEAK0, V4
+	vpclmulqdq	$0x01, GF_POLY, V0, V1
+	vpclmulqdq	$0x01, GF_POLY, V2, V3
+	vpclmulqdq	$0x01, GF_POLY, V4, V5
+	vpslldq		$8, V0, V0
+	vpslldq		$8, V2, V2
+	vpslldq		$8, V4, V4
+	vpsllq		$1*VL/16, TWEAK0, TWEAK1
+	vpsllq		$2*VL/16, TWEAK0, TWEAK2
+	vpsllq		$3*VL/16, TWEAK0, TWEAK3
+.if USE_AVX10
+	vpternlogd	$0x96, V0, V1, TWEAK1
+	vpternlogd	$0x96, V2, V3, TWEAK2
+	vpternlogd	$0x96, V4, V5, TWEAK3
+.else
+	vpxor		V0, TWEAK1, TWEAK1
+	vpxor		V2, TWEAK2, TWEAK2
+	vpxor		V4, TWEAK3, TWEAK3
+	vpxor		V1, TWEAK1, TWEAK1
+	vpxor		V3, TWEAK2, TWEAK2
+	vpxor		V5, TWEAK3, TWEAK3
+.endif
+.endif
+.endm
+
+// Do one step in computing the next set of tweaks using the method of just
+// multiplying by x repeatedly (the same method _next_tweak uses).
+.macro	_tweak_step_mulx	i
+.if \i == 0
+	.set PREV_TWEAK, TWEAK3
+	.set NEXT_TWEAK, NEXT_TWEAK0
+.elseif \i == 5
+	.set PREV_TWEAK, NEXT_TWEAK0
+	.set NEXT_TWEAK, NEXT_TWEAK1
+.elseif \i == 10
+	.set PREV_TWEAK, NEXT_TWEAK1
+	.set NEXT_TWEAK, NEXT_TWEAK2
+.elseif \i == 15
+	.set PREV_TWEAK, NEXT_TWEAK2
+	.set NEXT_TWEAK, NEXT_TWEAK3
+.endif
+.if \i >= 0 && \i < 20 && \i % 5 == 0
+	vpshufd		$0x13, PREV_TWEAK, V5
+.elseif \i >= 0 && \i < 20 && \i % 5 == 1
+	vpaddq		PREV_TWEAK, PREV_TWEAK, NEXT_TWEAK
+.elseif \i >= 0 && \i < 20 && \i % 5 == 2
+	vpsrad		$31, V5, V5
+.elseif \i >= 0 && \i < 20 && \i % 5 == 3
+	vpand		GF_POLY, V5, V5
+.elseif \i >= 0 && \i < 20 && \i % 5 == 4
+	vpxor		V5, NEXT_TWEAK, NEXT_TWEAK
+.elseif \i == 1000
+	vmovdqa		NEXT_TWEAK0, TWEAK0
+	vmovdqa		NEXT_TWEAK1, TWEAK1
+	vmovdqa		NEXT_TWEAK2, TWEAK2
+	vmovdqa		NEXT_TWEAK3, TWEAK3
+.endif
+.endm
+
+// Do one step in computing the next set of tweaks using the VPCLMULQDQ method
+// (the same method _next_tweakvec uses for VL > 16).  This means multiplying
+// each tweak by x^(4*VL/16) independently.  Since 4*VL/16 is a multiple of 8
+// when VL > 16 (which it is here), the needed shift amounts are byte-aligned,
+// which allows the use of vpsrldq and vpslldq to do 128-bit wide shifts.
+.macro	_tweak_step_pclmul	i
+.if \i == 0
+	vpsrldq		$(128 - 4*VL/16) / 8, TWEAK0, NEXT_TWEAK0
+.elseif \i == 2
+	vpsrldq		$(128 - 4*VL/16) / 8, TWEAK1, NEXT_TWEAK1
+.elseif \i == 4
+	vpsrldq		$(128 - 4*VL/16) / 8, TWEAK2, NEXT_TWEAK2
+.elseif \i == 6
+	vpsrldq		$(128 - 4*VL/16) / 8, TWEAK3, NEXT_TWEAK3
+.elseif \i == 8
+	vpclmulqdq	$0x00, GF_POLY, NEXT_TWEAK0, NEXT_TWEAK0
+.elseif \i == 10
+	vpclmulqdq	$0x00, GF_POLY, NEXT_TWEAK1, NEXT_TWEAK1
+.elseif \i == 12
+	vpclmulqdq	$0x00, GF_POLY, NEXT_TWEAK2, NEXT_TWEAK2
+.elseif \i == 14
+	vpclmulqdq	$0x00, GF_POLY, NEXT_TWEAK3, NEXT_TWEAK3
+.elseif \i == 1000
+	vpslldq		$(4*VL/16) / 8, TWEAK0, TWEAK0
+	vpslldq		$(4*VL/16) / 8, TWEAK1, TWEAK1
+	vpslldq		$(4*VL/16) / 8, TWEAK2, TWEAK2
+	vpslldq		$(4*VL/16) / 8, TWEAK3, TWEAK3
+	_vpxor		NEXT_TWEAK0, TWEAK0, TWEAK0
+	_vpxor		NEXT_TWEAK1, TWEAK1, TWEAK1
+	_vpxor		NEXT_TWEAK2, TWEAK2, TWEAK2
+	_vpxor		NEXT_TWEAK3, TWEAK3, TWEAK3
+.endif
+.endm
+
+// _tweak_step does one step of the computation of the next set of tweaks from
+// TWEAK[0-3].  To complete all steps, this is invoked with increasing values of
+// \i that include at least 0 through 19, then 1000 which signals the last step.
+//
+// This is used to interleave the computation of the next set of tweaks with the
+// AES en/decryptions, which increases performance in some cases.
+.macro	_tweak_step	i
+.if VL == 16
+	_tweak_step_mulx	\i
+.else
+	_tweak_step_pclmul	\i
+.endif
+.endm
+
+.macro	_setup_round_keys	enc
+
+	// Select either the encryption round keys or the decryption round keys.
+.if \enc
+	.set	OFFS, 0
+.else
+	.set	OFFS, 240
+.endif
+
+	// Load the round key for "round 0".
+	_vbroadcast128	OFFS(KEY), KEY0
+
+	// Increment KEY to make it so that 7*16(KEY) is the last round key.
+	// For AES-128, increment by 3*16, resulting in the 10 round keys (not
+	// counting the zero-th round key which was just loaded into KEY0) being
+	// -2*16(KEY) through 7*16(KEY).  For AES-192, increment by 5*16 and use
+	// 12 round keys -4*16(KEY) through 7*16(KEY).  For AES-256, increment
+	// by 7*16 and use 14 round keys -6*16(KEY) through 7*16(KEY).
+	//
+	// This rebasing provides two benefits.  First, it makes the offset to
+	// any round key be in the range [-96, 112], fitting in a signed byte.
+	// This shortens VEX-encoded instructions that access the later round
+	// keys which otherwise would need 4-byte offsets.  Second, it makes it
+	// easy to do AES-128 and AES-192 by skipping irrelevant rounds at the
+	// beginning.  Skipping rounds at the end doesn't work as well because
+	// the last round needs different instructions.
+	//
+	// An alternative approach would be to roll up all the round loops.  We
+	// don't do that because it isn't compatible with caching the round keys
+	// in registers which we do when possible (see below), and also because
+	// it seems unwise to rely *too* heavily on the CPU's branch predictor.
+	lea		OFFS-16(KEY, KEYLEN64, 4), KEY
+
+	// If all 32 SIMD registers are available, cache all the round keys.
+.if USE_AVX10
+	cmp		$24, KEYLEN
+	jl		.Laes128\@
+	je		.Laes192\@
+	_vbroadcast128	-6*16(KEY), KEY1
+	_vbroadcast128	-5*16(KEY), KEY2
+.Laes192\@:
+	_vbroadcast128	-4*16(KEY), KEY3
+	_vbroadcast128	-3*16(KEY), KEY4
+.Laes128\@:
+	_vbroadcast128	-2*16(KEY), KEY5
+	_vbroadcast128	-1*16(KEY), KEY6
+	_vbroadcast128	0*16(KEY), KEY7
+	_vbroadcast128	1*16(KEY), KEY8
+	_vbroadcast128	2*16(KEY), KEY9
+	_vbroadcast128	3*16(KEY), KEY10
+	_vbroadcast128	4*16(KEY), KEY11
+	_vbroadcast128	5*16(KEY), KEY12
+	_vbroadcast128	6*16(KEY), KEY13
+	_vbroadcast128	7*16(KEY), KEY14
+.endif
+.endm
+
+// Do a single round of AES encryption (if \enc==1) or decryption (if \enc==0)
+// on the block(s) in \data using the round key(s) in \key.  The register length
+// determines the number of AES blocks en/decrypted.
+.macro	_vaes	enc, last, key, data
+.if \enc
+.if \last
+	vaesenclast	\key, \data, \data
+.else
+	vaesenc		\key, \data, \data
+.endif
+.else
+.if \last
+	vaesdeclast	\key, \data, \data
+.else
+	vaesdec		\key, \data, \data
+.endif
+.endif
+.endm
+
+// Do a single round of AES en/decryption on the block(s) in \data, using the
+// same key for all block(s).  The round key is loaded from the appropriate
+// register or memory location for round \i.  May clobber V4.
+.macro _vaes_1x		enc, last, i, xmm_suffix, data
+.if USE_AVX10
+	_vaes		\enc, \last, KEY\i\xmm_suffix, \data
+.else
+.ifnb \xmm_suffix
+	_vaes		\enc, \last, (\i-7)*16(KEY), \data
+.else
+	_vbroadcast128	(\i-7)*16(KEY), V4
+	_vaes		\enc, \last, V4, \data
+.endif
+.endif
+.endm
+
+// Do a single round of AES en/decryption on the blocks in registers V0-V3,
+// using the same key for all blocks.  The round key is loaded from the
+// appropriate register or memory location for round \i.  In addition, does two
+// steps of the computation of the next set of tweaks.  May clobber V4.
+.macro	_vaes_4x	enc, last, i
+.if USE_AVX10
+	_tweak_step	(2*(\i-5))
+	_vaes		\enc, \last, KEY\i, V0
+	_vaes		\enc, \last, KEY\i, V1
+	_tweak_step	(2*(\i-5) + 1)
+	_vaes		\enc, \last, KEY\i, V2
+	_vaes		\enc, \last, KEY\i, V3
+.else
+	_vbroadcast128	(\i-7)*16(KEY), V4
+	_tweak_step	(2*(\i-5))
+	_vaes		\enc, \last, V4, V0
+	_vaes		\enc, \last, V4, V1
+	_tweak_step	(2*(\i-5) + 1)
+	_vaes		\enc, \last, V4, V2
+	_vaes		\enc, \last, V4, V3
+.endif
+.endm
+
+// Do tweaked AES en/decryption (i.e., XOR with \tweak, then AES en/decrypt,
+// then XOR with \tweak again) of the block(s) in \data.  To process a single
+// block, use xmm registers and set \xmm_suffix=_XMM.  To process a vector of
+// length VL, use V* registers and leave \xmm_suffix empty.  May clobber V4.
+.macro	_aes_crypt	enc, xmm_suffix, tweak, data
+	_xor3		KEY0\xmm_suffix, \tweak, \data
+	cmp		$24, KEYLEN
+	jl		.Laes128\@
+	je		.Laes192\@
+	_vaes_1x	\enc, 0, 1, \xmm_suffix, \data
+	_vaes_1x	\enc, 0, 2, \xmm_suffix, \data
+.Laes192\@:
+	_vaes_1x	\enc, 0, 3, \xmm_suffix, \data
+	_vaes_1x	\enc, 0, 4, \xmm_suffix, \data
+.Laes128\@:
+	_vaes_1x	\enc, 0, 5, \xmm_suffix, \data
+	_vaes_1x	\enc, 0, 6, \xmm_suffix, \data
+	_vaes_1x	\enc, 0, 7, \xmm_suffix, \data
+	_vaes_1x	\enc, 0, 8, \xmm_suffix, \data
+	_vaes_1x	\enc, 0, 9, \xmm_suffix, \data
+	_vaes_1x	\enc, 0, 10, \xmm_suffix, \data
+	_vaes_1x	\enc, 0, 11, \xmm_suffix, \data
+	_vaes_1x	\enc, 0, 12, \xmm_suffix, \data
+	_vaes_1x	\enc, 0, 13, \xmm_suffix, \data
+	_vaes_1x	\enc, 1, 14, \xmm_suffix, \data
+	_vpxor		\tweak, \data, \data
+.endm
+
+.macro	_aes_xts_crypt	enc
+	_define_aliases
+
+.if !\enc
+	// When decrypting a message whose length isn't a multiple of the AES
+	// block length, exclude the last full block from the main loop by
+	// subtracting 16 from LEN.  This is needed because ciphertext stealing
+	// decryption uses the last two tweaks in reverse order.  We'll handle
+	// the last full block and the partial block specially at the end.
+	lea		-16(LEN), %eax
+	test		$15, LEN8
+	cmovnz		%eax, LEN
+.endif
+
+	// Load the AES key length: 16 (AES-128), 24 (AES-192), or 32 (AES-256).
+	movl		480(KEY), KEYLEN
+
+	// Setup the pointer to the round keys and cache as many as possible.
+	_setup_round_keys	\enc
+
+	// Compute the first set of tweaks TWEAK[0-3].
+	_compute_first_set_of_tweaks
+
+	sub		$4*VL, LEN
+	jl		.Lhandle_remainder\@
+
+.Lmain_loop\@:
+	// This is the main loop, en/decrypting 4*VL bytes per iteration.
+
+	// XOR each source block with its tweak and the zero-th round key.
+.if USE_AVX10
+	vmovdqu8	0*VL(SRC), V0
+	vmovdqu8	1*VL(SRC), V1
+	vmovdqu8	2*VL(SRC), V2
+	vmovdqu8	3*VL(SRC), V3
+	vpternlogd	$0x96, TWEAK0, KEY0, V0
+	vpternlogd	$0x96, TWEAK1, KEY0, V1
+	vpternlogd	$0x96, TWEAK2, KEY0, V2
+	vpternlogd	$0x96, TWEAK3, KEY0, V3
+.else
+	vpxor		0*VL(SRC), KEY0, V0
+	vpxor		1*VL(SRC), KEY0, V1
+	vpxor		2*VL(SRC), KEY0, V2
+	vpxor		3*VL(SRC), KEY0, V3
+	vpxor		TWEAK0, V0, V0
+	vpxor		TWEAK1, V1, V1
+	vpxor		TWEAK2, V2, V2
+	vpxor		TWEAK3, V3, V3
+.endif
+	cmp		$24, KEYLEN
+	jl		.Laes128\@
+	je		.Laes192\@
+	// Do all the AES rounds on the data blocks, interleaved with
+	// the computation of the next set of tweaks.
+	_vaes_4x	\enc, 0, 1
+	_vaes_4x	\enc, 0, 2
+.Laes192\@:
+	_vaes_4x	\enc, 0, 3
+	_vaes_4x	\enc, 0, 4
+.Laes128\@:
+	_vaes_4x	\enc, 0, 5
+	_vaes_4x	\enc, 0, 6
+	_vaes_4x	\enc, 0, 7
+	_vaes_4x	\enc, 0, 8
+	_vaes_4x	\enc, 0, 9
+	_vaes_4x	\enc, 0, 10
+	_vaes_4x	\enc, 0, 11
+	_vaes_4x	\enc, 0, 12
+	_vaes_4x	\enc, 0, 13
+	_vaes_4x	\enc, 1, 14
+
+	// XOR in the tweaks again.
+	_vpxor		TWEAK0, V0, V0
+	_vpxor		TWEAK1, V1, V1
+	_vpxor		TWEAK2, V2, V2
+	_vpxor		TWEAK3, V3, V3
+
+	// Store the destination blocks.
+	_vmovdqu	V0, 0*VL(DST)
+	_vmovdqu	V1, 1*VL(DST)
+	_vmovdqu	V2, 2*VL(DST)
+	_vmovdqu	V3, 3*VL(DST)
+
+	// Finish computing the next set of tweaks.
+	_tweak_step	1000
+
+	add		$4*VL, SRC
+	add		$4*VL, DST
+	sub		$4*VL, LEN
+	jge		.Lmain_loop\@
+
+	// Check for the uncommon case where the data length isn't a multiple of
+	// 4*VL.  Handle it out-of-line in order to optimize for the common
+	// case.  In the common case, just fall through to the ret.
+	test		$4*VL-1, LEN8
+	jnz		.Lhandle_remainder\@
+.Ldone\@:
+	// Store the next tweak back to *TWEAK to support continuation calls.
+	vmovdqu		TWEAK0_XMM, (TWEAK)
+.if VL > 16
+	vzeroupper
+.endif
+	RET
+
+.Lhandle_remainder\@:
+
+	// En/decrypt any remaining full blocks, one vector at a time.
+.if VL > 16
+	add		$3*VL, LEN	// Undo extra sub of 4*VL, then sub VL.
+	jl		.Lvec_at_a_time_done\@
+.Lvec_at_a_time\@:
+	_vmovdqu	(SRC), V0
+	_aes_crypt	\enc, , TWEAK0, V0
+	_vmovdqu	V0, (DST)
+	_next_tweakvec	TWEAK0, V0, V1, TWEAK0
+	add		$VL, SRC
+	add		$VL, DST
+	sub		$VL, LEN
+	jge		.Lvec_at_a_time\@
+.Lvec_at_a_time_done\@:
+	add		$VL-16, LEN	// Undo extra sub of VL, then sub 16.
+.else
+	add		$4*VL-16, LEN	// Undo extra sub of 4*VL, then sub 16.
+.endif
+
+	// En/decrypt any remaining full blocks, one at a time.
+	jl		.Lblock_at_a_time_done\@
+.Lblock_at_a_time\@:
+	vmovdqu		(SRC), %xmm0
+	_aes_crypt	\enc, _XMM, TWEAK0_XMM, %xmm0
+	vmovdqu		%xmm0, (DST)
+	_next_tweak	TWEAK0_XMM, %xmm0, TWEAK0_XMM
+	add		$16, SRC
+	add		$16, DST
+	sub		$16, LEN
+	jge		.Lblock_at_a_time\@
+.Lblock_at_a_time_done\@:
+	add		$16, LEN	// Undo the extra sub of 16.
+	// Now 0 <= LEN <= 15.  If LEN is zero, we're done.
+	jz		.Ldone\@
+
+	// Otherwise 1 <= LEN <= 15, but the real remaining length is 16 + LEN.
+	// Do ciphertext stealing to process the last 16 + LEN bytes.
+
+.if \enc
+	// If encrypting, the main loop already encrypted the last full block to
+	// create the CTS intermediate ciphertext.  Prepare for the rest of CTS
+	// by rewinding the pointers and loading the intermediate ciphertext.
+	sub		$16, SRC
+	sub		$16, DST
+	vmovdqu		(DST), %xmm0
+.else
+	// If decrypting, the main loop didn't decrypt the last full block
+	// because CTS decryption uses the last two tweaks in reverse order.
+	// Do it now by advancing the tweak and decrypting the last full block.
+	_next_tweak	TWEAK0_XMM, %xmm0, TWEAK1_XMM
+	vmovdqu		(SRC), %xmm0
+	_aes_crypt	\enc, _XMM, TWEAK1_XMM, %xmm0
+.endif
+
+.if USE_AVX10
+	// Create a mask that has the first LEN bits set.
+	mov		$-1, %r9d
+	bzhi		LEN, %r9d, %r9d
+	kmovd		%r9d, %k1
+
+	// Swap the first LEN bytes of the en/decryption of the last full block
+	// with the partial block.  Note that to support in-place en/decryption,
+	// the load from the src partial block must happen before the store to
+	// the dst partial block.
+	vmovdqa		%xmm0, %xmm1
+	vmovdqu8	16(SRC), %xmm0{%k1}
+	vmovdqu8	%xmm1, 16(DST){%k1}
+.else
+	lea		.Lcts_permute_table(%rip), %r9
+
+	// Load the src partial block, left-aligned.  Note that to support
+	// in-place en/decryption, this must happen before the store to the dst
+	// partial block.
+	vmovdqu		(SRC, LEN64, 1), %xmm1
+
+	// Shift the first LEN bytes of the en/decryption of the last full block
+	// to the end of a register, then store it to DST+LEN.  This stores the
+	// dst partial block.  It also writes to the second part of the dst last
+	// full block, but that part is overwritten later.
+	vpshufb		(%r9, LEN64, 1), %xmm0, %xmm2
+	vmovdqu		%xmm2, (DST, LEN64, 1)
+
+	// Make xmm3 contain [16-LEN,16-LEN+1,...,14,15,0x80,0x80,...].
+	sub		LEN64, %r9
+	vmovdqu		32(%r9), %xmm3
+
+	// Shift the src partial block to the beginning of its register.
+	vpshufb		%xmm3, %xmm1, %xmm1
+
+	// Do a blend to generate the src partial block followed by the second
+	// part of the en/decryption of the last full block.
+	vpblendvb	%xmm3, %xmm0, %xmm1, %xmm0
+.endif
+	// En/decrypt again and store the last full block.
+	_aes_crypt	\enc, _XMM, TWEAK0_XMM, %xmm0
+	vmovdqu		%xmm0, (DST)
+	jmp		.Ldone\@
+.endm
+
+// void aes_xts_encrypt_iv(const struct crypto_aes_ctx *tweak_key,
+//			   u8 iv[AES_BLOCK_SIZE]);
+SYM_TYPED_FUNC_START(aes_xts_encrypt_iv)
+	vmovdqu		(%rsi), %xmm0
+	vpxor		(%rdi), %xmm0, %xmm0
+	movl		480(%rdi), %eax		// AES key length
+	lea		-16(%rdi, %rax, 4), %rdi
+	cmp		$24, %eax
+	jl		.Lencrypt_iv_aes128
+	je		.Lencrypt_iv_aes192
+	vaesenc		-6*16(%rdi), %xmm0, %xmm0
+	vaesenc		-5*16(%rdi), %xmm0, %xmm0
+.Lencrypt_iv_aes192:
+	vaesenc		-4*16(%rdi), %xmm0, %xmm0
+	vaesenc		-3*16(%rdi), %xmm0, %xmm0
+.Lencrypt_iv_aes128:
+	vaesenc		-2*16(%rdi), %xmm0, %xmm0
+	vaesenc		-1*16(%rdi), %xmm0, %xmm0
+	vaesenc		0*16(%rdi), %xmm0, %xmm0
+	vaesenc		1*16(%rdi), %xmm0, %xmm0
+	vaesenc		2*16(%rdi), %xmm0, %xmm0
+	vaesenc		3*16(%rdi), %xmm0, %xmm0
+	vaesenc		4*16(%rdi), %xmm0, %xmm0
+	vaesenc		5*16(%rdi), %xmm0, %xmm0
+	vaesenc		6*16(%rdi), %xmm0, %xmm0
+	vaesenclast	7*16(%rdi), %xmm0, %xmm0
+	vmovdqu		%xmm0, (%rsi)
+	RET
+SYM_FUNC_END(aes_xts_encrypt_iv)
+
+// Below are the actual AES-XTS encryption and decryption functions,
+// instantiated from the above macro.  They all have the following prototype:
+//
+// void (*xts_asm_func)(const struct crypto_aes_ctx *key,
+//			const u8 *src, u8 *dst, unsigned int len,
+//			u8 tweak[AES_BLOCK_SIZE]);
+//
+// |key| is the data key.  |tweak| contains the next tweak; the encryption of
+// the original IV with the tweak key was already done.  This function supports
+// incremental computation, but |len| must always be >= 16 (AES_BLOCK_SIZE), and
+// |len| must be a multiple of 16 except on the last call.  If |len| is a
+// multiple of 16, then this function updates |tweak| to contain the next tweak.
+
+.set	VL, 16
+.set	USE_AVX10, 0
+SYM_TYPED_FUNC_START(aes_xts_encrypt_aesni_avx)
+	_aes_xts_crypt	1
+SYM_FUNC_END(aes_xts_encrypt_aesni_avx)
+SYM_TYPED_FUNC_START(aes_xts_decrypt_aesni_avx)
+	_aes_xts_crypt	0
+SYM_FUNC_END(aes_xts_decrypt_aesni_avx)
+
+#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
+.set	VL, 32
+.set	USE_AVX10, 0
+SYM_TYPED_FUNC_START(aes_xts_encrypt_vaes_avx2)
+	_aes_xts_crypt	1
+SYM_FUNC_END(aes_xts_encrypt_vaes_avx2)
+SYM_TYPED_FUNC_START(aes_xts_decrypt_vaes_avx2)
+	_aes_xts_crypt	0
+SYM_FUNC_END(aes_xts_decrypt_vaes_avx2)
+
+.set	VL, 32
+.set	USE_AVX10, 1
+SYM_TYPED_FUNC_START(aes_xts_encrypt_vaes_avx10_256)
+	_aes_xts_crypt	1
+SYM_FUNC_END(aes_xts_encrypt_vaes_avx10_256)
+SYM_TYPED_FUNC_START(aes_xts_decrypt_vaes_avx10_256)
+	_aes_xts_crypt	0
+SYM_FUNC_END(aes_xts_decrypt_vaes_avx10_256)
+
+.set	VL, 64
+.set	USE_AVX10, 1
+SYM_TYPED_FUNC_START(aes_xts_encrypt_vaes_avx10_512)
+	_aes_xts_crypt	1
+SYM_FUNC_END(aes_xts_encrypt_vaes_avx10_512)
+SYM_TYPED_FUNC_START(aes_xts_decrypt_vaes_avx10_512)
+	_aes_xts_crypt	0
+SYM_FUNC_END(aes_xts_decrypt_vaes_avx10_512)
+#endif /* CONFIG_AS_VAES && CONFIG_AS_VPCLMULQDQ */
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 411d8c83e88a..39066b57a70e 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -83,9 +83,6 @@ ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
 
 .text
 
-
-#define	STACK_OFFSET    8*3
-
 #define AadHash 16*0
 #define AadLen 16*1
 #define InLen (16*1)+8
@@ -116,11 +113,6 @@ ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
 #define arg4 rcx
 #define arg5 r8
 #define arg6 r9
-#define arg7 STACK_OFFSET+8(%rsp)
-#define arg8 STACK_OFFSET+16(%rsp)
-#define arg9 STACK_OFFSET+24(%rsp)
-#define arg10 STACK_OFFSET+32(%rsp)
-#define arg11 STACK_OFFSET+40(%rsp)
 #define keysize 2*15*16(%arg1)
 #endif
 
@@ -1507,184 +1499,6 @@ _esb_loop_\@:
 	MOVADQ		(%r10),\TMP1
 	aesenclast	\TMP1,\XMM0
 .endm
-/*****************************************************************************
-* void aesni_gcm_dec(void *aes_ctx,    // AES Key schedule. Starts on a 16 byte boundary.
-*                   struct gcm_context_data *data
-*                                      // Context data
-*                   u8 *out,           // Plaintext output. Encrypt in-place is allowed.
-*                   const u8 *in,      // Ciphertext input
-*                   u64 plaintext_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 *hash_subkey,   // H, the Hash sub key input. Data starts on a 16-byte boundary.
-*                   const u8 *aad,     // Additional Authentication Data (AAD)
-*                   u64 aad_len,       // Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 bytes
-*                   u8  *auth_tag,     // Authenticated Tag output. The driver will compare this to the
-*                                      // given authentication tag and only return the plaintext if they match.
-*                   u64 auth_tag_len); // Authenticated Tag Length in bytes. Valid values are 16
-*                                      // (most likely), 12 or 8.
-*
-* Assumptions:
-*
-* keys:
-*       keys are pre-expanded and aligned to 16 bytes. we are using the first
-*       set of 11 keys in the data structure void *aes_ctx
-*
-* iv:
-*       0                   1                   2                   3
-*       0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*       |                             Salt  (From the SA)               |
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*       |                     Initialization Vector                     |
-*       |         (This is the sequence number from IPSec header)       |
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*       |                              0x1                              |
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*
-*
-*
-* AAD:
-*       AAD padded to 128 bits with 0
-*       for example, assume AAD is a u32 vector
-*
-*       if AAD is 8 bytes:
-*       AAD[3] = {A0, A1};
-*       padded AAD in xmm register = {A1 A0 0 0}
-*
-*       0                   1                   2                   3
-*       0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*       |                               SPI (A1)                        |
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*       |                     32-bit Sequence Number (A0)               |
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*       |                              0x0                              |
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*
-*                                       AAD Format with 32-bit Sequence Number
-*
-*       if AAD is 12 bytes:
-*       AAD[3] = {A0, A1, A2};
-*       padded AAD in xmm register = {A2 A1 A0 0}
-*
-*       0                   1                   2                   3
-*       0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*       0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*       |                               SPI (A2)                        |
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*       |                 64-bit Extended Sequence Number {A1,A0}       |
-*       |                                                               |
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*       |                              0x0                              |
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*
-*                        AAD Format with 64-bit Extended Sequence Number
-*
-* poly = x^128 + x^127 + x^126 + x^121 + 1
-*
-*****************************************************************************/
-SYM_FUNC_START(aesni_gcm_dec)
-	FUNC_SAVE
-
-	GCM_INIT %arg6, arg7, arg8, arg9
-	GCM_ENC_DEC dec
-	GCM_COMPLETE arg10, arg11
-	FUNC_RESTORE
-	RET
-SYM_FUNC_END(aesni_gcm_dec)
-
-
-/*****************************************************************************
-* void aesni_gcm_enc(void *aes_ctx,      // AES Key schedule. Starts on a 16 byte boundary.
-*                    struct gcm_context_data *data
-*                                        // Context data
-*                    u8 *out,            // Ciphertext output. Encrypt in-place is allowed.
-*                    const u8 *in,       // Plaintext input
-*                    u64 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 *hash_subkey,    // H, the Hash sub key input. Data starts on a 16-byte boundary.
-*                    const u8 *aad,      // Additional Authentication Data (AAD)
-*                    u64 aad_len,        // Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 bytes
-*                    u8 *auth_tag,       // Authenticated Tag output.
-*                    u64 auth_tag_len);  // Authenticated Tag Length in bytes. Valid values are 16 (most likely),
-*                                        // 12 or 8.
-*
-* Assumptions:
-*
-* keys:
-*       keys are pre-expanded and aligned to 16 bytes. we are using the
-*       first set of 11 keys in the data structure void *aes_ctx
-*
-*
-* iv:
-*       0                   1                   2                   3
-*       0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*       |                             Salt  (From the SA)               |
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*       |                     Initialization Vector                     |
-*       |         (This is the sequence number from IPSec header)       |
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*       |                              0x1                              |
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*
-*
-*
-* AAD:
-*       AAD padded to 128 bits with 0
-*       for example, assume AAD is a u32 vector
-*
-*       if AAD is 8 bytes:
-*       AAD[3] = {A0, A1};
-*       padded AAD in xmm register = {A1 A0 0 0}
-*
-*       0                   1                   2                   3
-*       0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*       |                               SPI (A1)                        |
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*       |                     32-bit Sequence Number (A0)               |
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*       |                              0x0                              |
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*
-*                                 AAD Format with 32-bit Sequence Number
-*
-*       if AAD is 12 bytes:
-*       AAD[3] = {A0, A1, A2};
-*       padded AAD in xmm register = {A2 A1 A0 0}
-*
-*       0                   1                   2                   3
-*       0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*       |                               SPI (A2)                        |
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*       |                 64-bit Extended Sequence Number {A1,A0}       |
-*       |                                                               |
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*       |                              0x0                              |
-*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-*
-*                         AAD Format with 64-bit Extended Sequence Number
-*
-* poly = x^128 + x^127 + x^126 + x^121 + 1
-***************************************************************************/
-SYM_FUNC_START(aesni_gcm_enc)
-	FUNC_SAVE
-
-	GCM_INIT %arg6, arg7, arg8, arg9
-	GCM_ENC_DEC enc
-
-	GCM_COMPLETE arg10, arg11
-	FUNC_RESTORE
-	RET
-SYM_FUNC_END(aesni_gcm_enc)
 
 /*****************************************************************************
 * void aesni_gcm_init(void *aes_ctx,      // AES Key schedule. Starts on a 16 byte boundary.
@@ -1820,8 +1634,8 @@ SYM_FUNC_START_LOCAL(_key_expansion_256b)
 SYM_FUNC_END(_key_expansion_256b)
 
 /*
- * int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key,
- *                   unsigned int key_len)
+ * void aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key,
+ *                    unsigned int key_len)
  */
 SYM_FUNC_START(aesni_set_key)
 	FRAME_BEGIN
@@ -1926,7 +1740,6 @@ SYM_FUNC_START(aesni_set_key)
 	sub $0x10, UKEYP
 	cmp TKEYP, KEYP
 	jb .Ldec_key_loop
-	xor AREG, AREG
 #ifndef __x86_64__
 	popl KEYP
 #endif
@@ -2826,28 +2639,24 @@ SYM_FUNC_END(aesni_ctr_enc)
 .previous
 
 /*
- * _aesni_gf128mul_x_ble:		internal ABI
- *	Multiply in GF(2^128) for XTS IVs
+ * _aesni_gf128mul_x_ble: Multiply in GF(2^128) for XTS IVs
  * input:
  *	IV:	current IV
  *	GF128MUL_MASK == mask with 0x87 and 0x01
  * output:
  *	IV:	next IV
  * changed:
- *	CTR:	== temporary value
+ *	KEY:	== temporary value
  */
-#define _aesni_gf128mul_x_ble() \
-	pshufd $0x13, IV, KEY; \
-	paddq IV, IV; \
-	psrad $31, KEY; \
-	pand GF128MUL_MASK, KEY; \
-	pxor KEY, IV;
+.macro _aesni_gf128mul_x_ble
+	pshufd $0x13, IV, KEY
+	paddq IV, IV
+	psrad $31, KEY
+	pand GF128MUL_MASK, KEY
+	pxor KEY, IV
+.endm
 
-/*
- * void aesni_xts_encrypt(const struct crypto_aes_ctx *ctx, u8 *dst,
- *			  const u8 *src, unsigned int len, le128 *iv)
- */
-SYM_FUNC_START(aesni_xts_encrypt)
+.macro	_aesni_xts_crypt	enc
 	FRAME_BEGIN
 #ifndef __x86_64__
 	pushl IVP
@@ -2866,35 +2675,46 @@ SYM_FUNC_START(aesni_xts_encrypt)
 	movups (IVP), IV
 
 	mov 480(KEYP), KLEN
+.if !\enc
+	add $240, KEYP
 
-.Lxts_enc_loop4:
+	test $15, LEN
+	jz .Lxts_loop4\@
+	sub $16, LEN
+.endif
+
+.Lxts_loop4\@:
 	sub $64, LEN
-	jl .Lxts_enc_1x
+	jl .Lxts_1x\@
 
 	movdqa IV, STATE1
 	movdqu 0x00(INP), IN
 	pxor IN, STATE1
 	movdqu IV, 0x00(OUTP)
 
-	_aesni_gf128mul_x_ble()
+	_aesni_gf128mul_x_ble
 	movdqa IV, STATE2
 	movdqu 0x10(INP), IN
 	pxor IN, STATE2
 	movdqu IV, 0x10(OUTP)
 
-	_aesni_gf128mul_x_ble()
+	_aesni_gf128mul_x_ble
 	movdqa IV, STATE3
 	movdqu 0x20(INP), IN
 	pxor IN, STATE3
 	movdqu IV, 0x20(OUTP)
 
-	_aesni_gf128mul_x_ble()
+	_aesni_gf128mul_x_ble
 	movdqa IV, STATE4
 	movdqu 0x30(INP), IN
 	pxor IN, STATE4
 	movdqu IV, 0x30(OUTP)
 
+.if \enc
 	call _aesni_enc4
+.else
+	call _aesni_dec4
+.endif
 
 	movdqu 0x00(OUTP), IN
 	pxor IN, STATE1
@@ -2912,17 +2732,17 @@ SYM_FUNC_START(aesni_xts_encrypt)
 	pxor IN, STATE4
 	movdqu STATE4, 0x30(OUTP)
 
-	_aesni_gf128mul_x_ble()
+	_aesni_gf128mul_x_ble
 
 	add $64, INP
 	add $64, OUTP
 	test LEN, LEN
-	jnz .Lxts_enc_loop4
+	jnz .Lxts_loop4\@
 
-.Lxts_enc_ret_iv:
+.Lxts_ret_iv\@:
 	movups IV, (IVP)
 
-.Lxts_enc_ret:
+.Lxts_ret\@:
 #ifndef __x86_64__
 	popl KLEN
 	popl KEYP
@@ -2932,201 +2752,60 @@ SYM_FUNC_START(aesni_xts_encrypt)
 	FRAME_END
 	RET
 
-.Lxts_enc_1x:
+.Lxts_1x\@:
 	add $64, LEN
-	jz .Lxts_enc_ret_iv
+	jz .Lxts_ret_iv\@
+.if \enc
 	sub $16, LEN
-	jl .Lxts_enc_cts4
+	jl .Lxts_cts4\@
+.endif
 
-.Lxts_enc_loop1:
+.Lxts_loop1\@:
 	movdqu (INP), STATE
+.if \enc
 	pxor IV, STATE
 	call _aesni_enc1
-	pxor IV, STATE
-	_aesni_gf128mul_x_ble()
-
-	test LEN, LEN
-	jz .Lxts_enc_out
-
+.else
 	add $16, INP
 	sub $16, LEN
-	jl .Lxts_enc_cts1
-
-	movdqu STATE, (OUTP)
-	add $16, OUTP
-	jmp .Lxts_enc_loop1
-
-.Lxts_enc_out:
-	movdqu STATE, (OUTP)
-	jmp .Lxts_enc_ret_iv
-
-.Lxts_enc_cts4:
-	movdqa STATE4, STATE
-	sub $16, OUTP
-
-.Lxts_enc_cts1:
-#ifndef __x86_64__
-	lea .Lcts_permute_table, T1
-#else
-	lea .Lcts_permute_table(%rip), T1
-#endif
-	add LEN, INP		/* rewind input pointer */
-	add $16, LEN		/* # bytes in final block */
-	movups (INP), IN1
-
-	mov T1, IVP
-	add $32, IVP
-	add LEN, T1
-	sub LEN, IVP
-	add OUTP, LEN
-
-	movups (T1), %xmm4
-	movaps STATE, IN2
-	pshufb %xmm4, STATE
-	movups STATE, (LEN)
-
-	movups (IVP), %xmm0
-	pshufb %xmm0, IN1
-	pblendvb IN2, IN1
-	movaps IN1, STATE
-
+	jl .Lxts_cts1\@
 	pxor IV, STATE
-	call _aesni_enc1
+	call _aesni_dec1
+.endif
 	pxor IV, STATE
+	_aesni_gf128mul_x_ble
 
-	movups STATE, (OUTP)
-	jmp .Lxts_enc_ret
-SYM_FUNC_END(aesni_xts_encrypt)
-
-/*
- * void aesni_xts_decrypt(const struct crypto_aes_ctx *ctx, u8 *dst,
- *			  const u8 *src, unsigned int len, le128 *iv)
- */
-SYM_FUNC_START(aesni_xts_decrypt)
-	FRAME_BEGIN
-#ifndef __x86_64__
-	pushl IVP
-	pushl LEN
-	pushl KEYP
-	pushl KLEN
-	movl (FRAME_OFFSET+20)(%esp), KEYP	# ctx
-	movl (FRAME_OFFSET+24)(%esp), OUTP	# dst
-	movl (FRAME_OFFSET+28)(%esp), INP	# src
-	movl (FRAME_OFFSET+32)(%esp), LEN	# len
-	movl (FRAME_OFFSET+36)(%esp), IVP	# iv
-	movdqa .Lgf128mul_x_ble_mask, GF128MUL_MASK
-#else
-	movdqa .Lgf128mul_x_ble_mask(%rip), GF128MUL_MASK
-#endif
-	movups (IVP), IV
-
-	mov 480(KEYP), KLEN
-	add $240, KEYP
-
-	test $15, LEN
-	jz .Lxts_dec_loop4
-	sub $16, LEN
-
-.Lxts_dec_loop4:
-	sub $64, LEN
-	jl .Lxts_dec_1x
-
-	movdqa IV, STATE1
-	movdqu 0x00(INP), IN
-	pxor IN, STATE1
-	movdqu IV, 0x00(OUTP)
-
-	_aesni_gf128mul_x_ble()
-	movdqa IV, STATE2
-	movdqu 0x10(INP), IN
-	pxor IN, STATE2
-	movdqu IV, 0x10(OUTP)
-
-	_aesni_gf128mul_x_ble()
-	movdqa IV, STATE3
-	movdqu 0x20(INP), IN
-	pxor IN, STATE3
-	movdqu IV, 0x20(OUTP)
-
-	_aesni_gf128mul_x_ble()
-	movdqa IV, STATE4
-	movdqu 0x30(INP), IN
-	pxor IN, STATE4
-	movdqu IV, 0x30(OUTP)
-
-	call _aesni_dec4
-
-	movdqu 0x00(OUTP), IN
-	pxor IN, STATE1
-	movdqu STATE1, 0x00(OUTP)
-
-	movdqu 0x10(OUTP), IN
-	pxor IN, STATE2
-	movdqu STATE2, 0x10(OUTP)
-
-	movdqu 0x20(OUTP), IN
-	pxor IN, STATE3
-	movdqu STATE3, 0x20(OUTP)
-
-	movdqu 0x30(OUTP), IN
-	pxor IN, STATE4
-	movdqu STATE4, 0x30(OUTP)
-
-	_aesni_gf128mul_x_ble()
-
-	add $64, INP
-	add $64, OUTP
 	test LEN, LEN
-	jnz .Lxts_dec_loop4
-
-.Lxts_dec_ret_iv:
-	movups IV, (IVP)
-
-.Lxts_dec_ret:
-#ifndef __x86_64__
-	popl KLEN
-	popl KEYP
-	popl LEN
-	popl IVP
-#endif
-	FRAME_END
-	RET
-
-.Lxts_dec_1x:
-	add $64, LEN
-	jz .Lxts_dec_ret_iv
-
-.Lxts_dec_loop1:
-	movdqu (INP), STATE
+	jz .Lxts_out\@
 
+.if \enc
 	add $16, INP
 	sub $16, LEN
-	jl .Lxts_dec_cts1
-
-	pxor IV, STATE
-	call _aesni_dec1
-	pxor IV, STATE
-	_aesni_gf128mul_x_ble()
-
-	test LEN, LEN
-	jz .Lxts_dec_out
+	jl .Lxts_cts1\@
+.endif
 
 	movdqu STATE, (OUTP)
 	add $16, OUTP
-	jmp .Lxts_dec_loop1
+	jmp .Lxts_loop1\@
 
-.Lxts_dec_out:
+.Lxts_out\@:
 	movdqu STATE, (OUTP)
-	jmp .Lxts_dec_ret_iv
+	jmp .Lxts_ret_iv\@
 
-.Lxts_dec_cts1:
+.if \enc
+.Lxts_cts4\@:
+	movdqa STATE4, STATE
+	sub $16, OUTP
+.Lxts_cts1\@:
+.else
+.Lxts_cts1\@:
 	movdqa IV, STATE4
-	_aesni_gf128mul_x_ble()
+	_aesni_gf128mul_x_ble
 
 	pxor IV, STATE
 	call _aesni_dec1
 	pxor IV, STATE
-
+.endif
 #ifndef __x86_64__
 	lea .Lcts_permute_table, T1
 #else
@@ -3152,10 +2831,32 @@ SYM_FUNC_START(aesni_xts_decrypt)
 	pblendvb IN2, IN1
 	movaps IN1, STATE
 
+.if \enc
+	pxor IV, STATE
+	call _aesni_enc1
+	pxor IV, STATE
+.else
 	pxor STATE4, STATE
 	call _aesni_dec1
 	pxor STATE4, STATE
+.endif
 
 	movups STATE, (OUTP)
-	jmp .Lxts_dec_ret
-SYM_FUNC_END(aesni_xts_decrypt)
+	jmp .Lxts_ret\@
+.endm
+
+/*
+ * void aesni_xts_enc(const struct crypto_aes_ctx *ctx, u8 *dst,
+ *		      const u8 *src, unsigned int len, le128 *iv)
+ */
+SYM_FUNC_START(aesni_xts_enc)
+	_aesni_xts_crypt	1
+SYM_FUNC_END(aesni_xts_enc)
+
+/*
+ * void aesni_xts_dec(const struct crypto_aes_ctx *ctx, u8 *dst,
+ *		      const u8 *src, unsigned int len, le128 *iv)
+ */
+SYM_FUNC_START(aesni_xts_dec)
+	_aesni_xts_crypt	0
+SYM_FUNC_END(aesni_xts_dec)
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index b1d90c25975a..5b25d2a58aeb 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -40,7 +40,6 @@
 #define AESNI_ALIGN	16
 #define AESNI_ALIGN_ATTR __attribute__ ((__aligned__(AESNI_ALIGN)))
 #define AES_BLOCK_MASK	(~(AES_BLOCK_SIZE - 1))
-#define RFC4106_HASH_SUBKEY_SIZE 16
 #define AESNI_ALIGN_EXTRA ((AESNI_ALIGN - 1) & ~(CRYPTO_MINALIGN - 1))
 #define CRYPTO_AES_CTX_SIZE (sizeof(struct crypto_aes_ctx) + AESNI_ALIGN_EXTRA)
 #define XTS_AES_CTX_SIZE (sizeof(struct aesni_xts_ctx) + AESNI_ALIGN_EXTRA)
@@ -87,8 +86,8 @@ static inline void *aes_align_addr(void *addr)
 	return PTR_ALIGN(addr, AESNI_ALIGN);
 }
 
-asmlinkage int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key,
-			     unsigned int key_len);
+asmlinkage void aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key,
+			      unsigned int key_len);
 asmlinkage void aesni_enc(const void *ctx, u8 *out, const u8 *in);
 asmlinkage void aesni_dec(const void *ctx, u8 *out, const u8 *in);
 asmlinkage void aesni_ecb_enc(struct crypto_aes_ctx *ctx, u8 *out,
@@ -107,11 +106,11 @@ asmlinkage void aesni_cts_cbc_dec(struct crypto_aes_ctx *ctx, u8 *out,
 #define AVX_GEN2_OPTSIZE 640
 #define AVX_GEN4_OPTSIZE 4096
 
-asmlinkage void aesni_xts_encrypt(const struct crypto_aes_ctx *ctx, u8 *out,
-				  const u8 *in, unsigned int len, u8 *iv);
+asmlinkage void aesni_xts_enc(const struct crypto_aes_ctx *ctx, u8 *out,
+			      const u8 *in, unsigned int len, u8 *iv);
 
-asmlinkage void aesni_xts_decrypt(const struct crypto_aes_ctx *ctx, u8 *out,
-				  const u8 *in, unsigned int len, u8 *iv);
+asmlinkage void aesni_xts_dec(const struct crypto_aes_ctx *ctx, u8 *out,
+			      const u8 *in, unsigned int len, u8 *iv);
 
 #ifdef CONFIG_X86_64
 
@@ -233,19 +232,17 @@ static int aes_set_key_common(struct crypto_aes_ctx *ctx,
 {
 	int err;
 
-	if (key_len != AES_KEYSIZE_128 && key_len != AES_KEYSIZE_192 &&
-	    key_len != AES_KEYSIZE_256)
-		return -EINVAL;
-
 	if (!crypto_simd_usable())
-		err = aes_expandkey(ctx, in_key, key_len);
-	else {
-		kernel_fpu_begin();
-		err = aesni_set_key(ctx, in_key, key_len);
-		kernel_fpu_end();
-	}
+		return aes_expandkey(ctx, in_key, key_len);
 
-	return err;
+	err = aes_check_keylen(key_len);
+	if (err)
+		return err;
+
+	kernel_fpu_begin();
+	aesni_set_key(ctx, in_key, key_len);
+	kernel_fpu_end();
+	return 0;
 }
 
 static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
@@ -592,23 +589,12 @@ static int xctr_crypt(struct skcipher_request *req)
 	return err;
 }
 
-static int
-rfc4106_set_hash_subkey(u8 *hash_subkey, const u8 *key, unsigned int key_len)
+static int aes_gcm_derive_hash_subkey(const struct crypto_aes_ctx *aes_key,
+				      u8 hash_subkey[AES_BLOCK_SIZE])
 {
-	struct crypto_aes_ctx ctx;
-	int ret;
-
-	ret = aes_expandkey(&ctx, key, key_len);
-	if (ret)
-		return ret;
-
-	/* Clear the data in the hash sub key container to zero.*/
-	/* We want to cipher all zeros to create the hash sub key. */
-	memset(hash_subkey, 0, RFC4106_HASH_SUBKEY_SIZE);
-
-	aes_encrypt(&ctx, hash_subkey, hash_subkey);
+	static const u8 zeroes[AES_BLOCK_SIZE];
 
-	memzero_explicit(&ctx, sizeof(ctx));
+	aes_encrypt(aes_key, hash_subkey, zeroes);
 	return 0;
 }
 
@@ -626,7 +612,8 @@ static int common_rfc4106_set_key(struct crypto_aead *aead, const u8 *key,
 	memcpy(ctx->nonce, key + key_len, sizeof(ctx->nonce));
 
 	return aes_set_key_common(&ctx->aes_key_expanded, key, key_len) ?:
-	       rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len);
+	       aes_gcm_derive_hash_subkey(&ctx->aes_key_expanded,
+					  ctx->hash_subkey);
 }
 
 /* This is the Integrity Check Value (aka the authentication tag) length and can
@@ -877,7 +864,7 @@ static int helper_rfc4106_decrypt(struct aead_request *req)
 }
 #endif
 
-static int xts_aesni_setkey(struct crypto_skcipher *tfm, const u8 *key,
+static int xts_setkey_aesni(struct crypto_skcipher *tfm, const u8 *key,
 			    unsigned int keylen)
 {
 	struct aesni_xts_ctx *ctx = aes_xts_ctx(tfm);
@@ -898,108 +885,149 @@ static int xts_aesni_setkey(struct crypto_skcipher *tfm, const u8 *key,
 	return aes_set_key_common(&ctx->tweak_ctx, key + keylen, keylen);
 }
 
-static int xts_crypt(struct skcipher_request *req, bool encrypt)
+typedef void (*xts_encrypt_iv_func)(const struct crypto_aes_ctx *tweak_key,
+				    u8 iv[AES_BLOCK_SIZE]);
+typedef void (*xts_crypt_func)(const struct crypto_aes_ctx *key,
+			       const u8 *src, u8 *dst, unsigned int len,
+			       u8 tweak[AES_BLOCK_SIZE]);
+
+/* This handles cases where the source and/or destination span pages. */
+static noinline int
+xts_crypt_slowpath(struct skcipher_request *req, xts_crypt_func crypt_func)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	struct aesni_xts_ctx *ctx = aes_xts_ctx(tfm);
+	const struct aesni_xts_ctx *ctx = aes_xts_ctx(tfm);
 	int tail = req->cryptlen % AES_BLOCK_SIZE;
+	struct scatterlist sg_src[2], sg_dst[2];
 	struct skcipher_request subreq;
 	struct skcipher_walk walk;
+	struct scatterlist *src, *dst;
 	int err;
 
-	if (req->cryptlen < AES_BLOCK_SIZE)
-		return -EINVAL;
-
-	err = skcipher_walk_virt(&walk, req, false);
-	if (!walk.nbytes)
-		return err;
-
-	if (unlikely(tail > 0 && walk.nbytes < walk.total)) {
-		int blocks = DIV_ROUND_UP(req->cryptlen, AES_BLOCK_SIZE) - 2;
-
-		skcipher_walk_abort(&walk);
-
+	/*
+	 * If the message length isn't divisible by the AES block size, then
+	 * separate off the last full block and the partial block.  This ensures
+	 * that they are processed in the same call to the assembly function,
+	 * which is required for ciphertext stealing.
+	 */
+	if (tail) {
 		skcipher_request_set_tfm(&subreq, tfm);
 		skcipher_request_set_callback(&subreq,
 					      skcipher_request_flags(req),
 					      NULL, NULL);
 		skcipher_request_set_crypt(&subreq, req->src, req->dst,
-					   blocks * AES_BLOCK_SIZE, req->iv);
+					   req->cryptlen - tail - AES_BLOCK_SIZE,
+					   req->iv);
 		req = &subreq;
+	}
 
-		err = skcipher_walk_virt(&walk, req, false);
-		if (!walk.nbytes)
-			return err;
-	} else {
-		tail = 0;
+	err = skcipher_walk_virt(&walk, req, false);
+
+	while (walk.nbytes) {
+		kernel_fpu_begin();
+		(*crypt_func)(&ctx->crypt_ctx,
+			      walk.src.virt.addr, walk.dst.virt.addr,
+			      walk.nbytes & ~(AES_BLOCK_SIZE - 1), req->iv);
+		kernel_fpu_end();
+		err = skcipher_walk_done(&walk,
+					 walk.nbytes & (AES_BLOCK_SIZE - 1));
 	}
 
-	kernel_fpu_begin();
+	if (err || !tail)
+		return err;
 
-	/* calculate first value of T */
-	aesni_enc(&ctx->tweak_ctx, walk.iv, walk.iv);
+	/* Do ciphertext stealing with the last full block and partial block. */
 
-	while (walk.nbytes > 0) {
-		int nbytes = walk.nbytes;
-
-		if (nbytes < walk.total)
-			nbytes &= ~(AES_BLOCK_SIZE - 1);
-
-		if (encrypt)
-			aesni_xts_encrypt(&ctx->crypt_ctx,
-					  walk.dst.virt.addr, walk.src.virt.addr,
-					  nbytes, walk.iv);
-		else
-			aesni_xts_decrypt(&ctx->crypt_ctx,
-					  walk.dst.virt.addr, walk.src.virt.addr,
-					  nbytes, walk.iv);
-		kernel_fpu_end();
+	dst = src = scatterwalk_ffwd(sg_src, req->src, req->cryptlen);
+	if (req->dst != req->src)
+		dst = scatterwalk_ffwd(sg_dst, req->dst, req->cryptlen);
 
-		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+	skcipher_request_set_crypt(req, src, dst, AES_BLOCK_SIZE + tail,
+				   req->iv);
 
-		if (walk.nbytes > 0)
-			kernel_fpu_begin();
-	}
+	err = skcipher_walk_virt(&walk, req, false);
+	if (err)
+		return err;
 
-	if (unlikely(tail > 0 && !err)) {
-		struct scatterlist sg_src[2], sg_dst[2];
-		struct scatterlist *src, *dst;
+	kernel_fpu_begin();
+	(*crypt_func)(&ctx->crypt_ctx, walk.src.virt.addr, walk.dst.virt.addr,
+		      walk.nbytes, req->iv);
+	kernel_fpu_end();
 
-		dst = src = scatterwalk_ffwd(sg_src, req->src, req->cryptlen);
-		if (req->dst != req->src)
-			dst = scatterwalk_ffwd(sg_dst, req->dst, req->cryptlen);
+	return skcipher_walk_done(&walk, 0);
+}
 
-		skcipher_request_set_crypt(req, src, dst, AES_BLOCK_SIZE + tail,
-					   req->iv);
+/* __always_inline to avoid indirect call in fastpath */
+static __always_inline int
+xts_crypt(struct skcipher_request *req, xts_encrypt_iv_func encrypt_iv,
+	  xts_crypt_func crypt_func)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct aesni_xts_ctx *ctx = aes_xts_ctx(tfm);
+	const unsigned int cryptlen = req->cryptlen;
+	struct scatterlist *src = req->src;
+	struct scatterlist *dst = req->dst;
 
-		err = skcipher_walk_virt(&walk, &subreq, false);
-		if (err)
-			return err;
+	if (unlikely(cryptlen < AES_BLOCK_SIZE))
+		return -EINVAL;
 
-		kernel_fpu_begin();
-		if (encrypt)
-			aesni_xts_encrypt(&ctx->crypt_ctx,
-					  walk.dst.virt.addr, walk.src.virt.addr,
-					  walk.nbytes, walk.iv);
-		else
-			aesni_xts_decrypt(&ctx->crypt_ctx,
-					  walk.dst.virt.addr, walk.src.virt.addr,
-					  walk.nbytes, walk.iv);
-		kernel_fpu_end();
+	kernel_fpu_begin();
+	(*encrypt_iv)(&ctx->tweak_ctx, req->iv);
 
-		err = skcipher_walk_done(&walk, 0);
+	/*
+	 * In practice, virtually all XTS plaintexts and ciphertexts are either
+	 * 512 or 4096 bytes, aligned such that they don't span page boundaries.
+	 * To optimize the performance of these cases, and also any other case
+	 * where no page boundary is spanned, the below fast-path handles
+	 * single-page sources and destinations as efficiently as possible.
+	 */
+	if (likely(src->length >= cryptlen && dst->length >= cryptlen &&
+		   src->offset + cryptlen <= PAGE_SIZE &&
+		   dst->offset + cryptlen <= PAGE_SIZE)) {
+		struct page *src_page = sg_page(src);
+		struct page *dst_page = sg_page(dst);
+		void *src_virt = kmap_local_page(src_page) + src->offset;
+		void *dst_virt = kmap_local_page(dst_page) + dst->offset;
+
+		(*crypt_func)(&ctx->crypt_ctx, src_virt, dst_virt, cryptlen,
+			      req->iv);
+		kunmap_local(dst_virt);
+		kunmap_local(src_virt);
+		kernel_fpu_end();
+		return 0;
 	}
-	return err;
+	kernel_fpu_end();
+	return xts_crypt_slowpath(req, crypt_func);
+}
+
+static void aesni_xts_encrypt_iv(const struct crypto_aes_ctx *tweak_key,
+				 u8 iv[AES_BLOCK_SIZE])
+{
+	aesni_enc(tweak_key, iv, iv);
+}
+
+static void aesni_xts_encrypt(const struct crypto_aes_ctx *key,
+			      const u8 *src, u8 *dst, unsigned int len,
+			      u8 tweak[AES_BLOCK_SIZE])
+{
+	aesni_xts_enc(key, dst, src, len, tweak);
 }
 
-static int xts_encrypt(struct skcipher_request *req)
+static void aesni_xts_decrypt(const struct crypto_aes_ctx *key,
+			      const u8 *src, u8 *dst, unsigned int len,
+			      u8 tweak[AES_BLOCK_SIZE])
 {
-	return xts_crypt(req, true);
+	aesni_xts_dec(key, dst, src, len, tweak);
 }
 
-static int xts_decrypt(struct skcipher_request *req)
+static int xts_encrypt_aesni(struct skcipher_request *req)
 {
-	return xts_crypt(req, false);
+	return xts_crypt(req, aesni_xts_encrypt_iv, aesni_xts_encrypt);
+}
+
+static int xts_decrypt_aesni(struct skcipher_request *req)
+{
+	return xts_crypt(req, aesni_xts_encrypt_iv, aesni_xts_decrypt);
 }
 
 static struct crypto_alg aesni_cipher_alg = {
@@ -1103,9 +1131,9 @@ static struct skcipher_alg aesni_skciphers[] = {
 		.max_keysize	= 2 * AES_MAX_KEY_SIZE,
 		.ivsize		= AES_BLOCK_SIZE,
 		.walksize	= 2 * AES_BLOCK_SIZE,
-		.setkey		= xts_aesni_setkey,
-		.encrypt	= xts_encrypt,
-		.decrypt	= xts_decrypt,
+		.setkey		= xts_setkey_aesni,
+		.encrypt	= xts_encrypt_aesni,
+		.decrypt	= xts_decrypt_aesni,
 	}
 };
 
@@ -1137,7 +1165,149 @@ static struct skcipher_alg aesni_xctr = {
 };
 
 static struct simd_skcipher_alg *aesni_simd_xctr;
-#endif /* CONFIG_X86_64 */
+
+asmlinkage void aes_xts_encrypt_iv(const struct crypto_aes_ctx *tweak_key,
+				   u8 iv[AES_BLOCK_SIZE]);
+
+#define DEFINE_XTS_ALG(suffix, driver_name, priority)			       \
+									       \
+asmlinkage void								       \
+aes_xts_encrypt_##suffix(const struct crypto_aes_ctx *key, const u8 *src,      \
+			 u8 *dst, unsigned int len, u8 tweak[AES_BLOCK_SIZE]); \
+asmlinkage void								       \
+aes_xts_decrypt_##suffix(const struct crypto_aes_ctx *key, const u8 *src,      \
+			 u8 *dst, unsigned int len, u8 tweak[AES_BLOCK_SIZE]); \
+									       \
+static int xts_encrypt_##suffix(struct skcipher_request *req)		       \
+{									       \
+	return xts_crypt(req, aes_xts_encrypt_iv, aes_xts_encrypt_##suffix);   \
+}									       \
+									       \
+static int xts_decrypt_##suffix(struct skcipher_request *req)		       \
+{									       \
+	return xts_crypt(req, aes_xts_encrypt_iv, aes_xts_decrypt_##suffix);   \
+}									       \
+									       \
+static struct skcipher_alg aes_xts_alg_##suffix = {			       \
+	.base = {							       \
+		.cra_name		= "__xts(aes)",			       \
+		.cra_driver_name	= "__" driver_name,		       \
+		.cra_priority		= priority,			       \
+		.cra_flags		= CRYPTO_ALG_INTERNAL,		       \
+		.cra_blocksize		= AES_BLOCK_SIZE,		       \
+		.cra_ctxsize		= XTS_AES_CTX_SIZE,		       \
+		.cra_module		= THIS_MODULE,			       \
+	},								       \
+	.min_keysize	= 2 * AES_MIN_KEY_SIZE,				       \
+	.max_keysize	= 2 * AES_MAX_KEY_SIZE,				       \
+	.ivsize		= AES_BLOCK_SIZE,				       \
+	.walksize	= 2 * AES_BLOCK_SIZE,				       \
+	.setkey		= xts_setkey_aesni,				       \
+	.encrypt	= xts_encrypt_##suffix,				       \
+	.decrypt	= xts_decrypt_##suffix,				       \
+};									       \
+									       \
+static struct simd_skcipher_alg *aes_xts_simdalg_##suffix
+
+DEFINE_XTS_ALG(aesni_avx, "xts-aes-aesni-avx", 500);
+#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
+DEFINE_XTS_ALG(vaes_avx2, "xts-aes-vaes-avx2", 600);
+DEFINE_XTS_ALG(vaes_avx10_256, "xts-aes-vaes-avx10_256", 700);
+DEFINE_XTS_ALG(vaes_avx10_512, "xts-aes-vaes-avx10_512", 800);
+#endif
+
+/*
+ * This is a list of CPU models that are known to suffer from downclocking when
+ * zmm registers (512-bit vectors) are used.  On these CPUs, the AES-XTS
+ * implementation with zmm registers won't be used by default.  An
+ * implementation with ymm registers (256-bit vectors) will be used instead.
+ */
+static const struct x86_cpu_id zmm_exclusion_list[] = {
+	{ .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_SKYLAKE_X },
+	{ .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE_X },
+	{ .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE_D },
+	{ .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE },
+	{ .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE_L },
+	{ .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE_NNPI },
+	{ .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_TIGERLAKE_L },
+	{ .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_TIGERLAKE },
+	/* Allow Rocket Lake and later, and Sapphire Rapids and later. */
+	/* Also allow AMD CPUs (starting with Zen 4, the first with AVX-512). */
+	{},
+};
+
+static int __init register_xts_algs(void)
+{
+	int err;
+
+	if (!boot_cpu_has(X86_FEATURE_AVX))
+		return 0;
+	err = simd_register_skciphers_compat(&aes_xts_alg_aesni_avx, 1,
+					     &aes_xts_simdalg_aesni_avx);
+	if (err)
+		return err;
+#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
+	if (!boot_cpu_has(X86_FEATURE_AVX2) ||
+	    !boot_cpu_has(X86_FEATURE_VAES) ||
+	    !boot_cpu_has(X86_FEATURE_VPCLMULQDQ) ||
+	    !boot_cpu_has(X86_FEATURE_PCLMULQDQ) ||
+	    !cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL))
+		return 0;
+	err = simd_register_skciphers_compat(&aes_xts_alg_vaes_avx2, 1,
+					     &aes_xts_simdalg_vaes_avx2);
+	if (err)
+		return err;
+
+	if (!boot_cpu_has(X86_FEATURE_AVX512BW) ||
+	    !boot_cpu_has(X86_FEATURE_AVX512VL) ||
+	    !boot_cpu_has(X86_FEATURE_BMI2) ||
+	    !cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM |
+			       XFEATURE_MASK_AVX512, NULL))
+		return 0;
+
+	err = simd_register_skciphers_compat(&aes_xts_alg_vaes_avx10_256, 1,
+					     &aes_xts_simdalg_vaes_avx10_256);
+	if (err)
+		return err;
+
+	if (x86_match_cpu(zmm_exclusion_list))
+		aes_xts_alg_vaes_avx10_512.base.cra_priority = 1;
+
+	err = simd_register_skciphers_compat(&aes_xts_alg_vaes_avx10_512, 1,
+					     &aes_xts_simdalg_vaes_avx10_512);
+	if (err)
+		return err;
+#endif /* CONFIG_AS_VAES && CONFIG_AS_VPCLMULQDQ */
+	return 0;
+}
+
+static void unregister_xts_algs(void)
+{
+	if (aes_xts_simdalg_aesni_avx)
+		simd_unregister_skciphers(&aes_xts_alg_aesni_avx, 1,
+					  &aes_xts_simdalg_aesni_avx);
+#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
+	if (aes_xts_simdalg_vaes_avx2)
+		simd_unregister_skciphers(&aes_xts_alg_vaes_avx2, 1,
+					  &aes_xts_simdalg_vaes_avx2);
+	if (aes_xts_simdalg_vaes_avx10_256)
+		simd_unregister_skciphers(&aes_xts_alg_vaes_avx10_256, 1,
+					  &aes_xts_simdalg_vaes_avx10_256);
+	if (aes_xts_simdalg_vaes_avx10_512)
+		simd_unregister_skciphers(&aes_xts_alg_vaes_avx10_512, 1,
+					  &aes_xts_simdalg_vaes_avx10_512);
+#endif
+}
+#else /* CONFIG_X86_64 */
+static int __init register_xts_algs(void)
+{
+	return 0;
+}
+
+static void unregister_xts_algs(void)
+{
+}
+#endif /* !CONFIG_X86_64 */
 
 #ifdef CONFIG_X86_64
 static int generic_gcmaes_set_key(struct crypto_aead *aead, const u8 *key,
@@ -1146,7 +1316,8 @@ static int generic_gcmaes_set_key(struct crypto_aead *aead, const u8 *key,
 	struct generic_gcmaes_ctx *ctx = generic_gcmaes_ctx_get(aead);
 
 	return aes_set_key_common(&ctx->aes_key_expanded, key, key_len) ?:
-	       rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len);
+	       aes_gcm_derive_hash_subkey(&ctx->aes_key_expanded,
+					  ctx->hash_subkey);
 }
 
 static int generic_gcmaes_encrypt(struct aead_request *req)
@@ -1276,13 +1447,21 @@ static int __init aesni_init(void)
 		goto unregister_aeads;
 #endif /* CONFIG_X86_64 */
 
+	err = register_xts_algs();
+	if (err)
+		goto unregister_xts;
+
 	return 0;
 
+unregister_xts:
+	unregister_xts_algs();
 #ifdef CONFIG_X86_64
+	if (aesni_simd_xctr)
+		simd_unregister_skciphers(&aesni_xctr, 1, &aesni_simd_xctr);
 unregister_aeads:
+#endif /* CONFIG_X86_64 */
 	simd_unregister_aeads(aesni_aeads, ARRAY_SIZE(aesni_aeads),
 				aesni_simd_aeads);
-#endif /* CONFIG_X86_64 */
 
 unregister_skciphers:
 	simd_unregister_skciphers(aesni_skciphers, ARRAY_SIZE(aesni_skciphers),
@@ -1303,6 +1482,7 @@ static void __exit aesni_exit(void)
 	if (boot_cpu_has(X86_FEATURE_AVX))
 		simd_unregister_skciphers(&aesni_xctr, 1, &aesni_simd_xctr);
 #endif /* CONFIG_X86_64 */
+	unregister_xts_algs();
 }
 
 late_initcall(aesni_init);
diff --git a/arch/x86/crypto/nh-avx2-x86_64.S b/arch/x86/crypto/nh-avx2-x86_64.S
index ef73a3ab8726..791386d9a83a 100644
--- a/arch/x86/crypto/nh-avx2-x86_64.S
+++ b/arch/x86/crypto/nh-avx2-x86_64.S
@@ -154,5 +154,6 @@ SYM_TYPED_FUNC_START(nh_avx2)
 	vpaddq		T1, T0, T0
 	vpaddq		T4, T0, T0
 	vmovdqu		T0, (HASH)
+	vzeroupper
 	RET
 SYM_FUNC_END(nh_avx2)
diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S
index 9918212faf91..0ffb072be956 100644
--- a/arch/x86/crypto/sha256-avx2-asm.S
+++ b/arch/x86/crypto/sha256-avx2-asm.S
@@ -716,6 +716,7 @@ SYM_TYPED_FUNC_START(sha256_transform_rorx)
 	popq	%r13
 	popq	%r12
 	popq	%rbx
+	vzeroupper
 	RET
 SYM_FUNC_END(sha256_transform_rorx)
 
diff --git a/arch/x86/crypto/sha256_ni_asm.S b/arch/x86/crypto/sha256_ni_asm.S
index 537b6dcd7ed8..d515a55a3bc1 100644
--- a/arch/x86/crypto/sha256_ni_asm.S
+++ b/arch/x86/crypto/sha256_ni_asm.S
@@ -62,20 +62,41 @@
 
 #define SHA256CONSTANTS	%rax
 
-#define MSG		%xmm0
+#define MSG		%xmm0  /* sha256rnds2 implicit operand */
 #define STATE0		%xmm1
 #define STATE1		%xmm2
-#define MSGTMP0		%xmm3
-#define MSGTMP1		%xmm4
-#define MSGTMP2		%xmm5
-#define MSGTMP3		%xmm6
-#define MSGTMP4		%xmm7
+#define MSG0		%xmm3
+#define MSG1		%xmm4
+#define MSG2		%xmm5
+#define MSG3		%xmm6
+#define TMP		%xmm7
 
 #define SHUF_MASK	%xmm8
 
 #define ABEF_SAVE	%xmm9
 #define CDGH_SAVE	%xmm10
 
+.macro do_4rounds	i, m0, m1, m2, m3
+.if \i < 16
+	movdqu		\i*4(DATA_PTR), \m0
+	pshufb		SHUF_MASK, \m0
+.endif
+	movdqa		(\i-32)*4(SHA256CONSTANTS), MSG
+	paddd		\m0, MSG
+	sha256rnds2	STATE0, STATE1
+.if \i >= 12 && \i < 60
+	movdqa		\m0, TMP
+	palignr		$4, \m3, TMP
+	paddd		TMP, \m1
+	sha256msg2	\m0, \m1
+.endif
+	punpckhqdq	MSG, MSG
+	sha256rnds2	STATE1, STATE0
+.if \i >= 4 && \i < 52
+	sha256msg1	\m0, \m3
+.endif
+.endm
+
 /*
  * Intel SHA Extensions optimized implementation of a SHA-256 update function
  *
@@ -86,9 +107,6 @@
  * store partial blocks.  All message padding and hash value initialization must
  * be done outside the update function.
  *
- * The indented lines in the loop are instructions related to rounds processing.
- * The non-indented lines are instructions related to the message schedule.
- *
  * void sha256_ni_transform(uint32_t *digest, const void *data,
 		uint32_t numBlocks);
  * digest : pointer to digest
@@ -108,202 +126,29 @@ SYM_TYPED_FUNC_START(sha256_ni_transform)
 	 * Need to reorder these appropriately
 	 * DCBA, HGFE -> ABEF, CDGH
 	 */
-	movdqu		0*16(DIGEST_PTR), STATE0
-	movdqu		1*16(DIGEST_PTR), STATE1
+	movdqu		0*16(DIGEST_PTR), STATE0	/* DCBA */
+	movdqu		1*16(DIGEST_PTR), STATE1	/* HGFE */
 
-	pshufd		$0xB1, STATE0,  STATE0		/* CDAB */
-	pshufd		$0x1B, STATE1,  STATE1		/* EFGH */
-	movdqa		STATE0, MSGTMP4
-	palignr		$8, STATE1,  STATE0		/* ABEF */
-	pblendw		$0xF0, MSGTMP4, STATE1		/* CDGH */
+	movdqa		STATE0, TMP
+	punpcklqdq	STATE1, STATE0			/* FEBA */
+	punpckhqdq	TMP, STATE1			/* DCHG */
+	pshufd		$0x1B, STATE0, STATE0		/* ABEF */
+	pshufd		$0xB1, STATE1, STATE1		/* CDGH */
 
 	movdqa		PSHUFFLE_BYTE_FLIP_MASK(%rip), SHUF_MASK
-	lea		K256(%rip), SHA256CONSTANTS
+	lea		K256+32*4(%rip), SHA256CONSTANTS
 
 .Lloop0:
 	/* Save hash values for addition after rounds */
 	movdqa		STATE0, ABEF_SAVE
 	movdqa		STATE1, CDGH_SAVE
 
-	/* Rounds 0-3 */
-	movdqu		0*16(DATA_PTR), MSG
-	pshufb		SHUF_MASK, MSG
-	movdqa		MSG, MSGTMP0
-		paddd		0*16(SHA256CONSTANTS), MSG
-		sha256rnds2	STATE0, STATE1
-		pshufd 		$0x0E, MSG, MSG
-		sha256rnds2	STATE1, STATE0
-
-	/* Rounds 4-7 */
-	movdqu		1*16(DATA_PTR), MSG
-	pshufb		SHUF_MASK, MSG
-	movdqa		MSG, MSGTMP1
-		paddd		1*16(SHA256CONSTANTS), MSG
-		sha256rnds2	STATE0, STATE1
-		pshufd 		$0x0E, MSG, MSG
-		sha256rnds2	STATE1, STATE0
-	sha256msg1	MSGTMP1, MSGTMP0
-
-	/* Rounds 8-11 */
-	movdqu		2*16(DATA_PTR), MSG
-	pshufb		SHUF_MASK, MSG
-	movdqa		MSG, MSGTMP2
-		paddd		2*16(SHA256CONSTANTS), MSG
-		sha256rnds2	STATE0, STATE1
-		pshufd 		$0x0E, MSG, MSG
-		sha256rnds2	STATE1, STATE0
-	sha256msg1	MSGTMP2, MSGTMP1
-
-	/* Rounds 12-15 */
-	movdqu		3*16(DATA_PTR), MSG
-	pshufb		SHUF_MASK, MSG
-	movdqa		MSG, MSGTMP3
-		paddd		3*16(SHA256CONSTANTS), MSG
-		sha256rnds2	STATE0, STATE1
-	movdqa		MSGTMP3, MSGTMP4
-	palignr		$4, MSGTMP2, MSGTMP4
-	paddd		MSGTMP4, MSGTMP0
-	sha256msg2	MSGTMP3, MSGTMP0
-		pshufd 		$0x0E, MSG, MSG
-		sha256rnds2	STATE1, STATE0
-	sha256msg1	MSGTMP3, MSGTMP2
-
-	/* Rounds 16-19 */
-	movdqa		MSGTMP0, MSG
-		paddd		4*16(SHA256CONSTANTS), MSG
-		sha256rnds2	STATE0, STATE1
-	movdqa		MSGTMP0, MSGTMP4
-	palignr		$4, MSGTMP3, MSGTMP4
-	paddd		MSGTMP4, MSGTMP1
-	sha256msg2	MSGTMP0, MSGTMP1
-		pshufd 		$0x0E, MSG, MSG
-		sha256rnds2	STATE1, STATE0
-	sha256msg1	MSGTMP0, MSGTMP3
-
-	/* Rounds 20-23 */
-	movdqa		MSGTMP1, MSG
-		paddd		5*16(SHA256CONSTANTS), MSG
-		sha256rnds2	STATE0, STATE1
-	movdqa		MSGTMP1, MSGTMP4
-	palignr		$4, MSGTMP0, MSGTMP4
-	paddd		MSGTMP4, MSGTMP2
-	sha256msg2	MSGTMP1, MSGTMP2
-		pshufd 		$0x0E, MSG, MSG
-		sha256rnds2	STATE1, STATE0
-	sha256msg1	MSGTMP1, MSGTMP0
-
-	/* Rounds 24-27 */
-	movdqa		MSGTMP2, MSG
-		paddd		6*16(SHA256CONSTANTS), MSG
-		sha256rnds2	STATE0, STATE1
-	movdqa		MSGTMP2, MSGTMP4
-	palignr		$4, MSGTMP1, MSGTMP4
-	paddd		MSGTMP4, MSGTMP3
-	sha256msg2	MSGTMP2, MSGTMP3
-		pshufd 		$0x0E, MSG, MSG
-		sha256rnds2	STATE1, STATE0
-	sha256msg1	MSGTMP2, MSGTMP1
-
-	/* Rounds 28-31 */
-	movdqa		MSGTMP3, MSG
-		paddd		7*16(SHA256CONSTANTS), MSG
-		sha256rnds2	STATE0, STATE1
-	movdqa		MSGTMP3, MSGTMP4
-	palignr		$4, MSGTMP2, MSGTMP4
-	paddd		MSGTMP4, MSGTMP0
-	sha256msg2	MSGTMP3, MSGTMP0
-		pshufd 		$0x0E, MSG, MSG
-		sha256rnds2	STATE1, STATE0
-	sha256msg1	MSGTMP3, MSGTMP2
-
-	/* Rounds 32-35 */
-	movdqa		MSGTMP0, MSG
-		paddd		8*16(SHA256CONSTANTS), MSG
-		sha256rnds2	STATE0, STATE1
-	movdqa		MSGTMP0, MSGTMP4
-	palignr		$4, MSGTMP3, MSGTMP4
-	paddd		MSGTMP4, MSGTMP1
-	sha256msg2	MSGTMP0, MSGTMP1
-		pshufd 		$0x0E, MSG, MSG
-		sha256rnds2	STATE1, STATE0
-	sha256msg1	MSGTMP0, MSGTMP3
-
-	/* Rounds 36-39 */
-	movdqa		MSGTMP1, MSG
-		paddd		9*16(SHA256CONSTANTS), MSG
-		sha256rnds2	STATE0, STATE1
-	movdqa		MSGTMP1, MSGTMP4
-	palignr		$4, MSGTMP0, MSGTMP4
-	paddd		MSGTMP4, MSGTMP2
-	sha256msg2	MSGTMP1, MSGTMP2
-		pshufd 		$0x0E, MSG, MSG
-		sha256rnds2	STATE1, STATE0
-	sha256msg1	MSGTMP1, MSGTMP0
-
-	/* Rounds 40-43 */
-	movdqa		MSGTMP2, MSG
-		paddd		10*16(SHA256CONSTANTS), MSG
-		sha256rnds2	STATE0, STATE1
-	movdqa		MSGTMP2, MSGTMP4
-	palignr		$4, MSGTMP1, MSGTMP4
-	paddd		MSGTMP4, MSGTMP3
-	sha256msg2	MSGTMP2, MSGTMP3
-		pshufd 		$0x0E, MSG, MSG
-		sha256rnds2	STATE1, STATE0
-	sha256msg1	MSGTMP2, MSGTMP1
-
-	/* Rounds 44-47 */
-	movdqa		MSGTMP3, MSG
-		paddd		11*16(SHA256CONSTANTS), MSG
-		sha256rnds2	STATE0, STATE1
-	movdqa		MSGTMP3, MSGTMP4
-	palignr		$4, MSGTMP2, MSGTMP4
-	paddd		MSGTMP4, MSGTMP0
-	sha256msg2	MSGTMP3, MSGTMP0
-		pshufd 		$0x0E, MSG, MSG
-		sha256rnds2	STATE1, STATE0
-	sha256msg1	MSGTMP3, MSGTMP2
-
-	/* Rounds 48-51 */
-	movdqa		MSGTMP0, MSG
-		paddd		12*16(SHA256CONSTANTS), MSG
-		sha256rnds2	STATE0, STATE1
-	movdqa		MSGTMP0, MSGTMP4
-	palignr		$4, MSGTMP3, MSGTMP4
-	paddd		MSGTMP4, MSGTMP1
-	sha256msg2	MSGTMP0, MSGTMP1
-		pshufd 		$0x0E, MSG, MSG
-		sha256rnds2	STATE1, STATE0
-	sha256msg1	MSGTMP0, MSGTMP3
-
-	/* Rounds 52-55 */
-	movdqa		MSGTMP1, MSG
-		paddd		13*16(SHA256CONSTANTS), MSG
-		sha256rnds2	STATE0, STATE1
-	movdqa		MSGTMP1, MSGTMP4
-	palignr		$4, MSGTMP0, MSGTMP4
-	paddd		MSGTMP4, MSGTMP2
-	sha256msg2	MSGTMP1, MSGTMP2
-		pshufd 		$0x0E, MSG, MSG
-		sha256rnds2	STATE1, STATE0
-
-	/* Rounds 56-59 */
-	movdqa		MSGTMP2, MSG
-		paddd		14*16(SHA256CONSTANTS), MSG
-		sha256rnds2	STATE0, STATE1
-	movdqa		MSGTMP2, MSGTMP4
-	palignr		$4, MSGTMP1, MSGTMP4
-	paddd		MSGTMP4, MSGTMP3
-	sha256msg2	MSGTMP2, MSGTMP3
-		pshufd 		$0x0E, MSG, MSG
-		sha256rnds2	STATE1, STATE0
-
-	/* Rounds 60-63 */
-	movdqa		MSGTMP3, MSG
-		paddd		15*16(SHA256CONSTANTS), MSG
-		sha256rnds2	STATE0, STATE1
-		pshufd 		$0x0E, MSG, MSG
-		sha256rnds2	STATE1, STATE0
+.irp i, 0, 16, 32, 48
+	do_4rounds	(\i + 0),  MSG0, MSG1, MSG2, MSG3
+	do_4rounds	(\i + 4),  MSG1, MSG2, MSG3, MSG0
+	do_4rounds	(\i + 8),  MSG2, MSG3, MSG0, MSG1
+	do_4rounds	(\i + 12), MSG3, MSG0, MSG1, MSG2
+.endr
 
 	/* Add current hash values with previously saved */
 	paddd		ABEF_SAVE, STATE0
@@ -315,14 +160,14 @@ SYM_TYPED_FUNC_START(sha256_ni_transform)
 	jne		.Lloop0
 
 	/* Write hash values back in the correct order */
-	pshufd		$0x1B, STATE0,  STATE0		/* FEBA */
-	pshufd		$0xB1, STATE1,  STATE1		/* DCHG */
-	movdqa		STATE0, MSGTMP4
-	pblendw		$0xF0, STATE1,  STATE0		/* DCBA */
-	palignr		$8, MSGTMP4, STATE1		/* HGFE */
-
-	movdqu		STATE0, 0*16(DIGEST_PTR)
-	movdqu		STATE1, 1*16(DIGEST_PTR)
+	movdqa		STATE0, TMP
+	punpcklqdq	STATE1, STATE0			/* GHEF */
+	punpckhqdq	TMP, STATE1			/* ABCD */
+	pshufd		$0xB1, STATE0, STATE0		/* HGFE */
+	pshufd		$0x1B, STATE1, STATE1		/* DCBA */
+
+	movdqu		STATE1, 0*16(DIGEST_PTR)
+	movdqu		STATE0, 1*16(DIGEST_PTR)
 
 .Ldone_hash:
 
diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S
index f08496cd6870..24973f42c43f 100644
--- a/arch/x86/crypto/sha512-avx2-asm.S
+++ b/arch/x86/crypto/sha512-avx2-asm.S
@@ -680,6 +680,7 @@ SYM_TYPED_FUNC_START(sha512_transform_rorx)
 	pop	%r12
 	pop	%rbx
 
+	vzeroupper
 	RET
 SYM_FUNC_END(sha512_transform_rorx)